litellm - 💡(How to fix) Fix [Bug]: Litellm v1.83.8, v1.83.3, v1.82.2 Claud Code v2.1.110, v2.1.92, v2.1.52 OpenAI-compatible Translation Empty [1 participants]

litellm2026-04-16 08:16:35

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

BerriAI/litellm#25848•Fetched 2026-04-17 08:28:42

View on GitHub

Comments

Participants

Timeline

Reactions

Author

lkaupp

Participants

lkaupp

Timeline (top)

labeled ×4subscribed ×1

Error Message

"error": null, "description": "A powerful search tool built on ripgrep\n\n Usage:\n - ALWAYS use Grep for search tasks. NEVER invoke grep or rg as a Bash command. The Grep tool has been optimized for correct permissions and access.\n - Supports full regex syntax (e.g., "log.Error", "function\s+\w+")\n - Filter files with glob parameter (e.g., ".js", "/*.tsx") or type parameter (e.g., "js", "py", "rust")\n - Output modes: "content" shows matching lines, "files_with_matches" shows only file paths (default), "count" shows match counts\n - Use Task tool for open-ended searches requiring multiple rounds\n - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use interface\\{\\} to find interface{} in Go code)\n - Multiline matching: By default patterns match within single lines only. For cross-line patterns like struct \\{[\\s\\S]*?field, use multiline: true\n" "description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows Claude Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Claude Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: "1-5"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents." "description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your Read tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if old_string is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use replace_all to change every instance of old_string.\n- Use replace_all for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance." "description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\nPrefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. New Feature Implementation: Adding meaningful new functionality\n - Example: "Add a logout button" - where should it go? What should happen on click?\n - Example: "Add form validation" - what rules? What error messages?\n\n2. **Multi... (litellm_truncated skipped 1974 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set MAX_STRING_LENGTH_PROMPT_IN_DB in your env.) ...stion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: "Add user authentication to the app"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: "Optimize the database queries"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: "Implement dark mode"\n- Architectural decision on theme system, affects many components\n\nUser: "Add a delete button to the user profile"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: "Update the error handling in the API"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: "Fix the typo in the README"\n- Straightforward, no planning needed\n\nUser: "Add a console.log to debug this function"\n- Simple, obvious implementation\n\nUser: "What files handle routing?"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n"

Root Cause

Here is the response from the server:

