crewAIInc/crewAI · error · ValueError

action='read' requires 'path'

Error message

action='read' requires 'path'

What it means

Inside DaytonaFileTool._run, each action re-checks its required argument defensively. For action='read' a None path raises ValueError("action='read' requires 'path'"). Under normal use the Pydantic schema validator already rejects a missing path, so this branch is only reachable when _run is invoked directly (bypassing schema validation), e.g. in tests or custom wiring.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/daytona_sandbox_tool/daytona_file_tool.py:257

        self,
        action: FileAction,
        path: str | None = None,
        content: str | None = None,
        binary: bool = False,
        recursive: bool = False,
        mode: str | None = None,
        destination: str | None = None,
        pattern: str | None = None,
        replacement: str | None = None,
        paths: list[str] | None = None,
        owner: str | None = None,
        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}

View on GitHub (pinned to 754d7323be)

Solutions

1. Invoke the tool through its public API (tool.run / BaseToolInputModel-validated path) so the schema catches bad input first.
2. If calling _run directly, always pass a concrete path: tool._run(action='read', path='/workspace/file.txt').
3. In tests, build arguments via the schema: DaytonaFileToolSchema(action='read', path=...).model_dump().

Example fix

# before
tool._run(action="read", path=None)  # ValueError

# after
tool.run(action="read", path="/workspace/main.py")

def validated_read_call(tool, path: str | None) -> Any:
    if path is None:
        raise ValueError("action='read' requires an explicit path")
    return tool.run(action="read", path=path)  # schema-validated invocation

try:
    data = tool.run(action="read", path=p)
except ValueError as e:
    if "requires 'path'" in str(e):
        p = resolve_default_file()
        data = tool.run(action="read", path=p)
    else:
        raise

When it happens

Trigger: Calling tool._run(action='read', path=None, ...) directly instead of tool.run(...) / validated invocation; subclass or test harness that constructs arguments programmatically and skips the Pydantic model_validator.

Common situations: Unit tests exercising _run directly; custom tool wrappers calling the private method; monkeypatched paths where the schema step is skipped.

Related errors

• action='write' requires 'path'
• action='append' requires 'path'
• action='list' requires 'path'
• action={self.action!r} requires 'path'.
• action='append' requires 'content'. Pass the chunk to append

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/185a34e2e1f2bf2c. Report an issue: GitHub.