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: 777
 10    host: ""
 11    body: '{"max_tokens":40,"messages":[{"content":[{"text":"Generate a concise title for the following content:\n\nupdate the main.go file by changing the print to say hello from crush\n \u003cthink\u003e\n\n\u003c/think\u003e","type":"text"}],"role":"user"}],"model":"claude-3-5-haiku-20241022","system":[{"text":"you will generate a short title based on the first message a user begins a conversation with\n\n\u003crules\u003e\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\u003c/rules\u003e\n\n /no_think","type":"text"}],"stream":true}'
 12    headers:
 13      Accept:
 14      - application/json
 15      Content-Type:
 16      - application/json
 17      User-Agent:
 18      - Anthropic/Go 1.14.0
 19    url: https://api.anthropic.com/v1/messages
 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      event: message_start
 28      data: {"type":"message_start","message":{"model":"claude-3-5-haiku-20241022","id":"msg_01V2gbirhEyjs4DiYnh93EC9","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"cache_creation":{"ephemeral_5m_input_tokens":0,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}             }
 29
 30      event: content_block_start
 31      data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}     }
 32
 33      event: content_block_delta
 34      data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Update"}               }
 35
 36      event: content_block_delta
 37      data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" main.go hello"}           }
 38
 39      event: ping
 40      data: {"type": "ping"}
 41
 42      event: content_block_delta
 43      data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" print"}               }
 44
 45      event: content_block_stop
 46      data: {"type":"content_block_stop","index":0              }
 47
 48      event: message_delta
 49      data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":145,"cache_creation_input_tokens":0,"cache_read_input_tokens":0,"output_tokens":9}   }
 50
 51      event: message_stop
 52      data: {"type":"message_stop" }
 53
 54    headers:
 55      Content-Type:
 56      - text/event-stream; charset=utf-8
 57    status: 200 OK
 58    code: 200
 59    duration: 700.907542ms
 60- id: 1
 61  request:
 62    proto: HTTP/1.1
 63    proto_major: 1
 64    proto_minor: 1
 65    content_length: 31163
 66    host: ""
 67    body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\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\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\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\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\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\\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\\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\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\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\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\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\\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\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\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\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\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\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\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)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\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\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"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\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\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 \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\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 '\\u0026\\u0026', 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\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\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 \\u003ccommit_analysis\\u003e 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 \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n   ## Summary\\n\\n   \\u0026lt;1-3 bullet points\\u003e\\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\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"edit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\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\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"multiedit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\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\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\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\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\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\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\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\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\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\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\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\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\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\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\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\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
 68    headers:
 69      Accept:
 70      - application/json
 71      Content-Type:
 72      - application/json
 73      User-Agent:
 74      - Anthropic/Go 1.14.0
 75    url: https://api.anthropic.com/v1/messages
 76    method: POST
 77  response:
 78    proto: HTTP/2.0
 79    proto_major: 2
 80    proto_minor: 0
 81    content_length: -1
 82    body: |+
 83      event: message_start
