1---
  2version: 2
  3interactions:
  4- id: 0
  5  request:
  6    proto: HTTP/1.1
  7    proto_major: 1
  8    proto_minor: 1
  9    content_length: 727
 10    host: ""
 11    body: '{"messages":[{"content":"you will generate a short title based on the first message a user begins a conversation with\n\n<rules>\n- ensure it is not more than 50 characters long\n- the title should be a summary of the user''s message\n- it should be one line long\n- do not use quotes or colons\n- the entire text you return will be used as the title\n- never return anything that is more than one sentence (one line) long\n</rules>\n\n /no_think","role":"system"},{"content":"Generate a concise title for the following content:\n\nupdate the main.go file by changing the print to say hello from crush\n <think>\n\n</think>","role":"user"}],"model":"gpt-4o","max_tokens":40,"stream_options":{"include_usage":true},"stream":true}'
 12    headers:
 13      Accept:
 14      - application/json
 15      Content-Type:
 16      - application/json
 17      User-Agent:
 18      - OpenAI/Go 2.7.1
 19    url: https://api.openai.com/v1/chat/completions
 20    method: POST
 21  response:
 22    proto: HTTP/2.0
 23    proto_major: 2
 24    proto_minor: 0
 25    content_length: -1
 26    body: |+
 27      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"EKCOd06vmcIddk"}
 28
 29      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Update"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0OYz1m5jLX"}
 30
 31      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" main"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"p4nHifyvhN4"}
 32
 33      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":".go"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"F2Rbvr8RJCrSa"}
 34
 35      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" to"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"o5nLkzOENKDA1"}
 36
 37      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Print"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"69mGHAJkUa"}
 38
 39      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" \""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"nnZZ5wSixKVKe"}
 40
 41      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"o6Zx5r42r5d"}
 42
 43      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" from"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"0yejUWmUrBi"}
 44
 45      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":" Crush"},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"Sd93OiuCPr"}
 46
 47      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{"content":"\""},"logprobs":null,"finish_reason":null}],"usage":null,"obfuscation":"sjf8VtrHRDxXIX"}
 48
 49      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"usage":null,"obfuscation":"ZK3NZXgwt2"}
 50
 51      data: {"id":"chatcmpl-CTtCIaOhzMJZhYpyLFfYHvspr5OH4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-4o-2024-08-06","service_tier":"default","system_fingerprint":"fp_a788c5aef0","choices":[],"usage":{"prompt_tokens":139,"completion_tokens":10,"total_tokens":149,"prompt_tokens_details":{"cached_tokens":0,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"iNuQdkM72ThLL"}
 52
 53      data: [DONE]
 54
 55    headers:
 56      Content-Type:
 57      - text/event-stream; charset=utf-8
 58    status: 200 OK
 59    code: 200
 60    duration: 597.170459ms
 61- id: 1
 62  request:
 63    proto: HTTP/1.1
 64    proto_major: 1
 65    proto_minor: 1
 66    content_length: 34339
 67    host: ""
 68    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
 69    headers:
 70      Accept:
 71      - application/json
 72      Content-Type:
 73      - application/json
 74      User-Agent:
 75      - OpenAI/Go 2.7.1
 76    url: https://api.openai.com/v1/chat/completions
 77    method: POST
 78  response:
 79    proto: HTTP/2.0
 80    proto_major: 2
 81    proto_minor: 0
 82    content_length: -1
 83    body: |+
 84      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_pXKzauntjK740LCfAkfJsrRS","type":"function","function":{"name":"ls","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"78JusVqMwAvgsl"}
 85
 86      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"8TkiaMph5RbTH2p"}
 87
 88      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N89xNo03HZ3Ao3"}
 89
 90      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5WJ9Qpno9TaoM0g"}
 91
 92      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FRJaxongiFGF8g"}
 93
 94      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TQDv77rX8QQlKgR"}
 95
 96      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0w4iUIKK1LGbIEA"}
 97
 98      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"yGcqKZHGHHZcUXR"}
 99
100      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vo75C5grOYoME"}
101
102      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TL5SiUjHPo5dP"}
103
104      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"vvsyvhEwWkO23"}
105
106      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"I1mfdiduCZmGS"}
107
108      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GIu3W2cqzb8Sw"}
109
110      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
111
112      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
113
114      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
115
116      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"W"}
117
118      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"z"}
119
120      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Oz3w4Yw5lVf"}
121
122      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
123
124      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FMcbWFuW0iFi9"}
125
126      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\","}}]},"finish_reason":null}],"usage":null,"obfuscation":"UZreLktZE56gDjZ"}
127
128      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" \""}}]},"finish_reason":null}],"usage":null,"obfuscation":"BuRk2doMmL7Us9R"}
129
130      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"depth"}}]},"finish_reason":null}],"usage":null,"obfuscation":"3XTqC2jPecO3Y"}
131
132      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LT4Q3QaQ1VOKYla"}
133
134      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" "}}]},"finish_reason":null}],"usage":null,"obfuscation":"1"}
135
136      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"2"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"}
137
138      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"B"}
139
140      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}
141
142      data: {"id":"chatcmpl-CTtCIJOANVVkXiTJriR0B16gD7CY4","object":"chat.completion.chunk","created":1761239726,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7409,"completion_tokens":173,"total_tokens":7582,"prompt_tokens_details":{"cached_tokens":1920,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":128,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"n"}
143
144      data: [DONE]
145
146    headers:
147      Content-Type:
148      - text/event-stream; charset=utf-8
149    status: 200 OK
150    code: 200
151    duration: 4.983803959s
152- id: 2
153  request:
154    proto: HTTP/1.1
155    proto_major: 1
156    proto_minor: 1
157    content_length: 34724
158    host: ""
159    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n  - go.mod\\n  - main.go\\n\",\"tool_call_id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
160    headers:
161      Accept:
162      - application/json
163      Content-Type:
164      - application/json
165      User-Agent:
166      - OpenAI/Go 2.7.1
167    url: https://api.openai.com/v1/chat/completions
168    method: POST
169  response:
170    proto: HTTP/2.0
171    proto_major: 2
172    proto_minor: 0
173    content_length: -1
174    body: |+
175      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_8CabCVI9eFDOvoNwIRlcpqKa","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"KOpWdy3tUyDC"}
176
177      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"cr9h1HgzMpGqhTs"}
