crewAIInc/crewAI · error · ValueError

action='append' requires 'content'. Pass the chunk to append

Error message

action='append' requires 'content'. Pass the chunk to append in the 'content' field.

What it means

Raised by a Pydantic model_validator (mode='after') on E2BFileToolSchema when the tool is invoked with action='append' but no 'content' field. The schema enforces that append operations carry the chunk of data to append, since appending nothing is meaningless. It fires at input-validation time, before any sandbox call is made.

Source

Thrown at lib/crewai-tools/src/crewai_tools/tools/e2b_sandbox_tool/e2b_file_tool.py:61

        ),
    )
    binary: bool = Field(
        default=False,
        description=(
            "For 'write'/'append': treat content as base64 and upload raw "
            "bytes. For 'read': return contents as base64 instead of decoded "
            "utf-8."
        ),
    )
    depth: int = Field(
        default=1,
        description="For action='list': how many levels deep to recurse (default 1).",
    )

    @model_validator(mode="after")
    def _validate_action_args(self) -> E2BFileToolSchema:
        if self.action == "append" and self.content is None:
            raise ValueError(
                "action='append' requires 'content'. Pass the chunk to append "
                "in the 'content' field."
            )
        return self


class E2BFileTool(E2BBaseTool):
    """Read, write, and manage files inside an E2B sandbox.

    Notes:
      - Most useful with `persistent=True` or an explicit `sandbox_id`. With
        the default ephemeral mode, files disappear when this tool call
        finishes.
    """

    name: str = "E2B Sandbox Files"
    description: str = (
        "Perform filesystem operations inside an E2B sandbox: read a file, "

View on GitHub (pinned to 754d7323be)

Solutions

Pass the data to append: tool._run(action='append', path='/tmp/log.txt', content='new line\n').
If the content may be empty, guard on your side: only invoke append when the chunk is non-empty.
If appending nothing is intentional, skip the tool call entirely instead of calling append with no content.

Example fix

# before
tool._run(action='append', path='/tmp/log.txt')

# after
tool._run(action='append', path='/tmp/log.txt', content='new line\n')

Defensive patterns

Strategy: validation

Validate before calling

def build_append_args(path: str, chunk: str | None) -> dict:
    if not chunk:
        raise ValueError('refusing to append empty/missing content')
    return {'action': 'append', 'path': path, 'content': chunk}

Try / catch

from pydantic import ValidationError
try:
    tool._run(action='append', path=p, content=c)
except ValidationError as e:
    logger.warning('append rejected: %s', e.errors()[0]['msg'])

Prevention

Always construct tool args as an explicit dict including content for append actions.
Skip the tool call when the append chunk is empty instead of sending None.

When it happens

Trigger: Calling E2BFileTool._run(action='append', path='/tmp/log.txt') without passing content, or passing content=None explicitly (e.g. an LLM agent omitting the argument, or a dict-based invocation that drops the key).

Common situations: An LLM agent using the tool decides to 'append' but leaves content out of its action input; programmatic callers building kwargs conditionally and skipping content when the buffer is empty.

Related errors

AI-assisted analysis of crewAIInc/crewAI@754d7323be (2026-08-15). Data as JSON: /api/errors/531a4fbbed535a54. Report an issue: GitHub.