 84      data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01BGZLUc1twLVbQk15aHwo1v","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"cache_creation":{"ephemeral_5m_input_tokens":1716,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}            }
 85
 86      event: content_block_start
 87      data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_011XTovZHHrqbeMteDcXFDxD","name":"view","input":{}}              }
 88
 89      event: content_block_delta
 90      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}           }
 91
 92      event: content_block_delta
 93      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_pat"}               }
 94
 95      event: content_block_delta
 96      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"h\": "}      }
 97
 98      event: content_block_delta
 99      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"main.go"}  }
100
101      event: content_block_delta
102      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\"}"}}
103
104      event: content_block_stop
105      data: {"type":"content_block_stop","index":0         }
106
107      event: message_delta
108      data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":2,"cache_creation_input_tokens":1716,"cache_read_input_tokens":6852,"output_tokens":55} }
109
110      event: message_stop
111      data: {"type":"message_stop"     }
112
113    headers:
114      Content-Type:
115      - text/event-stream; charset=utf-8
116    status: 200 OK
117    code: 200
118    duration: 2.543036458s
119- id: 2
120  request:
121    proto: HTTP/1.1
122    proto_major: 1
123    proto_minor: 1
124    content_length: 31645
125    host: ""
126    body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cfile\\u003e\\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\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\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\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\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\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\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\\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\\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\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\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\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\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\\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\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\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\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\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\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\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)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\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\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"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\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\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 \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\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 '\\u0026\\u0026', 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\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\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 \\u003ccommit_analysis\\u003e 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 \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n   ## Summary\\n\\n   \\u0026lt;1-3 bullet points\\u003e\\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\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"edit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\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\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"multiedit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\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\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\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\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\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\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\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\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\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\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\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\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\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\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\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\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
127    headers:
128      Accept:
129      - application/json
130      Content-Type:
131      - application/json
132      User-Agent:
133      - Anthropic/Go 1.14.0
134    url: https://api.anthropic.com/v1/messages
135    method: POST
136  response:
137    proto: HTTP/2.0
138    proto_major: 2
139    proto_minor: 0
140    content_length: -1
141    body: |+
142      event: message_start
143      data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_01SxNBCVbJi3vF81CoCZVean","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":8568,"cache_creation":{"ephemeral_5m_input_tokens":120,"ephemeral_1h_input_tokens":0},"output_tokens":33,"service_tier":"standard"}}         }
144
145      event: content_block_start
146      data: {"type":"content_block_start","index":0,"content_block":{"type":"tool_use","id":"toolu_017DGAG8X47hb2gawfBGnBz1","name":"edit","input":{}}}
147
148      event: content_block_delta
149      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":""}      }
150
151      event: content_block_delta
152      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"{\"file_path\""}              }
153