178
179      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"XKWXaw0RrpD4yz"}
180
181      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xVF4ulppsJQEV"}
182
183      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2oYCPwiGcgO1lVu"}
184
185      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CGcJ7Y5vEVNKRJF"}
186
187      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"VQrJYRjfR6uyBLH"}
188
189      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"y38UfUIDFodfWqM"}
190
191      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"nKrIqbd1hZK23wC"}
192
193      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KsoODOXXlqkgh"}
194
195      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"E63HCJMTPlTlm"}
196
197      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TgOoifMzzvhUN"}
198
199      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"tYO6diPT1Aec6"}
200
201      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8Asp0zlfUQAgD"}
202
203      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
204
205      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
206
207      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
208
209      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"C"}
210
211      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"}
212
213      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Ung5YnGYiEO"}
214
215      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
216
217      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rF7KTtyyTeEU0"}
218
219      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N4fW3ZCOkok5j"}
220
221      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iADOUXLMovP2821"}
222
223      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pT7Wh6Rh9SHMZZJ"}
224
225      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}
226
227      data: {"id":"chatcmpl-CTtCN9oLXPFY9HSZiVaT9J1OvQT87","object":"chat.completion.chunk","created":1761239731,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7486,"completion_tokens":35,"total_tokens":7521,"prompt_tokens_details":{"cached_tokens":7296,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"OTi5"}
228
229      data: [DONE]
230
231    headers:
232      Content-Type:
233      - text/event-stream; charset=utf-8
234    status: 200 OK
235    code: 200
236    duration: 2.637065708s
237- id: 3
238  request:
239    proto: HTTP/1.1
240    proto_major: 1
241    proto_minor: 1
242    content_length: 35172
243    host: ""
244    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n  - go.mod\\n  - main.go\\n\",\"tool_call_id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|package main\\n     2|\\n     3|import \\\"fmt\\\"\\n     4|\\n     5|func main() {\\n     6|\\tfmt.Println(\\\"Hello, World!\\\")\\n     7|}\\n</file>\\n\",\"tool_call_id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
245    headers:
246      Accept:
247      - application/json
248      Content-Type:
249      - application/json
250      User-Agent:
251      - OpenAI/Go 2.7.1
252    url: https://api.openai.com/v1/chat/completions
253    method: POST
254  response:
255    proto: HTTP/2.0
256    proto_major: 2
257    proto_minor: 0
258    content_length: -1
259    body: |+
260      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_FPzIXdEJMaLXuwgcDzp1GrUe","type":"function","function":{"name":"view","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"w4e2zKOLEFuc"}
261
262      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"XvIK254vUyE2Wzy"}
263
264      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n0ywMXawh5w2kf"}
265
266      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"aFUoRe9s42rFX"}
267
268      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7n6IkRzeW1tGa4j"}
269
270      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Mi6L4jgkXmjJbnZ"}
271
272      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pMAJya66j7HRb37"}
273
274      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"bEupnJqL4w8t1hB"}
275
276      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m3GWj1SFlFRkaVQ"}
277
278      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Zl0QbYz7eB4dE"}
279
280      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N3N1oObb0HHNo"}
281
282      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xwDE9wesC4EDy"}
283
284      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"GclIxYqLk7gfQ"}
285
286      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EIs7UOFlRFahO"}
287
288      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
289
290      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
291
292      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
293
294      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"l"}
295
296      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"e"}
297
298      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"YnoPka6HNhc"}
299
300      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
301
302      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9i71R6DZGKo71"}
303
304      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2Ak1L1mjYP1Vh5K"}
305
306      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".mod"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jPb5Jg4uUhmTPX"}
307
308      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"qcVQkQmm6ohemrF"}
309
310      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}
311
312      data: {"id":"chatcmpl-CTtCTd9sxUtSnFPT0CWK5knzPZl94","object":"chat.completion.chunk","created":1761239737,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7583,"completion_tokens":617,"total_tokens":8200,"prompt_tokens_details":{"cached_tokens":7424,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":576,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"o"}
313
314      data: [DONE]
315
316    headers:
317      Content-Type:
318      - text/event-stream; charset=utf-8
319    status: 200 OK
320    code: 200
321    duration: 18.60522775s
322- id: 4
323  request:
324    proto: HTTP/1.1
325    proto_major: 1
326    proto_minor: 1
327    content_length: 35548
328    host: ""
329    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n  - go.mod\\n  - main.go\\n\",\"tool_call_id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|package main\\n     2|\\n     3|import \\\"fmt\\\"\\n     4|\\n     5|func main() {\\n     6|\\tfmt.Println(\\\"Hello, World!\\\")\\n     7|}\\n</file>\\n\",\"tool_call_id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|module example.com/testproject\\n     2|\\n     3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
330    headers:
331      Accept:
332      - application/json
333      Content-Type:
334      - application/json
335      User-Agent:
336      - OpenAI/Go 2.7.1
337    url: https://api.openai.com/v1/chat/completions
338    method: POST
339  response:
340    proto: HTTP/2.0
341    proto_major: 2
342    proto_minor: 0
343    content_length: -1
344    body: |+
345      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_kDlxWt9HxmhuJQ799z3345KV","type":"function","function":{"name":"edit","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"siCFgzEzckuz"}
346
347      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"M8tUxm1amVYJ8Ji"}
348
349      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"595j4C3fDDJ5Oi"}
350
351      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_path"}}]},"finish_reason":null}],"usage":null,"obfuscation":"07Z50oIHc4PZ3"}
352
353      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":"}}]},"finish_reason":null}],"usage":null,"obfuscation":"O62t9os9HL9DIcq"}
354
355      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"/"}}]},"finish_reason":null}],"usage":null,"obfuscation":"OiO3rXjYGVLSzzy"}
356
357      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Y6zZKj4zrsDqjgX"}
358
359      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gQArNgrRsSoVaTy"}
360
361      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jFoxO11KsGPzeEJ"}