{
  "id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDoxNDc1NjNlNGZmNDRkNjkyMzliNGY4MDJkZGVhOWE3NDYzMzYzMzg2ZWQyNzI5ZWU5ZmU4NDYwMjAxN2JjNTFkO3Jlc3BvbnNlX2lkOnJlc3BfYmQ0OTg4NzRiNTJkZTg0Zg==",
  "text": null,
  "user": "user_a4e122d37d0f4540af7d7944c9ebb8a2ba530f6ae907ac7047429bd570c",
  "error": null,
  "model": "qwen3.5-397b-a17b",
  "store": null,
  "tools": [
    {
      "name": "Task",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "description",
          "prompt",
          "subagent_type"
        ],
        "properties": {
          "model": {
            "enum": [
              "sonnet",
              "opus",
              "haiku"
            ],
            "type": "string",
            "description": "Optional model to use for this agent. If not specified, inherits from parent. Prefer haiku for quick, straightforward tasks to minimize cost and latency."
          },
          "prompt": {
            "type": "string",
            "description": "The task for the agent to perform"
          },
          "resume": {
            "type": "string",
            "description": "Optional agent ID to resume from. If provided, the agent will continue from the previous execution transcript."
          },
          "isolation": {
            "enum": [
              "worktree"
            ],
            "type": "string",
            "description": "Isolation mode. \"worktree\" creates a temporary git worktree so the agent works on an isolated copy of the repo."
          },
          "max_turns": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Maximum number of agentic turns (API round-trips) before stopping. Used internally for warmup.",
            "exclusiveMinimum": 0
          },
          "description": {
            "type": "string",
            "description": "A short (3-5 word) description of the task"
          },
          "subagent_type": {
            "type": "string",
            "description": "The type of specialized agent to use for this task"
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this agent in the background. The tool result will include an output_file path - use Read tool or Bash tail to check on output."
          }
        },
        "additionalProperties": false
      },
      "description": "Launch a new agent to handle complex, multi-step tasks autonomously.\n\nThe Task tool launches specialized agents (subprocesses) that autonomously handle complex tasks. Each agent type has specific capabilities and tools available to it.\n\nAvailable agent types and the tools they have access to:\n- Bash: Command execution specialist for running bash commands. Use this for git operations, command execution, and other terminal tasks. (Tools: Bash)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to... (litellm_truncated skipped 5044 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...makes no changes; if changes are made, the worktree path and branch are returned in the result.\n\nExample usage:\n\n<example_agent_descriptions>\n\"test-runner\": use this agent after you are done writing code to run tests\n\"greeting-responder\": use this agent to respond to user greetings with a friendly joke\n</example_agent_descriptions>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a significant piece of code was written and the task was completed, now use the test-runner agent to run the tests\n</commentary>\nassistant: Now let me use the test-runner agent to run the tests\nassistant: Uses the Task tool to launch the test-runner agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the greeting-responder agent\"\n</example>\n"
    },
    {
      "name": "TaskOutput",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "task_id",
          "block",
          "timeout"
        ],
        "properties": {
          "block": {
            "type": "boolean",
            "default": true,
            "description": "Whether to wait for completion"
          },
          "task_id": {
            "type": "string",
            "description": "The task ID to get output from"
          },
          "timeout": {
            "type": "number",
            "default": 30000,
            "maximum": 600000,
            "minimum": 0,
            "description": "Max wait time in ms"
          }
        },
        "additionalProperties": false
      },
      "description": "- Retrieves output from a running or completed task (background shell, agent, or remote session)\n- Takes a task_id parameter identifying the task\n- Returns the task output along with status information\n- Use block=true (default) to wait for task completion\n- Use block=false for non-blocking check of current status\n- Task IDs can be found using the /tasks command\n- Works with all task types: background shells, async agents, and remote sessions"
    },
    {
      "name": "Bash",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "command"
        ],
        "properties": {
          "command": {
            "type": "string",
            "description": "The command to execute"
          },
          "timeout": {
            "type": "number",
            "description": "Optional timeout in milliseconds (max 600000)"
          },
          "description": {
            "type": "string",
            "description": "Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\""
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this command in the background. Use TaskOutput to read the output later."
          },
          "dangerouslyDisableSandbox": {
            "type": "boolean",
            "description": "Set this to true to dangerously override sandbox mode and run commands without sandboxing."
          }
        },
        "additionalProperties": false
      },
      "description": "Executes a given bash command with optional timeout. Working directory persists between commands; shell state (everything else) does not. The shell environment is initialized from the user's profile (bash or zsh).\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use `ls fo... (litellm_truncated skipped 8692 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...(from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request title and summary:\n   - Keep the PR title short (under 70 characters)\n   - Use the description/body for details, not the title\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Bulleted markdown checklist of TODOs for testing the pull request...]\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\nEOF\n)\"\n</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments"
    },
    {
      "name": "Glob",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."
          },
          "pattern": {
            "type": "string",
            "description": "The glob pattern to match files against"
          }
        },
        "additionalProperties": false
      },
      "description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You can call multiple tools in a single response. It is always better to speculatively perform multiple searches in parallel if they are potentially useful."
    },
    {
      "name": "Grep",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "-A": {
            "type": "number",
            "description": "Number of lines to show after each match (rg -A). Requires output_mode: \"content\", ignored otherwise."
          },
          "-B": {
            "type": "number",
            "description": "Number of lines to show before each match (rg -B). Requires output_mode: \"content\", ignored otherwise."
          },
          "-C": {
            "type": "number",
            "description": "Alias for context."
          },
          "-i": {
            "type": "boolean",
            "description": "Case insensitive search (rg -i)"
          },
          "-n": {
            "type": "boolean",
            "description": "Show line numbers in output (rg -n). Requires output_mode: \"content\", ignored otherwise. Defaults to true."
          },
          "glob": {
            "type": "string",
            "description": "Glob pattern to filter files (e.g. \"*.js\", \"*.{ts,tsx}\") - maps to rg --glob"
          },
          "path": {
            "type": "string",
            "description": "File or directory to search in (rg PATH). Defaults to current working directory."
          },
          "type": {
            "type": "string",
            "description": "File type to search (rg --type). Common types: js, py, rust, go, java, etc. More efficient than include for standard file types."
          },
          "offset": {
            "type": "number",
            "description": "Skip first N lines/entries before applying head_limit, equivalent to \"| tail -n +N | head -N\". Works across all output modes. Defaults to 0."
          },
          "context": {
            "type": "number",
            "description": "Number of lines to show before and after each match (rg -C). Requires output_mode: \"content\", ignored otherwise."
          },
          "pattern": {
            "type": "string",
            "description": "The regular expression pattern to search for in file contents"
          },
          "multiline": {
            "type": "boolean",
            "description": "Enable multiline mode where . matches newlines and patterns can span lines (rg -U --multiline-dotall). Default: false."
          },
          "head_limit": {
            "type": "number",
            "description": "Limit output to first N lines/entries, equivalent to \"| head -N\". Works across all output modes: content (limits output lines), files_with_matches (limits file paths), count (limits count entries). Defaults to 0 (unlimited)."
          },
          "output_mode": {
            "enum": [
              "content",
              "files_with_matches",
              "count"
            ],
            "type": "string",
            "description": "Output mode: \"content\" shows matching lines (supports -A/-B/-C context, -n line numbers, head_limit), \"files_with_matches\" shows file paths (supports head_limit), \"count\" shows match counts (supports head_limit). Defaults to \"files_with_matches\"."
          }
        },
        "additionalProperties": false
      },
      "description": "A powerful search tool built on ripgrep\n\n  Usage:\n  - ALWAYS use Grep for search tasks. NEVER invoke `grep` or `rg` as a Bash command. The Grep tool has been optimized for correct permissions and access.\n  - Supports full regex syntax (e.g., \"log.*Error\", \"function\\s+\\w+\")\n  - Filter files with glob parameter (e.g., \"*.js\", \"**/*.tsx\") or type parameter (e.g., \"js\", \"py\", \"rust\")\n  - Output modes: \"content\" shows matching lines, \"files_with_matches\" shows only file paths (default), \"count\" shows match counts\n  - Use Task tool for open-ended searches requiring multiple rounds\n  - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use `interface\\{\\}` to find `interface{}` in Go code)\n  - Multiline matching: By default patterns match within single lines only. For cross-line patterns like `struct \\{[\\s\\S]*?field`, use `multiline: true`\n"
    },
    {
      "name": "ExitPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "allowedPrompts": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "tool",
                "prompt"
              ],
              "properties": {
                "tool": {
                  "enum": [
                    "Bash"
                  ],
                  "type": "string",
                  "description": "The tool this prompt applies to"
                },
                "prompt": {
                  "type": "string",
                  "description": "Semantic description of the action, e.g. \"run tests\", \"install dependencies\""
                }
              },
              "additionalProperties": false
            },
            "description": "Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands."
          }
        },
        "additionalProperties": {}
      },
      "description": "Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\n\n## How This Tool Works\n- You should have already written your plan to the plan file specified in the plan mode system message\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\n- This tool simply signals that you're done planning and ready for the user to review and approve\n- The user will see the contents of your plan file when they review it\n\n## When to Use This Tool\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\n\n## Before Using This Tool\nEnsure your plan is complete and unambiguous:\n- If you have unresolved questions about requirements or approach, use AskUserQuestion first (in earlier phases)\n- Once your plan is finalized, use THIS tool to request approval\n\n**Important:** Do NOT use AskUserQuestion to ask \"Is this plan okay?\" or \"Should I proceed?\" - that's exactly what THIS tool does. ExitPlanMode inherently requests user approval of your plan.\n\n## Examples\n\n1. Initial task: \"Search for and understand the implementation of vim mode in the codebase\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\n2. Initial task: \"Help me implement yank mode for vim\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\n3. Initial task: \"Add a new feature to handle user authentication\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\n"
    },
    {
      "name": "Read",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path"
        ],
        "properties": {
          "limit": {
            "type": "number",
            "description": "The number of lines to read. Only provide if the file is too large to read at once."
          },
          "pages": {
            "type": "string",
            "description": "Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request."
          },
          "offset": {
            "type": "number",
            "description": "The line number to start reading from. Only provide if the file is too large to read at once"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to read"
          }
        },
        "additionalProperties": false
      },
      "description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows Claude Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Claude Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: \"1-5\"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents."
    },
    {
      "name": "Edit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "old_string",
          "new_string"
        ],
        "properties": {
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to modify"
          },
          "new_string": {
            "type": "string",
            "description": "The text to replace it with (must be different from old_string)"
          },
          "old_string": {
            "type": "string",
            "description": "The text to replace"
          },
          "replace_all": {
            "type": "boolean",
            "default": false,
            "description": "Replace all occurrences of old_string (default false)"
          }
        },
        "additionalProperties": false
      },
      "description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.\n- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance."
    },
    {
      "name": "Write",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "content"
        ],
        "properties": {
          "content": {
            "type": "string",
            "description": "The content to write to the file"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to write (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked."
    },
    {
      "name": "NotebookEdit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "notebook_path",
          "new_source"
        ],
        "properties": {
          "cell_id": {
            "type": "string",
            "description": "The ID of the cell to edit. When inserting a new cell, the new cell will be inserted after the cell with this ID, or at the beginning if not specified."
          },
          "cell_type": {
            "enum": [
              "code",
              "markdown"
            ],
            "type": "string",
            "description": "The type of the cell (code or markdown). If not specified, it defaults to the current cell type. If using edit_mode=insert, this is required."
          },
          "edit_mode": {
            "enum": [
              "replace",
              "insert",
              "delete"
            ],
            "type": "string",
            "description": "The type of edit to make (replace, insert, delete). Defaults to replace."
          },
          "new_source": {
            "type": "string",
            "description": "The new source for the cell"
          },
          "notebook_path": {
            "type": "string",
            "description": "The absolute path to the Jupyter notebook file to edit (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. Jupyter notebooks are interactive documents that combine code, text, and visualizations, commonly used for data analysis and scientific computing. The notebook_path parameter must be an absolute path, not a relative path. The cell_number is 0-indexed. Use edit_mode=insert to add a new cell at the index specified by cell_number. Use edit_mode=delete to delete the cell at the index specified by cell_number."
    },
    {
      "name": "WebFetch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "url",
          "prompt"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri",
            "description": "The URL to fetch content from"
          },
          "prompt": {
            "type": "string",
            "description": "The prompt to run on the fetched content"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Fetches content from a specified URL and processes it using an AI model\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n  - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.\n  - For GitHub URLs, prefer using the gh CLI via Bash instead (e.g., gh pr view, gh issue view, gh api).\n"
    },
    {
      "name": "WebSearch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string",
            "minLength": 2,
            "description": "The search query to use"
          },
          "allowed_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Only include search results from these domains"
          },
          "blocked_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Never include search results from these domains"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Allows Claude to search the web and use the results to inform responses\n- Provides up-to-date information for current events and recent data\n- Returns search result information formatted as search result blocks, including links as markdown hyperlinks\n- Use this tool for accessing information beyond Claude's knowledge cutoff\n- Searches are performed automatically within a single API call\n\nCRITICAL REQUIREMENT - You MUST follow this:\n  - After answering the user's question, you MUST include a \"Sources:\" section at the end of your response\n  - In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL)\n  - This is MANDATORY - never skip including sources in your response\n  - Example format:\n\n    [Your answer here]\n\n    Sources:\n    - [Source Title 1](https://example.com/1)\n    - [Source Title 2](https://example.com/2)\n\nUsage notes:\n  - Domain filtering is supported to include or block specific websites\n  - Web search is only available in the US\n\nIMPORTANT - Use the correct year in search queries:\n  - The current month is April 2026. You MUST use this year when searching for recent information, documentation, or current events.\n  - Example: If the user asks for \"latest React docs\", search for \"React documentation\" with the current year, NOT last year\n"
    },
    {
      "name": "TaskStop",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "task_id": {
            "type": "string",
            "description": "The ID of the background task to stop"
          },
          "shell_id": {
            "type": "string",
            "description": "Deprecated: use task_id instead"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Stops a running background task by its ID\n- Takes a task_id parameter identifying the task to stop\n- Returns a success or failure status\n- Use this tool when you need to terminate a long-running task\n"
    },
    {
      "name": "AskUserQuestion",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "questions"
        ],
        "properties": {
          "answers": {