154      event: content_block_delta
155      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":": \"m"}      }
156
157      event: content_block_delta
158      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ain"}           }
159
160      event: content_block_delta
161      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".go\""}               }
162
163      event: content_block_delta
164      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"ol"}         }
165
166      event: content_block_delta
167      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d_st"} }
168
169      event: content_block_delta
170      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ring\": \"func"}    }
171
172      event: content_block_delta
173      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" main()"}         }
174
175      event: content_block_delta
176      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" {\\n\\tfmt"}      }
177
178      event: content_block_delta
179      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":".P"}        }
180
181      event: content_block_delta
182      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ri"}              }
183
184      event: content_block_delta
185      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ntln(\\\"Hell"} }
186
187      event: content_block_delta
188      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"o, Worl"}      }
189
190      event: content_block_delta
191      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"d!"}               }
192
193      event: content_block_delta
194      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")\\n}\""}           }
195
196      event: content_block_delta
197      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":", \"new_str"}       }
198
199      event: content_block_delta
200      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"ing\": \"f"}               }
201
202      event: content_block_delta
203      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"unc main()"} }
204
205      event: content_block_delta
206      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":" {\\n\\tf"}               }
207
208      event: content_block_delta
209      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"mt."}           }
210
211      event: content_block_delta
212      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"Println"}          }
213
214      event: content_block_delta
215      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"(\\\"hel"}               }
216
217      event: content_block_delta
218      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"lo f"}       }
219
220      event: content_block_delta
221      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"rom crush"}            }
222
223      event: content_block_delta
224      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"\\\")\\n"}         }
225
226      event: content_block_delta
227      data: {"type":"content_block_delta","index":0,"delta":{"type":"input_json_delta","partial_json":"}\"}"}               }
228
229      event: content_block_stop
230      data: {"type":"content_block_stop","index":0     }
231
232      event: message_delta
233      data: {"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":120,"cache_read_input_tokens":8568,"output_tokens":123}              }
234
235      event: message_stop
236      data: {"type":"message_stop"     }
237
238    headers:
239      Content-Type:
240      - text/event-stream; charset=utf-8
241    status: 200 OK
242    code: 200
243    duration: 2.447528917s
244- id: 3
245  request:
246    proto: HTTP/1.1
247    proto_major: 1
248    proto_minor: 1
249    content_length: 32191
250    host: ""
251    body: "{\"max_tokens\":10000,\"messages\":[{\"content\":[{\"text\":\"update the main.go file by changing the print to say hello from crush\",\"type\":\"text\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"input\":{\"file_path\":\"main.go\"},\"name\":\"view\",\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_011XTovZHHrqbeMteDcXFDxD\",\"content\":[{\"text\":\"\\u003cfile\\u003e\\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\\u003c/file\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"},{\"content\":[{\"id\":\"toolu_017DGAG8X47hb2gawfBGnBz1\",\"input\":{\"file_path\":\"main.go\",\"new_string\":\"func main() {\\n\\tfmt.Println(\\\"hello from crush\\\")\\n}\",\"old_string\":\"func main() {\\n\\tfmt.Println(\\\"Hello, World!\\\")\\n}\"},\"name\":\"edit\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"tool_use\"}],\"role\":\"assistant\"},{\"content\":[{\"tool_use_id\":\"toolu_017DGAG8X47hb2gawfBGnBz1\",\"cache_control\":{\"type\":\"ephemeral\"},\"content\":[{\"text\":\"\\u003cresult\\u003e\\nContent replaced in file: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file/main.go\\n\\u003c/result\\u003e\\n\",\"type\":\"text\"}],\"type\":\"tool_result\"}],\"role\":\"user\"}],\"model\":\"claude-sonnet-4-5-20250929\",\"system\":[{\"text\":\"You are Crush, a powerful AI Assistant that runs in the CLI.\\n\\n\\u003ccritical_rules\\u003e\\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\\n\\u003c/critical_rules\\u003e\\n\\n\\u003ccommunication_style\\u003e\\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\\u003c/communication_style\\u003e\\n\\n\\u003cworkflow\\u003e\\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\\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\\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\\u003c/workflow\\u003e\\n\\n\\u003cdecision_making\\u003e\\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\\u003c/decision_making\\u003e\\n\\n\\u003cediting_files\\u003e\\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\\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\\u003c/editing_files\\u003e\\n\\n\\u003cerror_handling\\u003e\\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\\u003c/error_handling\\u003e\\n\\n\\u003cmemory_instructions\\u003e\\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\\u003c/memory_instructions\\u003e\\n\\n\\u003ccode_conventions\\u003e\\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)\\n\\nNever assume libraries are available - verify first.