362
363      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"CCMoBgE829ALx"}
364
365      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rZbBnMPmlVvRU"}
366
367      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"pzzcDxygI3Ys5"}
368
369      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"KTAkmeI4zZxNs"}
370
371      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ttkuS8jHT8bqI"}
372
373      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
374
375      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
376
377      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
378
379      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"k"}
380
381      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"f"}
382
383      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"hTRB0Wh7ocf"}
384
385      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
386
387      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LO92rmBhiTSBZ"}
388
389      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rh1xHG5miC1Lo"}
390
391      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"H4hUPzamZyIFBgD"}
392
393      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"pvtFGE5rBXJc0"}
394
395      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"old"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Gnz0FRubDuIswcB"}
396
397      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"rtQeERaTZGi"}
398
399      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"Xa5y2lJ0oSB4W"}
400
401      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"negB9xfsxPyUQS"}
402
403      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"fOW46peTGbsVZ"}
404
405      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
406
407      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Rw8nsn1amJKsZK"}
408
409      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"n"}
410
411      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gVyNaNc9SUn7cl9"}
412
413      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LiKgBOmqxClONkn"}
414
415      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"2JfinwK2TT"}
416
417      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"0qGNKggJF3aOH"}
418
419      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"FNnZODsbS5XXA"}
420
421      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":","}}]},"finish_reason":null}],"usage":null,"obfuscation":"x"}
422
423      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" World"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BMzYH8x2GGLu"}
424
425      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"!\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ARsWQ3QWpnrazVA"}
426
427      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"0ZnrJtfo9Mt9Zgb"}
428
429      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
430
431      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"}
432
433      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"EmMl8rZauW7iI55"}
434
435      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"}
436
437      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"WPobseSquUDJa"}
438
439      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"new"}}]},"finish_reason":null}],"usage":null,"obfuscation":"QBrH7MhxMm7XWa1"}
440
441      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_string"}}]},"finish_reason":null}],"usage":null,"obfuscation":"5kdlfj06HGQ"}
442
443      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"k4Cw2KDLXKHBx"}
444
445      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"func"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dx2fUJGVX0EcAS"}
446
447      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"1AWB7LYGeO1Yw"}
448
449      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"()"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
450
451      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" {\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ofnsEd91jFIgdH"}
452
453      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4"}
454
455      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\t"}}]},"finish_reason":null}],"usage":null,"obfuscation":"8eWR1xTqLe56FH5"}
456
457      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"fmt"}}]},"finish_reason":null}],"usage":null,"obfuscation":"apoM9TDNUvGM65c"}
458
459      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".Println"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uKOV6xmFj2"}
460
461      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"(\\\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"c6HoA8w1btvVh"}
462
463      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"hello"}}]},"finish_reason":null}],"usage":null,"obfuscation":"myM70VjKN1JWn"}
464
465      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" from"}}]},"finish_reason":null}],"usage":null,"obfuscation":"9bIsA1d3cg2OM"}
466
467      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" crush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"sgmZbfwY9Xl3"}
468
469      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\\")"}}]},"finish_reason":null}],"usage":null,"obfuscation":"xWCdWGaDq5xGZ"}
470
471      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
472
473      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Z"}
474
475      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"}\\"}}]},"finish_reason":null}],"usage":null,"obfuscation":"ATMwac8tCwSwplF"}
476
477      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"n"}}]},"finish_reason":null}],"usage":null,"obfuscation":"d"}
478
479      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"dPglyhH1gA6HbVC"}
480
481      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}
482
483      data: {"id":"chatcmpl-CTtCjxFE6XqNqpImcIZgPDFSF6xy5","object":"chat.completion.chunk","created":1761239753,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7658,"completion_tokens":724,"total_tokens":8382,"prompt_tokens_details":{"cached_tokens":7552,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":640,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"r"}
484
485      data: [DONE]
486
487    headers:
488      Content-Type:
489      - text/event-stream; charset=utf-8
490    status: 200 OK
491    code: 200
492    duration: 21.000050458s
493- id: 5
494  request:
495    proto: HTTP/1.1
496    proto_major: 1
497    proto_minor: 1
498    content_length: 36121
499    host: ""
500    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n  - go.mod\\n  - main.go\\n\",\"tool_call_id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|package main\\n     2|\\n     3|import \\\"fmt\\\"\\n     4|\\n     5|func main() {\\n     6|\\tfmt.Println(\\\"Hello, World!\\\")\\n     7|}\\n</file>\\n\",\"tool_call_id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|module example.com/testproject\\n     2|\\n     3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_kDlxWt9HxmhuJQ799z3345KV\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_kDlxWt9HxmhuJQ799z3345KV\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
501    headers:
502      Accept:
503      - application/json
504      Content-Type:
505      - application/json
506      User-Agent:
507      - OpenAI/Go 2.7.1
508    url: https://api.openai.com/v1/chat/completions
509    method: POST
510  response:
511    proto: HTTP/2.0
512    proto_major: 2
513    proto_minor: 0
514    content_length: -1
515    body: |+
516      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":null,"tool_calls":[{"index":0,"id":"call_A0s7KddYbxCPmcyi0pUyXIts","type":"function","function":{"name":"bash","arguments":""}}],"refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"EE2DFBoISbIK"}
517
518      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"2rjoPPRqHWA1MFb"}
519
520      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"command"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gBC6B1NrnS8"}
521