            "type": "object",
            "description": "User answers collected by the permission component",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "string"
            }
          },
          "metadata": {
            "type": "object",
            "properties": {
              "source": {
                "type": "string",
                "description": "Optional identifier for the source of this question (e.g., \"remember\" for /remember command). Used for analytics tracking."
              }
            },
            "description": "Optional metadata for tracking and analytics purposes. Not displayed to user.",
            "additionalProperties": false
          },
          "questions": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "question",
                "header",
                "options",
                "multiSelect"
              ],
              "properties": {
                "header": {
                  "type": "string",
                  "description": "Very short label displayed as a chip/tag (max 12 chars). Examples: \"Auth method\", \"Library\", \"Approach\"."
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "required": [
                      "label",
                      "description"
                    ],
                    "properties": {
                      "label": {
                        "type": "string",
                        "description": "The display text for this option that the user will see and select. Should be concise (1-5 words) and clearly describe the choice."
                      },
                      "markdown": {
                        "type": "string",
                        "description": "Optional preview content shown in a monospace box when this option is focused. Use for ASCII mockups, code snippets, or diagrams that help users visually compare options. Supports multi-line text with newlines."
                      },
                      "description": {
                        "type": "string",
                        "description": "Explanation of what this option means or what will happen if chosen. Useful for providing context about trade-offs or implications."
                      }
                    },
                    "additionalProperties": false
                  },
                  "maxItems": 4,
                  "minItems": 2,
                  "description": "The available choices for this question. Must have 2-4 options. Each option should be a distinct, mutually exclusive choice (unless multiSelect is enabled). There should be no 'Other' option, that will be provided automatically."
                },
                "question": {
                  "type": "string",
                  "description": "The complete question to ask the user. Should be clear, specific, and end with a question mark. Example: \"Which library should we use for date formatting?\" If multiSelect is true, phrase it accordingly, e.g. \"Which features do you want to enable?\""
                },
                "multiSelect": {
                  "type": "boolean",
                  "default": false,
                  "description": "Set to true to allow the user to select multiple options instead of just one. Use when choices are not mutually exclusive."
                }
              },
              "additionalProperties": false
            },
            "maxItems": 4,
            "minItems": 1,
            "description": "Questions to ask the user (1-4 questions)"
          },
          "annotations": {
            "type": "object",
            "description": "Optional per-question annotations from the user (e.g., notes on preview selections). Keyed by question text.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "object",
              "properties": {
                "notes": {
                  "type": "string",
                  "description": "Free-text notes the user added to their selection."
                },
                "markdown": {
                  "type": "string",
                  "description": "The markdown preview content of the selected option, if the question used previews."
                }
              },
              "additionalProperties": false
            }
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- Users will always be able to select \"Other\" to provide custom text input\n- Use multiSelect: true to allow multiple answers to be selected for a question\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n\nPlan mode note: In plan mode, use this tool to clarify requirements or choose between approaches BEFORE finalizing your plan. Do NOT use this tool to ask \"Is my plan ready?\" or \"Should I proceed?\" - use ExitPlanMode for plan approval. IMPORTANT: Do not reference \"the plan\" in your questions (e.g., \"Do you have feedback about the plan?\", \"Does the plan look good?\") because the user cannot see the plan in the UI until you call ExitPlanMode. If you need plan approval, use ExitPlanMode instead.\n\nPreview feature:\nUse the optional `markdown` field on options when presenting concrete artifacts that users need to visually compare:\n- ASCII mockups of UI layouts or components\n- Code snippets showing different implementations\n- Diagram variations\n- Configuration examples\n\nWhen any option has a markdown, the UI switches to a side-by-side layout with a vertical option list on the left and preview on the right. Do not use previews for simple preference questions where labels and descriptions suffice. Note: previews are only supported for single-select questions (not multiSelect).\n"
    },
    {
      "name": "Skill",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "skill"
        ],
        "properties": {
          "args": {
            "type": "string",
            "description": "Optional arguments for the skill"
          },
          "skill": {
            "type": "string",
            "description": "The skill name. E.g., \"commit\", \"review-pr\", or \"pdf\""
          }
        },
        "additionalProperties": false
      },
      "description": "Execute a skill within the main conversation\n\nWhen users ask you to perform tasks, check if any of the available skills match. Skills provide specialized capabilities and domain knowledge.\n\nWhen users reference a \"slash command\" or \"/<something>\" (e.g., \"/commit\", \"/review-pr\"), they are referring to a skill. Use this tool to invoke it.\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n\nImportant:\n- Available skills are listed in system-reminder messages in the conversation\n- When a skill matches the user's request, this is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- NEVER mention a skill without actually calling this tool\n- Do not invoke a skill that is already running\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n"
    },
    {
      "name": "EnterPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\n**Prefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. **New Feature Implementation**: Adding meaningful new functionality\n   - Example: \"Add a logout button\" - where should it go? What should happen on click?\n   - Example: \"Add form validation\" - what rules? What error messages?\n\n2. **Multi... (litellm_truncated skipped 1974 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...stion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: \"Add user authentication to the app\"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: \"Optimize the database queries\"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: \"Implement dark mode\"\n- Architectural decision on theme system, affects many components\n\nUser: \"Add a delete button to the user profile\"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: \"Update the error handling in the API\"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: \"Fix the typo in the README\"\n- Straightforward, no planning needed\n\nUser: \"Add a console.log to debug this function\"\n- Simple, obvious implementation\n\nUser: \"What files handle routing?\"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n"
    },
    {
      "name": "TaskCreate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "subject",
          "description"
        ],
        "properties": {
          "subject": {
            "type": "string",
            "description": "A brief title for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Arbitrary metadata to attach to the task",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "A detailed description of what needs to be done"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to create a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\n\nUse this tool proactively in these scenarios:\n\n- Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n- Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n- Plan mode - When using plan mode, create a task list to track the work\n- User explicitly requests todo list - When the user directly asks you to use the todo list\n- User provides multip... (litellm_truncated skipped 425 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...\n- There is only a single, straightforward task\n- The task is trivial and tracking it provides no organizational benefit\n- The task can be completed in less than 3 trivial steps\n- The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Task Fields\n\n- **subject**: A brief, actionable title in imperative form (e.g., \"Fix authentication bug in login flow\")\n- **description**: Detailed description of what needs to be done, including context and acceptance criteria\n- **activeForm**: Present continuous form shown in spinner when task is in_progress (e.g., \"Fixing authentication bug\"). This is displayed to the user while you work on the task.\n\n**IMPORTANT**: Always provide activeForm when creating tasks. The subject should be imperative (\"Run tests\") while activeForm should be present continuous (\"Running tests\"). All tasks are created with status `pending`.\n\n## Tips\n\n- Create tasks with clear, specific subjects that describe the outcome\n- Include enough detail in the description for another agent to understand and complete the task\n- After creating tasks, use TaskUpdate to set up dependencies (blocks/blockedBy) if needed\n- Check TaskList first to avoid creating duplicate tasks\n"
    },
    {
      "name": "TaskGet",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "taskId": {
            "type": "string",
            "description": "The ID of the task to retrieve"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to retrieve a task by its ID from the task list.\n\n## When to Use This Tool\n\n- When you need the full description and context before starting work on a task\n- To understand task dependencies (what it blocks, what blocks it)\n- After being assigned a task, to get complete requirements\n\n## Output\n\nReturns full task details:\n- **subject**: Task title\n- **description**: Detailed requirements and context\n- **status**: 'pending', 'in_progress', or 'completed'\n- **blocks**: Tasks waiting on this one to complete\n- **blockedBy**: Tasks that must complete before this one can start\n\n## Tips\n\n- After fetching a task, verify its blockedBy list is empty before beginning work.\n- Use TaskList to see all tasks in summary form.\n"
    },
    {
      "name": "TaskUpdate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "owner": {
            "type": "string",
            "description": "New owner for the task"
          },
          "status": {
            "anyOf": [
              {
                "enum": [
                  "pending",
                  "in_progress",
                  "completed"
                ],
                "type": "string"
              },
              {
                "type": "string",
                "const": "deleted"
              }
            ],
            "description": "New status for the task"
          },
          "taskId": {
            "type": "string",
            "description": "The ID of the task to update"
          },
          "subject": {
            "type": "string",
            "description": "New subject for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Metadata keys to merge into the task. Set a key to null to delete it.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "addBlocks": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that this task blocks"
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "New description for the task"
          },
          "addBlockedBy": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that block this task"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to update a task in the task list.\n\n## When to Use This Tool\n\n**Mark tasks as resolved:**\n- When you have completed the work described in a task\n- When a task is no longer needed or has been superseded\n- IMPORTANT: Always mark your assigned tasks as resolved when you finish them\n- After resolving, call TaskList to find your next task\n\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n  - Tests are failing\n  - Implementation is partial\n  - You encountered unresolved errors\n  - You couldn'... (litellm_truncated skipped 196 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...ils:**\n- When requirements change or become clearer\n- When establishing dependencies between tasks\n\n## Fields You Can Update\n\n- **status**: The task status (see Status Workflow below)\n- **subject**: Change the task title (imperative form, e.g., \"Run tests\")\n- **description**: Change the task description\n- **activeForm**: Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")\n- **owner**: Change the task owner (agent name)\n- **metadata**: Merge metadata keys into the task (set a key to null to delete it)\n- **addBlocks**: Mark tasks that cannot start until this one completes\n- **addBlockedBy**: Mark tasks that must complete before this one can start\n\n## Status Workflow\n\nStatus progresses: `pending` → `in_progress` → `completed`\n\nUse `deleted` to permanently remove a task.\n\n## Staleness\n\nMake sure to read a task's latest state using `TaskGet` before updating it.\n\n## Examples\n\nMark task as in progress when starting work:\n```json\n{\"taskId\": \"1\", \"status\": \"in_progress\"}\n```\n\nMark task as completed after finishing work:\n```json\n{\"taskId\": \"1\", \"status\": \"completed\"}\n```\n\nDelete a task:\n```json\n{\"taskId\": \"1\", \"status\": \"deleted\"}\n```\n\nClaim a task by setting owner:\n```json\n{\"taskId\": \"1\", \"owner\": \"my-name\"}\n```\n\nSet up task dependencies:\n```json\n{\"taskId\": \"2\", \"addBlockedBy\": [\"1\"]}\n```\n"
    },
    {
      "name": "TaskList",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool to list all tasks in the task list.\n\n## When to Use This Tool\n\n- To see what tasks are available to work on (status: 'pending', no owner, not blocked)\n- To check overall progress on the project\n- To find tasks that are blocked and need dependencies resolved\n- After completing a task, to check for newly unblocked work or claim the next available task\n- **Prefer working on tasks in ID order** (lowest ID first) when multiple tasks are available, as earlier tasks often set up context for later ones\n\n## Output\n\nReturns a summary of each task:\n- **id**: Task identifier (use with TaskGet, TaskUpdate)\n- **subject**: Brief description of the task\n- **status**: 'pending', 'in_progress', or 'completed'\n- **owner**: Agent ID if assigned, empty if available\n- **blockedBy**: List of open task IDs that must be resolved first (tasks with blockedBy cannot be claimed until dependencies resolve)\n\nUse TaskGet with a specific task ID to view full details including description and comments.\n"
    },
    {
      "name": "EnterWorktree",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "name": {
            "type": "string",
            "description": "Optional name for the worktree. A random name is generated if not provided."
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool ONLY when the user explicitly asks to work in a worktree. This tool creates an isolated git worktree and switches the current session into it.\n\n## When to Use\n\n- The user explicitly says \"worktree\" (e.g., \"start a worktree\", \"work in a worktree\", \"create a worktree\", \"use a worktree\")\n\n## When NOT to Use\n\n- The user asks to create a branch, switch branches, or work on a different branch — use git commands instead\n- The user asks to fix a bug or work on a feature — use normal git workflow unless they specifically mention worktrees\n- Never use this tool unless the user explicitly mentions \"worktree\"\n\n## Requirements\n\n- Must be in a git repository, OR have WorktreeCreate/WorktreeRemove hooks configured in settings.json\n- Must not already be in a worktree\n\n## Behavior\n\n- In a git repository: creates a new git worktree inside `.claude/worktrees/` with a new branch based on HEAD\n- Outside a git repository: delegates to WorktreeCreate/WorktreeRemove hooks for VCS-agnostic isolation\n- Switches the session's working directory to the new worktree\n- On session exit, the user will be prompted to keep or remove the worktree\n\n## Parameters\n\n- `name` (optional): A name for the worktree. If not provided, a random name is generated.\n"
    }
  ],
  "top_p": 0.95,
  "usage": {
    "total_tokens": 18552,
    "prompt_tokens": 18515,
    "completion_tokens": 37,
    "prompt_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "reasoning_tokens": 0,
      "accepted_prediction_tokens": null,
      "rejected_prediction_tokens": null
    }
  },
  "object": "response",
  "output": [
    {
      "id": "rs_b50f51586dcd7af2",
      "type": "reasoning",
      "content": [
        {
          "text": "The user is greeting me, so I should respond with a brief, friendly greeting and offer to help with their tasks.\n",
          "type": "reasoning_text"
        }
      ],
      "summary": []
    },
    {
      "id": "msg_9f53f5abe425a5e5",
      "role": "assistant",
      "type": "message",
      "phase": null,
      "status": "completed",
      "content": [
        {
          "text": "\n\nHi! How can I help you today?",
          "type": "output_text",
          "logprobs": null,
          "annotations": []
        }
      ]
    }
  ],
  "prompt": null,
  "status": "completed",
  "metadata": null,
  "reasoning": {
    "effort": "high",
    "summary": null,
    "generate_summary": null
  },
  "background": false,
  "created_at": 1776326448,
  "truncation": "disabled",
  "temperature": 0.6,
  "tool_choice": "auto",
  "instructions": "x-anthropic-billing-header: cc_version=2.1.51.ea8; cc_entrypoint=cli; cch=af527;\nYou are Claude Code, Anthropic's official CLI for Claude.\n\nYou are an interactive agent that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, s... (litellm_truncated skipped 13015 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...t be incomplete — verify against project docs before writing\n- Anything that duplicates or contradicts existing CLAUDE.md instructions\n- Speculative or unverified conclusions from reading a single file\n\n## Explicit user requests:\n- When the user asks you to remember something across sessions (e.g., \"always use bun\", \"never auto-commit\"), save it — no need to wait for multiple interactions\n- When the user asks to forget or stop remembering something, find and remove the relevant entries from your memory files\n\n\n# Environment\nYou have been invoked in the following environment: \n - Primary working directory: C:\\Users\\spies\\claudetest\n  - Is a git repository: false\n - Platform: win32\n - Shell: bash (use Unix shell syntax, not Windows — e.g., /dev/null not NUL, forward slashes in paths)\n - OS Version: Windows 11 Pro 10.0.26200\n - You are powered by the model qwen3.5-397b-a17b.\n - The most recent Claude model family is Claude 4.5/4.6. Model IDs — Opus 4.6: 'claude-opus-4-6', Sonnet 4.6: 'claude-sonnet-4-6', Haiku 4.5: 'claude-haiku-4-5-20251001'. When building AI applications, default to the latest and most capable Claude models.\n\n\n<fast_mode_info>\nFast mode for Claude Code uses the same Claude Opus 4.6 model with faster output. It does NOT switch to a different model. It can be toggled with /fast.\n</fast_mode_info>",
  "service_tier": "auto",
  "top_logprobs": null,
  "input_messages": null,
  "max_tool_calls": null,
  "output_messages": null,
  "max_output_tokens": 32000,
  "incomplete_details": null,
  "parallel_tool_calls": true,
  "previous_response_id": null
}

Fix Action

Fix / Workaround

Here is the response from the server:

{
  "id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDoxNDc1NjNlNGZmNDRkNjkyMzliNGY4MDJkZGVhOWE3NDYzMzYzMzg2ZWQyNzI5ZWU5ZmU4NDYwMjAxN2JjNTFkO3Jlc3BvbnNlX2lkOnJlc3BfYmQ0OTg4NzRiNTJkZTg0Zg==",
  "text": null,
  "user": "user_a4e122d37d0f4540af7d7944c9ebb8a2ba530f6ae907ac7047429bd570c",
  "error": null,
  "model": "qwen3.5-397b-a17b",
  "store": null,
  "tools": [
    {
      "name": "Task",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "description",
          "prompt",
          "subagent_type"
        ],
        "properties": {
          "model": {
            "enum": [
              "sonnet",
              "opus",
              "haiku"
            ],
            "type": "string",
            "description": "Optional model to use for this agent. If not specified, inherits from parent. Prefer haiku for quick, straightforward tasks to minimize cost and latency."
          },
          "prompt": {
            "type": "string",
            "description": "The task for the agent to perform"
          },
          "resume": {
            "type": "string",
            "description": "Optional agent ID to resume from. If provided, the agent will continue from the previous execution transcript."
          },
          "isolation": {
            "enum": [
              "worktree"
            ],
            "type": "string",
            "description": "Isolation mode. \"worktree\" creates a temporary git worktree so the agent works on an isolated copy of the repo."
          },
          "max_turns": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Maximum number of agentic turns (API round-trips) before stopping. Used internally for warmup.",
            "exclusiveMinimum": 0
          },
          "description": {
            "type": "string",
            "description": "A short (3-5 word) description of the task"
          },
          "subagent_type": {
            "type": "string",
            "description": "The type of specialized agent to use for this task"
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this agent in the background. The tool result will include an output_file path - use Read tool or Bash tail to check on output."
          }
        },
        "additionalProperties": false
      },
      "description": "Launch a new agent to handle complex, multi-step tasks autonomously.\n\nThe Task tool launches specialized agents (subprocesses) that autonomously handle complex tasks. Each agent type has specific capabilities and tools available to it.\n\nAvailable agent types and the tools they have access to:\n- Bash: Command execution specialist for running bash commands. Use this for git operations, command execution, and other terminal tasks. (Tools: Bash)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to... (litellm_truncated skipped 5044 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...makes no changes; if changes are made, the worktree path and branch are returned in the result.\n\nExample usage:\n\n<example_agent_descriptions>\n\"test-runner\": use this agent after you are done writing code to run tests\n\"greeting-responder\": use this agent to respond to user greetings with a friendly joke\n</example_agent_descriptions>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a significant piece of code was written and the task was completed, now use the test-runner agent to run the tests\n</commentary>\nassistant: Now let me use the test-runner agent to run the tests\nassistant: Uses the Task tool to launch the test-runner agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the greeting-responder agent\"\n</example>\n"
    },
    {
      "name": "TaskOutput",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "task_id",
          "block",
          "timeout"
        ],
        "properties": {
          "block": {
            "type": "boolean",
            "default": true,
            "description": "Whether to wait for completion"
          },
          "task_id": {
            "type": "string",
            "description": "The task ID to get output from"
          },
          "timeout": {
            "type": "number",
            "default": 30000,
            "maximum": 600000,
            "minimum": 0,
            "description": "Max wait time in ms"
          }
        },
        "additionalProperties": false
      },
      "description": "- Retrieves output from a running or completed task (background shell, agent, or remote session)\n- Takes a task_id parameter identifying the task\n- Returns the task output along with status information\n- Use block=true (default) to wait for task completion\n- Use block=false for non-blocking check of current status\n- Task IDs can be found using the /tasks command\n- Works with all task types: background shells, async agents, and remote sessions"
    },
    {
      "name": "Bash",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "command"
        ],
        "properties": {
          "command": {
            "type": "string",
            "description": "The command to execute"
          },
          "timeout": {
            "type": "number",
            "description": "Optional timeout in milliseconds (max 600000)"
          },
          "description": {
            "type": "string",
            "description": "Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\""
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this command in the background. Use TaskOutput to read the output later."
          },
          "dangerouslyDisableSandbox": {
            "type": "boolean",
            "description": "Set this to true to dangerously override sandbox mode and run commands without sandboxing."
          }
        },
        "additionalProperties": false
      },
      "description": "Executes a given bash command with optional timeout. Working directory persists between commands; shell state (everything else) does not. The shell environment is initialized from the user's profile (bash or zsh).\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use `ls fo... (litellm_truncated skipped 8692 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...(from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request title and summary:\n   - Keep the PR title short (under 70 characters)\n   - Use the description/body for details, not the title\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Bulleted markdown checklist of TODOs for testing the pull request...]\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\nEOF\n)\"\n</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments"
    },
    {
      "name": "Glob",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."
          },
          "pattern": {
            "type": "string",
            "description": "The glob pattern to match files against"
          }
        },
        "additionalProperties": false
      },
      "description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You can call multiple tools in a single response. It is always better to speculatively perform multiple searches in parallel if they are potentially useful."
    },
    {
      "name": "Grep",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "-A": {
            "type": "number",
            "description": "Number of lines to show after each match (rg -A). Requires output_mode: \"content\", ignored otherwise."
          },
          "-B": {
            "type": "number",
            "description": "Number of lines to show before each match (rg -B). Requires output_mode: \"content\", ignored otherwise."
          },
          "-C": {
            "type": "number",
            "description": "Alias for context."
          },
          "-i": {
            "type": "boolean",
            "description": "Case insensitive search (rg -i)"
          },
          "-n": {
            "type": "boolean",
            "description": "Show line numbers in output (rg -n). Requires output_mode: \"content\", ignored otherwise. Defaults to true."
          },
          "glob": {
            "type": "string",
            "description": "Glob pattern to filter files (e.g. \"*.js\", \"*.{ts,tsx}\") - maps to rg --glob"
          },
          "path": {
            "type": "string",
            "description": "File or directory to search in (rg PATH). Defaults to current working directory."
          },
          "type": {
            "type": "string",
            "description": "File type to search (rg --type). Common types: js, py, rust, go, java, etc. More efficient than include for standard file types."
          },
          "offset": {
            "type": "number",
            "description": "Skip first N lines/entries before applying head_limit, equivalent to \"| tail -n +N | head -N\". Works across all output modes. Defaults to 0."
          },
          "context": {
            "type": "number",
            "description": "Number of lines to show before and after each match (rg -C). Requires output_mode: \"content\", ignored otherwise."
          },
          "pattern": {
            "type": "string",
            "description": "The regular expression pattern to search for in file contents"
          },
          "multiline": {
            "type": "boolean",
            "description": "Enable multiline mode where . matches newlines and patterns can span lines (rg -U --multiline-dotall). Default: false."
          },
          "head_limit": {
            "type": "number",
            "description": "Limit output to first N lines/entries, equivalent to \"| head -N\". Works across all output modes: content (limits output lines), files_with_matches (limits file paths), count (limits count entries). Defaults to 0 (unlimited)."
          },
          "output_mode": {
            "enum": [
              "content",
              "files_with_matches",
              "count"
            ],
            "type": "string",
            "description": "Output mode: \"content\" shows matching lines (supports -A/-B/-C context, -n line numbers, head_limit), \"files_with_matches\" shows file paths (supports head_limit), \"count\" shows match counts (supports head_limit). Defaults to \"files_with_matches\"."
          }
        },
        "additionalProperties": false
      },
      "description": "A powerful search tool built on ripgrep\n\n  Usage:\n  - ALWAYS use Grep for search tasks. NEVER invoke `grep` or `rg` as a Bash command. The Grep tool has been optimized for correct permissions and access.\n  - Supports full regex syntax (e.g., \"log.*Error\", \"function\\s+\\w+\")\n  - Filter files with glob parameter (e.g., \"*.js\", \"**/*.tsx\") or type parameter (e.g., \"js\", \"py\", \"rust\")\n  - Output modes: \"content\" shows matching lines, \"files_with_matches\" shows only file paths (default), \"count\" shows match counts\n  - Use Task tool for open-ended searches requiring multiple rounds\n  - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use `interface\\{\\}` to find `interface{}` in Go code)\n  - Multiline matching: By default patterns match within single lines only. For cross-line patterns like `struct \\{[\\s\\S]*?field`, use `multiline: true`\n"
    },
    {
      "name": "ExitPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "allowedPrompts": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "tool",
                "prompt"
              ],
              "properties": {
                "tool": {
                  "enum": [
                    "Bash"
                  ],
                  "type": "string",
                  "description": "The tool this prompt applies to"
                },
                "prompt": {
                  "type": "string",
                  "description": "Semantic description of the action, e.g. \"run tests\", \"install dependencies\""
                }
              },
              "additionalProperties": false
            },
            "description": "Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands."
          }
        },
        "additionalProperties": {}
      },
      "description": "Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\n\n## How This Tool Works\n- You should have already written your plan to the plan file specified in the plan mode system message\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\n- This tool simply signals that you're done planning and ready for the user to review and approve\n- The user will see the contents of your plan file when they review it\n\n## When to Use This Tool\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\n\n## Before Using This Tool\nEnsure your plan is complete and unambiguous:\n- If you have unresolved questions about requirements or approach, use AskUserQuestion first (in earlier phases)\n- Once your plan is finalized, use THIS tool to request approval\n\n**Important:** Do NOT use AskUserQuestion to ask \"Is this plan okay?\" or \"Should I proceed?\" - that's exactly what THIS tool does. ExitPlanMode inherently requests user approval of your plan.\n\n## Examples\n\n1. Initial task: \"Search for and understand the implementation of vim mode in the codebase\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\n2. Initial task: \"Help me implement yank mode for vim\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\n3. Initial task: \"Add a new feature to handle user authentication\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\n"
    },
    {
      "name": "Read",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path"
        ],
        "properties": {
          "limit": {
            "type": "number",
            "description": "The number of lines to read. Only provide if the file is too large to read at once."
          },
          "pages": {
            "type": "string",
            "description": "Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request."
          },
          "offset": {
            "type": "number",
            "description": "The line number to start reading from. Only provide if the file is too large to read at once"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to read"
          }
        },
        "additionalProperties": false
      },
      "description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows Claude Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Claude Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: \"1-5\"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents."
    },
    {
      "name": "Edit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "old_string",
          "new_string"
        ],
        "properties": {
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to modify"
          },
          "new_string": {
            "type": "string",
            "description": "The text to replace it with (must be different from old_string)"
          },
          "old_string": {
            "type": "string",
            "description": "The text to replace"
          },
          "replace_all": {
            "type": "boolean",
            "default": false,
            "description": "Replace all occurrences of old_string (default false)"
          }
        },
        "additionalProperties": false
      },
      "description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.\n- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance."
    },
    {
      "name": "Write",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "content"
        ],
        "properties": {
          "content": {
            "type": "string",
            "description": "The content to write to the file"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to write (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked."
    },
    {
      "name": "NotebookEdit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "notebook_path",
          "new_source"
        ],
        "properties": {
          "cell_id": {
            "type": "string",
            "description": "The ID of the cell to edit. When inserting a new cell, the new cell will be inserted after the cell with this ID, or at the beginning if not specified."
          },
          "cell_type": {
            "enum": [
              "code",
              "markdown"
            ],
            "type": "string",
            "description": "The type of the cell (code or markdown). If not specified, it defaults to the current cell type. If using edit_mode=insert, this is required."
          },
          "edit_mode": {
            "enum": [
              "replace",
              "insert",
              "delete"
            ],
            "type": "string",
            "description": "The type of edit to make (replace, insert, delete). Defaults to replace."
          },
          "new_source": {
            "type": "string",
            "description": "The new source for the cell"
          },
          "notebook_path": {
            "type": "string",
            "description": "The absolute path to the Jupyter notebook file to edit (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. Jupyter notebooks are interactive documents that combine code, text, and visualizations, commonly used for data analysis and scientific computing. The notebook_path parameter must be an absolute path, not a relative path. The cell_number is 0-indexed. Use edit_mode=insert to add a new cell at the index specified by cell_number. Use edit_mode=delete to delete the cell at the index specified by cell_number."
    },
    {
      "name": "WebFetch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "url",
          "prompt"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri",
            "description": "The URL to fetch content from"
          },
          "prompt": {
            "type": "string",
            "description": "The prompt to run on the fetched content"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Fetches content from a specified URL and processes it using an AI model\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n  - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.\n  - For GitHub URLs, prefer using the gh CLI via Bash instead (e.g., gh pr view, gh issue view, gh api).\n"
    },
    {
      "name": "WebSearch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string",
            "minLength": 2,
            "description": "The search query to use"
          },
          "allowed_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Only include search results from these domains"
          },
          "blocked_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Never include search results from these domains"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Allows Claude to search the web and use the results to inform responses\n- Provides up-to-date information for current events and recent data\n- Returns search result information formatted as search result blocks, including links as markdown hyperlinks\n- Use this tool for accessing information beyond Claude's knowledge cutoff\n- Searches are performed automatically within a single API call\n\nCRITICAL REQUIREMENT - You MUST follow this:\n  - After answering the user's question, you MUST include a \"Sources:\" section at the end of your response\n  - In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL)\n  - This is MANDATORY - never skip including sources in your response\n  - Example format:\n\n    [Your answer here]\n\n    Sources:\n    - [Source Title 1](https://example.com/1)\n    - [Source Title 2](https://example.com/2)\n\nUsage notes:\n  - Domain filtering is supported to include or block specific websites\n  - Web search is only available in the US\n\nIMPORTANT - Use the correct year in search queries:\n  - The current month is April 2026. You MUST use this year when searching for recent information, documentation, or current events.\n  - Example: If the user asks for \"latest React docs\", search for \"React documentation\" with the current year, NOT last year\n"
    },
    {
      "name": "TaskStop",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "task_id": {
            "type": "string",
            "description": "The ID of the background task to stop"
          },
          "shell_id": {
            "type": "string",
            "description": "Deprecated: use task_id instead"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Stops a running background task by its ID\n- Takes a task_id parameter identifying the task to stop\n- Returns a success or failure status\n- Use this tool when you need to terminate a long-running task\n"
    },
    {
      "name": "AskUserQuestion",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "questions"
        ],
        "properties": {
          "answers": {
            "type": "object",
            "description": "User answers collected by the permission component",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "string"
            }
          },
          "metadata": {
            "type": "object",
            "properties": {
              "source": {
                "type": "string",
                "description": "Optional identifier for the source of this question (e.g., \"remember\" for /remember command). Used for analytics tracking."
              }
            },
            "description": "Optional metadata for tracking and analytics purposes. Not displayed to user.",
            "additionalProperties": false
          },
          "questions": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "question",
                "header",
                "options",
                "multiSelect"
              ],
              "properties": {
                "header": {
                  "type": "string",
                  "description": "Very short label displayed as a chip/tag (max 12 chars). Examples: \"Auth method\", \"Library\", \"Approach\"."
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "required": [
                      "label",
                      "description"
                    ],
                    "properties": {
                      "label": {
                        "type": "string",
                        "description": "The display text for this option that the user will see and select. Should be concise (1-5 words) and clearly describe the choice."
                      },
                      "markdown": {
                        "type": "string",
                        "description": "Optional preview content shown in a monospace box when this option is focused. Use for ASCII mockups, code snippets, or diagrams that help users visually compare options. Supports multi-line text with newlines."
                      },
                      "description": {
                        "type": "string",
                        "description": "Explanation of what this option means or what will happen if chosen. Useful for providing context about trade-offs or implications."
                      }
                    },
                    "additionalProperties": false
                  },
                  "maxItems": 4,
                  "minItems": 2,
                  "description": "The available choices for this question. Must have 2-4 options. Each option should be a distinct, mutually exclusive choice (unless multiSelect is enabled). There should be no 'Other' option, that will be provided automatically."
                },
                "question": {
                  "type": "string",
                  "description": "The complete question to ask the user. Should be clear, specific, and end with a question mark. Example: \"Which library should we use for date formatting?\" If multiSelect is true, phrase it accordingly, e.g. \"Which features do you want to enable?\""
                },
                "multiSelect": {
                  "type": "boolean",
                  "default": false,
                  "description": "Set to true to allow the user to select multiple options instead of just one. Use when choices are not mutually exclusive."
                }
              },
              "additionalProperties": false
            },
            "maxItems": 4,
            "minItems": 1,
            "description": "Questions to ask the user (1-4 questions)"
          },
          "annotations": {
            "type": "object",
            "description": "Optional per-question annotations from the user (e.g., notes on preview selections). Keyed by question text.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "object",
              "properties": {
                "notes": {
                  "type": "string",
                  "description": "Free-text notes the user added to their selection."
                },
                "markdown": {
                  "type": "string",
                  "description": "The markdown preview content of the selected option, if the question used previews."
                }
              },
              "additionalProperties": false
            }
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- Users will always be able to select \"Other\" to provide custom text input\n- Use multiSelect: true to allow multiple answers to be selected for a question\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n\nPlan mode note: In plan mode, use this tool to clarify requirements or choose between approaches BEFORE finalizing your plan. Do NOT use this tool to ask \"Is my plan ready?\" or \"Should I proceed?\" - use ExitPlanMode for plan approval. IMPORTANT: Do not reference \"the plan\" in your questions (e.g., \"Do you have feedback about the plan?\", \"Does the plan look good?\") because the user cannot see the plan in the UI until you call ExitPlanMode. If you need plan approval, use ExitPlanMode instead.\n\nPreview feature:\nUse the optional `markdown` field on options when presenting concrete artifacts that users need to visually compare:\n- ASCII mockups of UI layouts or components\n- Code snippets showing different implementations\n- Diagram variations\n- Configuration examples\n\nWhen any option has a markdown, the UI switches to a side-by-side layout with a vertical option list on the left and preview on the right. Do not use previews for simple preference questions where labels and descriptions suffice. Note: previews are only supported for single-select questions (not multiSelect).\n"
    },
    {
      "name": "Skill",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "skill"
        ],
        "properties": {
          "args": {
            "type": "string",
            "description": "Optional arguments for the skill"
          },
          "skill": {
            "type": "string",
            "description": "The skill name. E.g., \"commit\", \"review-pr\", or \"pdf\""
          }
        },
        "additionalProperties": false
      },
      "description": "Execute a skill within the main conversation\n\nWhen users ask you to perform tasks, check if any of the available skills match. Skills provide specialized capabilities and domain knowledge.\n\nWhen users reference a \"slash command\" or \"/<something>\" (e.g., \"/commit\", \"/review-pr\"), they are referring to a skill. Use this tool to invoke it.\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n\nImportant:\n- Available skills are listed in system-reminder messages in the conversation\n- When a skill matches the user's request, this is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- NEVER mention a skill without actually calling this tool\n- Do not invoke a skill that is already running\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n"
    },
    {
      "name": "EnterPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\n**Prefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. **New Feature Implementation**: Adding meaningful new functionality\n   - Example: \"Add a logout button\" - where should it go? What should happen on click?\n   - Example: \"Add form validation\" - what rules? What error messages?\n\n2. **Multi... (litellm_truncated skipped 1974 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...stion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: \"Add user authentication to the app\"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: \"Optimize the database queries\"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: \"Implement dark mode\"\n- Architectural decision on theme system, affects many components\n\nUser: \"Add a delete button to the user profile\"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: \"Update the error handling in the API\"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: \"Fix the typo in the README\"\n- Straightforward, no planning needed\n\nUser: \"Add a console.log to debug this function\"\n- Simple, obvious implementation\n\nUser: \"What files handle routing?\"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n"
    },
    {
      "name": "TaskCreate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "subject",
          "description"
        ],
        "properties": {
          "subject": {
            "type": "string",
            "description": "A brief title for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Arbitrary metadata to attach to the task",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "A detailed description of what needs to be done"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to create a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\n\nUse this tool proactively in these scenarios:\n\n- Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n- Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n- Plan mode - When using plan mode, create a task list to track the work\n- User explicitly requests todo list - When the user directly asks you to use the todo list\n- User provides multip... (litellm_truncated skipped 425 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...\n- There is only a single, straightforward task\n- The task is trivial and tracking it provides no organizational benefit\n- The task can be completed in less than 3 trivial steps\n- The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Task Fields\n\n- **subject**: A brief, actionable title in imperative form (e.g., \"Fix authentication bug in login flow\")\n- **description**: Detailed description of what needs to be done, including context and acceptance criteria\n- **activeForm**: Present continuous form shown in spinner when task is in_progress (e.g., \"Fixing authentication bug\"). This is displayed to the user while you work on the task.\n\n**IMPORTANT**: Always provide activeForm when creating tasks. The subject should be imperative (\"Run tests\") while activeForm should be present continuous (\"Running tests\"). All tasks are created with status `pending`.\n\n## Tips\n\n- Create tasks with clear, specific subjects that describe the outcome\n- Include enough detail in the description for another agent to understand and complete the task\n- After creating tasks, use TaskUpdate to set up dependencies (blocks/blockedBy) if needed\n- Check TaskList first to avoid creating duplicate tasks\n"
    },
    {
      "name": "TaskGet",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "taskId": {
            "type": "string",
            "description": "The ID of the task to retrieve"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to retrieve a task by its ID from the task list.\n\n## When to Use This Tool\n\n- When you need the full description and context before starting work on a task\n- To understand task dependencies (what it blocks, what blocks it)\n- After being assigned a task, to get complete requirements\n\n## Output\n\nReturns full task details:\n- **subject**: Task title\n- **description**: Detailed requirements and context\n- **status**: 'pending', 'in_progress', or 'completed'\n- **blocks**: Tasks waiting on this one to complete\n- **blockedBy**: Tasks that must complete before this one can start\n\n## Tips\n\n- After fetching a task, verify its blockedBy list is empty before beginning work.\n- Use TaskList to see all tasks in summary form.\n"
    },
    {
      "name": "TaskUpdate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "owner": {
            "type": "string",
            "description": "New owner for the task"
          },
          "status": {
            "anyOf": [
              {
                "enum": [
                  "pending",
                  "in_progress",
                  "completed"
                ],
                "type": "string"
              },
              {
                "type": "string",
                "const": "deleted"
              }
            ],
            "description": "New status for the task"
          },
          "taskId": {
            "type": "string",
            "description": "The ID of the task to update"
          },
          "subject": {
            "type": "string",
            "description": "New subject for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Metadata keys to merge into the task. Set a key to null to delete it.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "addBlocks": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that this task blocks"
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "New description for the task"
          },
          "addBlockedBy": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that block this task"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to update a task in the task list.\n\n## When to Use This Tool\n\n**Mark tasks as resolved:**\n- When you have completed the work described in a task\n- When a task is no longer needed or has been superseded\n- IMPORTANT: Always mark your assigned tasks as resolved when you finish them\n- After resolving, call TaskList to find your next task\n\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n  - Tests are failing\n  - Implementation is partial\n  - You encountered unresolved errors\n  - You couldn'... (litellm_truncated skipped 196 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...ils:**\n- When requirements change or become clearer\n- When establishing dependencies between tasks\n\n## Fields You Can Update\n\n- **status**: The task status (see Status Workflow below)\n- **subject**: Change the task title (imperative form, e.g., \"Run tests\")\n- **description**: Change the task description\n- **activeForm**: Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")\n- **owner**: Change the task owner (agent name)\n- **metadata**: Merge metadata keys into the task (set a key to null to delete it)\n- **addBlocks**: Mark tasks that cannot start until this one completes\n- **addBlockedBy**: Mark tasks that must complete before this one can start\n\n## Status Workflow\n\nStatus progresses: `pending` → `in_progress` → `completed`\n\nUse `deleted` to permanently remove a task.\n\n## Staleness\n\nMake sure to read a task's latest state using `TaskGet` before updating it.\n\n## Examples\n\nMark task as in progress when starting work:\n```json\n{\"taskId\": \"1\", \"status\": \"in_progress\"}\n```\n\nMark task as completed after finishing work:\n```json\n{\"taskId\": \"1\", \"status\": \"completed\"}\n```\n\nDelete a task:\n```json\n{\"taskId\": \"1\", \"status\": \"deleted\"}\n```\n\nClaim a task by setting owner:\n```json\n{\"taskId\": \"1\", \"owner\": \"my-name\"}\n```\n\nSet up task dependencies:\n```json\n{\"taskId\": \"2\", \"addBlockedBy\": [\"1\"]}\n```\n"
    },
    {
      "name": "TaskList",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool to list all tasks in the task list.\n\n## When to Use This Tool\n\n- To see what tasks are available to work on (status: 'pending', no owner, not blocked)\n- To check overall progress on the project\n- To find tasks that are blocked and need dependencies resolved\n- After completing a task, to check for newly unblocked work or claim the next available task\n- **Prefer working on tasks in ID order** (lowest ID first) when multiple tasks are available, as earlier tasks often set up context for later ones\n\n## Output\n\nReturns a summary of each task:\n- **id**: Task identifier (use with TaskGet, TaskUpdate)\n- **subject**: Brief description of the task\n- **status**: 'pending', 'in_progress', or 'completed'\n- **owner**: Agent ID if assigned, empty if available\n- **blockedBy**: List of open task IDs that must be resolved first (tasks with blockedBy cannot be claimed until dependencies resolve)\n\nUse TaskGet with a specific task ID to view full details including description and comments.\n"
    },
    {
      "name": "EnterWorktree",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "name": {
            "type": "string",
            "description": "Optional name for the worktree. A random name is generated if not provided."
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool ONLY when the user explicitly asks to work in a worktree. This tool creates an isolated git worktree and switches the current session into it.\n\n## When to Use\n\n- The user explicitly says \"worktree\" (e.g., \"start a worktree\", \"work in a worktree\", \"create a worktree\", \"use a worktree\")\n\n## When NOT to Use\n\n- The user asks to create a branch, switch branches, or work on a different branch — use git commands instead\n- The user asks to fix a bug or work on a feature — use normal git workflow unless they specifically mention worktrees\n- Never use this tool unless the user explicitly mentions \"worktree\"\n\n## Requirements\n\n- Must be in a git repository, OR have WorktreeCreate/WorktreeRemove hooks configured in settings.json\n- Must not already be in a worktree\n\n## Behavior\n\n- In a git repository: creates a new git worktree inside `.claude/worktrees/` with a new branch based on HEAD\n- Outside a git repository: delegates to WorktreeCreate/WorktreeRemove hooks for VCS-agnostic isolation\n- Switches the session's working directory to the new worktree\n- On session exit, the user will be prompted to keep or remove the worktree\n\n## Parameters\n\n- `name` (optional): A name for the worktree. If not provided, a random name is generated.\n"
    }
  ],
  "top_p": 0.95,
  "usage": {
    "total_tokens": 18552,
    "prompt_tokens": 18515,
    "completion_tokens": 37,
    "prompt_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "reasoning_tokens": 0,
      "accepted_prediction_tokens": null,
      "rejected_prediction_tokens": null
    }
  },
  "object": "response",
  "output": [
    {
      "id": "rs_b50f51586dcd7af2",
      "type": "reasoning",
      "content": [
        {
          "text": "The user is greeting me, so I should respond with a brief, friendly greeting and offer to help with their tasks.\n",
          "type": "reasoning_text"
        }
      ],
      "summary": []
    },
    {
      "id": "msg_9f53f5abe425a5e5",
      "role": "assistant",
      "type": "message",
      "phase": null,
      "status": "completed",
      "content": [
        {
          "text": "\n\nHi! How can I help you today?",
          "type": "output_text",
          "logprobs": null,
          "annotations": []
        }
      ]
    }
  ],
  "prompt": null,
  "status": "completed",
  "metadata": null,
  "reasoning": {
    "effort": "high",
    "summary": null,
    "generate_summary": null
  },
  "background": false,
  "created_at": 1776326448,
  "truncation": "disabled",
  "temperature": 0.6,
  "tool_choice": "auto",
  "instructions": "x-anthropic-billing-header: cc_version=2.1.51.ea8; cc_entrypoint=cli; cch=af527;\nYou are Claude Code, Anthropic's official CLI for Claude.\n\nYou are an interactive agent that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, s... (litellm_truncated skipped 13015 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...t be incomplete — verify against project docs before writing\n- Anything that duplicates or contradicts existing CLAUDE.md instructions\n- Speculative or unverified conclusions from reading a single file\n\n## Explicit user requests:\n- When the user asks you to remember something across sessions (e.g., \"always use bun\", \"never auto-commit\"), save it — no need to wait for multiple interactions\n- When the user asks to forget or stop remembering something, find and remove the relevant entries from your memory files\n\n\n# Environment\nYou have been invoked in the following environment: \n - Primary working directory: C:\\Users\\spies\\claudetest\n  - Is a git repository: false\n - Platform: win32\n - Shell: bash (use Unix shell syntax, not Windows — e.g., /dev/null not NUL, forward slashes in paths)\n - OS Version: Windows 11 Pro 10.0.26200\n - You are powered by the model qwen3.5-397b-a17b.\n - The most recent Claude model family is Claude 4.5/4.6. Model IDs — Opus 4.6: 'claude-opus-4-6', Sonnet 4.6: 'claude-sonnet-4-6', Haiku 4.5: 'claude-haiku-4-5-20251001'. When building AI applications, default to the latest and most capable Claude models.\n\n\n<fast_mode_info>\nFast mode for Claude Code uses the same Claude Opus 4.6 model with faster output. It does NOT switch to a different model. It can be toggled with /fast.\n</fast_mode_info>",
  "service_tier": "auto",
  "top_logprobs": null,
  "input_messages": null,
  "max_tool_calls": null,
  "output_messages": null,
  "max_output_tokens": 32000,
  "incomplete_details": null,
  "parallel_tool_calls": true,
  "previous_response_id": null
}