\\n\\u003c/code_conventions\\u003e\\n\\n\\u003ctesting\\u003e\\nAfter significant changes:\\n- Run relevant test suite\\n- If tests fail, fix before continuing\\n- Check memory for test commands\\n- Run lint/typecheck if available\\n- Suggest adding commands to memory if not found\\n\\u003c/testing\\u003e\\n\\n\\u003ctool_usage\\u003e\\n- Search before assuming\\n- Read files before editing\\n- Use Agent tool for complex searches\\n- Run tools in parallel when safe (no dependencies)\\n- Summarize tool output for user (they don't see it)\\n\\u003c/tool_usage\\u003e\\n\\n\\u003cproactiveness\\u003e\\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\\u003c/proactiveness\\u003e\\n\\n\\u003cenv\\u003e\\nWorking directory: /tmp/crush-test/TestCoderAgent/anthropic-sonnet/update_a_file\\nIs directory a git repo: no\\nPlatform: linux\\nToday's date: 1/1/2025\\n\\u003c/env\\u003e\\n\\n\\n\\n\\n\",\"cache_control\":{\"type\":\"ephemeral\"},\"type\":\"text\"}],\"tool_choice\":{\"disable_parallel_tool_use\":false,\"type\":\"auto\"},\"tools\":[{\"input_schema\":{\"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\"},\"name\":\"bash\",\"description\":\"Executes bash commands in persistent shell session with timeout and security measures.\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003cexecution_steps\\u003e\\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 \\u003ccwd\\u003e\\u003c/cwd\\u003e tags\\n\\u003c/execution_steps\\u003e\\n\\n\\u003cusage_notes\\u003e\\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 '\\u0026\\u0026', 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\\u003c/usage_notes\\u003e\\n\\n\\u003cgit_commits\\u003e\\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 \\u003ccommit_analysis\\u003e 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 \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n   Commit message here.\\n\\n   \U0001F498 Generated with Crush\\n\\n\\n   Co-Authored-By: Crush \\u003ccrush@charm.land\\u003e\\n\\n   EOF\\n   )\\\"\\n\\n5. If pre-commit hook fails, retry ONCE. If fails again, hook preventing commit. If succeeds but files modified, MUST amend.\\n\\n6. Run git status to verify.\\n\\nNotes: Use \\\"git commit -am\\\" when possible, don't stage unrelated files, NEVER update config, don't push, no -i flags, no empty commits, return empty response.\\n\\u003c/git_commits\\u003e\\n\\n\\u003cpull_requests\\u003e\\nUse gh command for ALL GitHub tasks. When user asks to create PR:\\n\\n1. Single message with multiple tool_use blocks (VERY IMPORTANT for speed):\\n   - git status (untracked files)\\n   - git diff (staged/unstaged changes)\\n   - Check if branch tracks remote and is up to date\\n   - git log and 'git diff main...HEAD' (full commit history from main divergence)\\n\\n2. Create new branch if needed\\n3. Commit changes if needed\\n4. Push to remote with -u flag if needed\\n\\n5. Analyze changes in \\u003cpr_analysis\\u003e tags:\\n   - List commits since diverging from main\\n   - Summarize nature of changes\\n   - Brainstorm purpose/motivation\\n   - Assess project impact\\n   - Don't use tools beyond git context\\n   - Check for sensitive information\\n   - Draft concise (1-2 bullet points) PR summary focusing on \\\"why\\\"\\n   - Ensure summary reflects ALL changes since main divergence\\n   - Clear, concise language\\n   - Accurate reflection of changes and purpose\\n   - Avoid generic summaries\\n   - Review draft\\n\\n6. Create PR with gh pr create using HEREDOC:\\n   gh pr create --title \\\"title\\\" --body \\\"$(cat \\u0026lt;\\u0026lt;'EOF'\\n\\n   ## Summary\\n\\n   \\u0026lt;1-3 bullet points\\u003e\\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\\u003c/pull_requests\\u003e\\n\\n\\u003cexamples\\u003e\\nGood: pytest /foo/bar/tests\\nBad: cd /foo/bar \\u0026\\u0026 pytest tests\\n\\u003c/examples\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"download\",\"description\":\"Downloads binary data from URL and saves to local file.\\n\\n\\u003cusage\\u003e\\n- Provide URL to download from\\n- Specify local file path where content should be saved\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\n- Use absolute paths or paths relative to working directory\\n- Set appropriate timeouts for large files or slow connections\\n\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"edit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. For new files: Use LS tool to verify parent directory exists\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003cspecial_cases\\u003e\\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\\u003c/special_cases\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cwindows_notes\\u003e\\n- Forward slashes work throughout (C:/path/file)\\n- File permissions handled automatically\\n- Line endings converted automatically (\\\\n ↔ \\\\r\\\\n)\\n\\u003c/windows_notes\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"multiedit\",\"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\\u003cprerequisites\\u003e\\n1. Use View tool to understand file contents and context\\n2. Verify directory path is correct\\n\\u003c/prerequisites\\u003e\\n\\n\\u003cparameters\\u003e\\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\\u003c/parameters\\u003e\\n\\n\\u003coperation\\u003e\\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\\u003c/operation\\u003e\\n\\n\\u003ccritical_requirements\\u003e\\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\\u003c/critical_requirements\\u003e\\n\\n\\u003cwarnings\\u003e\\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\\u003c/warnings\\u003e\\n\\n\\u003cbest_practices\\u003e\\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\\u003c/best_practices\\u003e\\n\\n\\u003cnew_file_creation\\u003e\\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\\u003c/new_file_creation\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"fetch\",\"description\":\"Fetches content from URL and returns it in specified format.