522      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"RvnW8b4FHJwcz"}
523
524      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"go"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
525
526      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4Hhl6ZbIp6avN7"}
527
528      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" /"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
529
530      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"tmp"}}]},"finish_reason":null}],"usage":null,"obfuscation":"6o9sRzYE2IuZ0tJ"}
531
532      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/cr"}}]},"finish_reason":null}],"usage":null,"obfuscation":"TF1n7ENRiPHBR8t"}
533
534      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ush"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DjNQ38dre1FFYMt"}
535
536      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"njJ7wPklPOLj7"}
537
538      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/Test"}}]},"finish_reason":null}],"usage":null,"obfuscation":"Upu1DP5HSweTs"}
539
540      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Coder"}}]},"finish_reason":null}],"usage":null,"obfuscation":"HCNEo55saR6mv"}
541
542      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Agent"}}]},"finish_reason":null}],"usage":null,"obfuscation":"K5NBRhbvL25eU"}
543
544      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/open"}}]},"finish_reason":null}],"usage":null,"obfuscation":"jU2C7904N2hng"}
545
546      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"ai"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
547
548      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-g"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
549
550      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"pt"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
551
552      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"-"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N"}
553
554      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"5"}}]},"finish_reason":null}],"usage":null,"obfuscation":"m"}
555
556      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/update"}}]},"finish_reason":null}],"usage":null,"obfuscation":"uBiyQG2xhI7"}
557
558      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_a"}}]},"finish_reason":null}],"usage":null,"obfuscation":""}
559
560      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"_file"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7VrrSnn7HpMu6"}
561
562      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"/main"}}]},"finish_reason":null}],"usage":null,"obfuscation":"efNOnTWVTypLB"}
563
564      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":".go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"N2avFO6b42o3SQT"}
565
566      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\",\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"hvzFtt3Y7vAen"}
567
568      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"description"}}]},"finish_reason":null}],"usage":null,"obfuscation":"gZgMxoz"}
569
570      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\":\""}}]},"finish_reason":null}],"usage":null,"obfuscation":"D9kZ3oFWKzVYW"}
571
572      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"Run"}}]},"finish_reason":null}],"usage":null,"obfuscation":"LTtKotf0S2ZEvkp"}
573
574      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" the"}}]},"finish_reason":null}],"usage":null,"obfuscation":"WleDBFYjrjk17p"}
575
576      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" Go"}}]},"finish_reason":null}],"usage":null,"obfuscation":"4jz4wHAA0NXoCwI"}
577
578      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" program"}}]},"finish_reason":null}],"usage":null,"obfuscation":"DNGcPIBaZI"}
579
580      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" to"}}]},"finish_reason":null}],"usage":null,"obfuscation":"iHcYq4zQ7rCLLu5"}
581
582      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" verify"}}]},"finish_reason":null}],"usage":null,"obfuscation":"BfJ9sQ5ekk4"}
583
584      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":" output"}}]},"finish_reason":null}],"usage":null,"obfuscation":"7bHW7wjpRHz"}
585
586      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"tool_calls":[{"index":0,"function":{"arguments":"\"}"}}]},"finish_reason":null}],"usage":null,"obfuscation":"SXP3gyknzSjvcfz"}
587
588      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"tool_calls"}],"usage":null,"obfuscation":""}
589
590      data: {"id":"chatcmpl-CTtD5lHr0JRjs2hX3wiFwyhyZDSE1","object":"chat.completion.chunk","created":1761239775,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7777,"completion_tokens":47,"total_tokens":7824,"prompt_tokens_details":{"cached_tokens":7552,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"uX40"}
591
592      data: [DONE]
593
594    headers:
595      Content-Type:
596      - text/event-stream; charset=utf-8
597    status: 200 OK
598    code: 200
599    duration: 2.08773825s
600- id: 6
601  request:
602    proto: HTTP/1.1
603    proto_major: 1
604    proto_minor: 1
605    content_length: 36568
606    host: ""
607    body: "{\"messages\":[{\"content\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n<critical_rules>\\nThese rules override everything else. Follow them strictly:\\n\\n1. **ALWAYS READ BEFORE EDITING**: Never edit a file you haven't read in this conversation (only read files if you did not read them before or they changed)\\n2. **BE AUTONOMOUS**: Don't ask questions - search, read, decide, act\\n3. **TEST AFTER CHANGES**: Run tests immediately after each modification\\n4. **BE CONCISE**: Under 4 lines unless user asks for detail\\n5. **USE EXACT MATCHES**: When editing, match text exactly including whitespace\\n6. **NEVER COMMIT**: Unless user explicitly says \\\"commit\\\"\\n7. **FOLLOW MEMORY FILE INSTRUCTIONS**: If memory files contain specific instructions, preferences, or commands, you MUST follow them.\\n8. **NEVER ADD COMMENTS**: Only add comments if the user asked you to do so. When adding comments, focus on *why* not *what*. NEVER communicate with the user through code comments.\\n9. **SECURITY FIRST**: Only assist with defensive security tasks. Refuse to create, modify, or improve code that may be used maliciously. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\\n10. **NO URL GUESSING**: Never generate or guess URLs unless you are confident they are for helping with programming. Only use URLs provided by the user or found in local files.\\n11. **NEVER PUSH TO REMOTE**: Don't push changes to remote repositories unless explicitly asked by the user.\\n12. **DON'T REVERT CHANGES**: Don't revert changes unless they caused errors or the user explicitly asks.\\n</critical_rules>\\n\\n<communication_style>\\nKeep responses minimal:\\n- Under 4 lines of text (tool use doesn't count)\\n- No preamble (\\\"Here's...\\\", \\\"I'll...\\\")\\n- No postamble (\\\"Let me know...\\\", \\\"Hope this helps...\\\")\\n- One-word answers when possible\\n- No emojis ever\\n- No explanations unless user asks\\n\\nExamples:\\nuser: what is 2+2?\\nassistant: 4\\n\\nuser: list files in src/\\nassistant: [uses ls tool]\\nfoo.c, bar.c, baz.c\\n\\nuser: which file has the foo implementation?\\nassistant: src/foo.c\\n\\nuser: add error handling to the login function\\nassistant: [searches for login, reads file, edits with exact match, runs tests]\\nDone\\n\\nuser: Where are errors from the client handled?\\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.go:712.