Code Example

{
  "id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDoxNDc1NjNlNGZmNDRkNjkyMzliNGY4MDJkZGVhOWE3NDYzMzYzMzg2ZWQyNzI5ZWU5ZmU4NDYwMjAxN2JjNTFkO3Jlc3BvbnNlX2lkOnJlc3BfYmQ0OTg4NzRiNTJkZTg0Zg==",
  "text": null,
  "user": "user_a4e122d37d0f4540af7d7944c9ebb8a2ba530f6ae907ac7047429bd570c",
  "error": null,
  "model": "qwen3.5-397b-a17b",
  "store": null,
  "tools": [
    {
      "name": "Task",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "description",
          "prompt",
          "subagent_type"
        ],
        "properties": {
          "model": {
            "enum": [
              "sonnet",
              "opus",
              "haiku"
            ],
            "type": "string",
            "description": "Optional model to use for this agent. If not specified, inherits from parent. Prefer haiku for quick, straightforward tasks to minimize cost and latency."
          },
          "prompt": {
            "type": "string",
            "description": "The task for the agent to perform"
          },
          "resume": {
            "type": "string",
            "description": "Optional agent ID to resume from. If provided, the agent will continue from the previous execution transcript."
          },
          "isolation": {
            "enum": [
              "worktree"
            ],
            "type": "string",
            "description": "Isolation mode. \"worktree\" creates a temporary git worktree so the agent works on an isolated copy of the repo."
          },
          "max_turns": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Maximum number of agentic turns (API round-trips) before stopping. Used internally for warmup.",
            "exclusiveMinimum": 0
          },
          "description": {
            "type": "string",
            "description": "A short (3-5 word) description of the task"
          },
          "subagent_type": {
            "type": "string",
            "description": "The type of specialized agent to use for this task"
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this agent in the background. The tool result will include an output_file path - use Read tool or Bash tail to check on output."
          }
        },
        "additionalProperties": false
      },
      "description": "Launch a new agent to handle complex, multi-step tasks autonomously.\n\nThe Task tool launches specialized agents (subprocesses) that autonomously handle complex tasks. Each agent type has specific capabilities and tools available to it.\n\nAvailable agent types and the tools they have access to:\n- Bash: Command execution specialist for running bash commands. Use this for git operations, command execution, and other terminal tasks. (Tools: Bash)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to... (litellm_truncated skipped 5044 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...makes no changes; if changes are made, the worktree path and branch are returned in the result.\n\nExample usage:\n\n<example_agent_descriptions>\n\"test-runner\": use this agent after you are done writing code to run tests\n\"greeting-responder\": use this agent to respond to user greetings with a friendly joke\n</example_agent_descriptions>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a significant piece of code was written and the task was completed, now use the test-runner agent to run the tests\n</commentary>\nassistant: Now let me use the test-runner agent to run the tests\nassistant: Uses the Task tool to launch the test-runner agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the greeting-responder agent\"\n</example>\n"
    },
    {
      "name": "TaskOutput",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "task_id",
          "block",
          "timeout"
        ],
        "properties": {
          "block": {
            "type": "boolean",
            "default": true,
            "description": "Whether to wait for completion"
          },
          "task_id": {
            "type": "string",
            "description": "The task ID to get output from"
          },
          "timeout": {
            "type": "number",
            "default": 30000,
            "maximum": 600000,
            "minimum": 0,
            "description": "Max wait time in ms"
          }
        },
        "additionalProperties": false
      },
      "description": "- Retrieves output from a running or completed task (background shell, agent, or remote session)\n- Takes a task_id parameter identifying the task\n- Returns the task output along with status information\n- Use block=true (default) to wait for task completion\n- Use block=false for non-blocking check of current status\n- Task IDs can be found using the /tasks command\n- Works with all task types: background shells, async agents, and remote sessions"
    },
    {
      "name": "Bash",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "command"
        ],
        "properties": {
          "command": {
            "type": "string",
            "description": "The command to execute"
          },
          "timeout": {
            "type": "number",
            "description": "Optional timeout in milliseconds (max 600000)"
          },
          "description": {
            "type": "string",
            "description": "Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\""
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this command in the background. Use TaskOutput to read the output later."
          },
          "dangerouslyDisableSandbox": {
            "type": "boolean",
            "description": "Set this to true to dangerously override sandbox mode and run commands without sandboxing."
          }
        },
        "additionalProperties": false
      },
      "description": "Executes a given bash command with optional timeout. Working directory persists between commands; shell state (everything else) does not. The shell environment is initialized from the user's profile (bash or zsh).\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use `ls fo... (litellm_truncated skipped 8692 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...(from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request title and summary:\n   - Keep the PR title short (under 70 characters)\n   - Use the description/body for details, not the title\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Bulleted markdown checklist of TODOs for testing the pull request...]\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\nEOF\n)\"\n</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments"
    },
    {
      "name": "Glob",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."
          },
          "pattern": {
            "type": "string",
            "description": "The glob pattern to match files against"
          }
        },
        "additionalProperties": false
      },
      "description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You can call multiple tools in a single response. It is always better to speculatively perform multiple searches in parallel if they are potentially useful."
    },
    {
      "name": "Grep",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "-A": {
            "type": "number",
            "description": "Number of lines to show after each match (rg -A). Requires output_mode: \"content\", ignored otherwise."
          },
          "-B": {
            "type": "number",
            "description": "Number of lines to show before each match (rg -B). Requires output_mode: \"content\", ignored otherwise."
          },
          "-C": {
            "type": "number",
            "description": "Alias for context."
          },
          "-i": {
            "type": "boolean",
            "description": "Case insensitive search (rg -i)"
          },
          "-n": {
            "type": "boolean",
            "description": "Show line numbers in output (rg -n). Requires output_mode: \"content\", ignored otherwise. Defaults to true."
          },
          "glob": {
            "type": "string",
            "description": "Glob pattern to filter files (e.g. \"*.js\", \"*.{ts,tsx}\") - maps to rg --glob"
          },
          "path": {
            "type": "string",
            "description": "File or directory to search in (rg PATH). Defaults to current working directory."
          },
          "type": {
            "type": "string",
            "description": "File type to search (rg --type). Common types: js, py, rust, go, java, etc. More efficient than include for standard file types."
          },
          "offset": {
            "type": "number",
            "description": "Skip first N lines/entries before applying head_limit, equivalent to \"| tail -n +N | head -N\". Works across all output modes. Defaults to 0."
          },
          "context": {
            "type": "number",
            "description": "Number of lines to show before and after each match (rg -C). Requires output_mode: \"content\", ignored otherwise."
          },
          "pattern": {
            "type": "string",
            "description": "The regular expression pattern to search for in file contents"
          },
          "multiline": {
            "type": "boolean",
            "description": "Enable multiline mode where . matches newlines and patterns can span lines (rg -U --multiline-dotall). Default: false."
          },
          "head_limit": {
            "type": "number",
            "description": "Limit output to first N lines/entries, equivalent to \"| head -N\". Works across all output modes: content (limits output lines), files_with_matches (limits file paths), count (limits count entries). Defaults to 0 (unlimited)."
          },
          "output_mode": {
            "enum": [
              "content",
              "files_with_matches",
              "count"
            ],
            "type": "string",
            "description": "Output mode: \"content\" shows matching lines (supports -A/-B/-C context, -n line numbers, head_limit), \"files_with_matches\" shows file paths (supports head_limit), \"count\" shows match counts (supports head_limit). Defaults to \"files_with_matches\"."
          }
        },
        "additionalProperties": false
      },
      "description": "A powerful search tool built on ripgrep\n\n  Usage:\n  - ALWAYS use Grep for search tasks. NEVER invoke `grep` or `rg` as a Bash command. The Grep tool has been optimized for correct permissions and access.\n  - Supports full regex syntax (e.g., \"log.*Error\", \"function\\s+\\w+\")\n  - Filter files with glob parameter (e.g., \"*.js\", \"**/*.tsx\") or type parameter (e.g., \"js\", \"py\", \"rust\")\n  - Output modes: \"content\" shows matching lines, \"files_with_matches\" shows only file paths (default), \"count\" shows match counts\n  - Use Task tool for open-ended searches requiring multiple rounds\n  - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use `interface\\{\\}` to find `interface{}` in Go code)\n  - Multiline matching: By default patterns match within single lines only. For cross-line patterns like `struct \\{[\\s\\S]*?field`, use `multiline: true`\n"
    },
    {
      "name": "ExitPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "allowedPrompts": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "tool",
                "prompt"
              ],
              "properties": {
                "tool": {
                  "enum": [
                    "Bash"
                  ],
                  "type": "string",
                  "description": "The tool this prompt applies to"
                },
                "prompt": {
                  "type": "string",
                  "description": "Semantic description of the action, e.g. \"run tests\", \"install dependencies\""
                }
              },
              "additionalProperties": false
            },
            "description": "Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands."
          }
        },
        "additionalProperties": {}
      },
      "description": "Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\n\n## How This Tool Works\n- You should have already written your plan to the plan file specified in the plan mode system message\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\n- This tool simply signals that you're done planning and ready for the user to review and approve\n- The user will see the contents of your plan file when they review it\n\n## When to Use This Tool\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\n\n## Before Using This Tool\nEnsure your plan is complete and unambiguous:\n- If you have unresolved questions about requirements or approach, use AskUserQuestion first (in earlier phases)\n- Once your plan is finalized, use THIS tool to request approval\n\n**Important:** Do NOT use AskUserQuestion to ask \"Is this plan okay?\" or \"Should I proceed?\" - that's exactly what THIS tool does. ExitPlanMode inherently requests user approval of your plan.\n\n## Examples\n\n1. Initial task: \"Search for and understand the implementation of vim mode in the codebase\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\n2. Initial task: \"Help me implement yank mode for vim\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\n3. Initial task: \"Add a new feature to handle user authentication\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\n"
    },
    {
      "name": "Read",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path"
        ],
        "properties": {
          "limit": {
            "type": "number",
            "description": "The number of lines to read. Only provide if the file is too large to read at once."
          },
          "pages": {
            "type": "string",
            "description": "Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request."
          },
          "offset": {
            "type": "number",
            "description": "The line number to start reading from. Only provide if the file is too large to read at once"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to read"
          }
        },
        "additionalProperties": false
      },
      "description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows Claude Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Claude Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: \"1-5\"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents."
    },
    {
      "name": "Edit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "old_string",
          "new_string"
        ],
        "properties": {
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to modify"
          },
          "new_string": {
            "type": "string",
            "description": "The text to replace it with (must be different from old_string)"
          },
          "old_string": {
            "type": "string",
            "description": "The text to replace"
          },
          "replace_all": {
            "type": "boolean",
            "default": false,
            "description": "Replace all occurrences of old_string (default false)"
          }
        },
        "additionalProperties": false
      },
      "description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.\n- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance."
    },
    {
      "name": "Write",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "content"
        ],
        "properties": {
          "content": {
            "type": "string",
            "description": "The content to write to the file"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to write (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked."
    },
    {
      "name": "NotebookEdit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "notebook_path",
          "new_source"
        ],
        "properties": {
          "cell_id": {
            "type": "string",
            "description": "The ID of the cell to edit. When inserting a new cell, the new cell will be inserted after the cell with this ID, or at the beginning if not specified."
          },
          "cell_type": {
            "enum": [
              "code",
              "markdown"
            ],
            "type": "string",
            "description": "The type of the cell (code or markdown). If not specified, it defaults to the current cell type. If using edit_mode=insert, this is required."
          },
          "edit_mode": {
            "enum": [
              "replace",
              "insert",
              "delete"
            ],
            "type": "string",
            "description": "The type of edit to make (replace, insert, delete). Defaults to replace."
          },
          "new_source": {
            "type": "string",
            "description": "The new source for the cell"
          },
          "notebook_path": {
            "type": "string",
            "description": "The absolute path to the Jupyter notebook file to edit (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. Jupyter notebooks are interactive documents that combine code, text, and visualizations, commonly used for data analysis and scientific computing. The notebook_path parameter must be an absolute path, not a relative path. The cell_number is 0-indexed. Use edit_mode=insert to add a new cell at the index specified by cell_number. Use edit_mode=delete to delete the cell at the index specified by cell_number."
    },
    {
      "name": "WebFetch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "url",
          "prompt"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri",
            "description": "The URL to fetch content from"
          },
          "prompt": {
            "type": "string",
            "description": "The prompt to run on the fetched content"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Fetches content from a specified URL and processes it using an AI model\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n  - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.\n  - For GitHub URLs, prefer using the gh CLI via Bash instead (e.g., gh pr view, gh issue view, gh api).\n"
    },
    {
      "name": "WebSearch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string",
            "minLength": 2,
            "description": "The search query to use"
          },
          "allowed_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Only include search results from these domains"
          },
          "blocked_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Never include search results from these domains"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Allows Claude to search the web and use the results to inform responses\n- Provides up-to-date information for current events and recent data\n- Returns search result information formatted as search result blocks, including links as markdown hyperlinks\n- Use this tool for accessing information beyond Claude's knowledge cutoff\n- Searches are performed automatically within a single API call\n\nCRITICAL REQUIREMENT - You MUST follow this:\n  - After answering the user's question, you MUST include a \"Sources:\" section at the end of your response\n  - In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL)\n  - This is MANDATORY - never skip including sources in your response\n  - Example format:\n\n    [Your answer here]\n\n    Sources:\n    - [Source Title 1](https://example.com/1)\n    - [Source Title 2](https://example.com/2)\n\nUsage notes:\n  - Domain filtering is supported to include or block specific websites\n  - Web search is only available in the US\n\nIMPORTANT - Use the correct year in search queries:\n  - The current month is April 2026. You MUST use this year when searching for recent information, documentation, or current events.\n  - Example: If the user asks for \"latest React docs\", search for \"React documentation\" with the current year, NOT last year\n"
    },
    {
      "name": "TaskStop",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "task_id": {
            "type": "string",
            "description": "The ID of the background task to stop"
          },
          "shell_id": {
            "type": "string",
            "description": "Deprecated: use task_id instead"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Stops a running background task by its ID\n- Takes a task_id parameter identifying the task to stop\n- Returns a success or failure status\n- Use this tool when you need to terminate a long-running task\n"
    },
    {
      "name": "AskUserQuestion",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "questions"
        ],
        "properties": {
          "answers": {
            "type": "object",
            "description": "User answers collected by the permission component",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "string"
            }
          },
          "metadata": {
            "type": "object",
            "properties": {
              "source": {
                "type": "string",
                "description": "Optional identifier for the source of this question (e.g., \"remember\" for /remember command). Used for analytics tracking."
              }
            },
            "description": "Optional metadata for tracking and analytics purposes. Not displayed to user.",
            "additionalProperties": false
          },
          "questions": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "question",
                "header",
                "options",
                "multiSelect"
              ],
              "properties": {
                "header": {
                  "type": "string",
                  "description": "Very short label displayed as a chip/tag (max 12 chars). Examples: \"Auth method\", \"Library\", \"Approach\"."
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "required": [
                      "label",
                      "description"
                    ],
                    "properties": {
                      "label": {
                        "type": "string",
                        "description": "The display text for this option that the user will see and select. Should be concise (1-5 words) and clearly describe the choice."
                      },
                      "markdown": {
                        "type": "string",
                        "description": "Optional preview content shown in a monospace box when this option is focused. Use for ASCII mockups, code snippets, or diagrams that help users visually compare options. Supports multi-line text with newlines."
                      },
                      "description": {
                        "type": "string",
                        "description": "Explanation of what this option means or what will happen if chosen. Useful for providing context about trade-offs or implications."
                      }
                    },
                    "additionalProperties": false
                  },
                  "maxItems": 4,
                  "minItems": 2,
                  "description": "The available choices for this question. Must have 2-4 options. Each option should be a distinct, mutually exclusive choice (unless multiSelect is enabled). There should be no 'Other' option, that will be provided automatically."
                },
                "question": {
                  "type": "string",
                  "description": "The complete question to ask the user. Should be clear, specific, and end with a question mark. Example: \"Which library should we use for date formatting?\" If multiSelect is true, phrase it accordingly, e.g. \"Which features do you want to enable?\""
                },
                "multiSelect": {
                  "type": "boolean",
                  "default": false,
                  "description": "Set to true to allow the user to select multiple options instead of just one. Use when choices are not mutually exclusive."
                }
              },
              "additionalProperties": false
            },
            "maxItems": 4,
            "minItems": 1,
            "description": "Questions to ask the user (1-4 questions)"
          },
          "annotations": {
            "type": "object",
            "description": "Optional per-question annotations from the user (e.g., notes on preview selections). Keyed by question text.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "object",
              "properties": {
                "notes": {
                  "type": "string",
                  "description": "Free-text notes the user added to their selection."
                },
                "markdown": {
                  "type": "string",
                  "description": "The markdown preview content of the selected option, if the question used previews."
                }
              },
              "additionalProperties": false
            }
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- Users will always be able to select \"Other\" to provide custom text input\n- Use multiSelect: true to allow multiple answers to be selected for a question\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n\nPlan mode note: In plan mode, use this tool to clarify requirements or choose between approaches BEFORE finalizing your plan. Do NOT use this tool to ask \"Is my plan ready?\" or \"Should I proceed?\" - use ExitPlanMode for plan approval. IMPORTANT: Do not reference \"the plan\" in your questions (e.g., \"Do you have feedback about the plan?\", \"Does the plan look good?\") because the user cannot see the plan in the UI until you call ExitPlanMode. If you need plan approval, use ExitPlanMode instead.\n\nPreview feature:\nUse the optional `markdown` field on options when presenting concrete artifacts that users need to visually compare:\n- ASCII mockups of UI layouts or components\n- Code snippets showing different implementations\n- Diagram variations\n- Configuration examples\n\nWhen any option has a markdown, the UI switches to a side-by-side layout with a vertical option list on the left and preview on the right. Do not use previews for simple preference questions where labels and descriptions suffice. Note: previews are only supported for single-select questions (not multiSelect).\n"
    },
    {
      "name": "Skill",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "skill"
        ],
        "properties": {
          "args": {
            "type": "string",
            "description": "Optional arguments for the skill"
          },
          "skill": {
            "type": "string",
            "description": "The skill name. E.g., \"commit\", \"review-pr\", or \"pdf\""
          }
        },
        "additionalProperties": false
      },
      "description": "Execute a skill within the main conversation\n\nWhen users ask you to perform tasks, check if any of the available skills match. Skills provide specialized capabilities and domain knowledge.\n\nWhen users reference a \"slash command\" or \"/<something>\" (e.g., \"/commit\", \"/review-pr\"), they are referring to a skill. Use this tool to invoke it.\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n\nImportant:\n- Available skills are listed in system-reminder messages in the conversation\n- When a skill matches the user's request, this is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- NEVER mention a skill without actually calling this tool\n- Do not invoke a skill that is already running\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n"
    },
    {
      "name": "EnterPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\n**Prefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. **New Feature Implementation**: Adding meaningful new functionality\n   - Example: \"Add a logout button\" - where should it go? What should happen on click?\n   - Example: \"Add form validation\" - what rules? What error messages?\n\n2. **Multi... (litellm_truncated skipped 1974 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...stion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: \"Add user authentication to the app\"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: \"Optimize the database queries\"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: \"Implement dark mode\"\n- Architectural decision on theme system, affects many components\n\nUser: \"Add a delete button to the user profile\"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: \"Update the error handling in the API\"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: \"Fix the typo in the README\"\n- Straightforward, no planning needed\n\nUser: \"Add a console.log to debug this function\"\n- Simple, obvious implementation\n\nUser: \"What files handle routing?\"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n"
    },
    {
      "name": "TaskCreate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "subject",
          "description"
        ],
        "properties": {
          "subject": {
            "type": "string",
            "description": "A brief title for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Arbitrary metadata to attach to the task",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "A detailed description of what needs to be done"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to create a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\n\nUse this tool proactively in these scenarios:\n\n- Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n- Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n- Plan mode - When using plan mode, create a task list to track the work\n- User explicitly requests todo list - When the user directly asks you to use the todo list\n- User provides multip... (litellm_truncated skipped 425 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...\n- There is only a single, straightforward task\n- The task is trivial and tracking it provides no organizational benefit\n- The task can be completed in less than 3 trivial steps\n- The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Task Fields\n\n- **subject**: A brief, actionable title in imperative form (e.g., \"Fix authentication bug in login flow\")\n- **description**: Detailed description of what needs to be done, including context and acceptance criteria\n- **activeForm**: Present continuous form shown in spinner when task is in_progress (e.g., \"Fixing authentication bug\"). This is displayed to the user while you work on the task.\n\n**IMPORTANT**: Always provide activeForm when creating tasks. The subject should be imperative (\"Run tests\") while activeForm should be present continuous (\"Running tests\"). All tasks are created with status `pending`.\n\n## Tips\n\n- Create tasks with clear, specific subjects that describe the outcome\n- Include enough detail in the description for another agent to understand and complete the task\n- After creating tasks, use TaskUpdate to set up dependencies (blocks/blockedBy) if needed\n- Check TaskList first to avoid creating duplicate tasks\n"
    },
    {
      "name": "TaskGet",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "taskId": {
            "type": "string",
            "description": "The ID of the task to retrieve"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to retrieve a task by its ID from the task list.\n\n## When to Use This Tool\n\n- When you need the full description and context before starting work on a task\n- To understand task dependencies (what it blocks, what blocks it)\n- After being assigned a task, to get complete requirements\n\n## Output\n\nReturns full task details:\n- **subject**: Task title\n- **description**: Detailed requirements and context\n- **status**: 'pending', 'in_progress', or 'completed'\n- **blocks**: Tasks waiting on this one to complete\n- **blockedBy**: Tasks that must complete before this one can start\n\n## Tips\n\n- After fetching a task, verify its blockedBy list is empty before beginning work.\n- Use TaskList to see all tasks in summary form.\n"
    },
    {
      "name": "TaskUpdate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "owner": {
            "type": "string",
            "description": "New owner for the task"
          },
          "status": {
            "anyOf": [
              {
                "enum": [
                  "pending",
                  "in_progress",
                  "completed"
                ],
                "type": "string"
              },
              {
                "type": "string",
                "const": "deleted"
              }
            ],
            "description": "New status for the task"
          },
          "taskId": {
            "type": "string",
            "description": "The ID of the task to update"
          },
          "subject": {
            "type": "string",
            "description": "New subject for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Metadata keys to merge into the task. Set a key to null to delete it.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "addBlocks": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that this task blocks"
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "New description for the task"
          },
          "addBlockedBy": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that block this task"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to update a task in the task list.\n\n## When to Use This Tool\n\n**Mark tasks as resolved:**\n- When you have completed the work described in a task\n- When a task is no longer needed or has been superseded\n- IMPORTANT: Always mark your assigned tasks as resolved when you finish them\n- After resolving, call TaskList to find your next task\n\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n  - Tests are failing\n  - Implementation is partial\n  - You encountered unresolved errors\n  - You couldn'... (litellm_truncated skipped 196 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...ils:**\n- When requirements change or become clearer\n- When establishing dependencies between tasks\n\n## Fields You Can Update\n\n- **status**: The task status (see Status Workflow below)\n- **subject**: Change the task title (imperative form, e.g., \"Run tests\")\n- **description**: Change the task description\n- **activeForm**: Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")\n- **owner**: Change the task owner (agent name)\n- **metadata**: Merge metadata keys into the task (set a key to null to delete it)\n- **addBlocks**: Mark tasks that cannot start until this one completes\n- **addBlockedBy**: Mark tasks that must complete before this one can start\n\n## Status Workflow\n\nStatus progresses: `pending` → `in_progress` → `completed`\n\nUse `deleted` to permanently remove a task.\n\n## Staleness\n\nMake sure to read a task's latest state using `TaskGet` before updating it.\n\n## Examples\n\nMark task as in progress when starting work:\n