\\n\\n\\u003cusage\\u003e\\n- Provide URL to fetch content from\\n- Specify desired output format (text, markdown, or html)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"glob\",\"description\":\"Fast file pattern matching tool that finds files by name/pattern, returning paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cpattern_syntax\\u003e\\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\\u003c/pattern_syntax\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"grep\",\"description\":\"Fast content search tool that finds files containing specific text/patterns, returning matching paths sorted by modification time (newest first).\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cregex_syntax\\u003e\\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\\u003c/regex_syntax\\u003e\\n\\n\\u003cinclude_patterns\\u003e\\n- '\\\\*.js' - Only search JavaScript files\\n- '\\\\*.{ts,tsx}' - Only search TypeScript files\\n- '\\\\*.go' - Only search Go files\\n\\u003c/include_patterns\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003cignore_support\\u003e\\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\\u003c/ignore_support\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"ls\",\"description\":\"Shows files and subdirectories in tree structure for exploring project organization.\\n\\n\\u003cusage\\u003e\\n- Provide path to list (defaults to current working directory)\\n- Optional glob patterns to ignore\\n- Results displayed in tree structure\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\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\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"sourcegraph\",\"description\":\"Search code across public repositories using Sourcegraph's GraphQL API.\\n\\n\\u003cusage\\u003e\\n- Provide search query using Sourcegraph syntax\\n- Optional result count (default: 10, max: 20)\\n- Optional timeout for request\\n\\u003c/usage\\u003e\\n\\n\\u003cbasic_syntax\\u003e\\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\\u003c/basic_syntax\\u003e\\n\\n\\u003ckey_filters\\u003e\\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\\u003c/key_filters\\u003e\\n\\n\\u003cexamples\\u003e\\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\\u003c/examples\\u003e\\n\\n\\u003cboolean_operators\\u003e\\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\\u003c/boolean_operators\\u003e\\n\\n\\u003climitations\\u003e\\n- Only searches public repositories\\n- Rate limits may apply\\n- Complex queries take longer\\n- Max 20 results per query\\n\\u003c/limitations\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"view\",\"description\":\"Reads and displays file contents with line numbers for examining code, logs, or text data.\\n\\n\\u003cusage\\u003e\\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\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Max file size: 250KB\\n- Default limit: 2000 lines\\n- Lines \\u003e2000 chars truncated\\n- Cannot display binary files/images (identifies them)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\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\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\"},{\"input_schema\":{\"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\"},\"name\":\"write\",\"description\":\"Creates or updates files in filesystem for saving/modifying text content.\\n\\n\\u003cusage\\u003e\\n- Provide file path to write\\n- Include content to write to file\\n- Tool creates necessary parent directories automatically\\n\\u003c/usage\\u003e\\n\\n\\u003cfeatures\\u003e\\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\\u003c/features\\u003e\\n\\n\\u003climitations\\u003e\\n- Read file before writing to avoid conflicts\\n- Cannot append (rewrites entire file)\\n\\u003c/limitations\\u003e\\n\\n\\u003ccross_platform\\u003e\\n- Use forward slashes (/) for compatibility\\n\\u003c/cross_platform\\u003e\\n\\n\\u003ctips\\u003e\\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\\u003c/tips\\u003e\\n\",\"cache_control\":{\"type\":\"ephemeral\"}}],\"stream\":true}"
252    headers:
253      Accept:
254      - application/json
255      Content-Type:
256      - application/json
257      User-Agent:
258      - Anthropic/Go 1.14.0
259    url: https://api.anthropic.com/v1/messages
260    method: POST
261  response:
262    proto: HTTP/2.0
263    proto_major: 2
264    proto_minor: 0
265    content_length: -1
266    body: |+
267      event: message_start
268      data: {"type":"message_start","message":{"model":"claude-sonnet-4-5-20250929","id":"msg_0156vJYCmnoDHddugupfiaQP","type":"message","role":"assistant","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":8688,"cache_creation":{"ephemeral_5m_input_tokens":175,"ephemeral_1h_input_tokens":0},"output_tokens":1,"service_tier":"standard"}}         }
269
270      event: content_block_start
271      data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}      }
272
273      event: content_block_delta
274      data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Done"}           }
275
276      event: content_block_stop
277      data: {"type":"content_block_stop","index":0         }
278
279      event: message_delta
280      data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":5,"cache_creation_input_tokens":175,"cache_read_input_tokens":8688,"output_tokens":4}    }
281
282      event: message_stop
283      data: {"type":"message_stop" }
284
285    headers:
286      Content-Type:
287      - text/event-stream; charset=utf-8
288    status: 200 OK
289    code: 200
290    duration: 2.651659958s