\\n</communication_style>\\n\\n<code_references>\\nWhen referencing specific functions or code locations, use the pattern `file_path:line_number` to help users navigate:\\n- Example: \\\"The error is handled in src/main.go:45\\\"\\n- Example: \\\"See the implementation in pkg/utils/helper.go:123-145\\\"\\n</code_references>\\n\\n<workflow>\\nFor every task, follow this sequence internally (don't narrate it):\\n\\n**Before acting**:\\n- Search codebase for relevant files\\n- Read files to understand current state\\n- Check memory for stored commands\\n- Identify what needs to change\\n- Use `git log` and `git blame` for additional context when needed\\n\\n**While acting**:\\n- Read entire file before editing it\\n- Use exact text for find/replace (include whitespace)\\n- Make one logical change at a time\\n- After each change: run tests\\n- If tests fail: fix immediately\\n- Keep going until query is completely resolved before yielding to user\\n- For longer tasks, send brief progress updates (under 10 words) at reasonable intervals\\n\\n**Before finishing**:\\n- Run lint/typecheck if in memory\\n- Verify all changes work\\n- Keep response under 4 lines\\n\\n**Key behaviors**:\\n- Use find_references before changing shared code\\n- Follow existing patterns (check similar files)\\n- If stuck, try different approach (don't repeat failures)\\n- Make decisions yourself (search first, don't ask)\\n- Fix problems at root cause, not surface-level patches\\n- Don't fix unrelated bugs or broken tests (mention them in final message if relevant)\\n</workflow>\\n\\n<decision_making>\\n**Make decisions autonomously** - don't ask when you can:\\n- Search to find the answer\\n- Read files to see patterns\\n- Check similar code\\n- Infer from context\\n- Try most likely approach\\n\\n**Only ask user if**:\\n- Truly ambiguous business requirement\\n- Multiple valid approaches with big tradeoffs\\n- Could cause data loss\\n- Exhausted all attempts\\n\\nExamples of autonomous decisions:\\n- File location → search for similar files\\n- Test command → check package.json/memory\\n- Code style → read existing code\\n- Library choice → check what's used\\n- Naming → follow existing names\\n</decision_making>\\n\\n<editing_files>\\nCritical: ALWAYS read files before editing them in this conversation.\\n\\nWhen using edit tools:\\n1. Read the file first\\n2. Find exact text to replace (include indentation/spaces)\\n3. Make replacement unambiguous (enough context)\\n4. Verify edit succeeded\\n5. Run tests\\n\\nEfficiency tips:\\n- Don't re-read files after successful edits (tool will fail if it didn't work)\\n- Same applies for making folders, deleting files, etc.\\n\\nCommon mistakes to avoid:\\n- Editing without reading first\\n- Approximate text matches\\n- Wrong indentation\\n- Not enough context (text appears multiple times)\\n- Not testing after changes\\n</editing_files>\\n\\n<error_handling>\\nWhen errors occur:\\n1. Read complete error message\\n2. Understand root cause\\n3. Try different approach (don't repeat same action)\\n4. Search for similar code that works\\n5. Make targeted fix\\n6. Test to verify\\n\\nCommon errors:\\n- Import/Module → check paths, spelling, what exists\\n- Syntax → check brackets, indentation, typos\\n- Tests fail → read test, see what it expects\\n- File not found → use ls, check exact path\\n</error_handling>\\n\\n<memory_instructions>\\nMemory files store commands, preferences, and codebase info. Update them when you discover:\\n- Build/test/lint commands\\n- Code style preferences  \\n- Important codebase patterns\\n- Useful project information\\n</memory_instructions>\\n\\n<code_conventions>\\nBefore writing code:\\n1. Check if library exists (look at imports, package.json)\\n2. Read similar code for patterns\\n3. Match existing style\\n4. Use same libraries/frameworks\\n5. Follow security best practices (never log secrets)\\n6. Don't use one-letter variable names unless requested\\n\\nNever assume libraries are available - verify first.\\n\\n**Ambition vs. precision**:\\n- New projects → be creative and ambitious with implementation\\n- Existing codebases → be surgical and precise, respect surrounding code\\n- Don't change filenames or variables unnecessarily\\n- Don't add formatters/linters/tests to codebases that don't have them\\n</code_conventions>\\n\\n<testing>\\nAfter significant changes:\\n- Start testing as specific as possible to code changed, then broaden to build confidence\\n- Use self-verification: write unit tests, add output logs, or use debug statements to verify your solutions\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available (on precise targets when possible)\\n- For formatters: iterate max 3 times to get it right; if still failing, present correct solution and note formatting issue\\n- Suggest adding commands to memory if not found\\n- Don't fix unrelated bugs or test failures (not your responsibility)\\n</testing>\\n\\n<tool_usage>\\n- Search before assuming\\n- Read files before editing\\n- Always use absolute paths for file operations (editing, reading, writing)\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- When making multiple independent bash calls, send them in a single message with multiple tool calls for parallel execution\\n- Summarize tool output for user (they don't see it)\\n\\n<bash_commands>\\nWhen running non-trivial bash commands (especially those that modify the system):\\n- Briefly explain what the command does and why you're running it\\n- This ensures the user understands potentially dangerous operations\\n- Simple read-only commands (ls, cat, etc.) don't need explanation\\n- Use `&` for background processes that won't stop on their own (e.g., `node server.js &`)\\n- Avoid interactive commands - use non-interactive versions (e.g., `npm init -y` not `npm init`)\\n- Combine related commands to save time (e.g., `git status && git diff HEAD && git log -n 3`)\\n</bash_commands>\\n</tool_usage>\\n\\n<proactiveness>\\nBalance autonomy with user intent:\\n- When asked to do something → do it fully (including follow-ups)\\n- When asked how to approach → explain first, don't auto-implement\\n- After completing work → stop, don't explain (unless asked)\\n- Don't surprise user with unexpected actions\\n</proactiveness>\\n\\n<final_answers>\\nAdapt verbosity to match the work completed:\\n\\n**Default (under 4 lines)**:\\n- Simple questions or single-file changes\\n- Casual conversation, greetings, acknowledgements\\n- One-word answers when possible\\n\\n**More detail allowed (up to 10-15 lines)**:\\n- Large multi-file changes that need walkthrough\\n- Complex refactoring where rationale adds value\\n- Tasks where understanding the approach is important\\n- When mentioning unrelated bugs/issues found\\n- Suggesting logical next steps user might want\\n\\n**What to include in verbose answers**:\\n- Brief summary of what was done and why\\n- Key files/functions changed (with `file:line` references)\\n- Any important decisions or tradeoffs made\\n- Next steps or things user should verify\\n- Issues found but not fixed\\n\\n**What to avoid**:\\n- Don't show full file contents unless explicitly asked\\n- Don't explain how to save files or copy code (user has access to your work)\\n- Don't use \\\"Here's what I did\\\" or \\\"Let me know if...\\\" style preambles/postambles\\n- Keep tone direct and factual, like handing off work to a teammate\\n</final_answers>\\n\\n<env>\\nWorking directory: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\n</env>\\n\\n\\n\\n\\n\",\"role\":\"system\"},{\"content\":\"update the main.go file by changing the print to say hello from crush\",\"role\":\"user\"},{\"tool_calls\":[{\"id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"function\":{\"arguments\":\"{\\\"path\\\": \\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file\\\", \\\"depth\\\": 2}\",\"name\":\"ls\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"\\n- /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/\\n  - go.mod\\n  - main.go\\n\",\"tool_call_id\":\"call_pXKzauntjK740LCfAkfJsrRS\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|package main\\n     2|\\n     3|import \\\"fmt\\\"\\n     4|\\n     5|func main() {\\n     6|\\tfmt.Println(\\\"Hello, World!\\\")\\n     7|}\\n</file>\\n\",\"tool_call_id\":\"call_8CabCVI9eFDOvoNwIRlcpqKa\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/go.mod\\\"}\",\"name\":\"view\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<file>\\n     1|module example.com/testproject\\n     2|\\n     3|go 1.23\\n</file>\\n\",\"tool_call_id\":\"call_FPzIXdEJMaLXuwgcDzp1GrUe\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_kDlxWt9HxmhuJQ799z3345KV\",\"function\":{\"arguments\":\"{\\\"file_path\\\":\\\"/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"old_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"Hello, World!