---

In the response the correct answer from the server can be found, which is somehow not backtranslated:

---

### Steps to Reproduce

---

compose.yaml:

---

Steps:
1. docker compose up -d
2. install e.g. claude stable (v2.1.92)
3. Say "hi"

### Relevant log output

RAW_BUFFERClick to expand / collapse

Check for existing issues

I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

OpenAI compatible endpoint returned output is empty, but the call of the api is successfull. In the repsonse json the message is returned, however the output in "pretty" is empty. For that reason, claude code tested in versions v2.1.110, v2.1.92, v2.1.52 and littellm versions: v1.83.8, v1.83.3, v1.82.2 do not deliver the answer to "hi".

Here is the response from the server:

{
  "id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDoxNDc1NjNlNGZmNDRkNjkyMzliNGY4MDJkZGVhOWE3NDYzMzYzMzg2ZWQyNzI5ZWU5ZmU4NDYwMjAxN2JjNTFkO3Jlc3BvbnNlX2lkOnJlc3BfYmQ0OTg4NzRiNTJkZTg0Zg==",
  "text": null,
  "user": "user_a4e122d37d0f4540af7d7944c9ebb8a2ba530f6ae907ac7047429bd570c",
  "error": null,
  "model": "qwen3.5-397b-a17b",
  "store": null,
  "tools": [
    {
      "name": "Task",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "description",
          "prompt",
          "subagent_type"
        ],
        "properties": {
          "model": {
            "enum": [
              "sonnet",
              "opus",
              "haiku"
            ],
            "type": "string",
            "description": "Optional model to use for this agent. If not specified, inherits from parent. Prefer haiku for quick, straightforward tasks to minimize cost and latency."
          },
          "prompt": {
            "type": "string",
            "description": "The task for the agent to perform"
          },
          "resume": {
            "type": "string",
            "description": "Optional agent ID to resume from. If provided, the agent will continue from the previous execution transcript."
          },
          "isolation": {
            "enum": [
              "worktree"
            ],
            "type": "string",
            "description": "Isolation mode. \"worktree\" creates a temporary git worktree so the agent works on an isolated copy of the repo."
          },
          "max_turns": {
            "type": "integer",
            "maximum": 9007199254740991,
            "description": "Maximum number of agentic turns (API round-trips) before stopping. Used internally for warmup.",
            "exclusiveMinimum": 0
          },
          "description": {
            "type": "string",
            "description": "A short (3-5 word) description of the task"
          },
          "subagent_type": {
            "type": "string",
            "description": "The type of specialized agent to use for this task"
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this agent in the background. The tool result will include an output_file path - use Read tool or Bash tail to check on output."
          }
        },
        "additionalProperties": false
      },
      "description": "Launch a new agent to handle complex, multi-step tasks autonomously.\n\nThe Task tool launches specialized agents (subprocesses) that autonomously handle complex tasks. Each agent type has specific capabilities and tools available to it.\n\nAvailable agent types and the tools they have access to:\n- Bash: Command execution specialist for running bash commands. Use this for git operations, command execution, and other terminal tasks. (Tools: Bash)\n- general-purpose: General-purpose agent for researching complex questions, searching for code, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to... (litellm_truncated skipped 5044 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...makes no changes; if changes are made, the worktree path and branch are returned in the result.\n\nExample usage:\n\n<example_agent_descriptions>\n\"test-runner\": use this agent after you are done writing code to run tests\n\"greeting-responder\": use this agent to respond to user greetings with a friendly joke\n</example_agent_descriptions>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a significant piece of code was written and the task was completed, now use the test-runner agent to run the tests\n</commentary>\nassistant: Now let me use the test-runner agent to run the tests\nassistant: Uses the Task tool to launch the test-runner agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the greeting-responder agent\"\n</example>\n"
    },
    {
      "name": "TaskOutput",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "task_id",
          "block",
          "timeout"
        ],
        "properties": {
          "block": {
            "type": "boolean",
            "default": true,
            "description": "Whether to wait for completion"
          },
          "task_id": {
            "type": "string",
            "description": "The task ID to get output from"
          },
          "timeout": {
            "type": "number",
            "default": 30000,
            "maximum": 600000,
            "minimum": 0,
            "description": "Max wait time in ms"
          }
        },
        "additionalProperties": false
      },
      "description": "- Retrieves output from a running or completed task (background shell, agent, or remote session)\n- Takes a task_id parameter identifying the task\n- Returns the task output along with status information\n- Use block=true (default) to wait for task completion\n- Use block=false for non-blocking check of current status\n- Task IDs can be found using the /tasks command\n- Works with all task types: background shells, async agents, and remote sessions"
    },
    {
      "name": "Bash",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "command"
        ],
        "properties": {
          "command": {
            "type": "string",
            "description": "The command to execute"
          },
          "timeout": {
            "type": "number",
            "description": "Optional timeout in milliseconds (max 600000)"
          },
          "description": {
            "type": "string",
            "description": "Clear, concise description of what this command does in active voice. Never use words like \"complex\" or \"risk\" in the description - just describe what it does.\n\nFor simple commands (git, npm, standard CLI tools), keep it brief (5-10 words):\n- ls → \"List files in current directory\"\n- git status → \"Show working tree status\"\n- npm install → \"Install package dependencies\"\n\nFor commands that are harder to parse at a glance (piped commands, obscure flags, etc.), add enough context to clarify what it does:\n- find . -name \"*.tmp\" -exec rm {} \\; → \"Find and delete all .tmp files recursively\"\n- git reset --hard origin/main → \"Discard all local changes and match remote main\"\n- curl -s url | jq '.data[]' → \"Fetch JSON from URL and extract data array elements\""
          },
          "run_in_background": {
            "type": "boolean",
            "description": "Set to true to run this command in the background. Use TaskOutput to read the output later."
          },
          "dangerouslyDisableSandbox": {
            "type": "boolean",
            "description": "Set this to true to dangerously override sandbox mode and run commands without sandboxing."
          }
        },
        "additionalProperties": false
      },
      "description": "Executes a given bash command with optional timeout. Working directory persists between commands; shell state (everything else) does not. The shell environment is initialized from the user's profile (bash or zsh).\n\nIMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) - use the specialized tools for this instead.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use `ls` to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use `ls fo... (litellm_truncated skipped 8692 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...(from the time it diverged from the base branch)\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request title and summary:\n   - Keep the PR title short (under 70 characters)\n   - Use the description/body for details, not the title\n3. You can call multiple tools in a single response. When multiple independent pieces of information are requested and all commands are likely to succeed, run multiple tool calls in parallel for optimal performance. run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\n## Test plan\n[Bulleted markdown checklist of TODOs for testing the pull request...]\n\n🤖 Generated with [Claude Code](https://claude.com/claude-code)\nEOF\n)\"\n</example>\n\nImportant:\n- DO NOT use the TodoWrite or Task tools\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments"
    },
    {
      "name": "Glob",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "path": {
            "type": "string",
            "description": "The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."
          },
          "pattern": {
            "type": "string",
            "description": "The glob pattern to match files against"
          }
        },
        "additionalProperties": false
      },
      "description": "- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You can call multiple tools in a single response. It is always better to speculatively perform multiple searches in parallel if they are potentially useful."
    },
    {
      "name": "Grep",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "pattern"
        ],
        "properties": {
          "-A": {
            "type": "number",
            "description": "Number of lines to show after each match (rg -A). Requires output_mode: \"content\", ignored otherwise."
          },
          "-B": {
            "type": "number",
            "description": "Number of lines to show before each match (rg -B). Requires output_mode: \"content\", ignored otherwise."
          },
          "-C": {
            "type": "number",
            "description": "Alias for context."
          },
          "-i": {
            "type": "boolean",
            "description": "Case insensitive search (rg -i)"
          },
          "-n": {
            "type": "boolean",
            "description": "Show line numbers in output (rg -n). Requires output_mode: \"content\", ignored otherwise. Defaults to true."
          },
          "glob": {
            "type": "string",
            "description": "Glob pattern to filter files (e.g. \"*.js\", \"*.{ts,tsx}\") - maps to rg --glob"
          },
          "path": {
            "type": "string",
            "description": "File or directory to search in (rg PATH). Defaults to current working directory."
          },
          "type": {
            "type": "string",
            "description": "File type to search (rg --type). Common types: js, py, rust, go, java, etc. More efficient than include for standard file types."
          },
          "offset": {
            "type": "number",
            "description": "Skip first N lines/entries before applying head_limit, equivalent to \"| tail -n +N | head -N\". Works across all output modes. Defaults to 0."
          },
          "context": {
            "type": "number",
            "description": "Number of lines to show before and after each match (rg -C). Requires output_mode: \"content\", ignored otherwise."
          },
          "pattern": {
            "type": "string",
            "description": "The regular expression pattern to search for in file contents"
          },
          "multiline": {
            "type": "boolean",
            "description": "Enable multiline mode where . matches newlines and patterns can span lines (rg -U --multiline-dotall). Default: false."
          },
          "head_limit": {
            "type": "number",
            "description": "Limit output to first N lines/entries, equivalent to \"| head -N\". Works across all output modes: content (limits output lines), files_with_matches (limits file paths), count (limits count entries). Defaults to 0 (unlimited)."
          },
          "output_mode": {
            "enum": [
              "content",
              "files_with_matches",
              "count"
            ],
            "type": "string",
            "description": "Output mode: \"content\" shows matching lines (supports -A/-B/-C context, -n line numbers, head_limit), \"files_with_matches\" shows file paths (supports head_limit), \"count\" shows match counts (supports head_limit). Defaults to \"files_with_matches\"."
          }
        },
        "additionalProperties": false
      },
      "description": "A powerful search tool built on ripgrep\n\n  Usage:\n  - ALWAYS use Grep for search tasks. NEVER invoke `grep` or `rg` as a Bash command. The Grep tool has been optimized for correct permissions and access.\n  - Supports full regex syntax (e.g., \"log.*Error\", \"function\\s+\\w+\")\n  - Filter files with glob parameter (e.g., \"*.js\", \"**/*.tsx\") or type parameter (e.g., \"js\", \"py\", \"rust\")\n  - Output modes: \"content\" shows matching lines, \"files_with_matches\" shows only file paths (default), \"count\" shows match counts\n  - Use Task tool for open-ended searches requiring multiple rounds\n  - Pattern syntax: Uses ripgrep (not grep) - literal braces need escaping (use `interface\\{\\}` to find `interface{}` in Go code)\n  - Multiline matching: By default patterns match within single lines only. For cross-line patterns like `struct \\{[\\s\\S]*?field`, use `multiline: true`\n"
    },
    {
      "name": "ExitPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "allowedPrompts": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "tool",
                "prompt"
              ],
              "properties": {
                "tool": {
                  "enum": [
                    "Bash"
                  ],
                  "type": "string",
                  "description": "The tool this prompt applies to"
                },
                "prompt": {
                  "type": "string",
                  "description": "Semantic description of the action, e.g. \"run tests\", \"install dependencies\""
                }
              },
              "additionalProperties": false
            },
            "description": "Prompt-based permissions needed to implement the plan. These describe categories of actions rather than specific commands."
          }
        },
        "additionalProperties": {}
      },
      "description": "Use this tool when you are in plan mode and have finished writing your plan to the plan file and are ready for user approval.\n\n## How This Tool Works\n- You should have already written your plan to the plan file specified in the plan mode system message\n- This tool does NOT take the plan content as a parameter - it will read the plan from the file you wrote\n- This tool simply signals that you're done planning and ready for the user to review and approve\n- The user will see the contents of your plan file when they review it\n\n## When to Use This Tool\nIMPORTANT: Only use this tool when the task requires planning the implementation steps of a task that requires writing code. For research tasks where you're gathering information, searching files, reading files or in general trying to understand the codebase - do NOT use this tool.\n\n## Before Using This Tool\nEnsure your plan is complete and unambiguous:\n- If you have unresolved questions about requirements or approach, use AskUserQuestion first (in earlier phases)\n- Once your plan is finalized, use THIS tool to request approval\n\n**Important:** Do NOT use AskUserQuestion to ask \"Is this plan okay?\" or \"Should I proceed?\" - that's exactly what THIS tool does. ExitPlanMode inherently requests user approval of your plan.\n\n## Examples\n\n1. Initial task: \"Search for and understand the implementation of vim mode in the codebase\" - Do not use the exit plan mode tool because you are not planning the implementation steps of a task.\n2. Initial task: \"Help me implement yank mode for vim\" - Use the exit plan mode tool after you have finished planning the implementation steps of the task.\n3. Initial task: \"Add a new feature to handle user authentication\" - If unsure about auth method (OAuth, JWT, etc.), use AskUserQuestion first, then use exit plan mode tool after clarifying the approach.\n"
    },
    {
      "name": "Read",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path"
        ],
        "properties": {
          "limit": {
            "type": "number",
            "description": "The number of lines to read. Only provide if the file is too large to read at once."
          },
          "pages": {
            "type": "string",
            "description": "Page range for PDF files (e.g., \"1-5\", \"3\", \"10-20\"). Only applicable to PDF files. Maximum 20 pages per request."
          },
          "offset": {
            "type": "number",
            "description": "The line number to start reading from. Only provide if the file is too large to read at once"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to read"
          }
        },
        "additionalProperties": false
      },
      "description": "Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The file_path parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool allows Claude Code to read images (eg PNG, JPG, etc). When reading an image file the contents are presented visually as Claude Code is a multimodal LLM.\n- This tool can read PDF files (.pdf). For large PDFs (more than 10 pages), you MUST provide the pages parameter to read specific page ranges (e.g., pages: \"1-5\"). Reading a large PDF without the pages parameter will fail. Maximum 20 pages per request.\n- This tool can read Jupyter notebooks (.ipynb files) and returns all cells with their outputs, combining code, text, and visualizations.\n- This tool can only read files, not directories. To read a directory, use an ls command via the Bash tool.\n- You can call multiple tools in a single response. It is always better to speculatively read multiple potentially useful files in parallel.\n- You will regularly be asked to read screenshots. If the user provides a path to a screenshot, ALWAYS use this tool to view the file at the path. This tool will work with all temporary file paths.\n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents."
    },
    {
      "name": "Edit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "old_string",
          "new_string"
        ],
        "properties": {
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to modify"
          },
          "new_string": {
            "type": "string",
            "description": "The text to replace it with (must be different from old_string)"
          },
          "old_string": {
            "type": "string",
            "description": "The text to replace"
          },
          "replace_all": {
            "type": "boolean",
            "default": false,
            "description": "Replace all occurrences of old_string (default false)"
          }
        },
        "additionalProperties": false
      },
      "description": "Performs exact string replacements in files.\n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `old_string` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replace_all` to change every instance of `old_string`.\n- Use `replace_all` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance."
    },
    {
      "name": "Write",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "file_path",
          "content"
        ],
        "properties": {
          "content": {
            "type": "string",
            "description": "The content to write to the file"
          },
          "file_path": {
            "type": "string",
            "description": "The absolute path to the file to write (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked."
    },
    {
      "name": "NotebookEdit",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "notebook_path",
          "new_source"
        ],
        "properties": {
          "cell_id": {
            "type": "string",
            "description": "The ID of the cell to edit. When inserting a new cell, the new cell will be inserted after the cell with this ID, or at the beginning if not specified."
          },
          "cell_type": {
            "enum": [
              "code",
              "markdown"
            ],
            "type": "string",
            "description": "The type of the cell (code or markdown). If not specified, it defaults to the current cell type. If using edit_mode=insert, this is required."
          },
          "edit_mode": {
            "enum": [
              "replace",
              "insert",
              "delete"
            ],
            "type": "string",
            "description": "The type of edit to make (replace, insert, delete). Defaults to replace."
          },
          "new_source": {
            "type": "string",
            "description": "The new source for the cell"
          },
          "notebook_path": {
            "type": "string",
            "description": "The absolute path to the Jupyter notebook file to edit (must be absolute, not relative)"
          }
        },
        "additionalProperties": false
      },
      "description": "Completely replaces the contents of a specific cell in a Jupyter notebook (.ipynb file) with new source. Jupyter notebooks are interactive documents that combine code, text, and visualizations, commonly used for data analysis and scientific computing. The notebook_path parameter must be an absolute path, not a relative path. The cell_number is 0-indexed. Use edit_mode=insert to add a new cell at the index specified by cell_number. Use edit_mode=delete to delete the cell at the index specified by cell_number."
    },
    {
      "name": "WebFetch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "url",
          "prompt"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri",
            "description": "The URL to fetch content from"
          },
          "prompt": {
            "type": "string",
            "description": "The prompt to run on the fetched content"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Fetches content from a specified URL and processes it using an AI model\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Processes the content with the prompt using a small, fast model\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions.\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n  - When a URL redirects to a different host, the tool will inform you and provide the redirect URL in a special format. You should then make a new WebFetch request with the redirect URL to fetch the content.\n  - For GitHub URLs, prefer using the gh CLI via Bash instead (e.g., gh pr view, gh issue view, gh api).\n"
    },
    {
      "name": "WebSearch",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "query"
        ],
        "properties": {
          "query": {
            "type": "string",
            "minLength": 2,
            "description": "The search query to use"
          },
          "allowed_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Only include search results from these domains"
          },
          "blocked_domains": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Never include search results from these domains"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Allows Claude to search the web and use the results to inform responses\n- Provides up-to-date information for current events and recent data\n- Returns search result information formatted as search result blocks, including links as markdown hyperlinks\n- Use this tool for accessing information beyond Claude's knowledge cutoff\n- Searches are performed automatically within a single API call\n\nCRITICAL REQUIREMENT - You MUST follow this:\n  - After answering the user's question, you MUST include a \"Sources:\" section at the end of your response\n  - In the Sources section, list all relevant URLs from the search results as markdown hyperlinks: [Title](URL)\n  - This is MANDATORY - never skip including sources in your response\n  - Example format:\n\n    [Your answer here]\n\n    Sources:\n    - [Source Title 1](https://example.com/1)\n    - [Source Title 2](https://example.com/2)\n\nUsage notes:\n  - Domain filtering is supported to include or block specific websites\n  - Web search is only available in the US\n\nIMPORTANT - Use the correct year in search queries:\n  - The current month is April 2026. You MUST use this year when searching for recent information, documentation, or current events.\n  - Example: If the user asks for \"latest React docs\", search for \"React documentation\" with the current year, NOT last year\n"
