microsoft/autogen · error · ValueError

All messages in task list must be valid BaseChatMessage type

Error message

All messages in task list must be valid BaseChatMessage types

What it means

Every element of a list task must be a BaseChatMessage instance (TextMessage, MultiModalMessage, etc.). The constructor loop isinstance-checks each element; anything else — including BaseAgentEvent subclasses or plain dicts — is rejected.

Source

Thrown at python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_base_group_chat.py:469

            asyncio.run(main())

        """
        # Create the messages list if the task is a string or a chat message.
        messages: List[BaseChatMessage] | None = None
        if task is None:
            pass
        elif isinstance(task, str):
            messages = [TextMessage(content=task, source="user")]
        elif isinstance(task, BaseChatMessage):
            messages = [task]
        elif isinstance(task, list):
            if not task:
                raise ValueError("Task list cannot be empty.")
            messages = []
            for msg in task:
                if not isinstance(msg, BaseChatMessage):
                    raise ValueError("All messages in task list must be valid BaseChatMessage types")
                messages.append(msg)
        else:
            raise ValueError("Task must be a string, a BaseChatMessage, or a list of BaseChatMessage.")
        # Check if the messages types are registered with the message factory.
        if messages is not None:
            for msg in messages:
                if not self._message_factory.is_registered(msg.__class__):
                    raise ValueError(
                        f"Message type {msg.__class__} is not registered with the message factory. "
                        "Please register it with the message factory by adding it to the "
                        "custom_message_types list when creating the team."
                    )

        if self._is_running:
            raise ValueError("The team is already running, it cannot run again until it is stopped.")
        self._is_running = True

        if self._embedded_runtime:

View on GitHub (pinned to 027ecf0a37)

Solutions

Wrap plain strings: task=[TextMessage(content="Start", source="user")].
Convert dicts with the message factory: factory.create(d) before passing.
Remove non-message items or convert them to a proper BaseChatMessage subclass.

Example fix

# before
await team.run(task=["plan the trip", {"content": "book flight"}])

# after
from autogen_agentchat.messages import TextMessage
await team.run(task=[TextMessage(content="plan the trip", source="user"), TextMessage(content="book flight", source="user")])

Defensive patterns

Strategy: type-guard

Validate before calling

from autogen_agentchat.messages import BaseChatMessage
if not all(isinstance(m, BaseChatMessage) for m in task):
    raise TypeError("task list must contain only BaseChatMessage instances")

Type guard

from autogen_agentchat.messages import BaseChatMessage
from typing import Any

def is_message_list(task: Any) -> bool:
    return isinstance(task, list) and all(isinstance(m, BaseChatMessage) for m in task)

Prevention

Convert raw strings/dicts to TextMessage / factory.create() before building the task list.
Do not mix agent events (BaseAgentEvent) into task lists.
Type-annotate task variables as list[BaseChatMessage] to catch mistakes statically.

When it happens

Trigger: Calling team.run_stream(task=["just a string"]) or mixing messages with events/dicts in the list: task=[TextMessage(...), {'content': 'x'}].

Common situations: Feeding raw LLM output or JSON-deserialized dicts back as a task; accidentally including agent events (e.g. ToolCallRequestEvent) which are events, not chat messages.

Related errors

AI-assisted analysis of microsoft/autogen@027ecf0a37 (2026-08-15). Data as JSON: /api/errors/50a120b74a25efb5. Report an issue: GitHub.