\\\\\\\")\\\\n}\\\\n\\\",\\\"new_string\\\":\\\"func main() {\\\\n\\\\tfmt.Println(\\\\\\\"hello from crush\\\\\\\")\\\\n}\\\\n\\\"}\",\"name\":\"edit\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"<result>\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\n</result>\\n\",\"tool_call_id\":\"call_kDlxWt9HxmhuJQ799z3345KV\",\"role\":\"tool\"},{\"tool_calls\":[{\"id\":\"call_A0s7KddYbxCPmcyi0pUyXIts\",\"function\":{\"arguments\":\"{\\\"command\\\":\\\"go run /tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file/main.go\\\",\\\"description\\\":\\\"Run the Go program to verify output\\\"}\",\"name\":\"bash\"},\"type\":\"function\"}],\"role\":\"assistant\"},{\"content\":\"hello from crush\\n\\n\\n<cwd>/tmp/crush-test/TestCoderAgent/openai-gpt-5/update_a_file</cwd>\",\"tool_call_id\":\"call_A0s7KddYbxCPmcyi0pUyXIts\",\"role\":\"tool\"}],\"model\":\"gpt-5\",\"max_completion_tokens\":10000,\"stream_options\":{\"include_usage\":true},\"tool_choice\":\"auto\",\"tools\":[{\"function\":{\"name\":\"bash\",\"strict\":false,\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n<cross_platform>\\nUses mvdan/sh interpreter (Bash-compatible on all platforms including Windows).\\nUse forward slashes for paths: \\\"ls C:/foo/bar\\\" not \\\"ls C:\\\\foo\\\\bar\\\".\\nCommon shell builtins and core utils available on Windows.\\n</cross_platform>\\n\\n<execution_steps>\\n1. Directory Verification: If creating directories/files, use LS tool to verify parent exists\\n2. Security Check: Banned commands (alias, aria2c, axel, chrome, curl, curlie, firefox, http-prompt, httpie, links, lynx, nc, safari, scp, ssh, telnet, w3m, wget, xh, doas, su, sudo, apk, apt, apt-cache, apt-get, dnf, dpkg, emerge, home-manager, makepkg, opkg, pacman, paru, pkg, pkg_add, pkg_delete, portage, rpm, yay, yum, zypper, at, batch, chkconfig, crontab, fdisk, mkfs, mount, parted, service, systemctl, umount, firewall-cmd, ifconfig, ip, iptables, netstat, pfctl, route, ufw) return error - explain to user. Safe read-only commands execute without prompts\\n3. Command Execution: Execute with proper quoting, capture output\\n4. Output Processing: Truncate if exceeds 30000 characters\\n5. Return Result: Include errors, metadata with <cwd></cwd> tags\\n</execution_steps>\\n\\n<usage_notes>\\n- Command required, timeout optional (max 600000ms/10min, default 30min if unspecified)\\n- IMPORTANT: Use Grep/Glob/Agent tools instead of 'find'/'grep'. Use View/LS tools instead of 'cat'/'head'/'tail'/'ls'\\n- Chain with ';' or '&&', avoid newlines except in quoted strings\\n- Shell state persists (env vars, virtual envs, cwd, etc.)\\n- Prefer absolute paths over 'cd' (use 'cd' only if user explicitly requests)\\n</usage_notes>\\n\\n<git_commits>\\nWhen user asks to create git commit:\\n\\n1. Single message with three tool_use blocks (IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - git log (recent commit message style)\\n\\n2. Add relevant untracked files to staging. Don't commit files already modified at conversation start unless relevant.\\n\\n3. Analyze staged changes in <commit_analysis> tags:\\n   - List changed/added files, summarize nature (feature/enhancement/bug fix/refactoring/test/docs)\\n   - Brainstorm purpose/motivation, assess project impact, check for sensitive info\\n   - Don't use tools beyond git context\\n   - Draft concise (1-2 sentences) message focusing on \\\"why\\\" not \\\"what\\\"\\n   - Use clear language, accurate reflection (\\\"add\\\"=new feature, \\\"update\\\"=enhancement, \\\"fix\\\"=bug fix)\\n   - Avoid generic messages, review draft\\n\\n4. Create commit with Crush signature using HEREDOC:\\n   git commit -m \\\"$(cat &lt;&lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush <crush@charm.land>\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n</git_commits>\\n\\n<pull_requests>\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in <pr_analysis> tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat &lt;&lt;'EOF'\\n\\n   ## Summary\\n\\n   &lt;1-3 bullet points>\\n\\n   ## Test plan\\n\\n   [Checklist of TODOs...]\\n\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   EOF\\n   )\\\"\\n\\nImportant:\\n\\n- Return empty response - user sees gh output\\n- Never update git config\\n</pull_requests>\\n\\n<examples>\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar && pytest tests\\n</examples>\\n\",\"parameters\":{\"properties\":{\"command\":{\"description\":\"The command to execute\",\"type\":\"string\"},\"description\":{\"description\":\"A brief description of what the command does\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in milliseconds (max 600000)\",\"type\":\"integer\"}},\"required\":[\"command\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"download\",\"strict\":false,\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n<usage>\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Downloads any file type (binary or text)\\n- Auto-creates parent directories if missing\\n- Handles large files efficiently with streaming\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max file size: 100MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n- Will overwrite existing files without warning\\n</limitations>\\n\\n<tips>\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The local file path where the downloaded content should be saved\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 600)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to download from\",\"type\":\"string\"}},\"required\":[\"url\",\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"edit\",\"strict\":false,\"description\":\"Edits files by replacing text, creating new files, or deleting content. For moving/renaming use Bash 'mv'. For large edits use Write tool.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. old_string: Text to replace (must match exactly including whitespace/indentation)\\n3. new_string: Replacement text\\n4. replace_all: Replace all occurrences (default false)\\n</parameters>\\n\\n<special_cases>\\n- Create file: provide file_path + new_string, leave old_string empty\\n- Delete content: provide file_path + old_string, leave new_string empty\\n</special_cases>\\n\\n<critical_requirements>\\nUNIQUENESS (when replace_all=false): old_string MUST uniquely identify target instance\\n\\n- Include 3-5 lines context BEFORE and AFTER change point\\n- Include exact whitespace, indentation, surrounding code\\n\\nSINGLE INSTANCE: Tool changes ONE instance when replace_all=false\\n\\n- For multiple instances: set replace_all=true OR make separate calls with unique context\\n- Plan calls carefully to avoid conflicts\\n\\nVERIFICATION: Before using\\n\\n- Check how many instances of target text exist\\n- Gather sufficient context for unique identification\\n- Plan separate calls or use replace_all\\n</critical_requirements>\\n\\n<warnings>\\nTool fails if:\\n- old_string matches multiple locations and replace_all=false\\n- old_string doesn't match exactly (including whitespace)\\n- Insufficient context causes wrong instance change\\n</warnings>\\n\\n<best_practices>\\n- Ensure edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use forward slashes (/) for cross-platform compatibility\\n- Multiple edits to same file: send all in single message with multiple tool calls\\n</best_practices>\\n\\n<windows_notes>\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n</windows_notes>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"},\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false)\",\"type\":\"boolean\"}},\"required\":[\"file_path\",\"old_string\",\"new_string\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"multiedit\",\"strict\":false,\"description\":\"Makes multiple edits to a single file in one operation. Built on Edit tool for efficient multiple find-and-replace operations. Prefer over Edit tool for multiple edits to same file.