microsoft/autogen · error · ValueError

Functions failed to load: {exec_result.output}

Error message

Functions failed to load: {exec_result.output}

What it means

Raised after a successful pip install during LocalCommandLineCodeExecutor setup: the generated functions module is executed once as a smoke test (_execute_code_dont_check_setup), and if that execution returns a nonzero exit code (syntax error, failing import, exception at import time), the ValueError embeds the captured output.

Source

Thrown at python/packages/autogen-ext/src/autogen_ext/code_executors/local/__init__.py:320

            cancellation_token.link_future(task)
            try:
                proc = await task
                stdout, stderr = await asyncio.wait_for(proc.communicate(), self._timeout)
            except asyncio.TimeoutError as e:
                raise ValueError("Pip install timed out") from e
            except asyncio.CancelledError as e:
                raise ValueError("Pip install was cancelled") from e

            if proc.returncode is not None and proc.returncode != 0:
                raise ValueError(f"Pip install failed. {stdout.decode()}, {stderr.decode()}")

        # Attempt to load the function file to check for syntax errors, imports etc.
        exec_result = await self._execute_code_dont_check_setup(
            [CodeBlock(code=func_file_content, language="python")], cancellation_token
        )

        if exec_result.exit_code != 0:
            raise ValueError(f"Functions failed to load: {exec_result.output}")

        self._setup_functions_complete = True

    async def execute_code_blocks(
        self, code_blocks: List[CodeBlock], cancellation_token: CancellationToken
    ) -> CommandLineCodeResult:
        """(Experimental) Execute the code blocks and return the result.

        Args:
            code_blocks (List[CodeBlock]): The code blocks to execute.
            cancellation_token (CancellationToken): a token to cancel the operation

        Returns:
            CommandLineCodeResult: The result of the code execution."""

        if not self._setup_functions_complete:
            await self._setup_functions(cancellation_token)

View on GitHub (pinned to 027ecf0a37)

Solutions

1. Read the exec output embedded in the message - it contains the Python traceback of the failed import/exec; fix the function code accordingly.
2. Make function modules import-safe: move I/O and side effects inside the function body, not at module top level.
3. Ensure the dependency is importable in the interpreter the executor uses (same venv); add the missing package to the function's imports so pip installs it.

Example fix

# before
@register_function
def load_config() -> dict:
    import json, os
    return json.load(open(os.environ.get("CONFIG", "/etc/app/config.json")))  # fails during smoke test

# after
@register_function
def load_config(path: str) -> dict:
    import json
    return json.load(open(path))

import ast

def functions_module_valid(module_src: str) -> bool:
    try:
        ast.parse(module_src)
        return True
    except SyntaxError:
        return False

try:
    await executor.execute_code_blocks(blocks, token)
except ValueError as e:
    if "Functions failed to load" in str(e):
        log.error("function module smoke test failed:\n%s", str(e))
        raise  # output contains the traceback; fix the function body
    raise

When it happens

Trigger: A registered function's module has a syntax error, or its top-level/import code raises (missing optional dependency not captured by pip, file/network access at import time), so the smoke-test execution fails.

Common situations: Functions that read files or env vars at import time which do not exist in the executor's working directory, syntax errors in hand-written function bodies, imports of packages installed in a different interpreter than the executor's virtual_env_context.

Related errors

• Pip install timed out
• Pip install failed. {stdout.decode()}, {stderr.decode()}
• Invalid message type
• Could not compile function: {e}
• Packages unavailable in environment: {missing_pkgs}

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/18af1f30ea0e8495. Report an issue: GitHub.