    },
    {
      "name": "TaskStop",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "task_id": {
            "type": "string",
            "description": "The ID of the background task to stop"
          },
          "shell_id": {
            "type": "string",
            "description": "Deprecated: use task_id instead"
          }
        },
        "additionalProperties": false
      },
      "description": "\n- Stops a running background task by its ID\n- Takes a task_id parameter identifying the task to stop\n- Returns a success or failure status\n- Use this tool when you need to terminate a long-running task\n"
    },
    {
      "name": "AskUserQuestion",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "questions"
        ],
        "properties": {
          "answers": {
            "type": "object",
            "description": "User answers collected by the permission component",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "string"
            }
          },
          "metadata": {
            "type": "object",
            "properties": {
              "source": {
                "type": "string",
                "description": "Optional identifier for the source of this question (e.g., \"remember\" for /remember command). Used for analytics tracking."
              }
            },
            "description": "Optional metadata for tracking and analytics purposes. Not displayed to user.",
            "additionalProperties": false
          },
          "questions": {
            "type": "array",
            "items": {
              "type": "object",
              "required": [
                "question",
                "header",
                "options",
                "multiSelect"
              ],
              "properties": {
                "header": {
                  "type": "string",
                  "description": "Very short label displayed as a chip/tag (max 12 chars). Examples: \"Auth method\", \"Library\", \"Approach\"."
                },
                "options": {
                  "type": "array",
                  "items": {
                    "type": "object",
                    "required": [
                      "label",
                      "description"
                    ],
                    "properties": {
                      "label": {
                        "type": "string",
                        "description": "The display text for this option that the user will see and select. Should be concise (1-5 words) and clearly describe the choice."
                      },
                      "markdown": {
                        "type": "string",
                        "description": "Optional preview content shown in a monospace box when this option is focused. Use for ASCII mockups, code snippets, or diagrams that help users visually compare options. Supports multi-line text with newlines."
                      },
                      "description": {
                        "type": "string",
                        "description": "Explanation of what this option means or what will happen if chosen. Useful for providing context about trade-offs or implications."
                      }
                    },
                    "additionalProperties": false
                  },
                  "maxItems": 4,
                  "minItems": 2,
                  "description": "The available choices for this question. Must have 2-4 options. Each option should be a distinct, mutually exclusive choice (unless multiSelect is enabled). There should be no 'Other' option, that will be provided automatically."
                },
                "question": {
                  "type": "string",
                  "description": "The complete question to ask the user. Should be clear, specific, and end with a question mark. Example: \"Which library should we use for date formatting?\" If multiSelect is true, phrase it accordingly, e.g. \"Which features do you want to enable?\""
                },
                "multiSelect": {
                  "type": "boolean",
                  "default": false,
                  "description": "Set to true to allow the user to select multiple options instead of just one. Use when choices are not mutually exclusive."
                }
              },
              "additionalProperties": false
            },
            "maxItems": 4,
            "minItems": 1,
            "description": "Questions to ask the user (1-4 questions)"
          },
          "annotations": {
            "type": "object",
            "description": "Optional per-question annotations from the user (e.g., notes on preview selections). Keyed by question text.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "object",
              "properties": {
                "notes": {
                  "type": "string",
                  "description": "Free-text notes the user added to their selection."
                },
                "markdown": {
                  "type": "string",
                  "description": "The markdown preview content of the selected option, if the question used previews."
                }
              },
              "additionalProperties": false
            }
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool when you need to ask the user questions during execution. This allows you to:\n1. Gather user preferences or requirements\n2. Clarify ambiguous instructions\n3. Get decisions on implementation choices as you work\n4. Offer choices to the user about what direction to take.\n\nUsage notes:\n- Users will always be able to select \"Other\" to provide custom text input\n- Use multiSelect: true to allow multiple answers to be selected for a question\n- If you recommend a specific option, make that the first option in the list and add \"(Recommended)\" at the end of the label\n\nPlan mode note: In plan mode, use this tool to clarify requirements or choose between approaches BEFORE finalizing your plan. Do NOT use this tool to ask \"Is my plan ready?\" or \"Should I proceed?\" - use ExitPlanMode for plan approval. IMPORTANT: Do not reference \"the plan\" in your questions (e.g., \"Do you have feedback about the plan?\", \"Does the plan look good?\") because the user cannot see the plan in the UI until you call ExitPlanMode. If you need plan approval, use ExitPlanMode instead.\n\nPreview feature:\nUse the optional `markdown` field on options when presenting concrete artifacts that users need to visually compare:\n- ASCII mockups of UI layouts or components\n- Code snippets showing different implementations\n- Diagram variations\n- Configuration examples\n\nWhen any option has a markdown, the UI switches to a side-by-side layout with a vertical option list on the left and preview on the right. Do not use previews for simple preference questions where labels and descriptions suffice. Note: previews are only supported for single-select questions (not multiSelect).\n"
    },
    {
      "name": "Skill",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "skill"
        ],
        "properties": {
          "args": {
            "type": "string",
            "description": "Optional arguments for the skill"
          },
          "skill": {
            "type": "string",
            "description": "The skill name. E.g., \"commit\", \"review-pr\", or \"pdf\""
          }
        },
        "additionalProperties": false
      },
      "description": "Execute a skill within the main conversation\n\nWhen users ask you to perform tasks, check if any of the available skills match. Skills provide specialized capabilities and domain knowledge.\n\nWhen users reference a \"slash command\" or \"/<something>\" (e.g., \"/commit\", \"/review-pr\"), they are referring to a skill. Use this tool to invoke it.\n\nHow to invoke:\n- Use this tool with the skill name and optional arguments\n- Examples:\n  - `skill: \"pdf\"` - invoke the pdf skill\n  - `skill: \"commit\", args: \"-m 'Fix bug'\"` - invoke with arguments\n  - `skill: \"review-pr\", args: \"123\"` - invoke with arguments\n  - `skill: \"ms-office-suite:pdf\"` - invoke using fully qualified name\n\nImportant:\n- Available skills are listed in system-reminder messages in the conversation\n- When a skill matches the user's request, this is a BLOCKING REQUIREMENT: invoke the relevant Skill tool BEFORE generating any other response about the task\n- NEVER mention a skill without actually calling this tool\n- Do not invoke a skill that is already running\n- Do not use this tool for built-in CLI commands (like /help, /clear, etc.)\n- If you see a <command-name> tag in the current conversation turn, the skill has ALREADY been loaded - follow the instructions directly instead of calling this tool again\n"
    },
    {
      "name": "EnterPlanMode",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool proactively when you're about to start a non-trivial implementation task. Getting user sign-off on your approach before writing code prevents wasted effort and ensures alignment. This tool transitions you into plan mode where you can explore the codebase and design an implementation approach for user approval.\n\n## When to Use This Tool\n\n**Prefer using EnterPlanMode** for implementation tasks unless they're simple. Use it when ANY of these conditions apply:\n\n1. **New Feature Implementation**: Adding meaningful new functionality\n   - Example: \"Add a logout button\" - where should it go? What should happen on click?\n   - Example: \"Add form validation\" - what rules? What error messages?\n\n2. **Multi... (litellm_truncated skipped 1974 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...stion if you need to clarify approaches\n6. Exit plan mode with ExitPlanMode when ready to implement\n\n## Examples\n\n### GOOD - Use EnterPlanMode:\nUser: \"Add user authentication to the app\"\n- Requires architectural decisions (session vs JWT, where to store tokens, middleware structure)\n\nUser: \"Optimize the database queries\"\n- Multiple approaches possible, need to profile first, significant impact\n\nUser: \"Implement dark mode\"\n- Architectural decision on theme system, affects many components\n\nUser: \"Add a delete button to the user profile\"\n- Seems simple but involves: where to place it, confirmation dialog, API call, error handling, state updates\n\nUser: \"Update the error handling in the API\"\n- Affects multiple files, user should approve the approach\n\n### BAD - Don't use EnterPlanMode:\nUser: \"Fix the typo in the README\"\n- Straightforward, no planning needed\n\nUser: \"Add a console.log to debug this function\"\n- Simple, obvious implementation\n\nUser: \"What files handle routing?\"\n- Research task, not implementation planning\n\n## Important Notes\n\n- This tool REQUIRES user approval - they must consent to entering plan mode\n- If unsure whether to use it, err on the side of planning - it's better to get alignment upfront than to redo work\n- Users appreciate being consulted before significant changes are made to their codebase\n"
    },
    {
      "name": "TaskCreate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "subject",
          "description"
        ],
        "properties": {
          "subject": {
            "type": "string",
            "description": "A brief title for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Arbitrary metadata to attach to the task",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "A detailed description of what needs to be done"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to create a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\n\nUse this tool proactively in these scenarios:\n\n- Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n- Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n- Plan mode - When using plan mode, create a task list to track the work\n- User explicitly requests todo list - When the user directly asks you to use the todo list\n- User provides multip... (litellm_truncated skipped 425 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...\n- There is only a single, straightforward task\n- The task is trivial and tracking it provides no organizational benefit\n- The task can be completed in less than 3 trivial steps\n- The task is purely conversational or informational\n\nNOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.\n\n## Task Fields\n\n- **subject**: A brief, actionable title in imperative form (e.g., \"Fix authentication bug in login flow\")\n- **description**: Detailed description of what needs to be done, including context and acceptance criteria\n- **activeForm**: Present continuous form shown in spinner when task is in_progress (e.g., \"Fixing authentication bug\"). This is displayed to the user while you work on the task.\n\n**IMPORTANT**: Always provide activeForm when creating tasks. The subject should be imperative (\"Run tests\") while activeForm should be present continuous (\"Running tests\"). All tasks are created with status `pending`.\n\n## Tips\n\n- Create tasks with clear, specific subjects that describe the outcome\n- Include enough detail in the description for another agent to understand and complete the task\n- After creating tasks, use TaskUpdate to set up dependencies (blocks/blockedBy) if needed\n- Check TaskList first to avoid creating duplicate tasks\n"
    },
    {
      "name": "TaskGet",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "taskId": {
            "type": "string",
            "description": "The ID of the task to retrieve"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to retrieve a task by its ID from the task list.\n\n## When to Use This Tool\n\n- When you need the full description and context before starting work on a task\n- To understand task dependencies (what it blocks, what blocks it)\n- After being assigned a task, to get complete requirements\n\n## Output\n\nReturns full task details:\n- **subject**: Task title\n- **description**: Detailed requirements and context\n- **status**: 'pending', 'in_progress', or 'completed'\n- **blocks**: Tasks waiting on this one to complete\n- **blockedBy**: Tasks that must complete before this one can start\n\n## Tips\n\n- After fetching a task, verify its blockedBy list is empty before beginning work.\n- Use TaskList to see all tasks in summary form.\n"
    },
    {
      "name": "TaskUpdate",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "required": [
          "taskId"
        ],
        "properties": {
          "owner": {
            "type": "string",
            "description": "New owner for the task"
          },
          "status": {
            "anyOf": [
              {
                "enum": [
                  "pending",
                  "in_progress",
                  "completed"
                ],
                "type": "string"
              },
              {
                "type": "string",
                "const": "deleted"
              }
            ],
            "description": "New status for the task"
          },
          "taskId": {
            "type": "string",
            "description": "The ID of the task to update"
          },
          "subject": {
            "type": "string",
            "description": "New subject for the task"
          },
          "metadata": {
            "type": "object",
            "description": "Metadata keys to merge into the task. Set a key to null to delete it.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          },
          "addBlocks": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that this task blocks"
          },
          "activeForm": {
            "type": "string",
            "description": "Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")"
          },
          "description": {
            "type": "string",
            "description": "New description for the task"
          },
          "addBlockedBy": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Task IDs that block this task"
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool to update a task in the task list.\n\n## When to Use This Tool\n\n**Mark tasks as resolved:**\n- When you have completed the work described in a task\n- When a task is no longer needed or has been superseded\n- IMPORTANT: Always mark your assigned tasks as resolved when you finish them\n- After resolving, call TaskList to find your next task\n\n- ONLY mark a task as completed when you have FULLY accomplished it\n- If you encounter errors, blockers, or cannot finish, keep the task as in_progress\n- When blocked, create a new task describing what needs to be resolved\n- Never mark a task as completed if:\n  - Tests are failing\n  - Implementation is partial\n  - You encountered unresolved errors\n  - You couldn'... (litellm_truncated skipped 196 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...ils:**\n- When requirements change or become clearer\n- When establishing dependencies between tasks\n\n## Fields You Can Update\n\n- **status**: The task status (see Status Workflow below)\n- **subject**: Change the task title (imperative form, e.g., \"Run tests\")\n- **description**: Change the task description\n- **activeForm**: Present continuous form shown in spinner when in_progress (e.g., \"Running tests\")\n- **owner**: Change the task owner (agent name)\n- **metadata**: Merge metadata keys into the task (set a key to null to delete it)\n- **addBlocks**: Mark tasks that cannot start until this one completes\n- **addBlockedBy**: Mark tasks that must complete before this one can start\n\n## Status Workflow\n\nStatus progresses: `pending` → `in_progress` → `completed`\n\nUse `deleted` to permanently remove a task.\n\n## Staleness\n\nMake sure to read a task's latest state using `TaskGet` before updating it.\n\n## Examples\n\nMark task as in progress when starting work:\n```json\n{\"taskId\": \"1\", \"status\": \"in_progress\"}\n```\n\nMark task as completed after finishing work:\n```json\n{\"taskId\": \"1\", \"status\": \"completed\"}\n```\n\nDelete a task:\n```json\n{\"taskId\": \"1\", \"status\": \"deleted\"}\n```\n\nClaim a task by setting owner:\n```json\n{\"taskId\": \"1\", \"owner\": \"my-name\"}\n```\n\nSet up task dependencies:\n```json\n{\"taskId\": \"2\", \"addBlockedBy\": [\"1\"]}\n```\n"
    },
    {
      "name": "TaskList",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {},
        "additionalProperties": false
      },
      "description": "Use this tool to list all tasks in the task list.\n\n## When to Use This Tool\n\n- To see what tasks are available to work on (status: 'pending', no owner, not blocked)\n- To check overall progress on the project\n- To find tasks that are blocked and need dependencies resolved\n- After completing a task, to check for newly unblocked work or claim the next available task\n- **Prefer working on tasks in ID order** (lowest ID first) when multiple tasks are available, as earlier tasks often set up context for later ones\n\n## Output\n\nReturns a summary of each task:\n- **id**: Task identifier (use with TaskGet, TaskUpdate)\n- **subject**: Brief description of the task\n- **status**: 'pending', 'in_progress', or 'completed'\n- **owner**: Agent ID if assigned, empty if available\n- **blockedBy**: List of open task IDs that must be resolved first (tasks with blockedBy cannot be claimed until dependencies resolve)\n\nUse TaskGet with a specific task ID to view full details including description and comments.\n"
    },
    {
      "name": "EnterWorktree",
      "type": "function",
      "strict": null,
      "parameters": {
        "type": "object",
        "$schema": "https://json-schema.org/draft/2020-12/schema",
        "properties": {
          "name": {
            "type": "string",
            "description": "Optional name for the worktree. A random name is generated if not provided."
          }
        },
        "additionalProperties": false
      },
      "description": "Use this tool ONLY when the user explicitly asks to work in a worktree. This tool creates an isolated git worktree and switches the current session into it.\n\n## When to Use\n\n- The user explicitly says \"worktree\" (e.g., \"start a worktree\", \"work in a worktree\", \"create a worktree\", \"use a worktree\")\n\n## When NOT to Use\n\n- The user asks to create a branch, switch branches, or work on a different branch — use git commands instead\n- The user asks to fix a bug or work on a feature — use normal git workflow unless they specifically mention worktrees\n- Never use this tool unless the user explicitly mentions \"worktree\"\n\n## Requirements\n\n- Must be in a git repository, OR have WorktreeCreate/WorktreeRemove hooks configured in settings.json\n- Must not already be in a worktree\n\n## Behavior\n\n- In a git repository: creates a new git worktree inside `.claude/worktrees/` with a new branch based on HEAD\n- Outside a git repository: delegates to WorktreeCreate/WorktreeRemove hooks for VCS-agnostic isolation\n- Switches the session's working directory to the new worktree\n- On session exit, the user will be prompted to keep or remove the worktree\n\n## Parameters\n\n- `name` (optional): A name for the worktree. If not provided, a random name is generated.\n"
    }
  ],
  "top_p": 0.95,
  "usage": {
    "total_tokens": 18552,
    "prompt_tokens": 18515,
    "completion_tokens": 37,
    "prompt_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": null,
      "audio_tokens": null,
      "image_tokens": null,
      "video_tokens": null,
      "reasoning_tokens": 0,
      "accepted_prediction_tokens": null,
      "rejected_prediction_tokens": null
    }
  },
  "object": "response",
  "output": [
    {
      "id": "rs_b50f51586dcd7af2",
      "type": "reasoning",
      "content": [
        {
          "text": "The user is greeting me, so I should respond with a brief, friendly greeting and offer to help with their tasks.\n",
          "type": "reasoning_text"
        }
      ],
      "summary": []
    },
    {
      "id": "msg_9f53f5abe425a5e5",
      "role": "assistant",
      "type": "message",
      "phase": null,
      "status": "completed",
      "content": [
        {
          "text": "\n\nHi! How can I help you today?",
          "type": "output_text",
          "logprobs": null,
          "annotations": []
        }
      ]
    }
  ],
  "prompt": null,
  "status": "completed",
  "metadata": null,
  "reasoning": {
    "effort": "high",
    "summary": null,
    "generate_summary": null
  },
  "background": false,
  "created_at": 1776326448,
  "truncation": "disabled",
  "temperature": 0.6,
  "tool_choice": "auto",
  "instructions": "x-anthropic-billing-header: cc_version=2.1.51.ea8; cc_entrypoint=cli; cch=af527;\nYou are Claude Code, Anthropic's official CLI for Claude.\n\nYou are an interactive agent that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, s... (litellm_truncated skipped 13015 chars. Truncation is a DB storage safeguard. Full, untruncated data is logged to logging callbacks (OTEL, Datadog, etc.). To increase the truncation limit, set `MAX_STRING_LENGTH_PROMPT_IN_DB` in your env.) ...t be incomplete — verify against project docs before writing\n- Anything that duplicates or contradicts existing CLAUDE.md instructions\n- Speculative or unverified conclusions from reading a single file\n\n## Explicit user requests:\n- When the user asks you to remember something across sessions (e.g., \"always use bun\", \"never auto-commit\"), save it — no need to wait for multiple interactions\n- When the user asks to forget or stop remembering something, find and remove the relevant entries from your memory files\n\n\n# Environment\nYou have been invoked in the following environment: \n - Primary working directory: C:\\Users\\spies\\claudetest\n  - Is a git repository: false\n - Platform: win32\n - Shell: bash (use Unix shell syntax, not Windows — e.g., /dev/null not NUL, forward slashes in paths)\n - OS Version: Windows 11 Pro 10.0.26200\n - You are powered by the model qwen3.5-397b-a17b.\n - The most recent Claude model family is Claude 4.5/4.6. Model IDs — Opus 4.6: 'claude-opus-4-6', Sonnet 4.6: 'claude-sonnet-4-6', Haiku 4.5: 'claude-haiku-4-5-20251001'. When building AI applications, default to the latest and most capable Claude models.\n\n\n<fast_mode_info>\nFast mode for Claude Code uses the same Claude Opus 4.6 model with faster output. It does NOT switch to a different model. It can be toggled with /fast.\n</fast_mode_info>",
  "service_tier": "auto",
  "top_logprobs": null,
  "input_messages": null,
  "max_tool_calls": null,
  "output_messages": null,
  "max_output_tokens": 32000,
  "incomplete_details": null,
  "parallel_tool_calls": true,
  "previous_response_id": null
}