\\n\\n<prerequisites>\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n</prerequisites>\\n\\n<parameters>\\n1. file_path: Absolute path to file (required)\\n2. edits: Array of edit operations, each containing:\\n   - old_string: Text to replace (must match exactly including whitespace/indentation)\\n   - new_string: Replacement text\\n   - replace_all: Replace all occurrences (optional, defaults to false)\\n</parameters>\\n\\n<operation>\\n- Edits applied sequentially in provided order\\n- Each edit operates on result of previous edit\\n- All edits must be valid for operation to succeed - if any fails, none applied\\n- Ideal for several changes to different parts of same file\\n</operation>\\n\\n<critical_requirements>\\n1. All edits follow same requirements as single Edit tool\\n2. Edits are atomic - either all succeed or none applied\\n3. Plan edits carefully to avoid conflicts between sequential operations\\n</critical_requirements>\\n\\n<warnings>\\n- Tool fails if old_string doesn't match file contents exactly (including whitespace)\\n- Tool fails if old_string and new_string are identical\\n- Earlier edits may affect text that later edits try to find - plan sequence carefully\\n</warnings>\\n\\n<best_practices>\\n- Ensure all edits result in correct, idiomatic code\\n- Don't leave code in broken state\\n- Use absolute file paths (starting with /)\\n- Use replace_all for renaming variables across file\\n- Avoid adding emojis unless user explicitly requests\\n</best_practices>\\n\\n<new_file_creation>\\n- Provide new file path (including directory if needed)\\n- First edit: empty old_string, new file contents as new_string\\n- Subsequent edits: normal edit operations on created content\\n</new_file_creation>\\n\",\"parameters\":{\"properties\":{\"edits\":{\"description\":\"Array of edit operations to perform sequentially on the file\",\"items\":{\"new_string\":{\"description\":\"The text to replace it with\",\"type\":\"string\"},\"old_string\":{\"description\":\"The text to replace\",\"type\":\"string\"},\"replace_all\":{\"description\":\"Replace all occurrences of old_string (default false).\",\"type\":\"boolean\"}},\"type\":\"array\"},\"file_path\":{\"description\":\"The absolute path to the file to modify\",\"type\":\"string\"}},\"required\":[\"file_path\",\"edits\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"fetch\",\"strict\":false,\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n<usage>\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n</usage>\\n\\n<features>\\n- Supports three output formats: text, markdown, html\\n- Auto-handles HTTP redirects\\n- Sets reasonable timeouts to prevent hanging\\n- Validates input parameters before requests\\n</features>\\n\\n<limitations>\\n- Max response size: 5MB\\n- Only supports HTTP and HTTPS protocols\\n- Cannot handle authentication or cookies\\n- Some websites may block automated requests\\n</limitations>\\n\\n<tips>\\n- Use text format for plain text content or simple API responses\\n- Use markdown format for content that should be rendered with formatting\\n- Use html format when you need raw HTML structure\\n- Set appropriate timeouts for potentially slow websites\\n</tips>\\n\",\"parameters\":{\"properties\":{\"format\":{\"description\":\"The format to return the content in (text, markdown, or html)\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"},\"url\":{\"description\":\"The URL to fetch content from\",\"type\":\"string\"}},\"required\":[\"url\",\"format\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"glob\",\"strict\":false,\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide glob pattern to match against file paths\\n- Optional starting directory (defaults to current working directory)\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<pattern_syntax>\\n- '\\\\*' matches any sequence of non-separator characters\\n- '\\\\*\\\\*' matches any sequence including separators\\n- '?' matches any single non-separator character\\n- '[...]' matches any character in brackets\\n- '[!...]' matches any character not in brackets\\n</pattern_syntax>\\n\\n<examples>\\n- '*.js' - JavaScript files in current directory\\n- '**/*.js' - JavaScript files in any subdirectory\\n- 'src/**/*.{ts,tsx}' - TypeScript files in src directory\\n- '*.{html,css,js}' - HTML, CSS, and JS files\\n</examples>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Does not search file contents (use Grep for that)\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<cross_platform>\\n- Path separators handled automatically (/ and \\\\ work)\\n- Uses ripgrep (rg) if available, otherwise Go implementation\\n- Patterns should use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Combine with Grep: find files with Glob, search contents with Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine pattern if needed\\n</tips>\\n\",\"parameters\":{\"properties\":{\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The glob pattern to match files against\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"grep\",\"strict\":false,\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n<usage>\\n- Provide regex pattern to search within file contents\\n- Set literal_text=true for exact text with special characters (recommended for non-regex users)\\n- Optional starting directory (defaults to current working directory)\\n- Optional include pattern to filter which files to search\\n- Results sorted with most recently modified files first\\n</usage>\\n\\n<regex_syntax>\\nWhen literal_text=false (supports standard regex):\\n\\n- 'function' searches for literal text \\\"function\\\"\\n- 'log\\\\..\\\\*Error' finds text starting with \\\"log.\\\" and ending with \\\"Error\\\"\\n- 'import\\\\s+.\\\\*\\\\s+from' finds import statements in JavaScript/TypeScript\\n</regex_syntax>\\n\\n<include_patterns>\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n</include_patterns>\\n\\n<limitations>\\n- Results limited to 100 files (newest first)\\n- Performance depends on number of files searched\\n- Very large binary files may be skipped\\n- Hidden files (starting with '.') skipped\\n</limitations>\\n\\n<ignore_support>\\n- Respects .gitignore patterns to skip ignored files/directories\\n- Respects .crushignore patterns for additional ignore rules\\n- Both ignore files auto-detected in search root directory\\n</ignore_support>\\n\\n<cross_platform>\\n- Uses ripgrep (rg) if available for better performance\\n- Falls back to Go implementation if ripgrep unavailable\\n- File paths normalized automatically for compatibility\\n</cross_platform>\\n\\n<tips>\\n- For faster searches: use Glob to find relevant files first, then Grep\\n- For iterative exploration requiring multiple searches, consider Agent tool\\n- Check if results truncated and refine search pattern if needed\\n- Use literal_text=true for exact text with special characters (dots, parentheses, etc.)\\n</tips>\\n\",\"parameters\":{\"properties\":{\"include\":{\"description\":\"File pattern to include in the search (e.g. \\\"*.js\\\", \\\"*.{ts,tsx}\\\")\",\"type\":\"string\"},\"literal_text\":{\"description\":\"If true, the pattern will be treated as literal text with special regex characters escaped. Default is false.\",\"type\":\"boolean\"},\"path\":{\"description\":\"The directory to search in. Defaults to the current working directory.\",\"type\":\"string\"},\"pattern\":{\"description\":\"The regex pattern to search for in file contents\",\"type\":\"string\"}},\"required\":[\"pattern\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"ls\",\"strict\":false,\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n<usage>\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n</usage>\\n\\n<features>\\n- Hierarchical view of files and directories\\n- Auto-skips hidden files/directories (starting with '.')