crewAIInc/crewAI · error · ValueError

action='info' requires 'path'

Error message

action='info' requires 'path'

What it means

For action='info' DaytonaFileTool._run needs a 'path' to fetch metadata for via self._info(sandbox, path). A missing path raises ValueError before any SDK call, so the error never reflects a sandbox-side problem. The info result (size, mode, timestamps) is only assembled after validation succeeds.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/daytona_sandbox_tool/daytona_file_tool.py:284

                return self._append(sandbox, path, content or "", binary=binary)
            if action == "list":
                if path is None:
                    raise ValueError("action='list' requires 'path'")
                return self._list(sandbox, path)
            if action == "delete":
                if path is None:
                    raise ValueError("action='delete' requires 'path'")
                sandbox.fs.delete_file(path, recursive=recursive)
                return {"status": "deleted", "path": path}
            if action == "mkdir":
                if path is None:
                    raise ValueError("action='mkdir' requires 'path'")
                mkdir_mode = mode or "0755"
                sandbox.fs.create_folder(path, mkdir_mode)
                return {"status": "created", "path": path, "mode": mkdir_mode}
            if action == "info":
                if path is None:
                    raise ValueError("action='info' requires 'path'")
                return self._info(sandbox, path)
            if action == "exists":
                if path is None:
                    raise ValueError("action='exists' requires 'path'")
                return self._exists(sandbox, path)
            if action == "move":
                if path is None or destination is None:
                    raise ValueError("action='move' requires 'path' and 'destination'")
                sandbox.fs.move_files(path, destination)
                return {"status": "moved", "from": path, "to": destination}
            if action == "find":
                if path is None or pattern is None:
                    raise ValueError("action='find' requires 'path' and 'pattern'")
                return self._find(sandbox, path, pattern)
            if action == "search":
                if path is None or pattern is None:
                    raise ValueError("action='search' requires 'path' and 'pattern'")
                return self._search(sandbox, path, pattern)

View on GitHub (pinned to 754d7323be)

Solutions

1. Include the target: _run(action='info', path='/workspace/report.pdf').
2. Validate the kwargs against the tool schema before calling.
3. If chaining operations in an agent, require the path in every step of the plan, not just the first.

Example fix

# before
info = file_tool._run(action='info')

# after
info = file_tool._run(action='info', path='/workspace/report.pdf')

def safe_info(file_tool, path: str | None):
    if not path:
        raise ValueError("action='info' requires 'path'")
    return file_tool._run(action='info', path=path)

try:
    info = file_tool._run(action='info', path=path)
except ValueError:
    # path was None — re-ask the caller for the target
    path = request_path_from_user_or_agent()

When it happens

Trigger: Calling _run(action='info') with path omitted or explicitly None; agents that pass only the action verb; using 'file' or 'target' as the kwarg instead of 'path'.

Common situations: Agent-generated calls that assume the tool remembers a previously used path (the tool is stateless per call); exploratory calls while testing the tool with minimal arguments.

Related errors

• action='delete' requires 'path'
• action='mkdir' requires 'path'
• action='exists' requires 'path'
• action='move' requires 'path' and 'destination'
• action='find' requires 'path' and 'pattern'

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/d5198b228c711e69. Report an issue: GitHub.