What causes "action='list' requires 'path'" in crewAIInc/crewAI?

Pass the directory explicitly: tool.run(action='list', path='/workspace').

crewAIInc/crewAI · error · ValueError

action='list' requires 'path'

Error message

action='list' requires 'path'

What it means

DaytonaFileTool._run's defensive check for action='list': a None path raises ValueError before self._list(sandbox, path) is called. The Pydantic schema normally rejects a missing path earlier, so this fires mainly on direct _run invocations. Note that listing requires an explicit directory path — there is no implicit root default.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/daytona_sandbox_tool/daytona_file_tool.py:269

        group: str | None = None,
    ) -> Any:
        sandbox, should_delete = self._acquire_sandbox()
        try:
            if action == "read":
                if path is None:
                    raise ValueError("action='read' requires 'path'")
                return self._read(sandbox, path, binary=binary)
            if action == "write":
                if path is None:
                    raise ValueError("action='write' requires 'path'")
                return self._write(sandbox, path, content or "", binary=binary)
            if action == "append":
                if path is None:
                    raise ValueError("action='append' requires 'path'")
                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:

View on GitHub (pinned to 754d7323be)

Solutions

Pass the directory explicitly: tool.run(action='list', path='/workspace').
Do not rely on a default root — always provide the directory to list.
If calling _run directly, ensure path is set before invocation.

Example fix

# before
tool._run(action="list")  # ValueError

# after
tool.run(action="list", path="/workspace")

Defensive patterns

Strategy: validation

Validate before calling

def validated_list_call(tool, path: str | None) -> Any:
    directory = path or "/workspace"  # explicit default; the tool has none
    return tool.run(action="list", path=directory)

Try / catch

try:
    entries = tool.run(action="list", path=p)
except ValueError as e:
    if "requires 'path'" in str(e):
        entries = tool.run(action="list", path="/workspace")
    else:
        raise

Prevention

The list action has no implicit root — always pass the directory.
Wrap list calls with an explicit default directory in your helper layer.
Go through run() so the schema validator reports missing fields clearly.

When it happens

Trigger: Calling tool._run(action='list', path=None) directly; assuming the tool defaults to the sandbox workspace root when path is omitted; test harness bypassing schema validation.

Common situations: Developers expecting a default directory listing; direct private-method calls in tests; argument dicts missing the path key.

Related errors

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/c9e6da12abebb3a4. Report an issue: GitHub.