\\n- Skips common system directories like __pycache__\\n- Can filter files matching specific patterns\\n</features>\\n\\n<limitations>\\n- Results limited to 1000 files\\n- Large directories truncated\\n- No file sizes or permissions shown\\n- Cannot recursively list all directories in large projects\\n</limitations>\\n\\n<cross_platform>\\n- Hidden file detection uses Unix convention (files starting with '.')\\n- Windows hidden files (with hidden attribute) not auto-skipped\\n- Common Windows directories (System32, Program Files) not in default ignore\\n- Path separators handled automatically (/ and \\\\ work)\\n</cross_platform>\\n\\n<tips>\\n- Use Glob for finding files by name patterns instead of browsing\\n- Use Grep for searching file contents\\n- Combine with other tools for effective exploration\\n</tips>\\n\",\"parameters\":{\"properties\":{\"depth\":{\"description\":\"The maximum depth to traverse\",\"type\":\"integer\"},\"ignore\":{\"description\":\"List of glob patterns to ignore\",\"items\":{},\"type\":\"array\"},\"path\":{\"description\":\"The path to the directory to list (defaults to current working directory)\",\"type\":\"string\"}},\"required\":[],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"sourcegraph\",\"strict\":false,\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n<usage>\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n</usage>\\n\\n<basic_syntax>\\n- \\\"fmt.Println\\\" - exact matches\\n- \\\"file:.go fmt.Println\\\" - limit to Go files\\n- \\\"repo:^github\\\\.com/golang/go$ fmt.Println\\\" - specific repos\\n- \\\"lang:go fmt.Println\\\" - limit to Go code\\n- \\\"fmt.Println AND log.Fatal\\\" - combined terms\\n- \\\"fmt\\\\.(Print|Printf|Println)\\\" - regex patterns\\n- \\\"\\\\\\\"exact phrase\\\\\\\"\\\" - exact phrase matching\\n- \\\"-file:test\\\" or \\\"-repo:forks\\\" - exclude matches\\n</basic_syntax>\\n\\n<key_filters>\\nRepository: repo:name, repo:^exact$, repo:org/repo@branch, -repo:exclude, fork:yes, archived:yes, visibility:public\\nFile: file:\\\\.js$, file:internal/, -file:test, file:has.content(text)\\nContent: content:\\\"exact\\\", -content:\\\"unwanted\\\", case:yes\\nType: type:symbol, type:file, type:path, type:diff, type:commit\\nTime: after:\\\"1 month ago\\\", before:\\\"2023-01-01\\\", author:name, message:\\\"fix\\\"\\nResult: select:repo, select:file, select:content, count:100, timeout:30s\\n</key_filters>\\n\\n<examples>\\n- \\\"file:.go context.WithTimeout\\\" - Go code using context.WithTimeout\\n- \\\"lang:typescript useState type:symbol\\\" - TypeScript React useState hooks\\n- \\\"repo:^github\\\\.com/kubernetes/kubernetes$ pod list type:file\\\" - Kubernetes pod files\\n- \\\"file:Dockerfile (alpine OR ubuntu) -content:alpine:latest\\\" - Dockerfiles with base images\\n</examples>\\n\\n<boolean_operators>\\n- \\\"term1 AND term2\\\" - both terms\\n- \\\"term1 OR term2\\\" - either term\\n- \\\"term1 NOT term2\\\" - term1 but not term2\\n- \\\"term1 and (term2 or term3)\\\" - grouping with parentheses\\n</boolean_operators>\\n\\n<limitations>\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n</limitations>\\n\\n<tips>\\n- Use specific file extensions to narrow results\\n- Add repo: filters for targeted searches\\n- Use type:symbol for function/method definitions\\n- Use type:file to find relevant files\\n</tips>\\n\",\"parameters\":{\"properties\":{\"context_window\":{\"description\":\"The context around the match to return (default: 10 lines)\",\"type\":\"integer\"},\"count\":{\"description\":\"Optional number of results to return (default: 10, max: 20)\",\"type\":\"integer\"},\"query\":{\"description\":\"The Sourcegraph search query\",\"type\":\"string\"},\"timeout\":{\"description\":\"Optional timeout in seconds (max 120)\",\"type\":\"integer\"}},\"required\":[\"query\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"view\",\"strict\":false,\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n<usage>\\n- Provide file path to read\\n- Optional offset: start reading from specific line (0-based)\\n- Optional limit: control lines read (default 2000)\\n- Don't use for directories (use LS tool instead)\\n</usage>\\n\\n<features>\\n- Displays contents with line numbers\\n- Can read from any file position using offset\\n- Handles large files by limiting lines read\\n- Auto-truncates very long lines for display\\n- Suggests similar filenames when file not found\\n</features>\\n\\n<limitations>\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines >2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n</limitations>\\n\\n<cross_platform>\\n- Handles Windows (CRLF) and Unix (LF) line endings\\n- Works with forward slashes (/) and backslashes (\\\\)\\n- Auto-detects text encoding for common formats\\n</cross_platform>\\n\\n<tips>\\n- Use with Glob to find files first\\n- For code exploration: Grep to find relevant files, then View to examine\\n- For large files: use offset parameter for specific sections\\n</tips>\\n\",\"parameters\":{\"properties\":{\"file_path\":{\"description\":\"The path to the file to read\",\"type\":\"string\"},\"limit\":{\"description\":\"The number of lines to read (defaults to 2000)\",\"type\":\"integer\"},\"offset\":{\"description\":\"The line number to start reading from (0-based)\",\"type\":\"integer\"}},\"required\":[\"file_path\"],\"type\":\"object\"}},\"type\":\"function\"},{\"function\":{\"name\":\"write\",\"strict\":false,\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n<usage>\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n</usage>\\n\\n<features>\\n- Creates new files or overwrites existing ones\\n- Auto-creates parent directories if missing\\n- Checks if file modified since last read for safety\\n- Avoids unnecessary writes when content unchanged\\n</features>\\n\\n<limitations>\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n</limitations>\\n\\n<cross_platform>\\n- Use forward slashes (/) for compatibility\\n</cross_platform>\\n\\n<tips>\\n- Use View tool first to examine existing files before modifying\\n- Use LS tool to verify location when creating new files\\n- Combine with Glob/Grep to find and modify multiple files\\n- Include descriptive comments when changing existing code\\n</tips>\\n\",\"parameters\":{\"properties\":{\"content\":{\"description\":\"The content to write to the file\",\"type\":\"string\"},\"file_path\":{\"description\":\"The path to the file to write\",\"type\":\"string\"}},\"required\":[\"file_path\",\"content\"],\"type\":\"object\"}},\"type\":\"function\"}],\"stream\":true}"
608    headers:
609      Accept:
610      - application/json
611      Content-Type:
612      - application/json
613      User-Agent:
614      - OpenAI/Go 2.7.1
615    url: https://api.openai.com/v1/chat/completions
616    method: POST
617  response:
618    proto: HTTP/2.0
619    proto_major: 2
620    proto_minor: 0
621    content_length: -1
622    body: |+
623      data: {"id":"chatcmpl-CTtD8mfWf7HnRw0EZVLTjpU8iDgL1","object":"chat.completion.chunk","created":1761239778,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":"","refusal":null},"finish_reason":null}],"usage":null,"obfuscation":"g2sV9ZoSc5"}
624
625      data: {"id":"chatcmpl-CTtD8mfWf7HnRw0EZVLTjpU8iDgL1","object":"chat.completion.chunk","created":1761239778,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Done"},"finish_reason":null}],"usage":null,"obfuscation":"GhwZ3C1U"}
626
627      data: {"id":"chatcmpl-CTtD8mfWf7HnRw0EZVLTjpU8iDgL1","object":"chat.completion.chunk","created":1761239778,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":null,"obfuscation":"vunUTh"}
628
629      data: {"id":"chatcmpl-CTtD8mfWf7HnRw0EZVLTjpU8iDgL1","object":"chat.completion.chunk","created":1761239778,"model":"gpt-5-2025-08-07","service_tier":"default","system_fingerprint":null,"choices":[],"usage":{"prompt_tokens":7860,"completion_tokens":4,"total_tokens":7864,"prompt_tokens_details":{"cached_tokens":7808,"audio_tokens":0},"completion_tokens_details":{"reasoning_tokens":0,"audio_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"obfuscation":"qWYa6"}
630
631      data: [DONE]
632
633    headers:
634      Content-Type:
635      - text/event-stream; charset=utf-8
636    status: 200 OK
637    code: 200
638    duration: 3.821753209s