In the response the correct answer from the server can be found, which is somehow not backtranslated:

"output": [
    {
      "id": "rs_b50f51586dcd7af2",
      "type": "reasoning",
      "content": [
        {
          "text": "The user is greeting me, so I should respond with a brief, friendly greeting and offer to help with their tasks.\n",
          "type": "reasoning_text"
        }
      ],
      "summary": []
    },
    {
      "id": "msg_9f53f5abe425a5e5",
      "role": "assistant",
      "type": "message",
      "phase": null,
      "status": "completed",
      "content": [
        {
          "text": "\n\nHi! How can I help you today?",
          "type": "output_text",
          "logprobs": null,
          "annotations": []
        }
      ]
    }
  ],

Steps to Reproduce

config.yaml:
model_list:
  - model_name: qwen3.5-397b-a17b
    litellm_params:
      model: openai/qwen3.5-397b-a17b  # Using openai/ prefix tells LiteLLM to use the OpenAI-compatible format
      api_base: <
      api_key: < # Replace with your actual key if required
      temperature: 0.6
      top_p: 0.95
      max_tokens: 256000
      stream: true
      drop_params: true
      metadata:
        stream_with_empty_messages: true
      # Define mapping for specific parameter adjustments
      input_filter_params:
        max_completion_tokens: max_tokens
  - model_name: devstral-2-123b-instruct-2512
    litellm_params:
      model: openai/devstral-2-123b-instruct-2512
      api_base: <
      api_key: <
      stream: false
      drop_params: true
      max_tokens: 256000
      # Define mapping for specific parameter adjustments
      input_filter_params:
        max_completion_tokens: max_tokens
  - model_name: mistral-large-3-675b-instruct-2512
    litellm_params:
      model: openai/mistral-large-3-675b-instruct-2512
      api_base: <
      api_key: <
      temperature: 0.08
      stream: false
      drop_params: true
      max_tokens: 256000
      # Define mapping for specific parameter adjustments
      input_filter_params:
        max_completion_tokens: max_tokens
  - model_name: qwen3.5-27b
    litellm_params:
      model: openai/qwen3.5-27b
      api_base: <
      api_key: <
      temperature: 0.6
      top_p: 0.95
      stream: false
      drop_params: true
      max_tokens: 256000
      # Define mapping for specific parameter adjustments
      input_filter_params:
        max_completion_tokens: max_tokens

general_settings:
  # Ensure your proxy has a master key
  master_key: <
  # Allows passing custom headers through to the provider
  debug: true
  store_prompts_in_spend_logs: true
  store_model_in_db: true

compose.yaml:

services:
  postgres:
    image: postgres:latest
    container_name: litellm-db
    environment:
      POSTGRES_USER: litellm_user
      POSTGRES_PASSWORD: yourpassword
      POSTGRES_DB: litellm_db
    volumes:
      - pgdata:/var/lib/postgresql

  litellm:
    image: docker.litellm.ai/berriai/litellm:v1.83.8-nightly
    container_name: litellm-proxy
    ports:
      - "4000:4000"
    volumes:
      - ./config.yaml:/app/config.yaml:Z
    environment:
      DATABASE_URL: "postgresql://litellm_user:yourpassword@postgres:5432/litellm_db"
      LITELLM_MASTER_KEY: "x"
      UI_USERNAME: "x"
      UI_PASSWORD: "x"
    command: ["--config", "/app/config.yaml"]
    depends_on:
      - postgres 

volumes:
  pgdata:

Steps:

docker compose up -d
install e.g. claude stable (v2.1.92)
Say "hi"

Relevant log output

"output": [
    {
      "id": "rs_b50f51586dcd7af2",
      "type": "reasoning",
      "content": [
        {
          "text": "The user is greeting me, so I should respond with a brief, friendly greeting and offer to help with their tasks.\n",
          "type": "reasoning_text"
        }
      ],
      "summary": []
    },
    {
      "id": "msg_9f53f5abe425a5e5",
      "role": "assistant",
      "type": "message",
      "phase": null,
      "status": "completed",
      "content": [
        {
          "text": "\n\nHi! How can I help you today?",
          "type": "output_text",
          "logprobs": null,
          "annotations": []
        }
      ]
    }
  ],

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.83.8

Twitter / LinkedIn details

No response

extent analysis

TL;DR

The issue seems to be related to the LiteLLM proxy not correctly backtranslating the response from the server, resulting in an empty output.

Guidance

Verify server response: The server response contains the correct answer, so the issue lies in the backtranslation process.
Check LiteLLM configuration: Review the config.yaml file to ensure that the litellm_params are correctly configured, especially the model and api_base parameters.
Inspect proxy logs: Check the LiteLLM proxy logs for any errors or warnings related to the backtranslation process.
Test with different models: Try using different models, such as devstral-2-123b-instruct-2512 or mistral-large-3-675b-instruct-2512, to see if the issue persists.

Example

No code example is provided as the issue seems to be related to the LiteLLM configuration and proxy setup.

Notes

The issue might be specific to the qwen3.5-397b-a17b model or the LiteLLM version v1.83.8. Further investigation is needed to determine the root cause.

Recommendation

Apply a workaround by checking the server response manually to ensure that the correct answer is being generated, and then investigate further to resolve the backtranslation issue.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #ssr #installation #tensor shape #autograd error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

litellm - 💡(How to fix) Fix [Bug]: Litellm v1.83.8, v1.83.3, v1.82.2 Claud Code v2.1.110, v2.1.92, v2.1.52 OpenAI-compatible Translation Empty [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

litellm - 💡(How to fix) Fix [Bug]: Litellm v1.83.8, v1.83.3, v1.82.2 Claud Code v2.1.110, v2.1.92, v2.1.52 OpenAI-compatible Translation Empty [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING