SelectorGroupChat not working with Gemini 2.0 Flash

[vishal-android-freak]

What happened?

Getting an error as soon as I run the main file

Traceback (most recent call last):
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/main.py", line 15, in <module>
    asyncio.run(main())
  File "/Users/naarang/.asdf/installs/python/3.11.3/lib/python3.11/asyncio/runners.py", line 190, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "/Users/naarang/.asdf/installs/python/3.11.3/lib/python3.11/asyncio/runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/.asdf/installs/python/3.11.3/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/main.py", line 11, in main
    await Console(team.run_stream(task="Draft an email for me to send to my boss."))
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_agentchat/ui/_console.py", line 117, in Console
    async for message in stream:
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_agentchat/teams/_group_chat/_base_group_chat.py", line 420, in run_stream
    await self._runtime.send_message(
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_core/_single_threaded_agent_runtime.py", line 328, in send_message
    return await future
           ^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_core/_single_threaded_agent_runtime.py", line 417, in _process_send
    response = await recipient_agent.on_message(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_core/_base_agent.py", line 113, in on_message
    return await self.on_message_impl(message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_agentchat/teams/_group_chat/_sequential_routed_agent.py", line 48, in on_message_impl
    return await super().on_message_impl(message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_core/_routed_agent.py", line 485, in on_message_impl
    return await h(self, message, ctx)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_core/_routed_agent.py", line 389, in wrapper
    return_value = await func(self, message, ctx)
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_agentchat/teams/_group_chat/_base_group_chat_manager.py", line 108, in handle_start
    speaker_topic_type = await speaker_topic_type_future
                         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_agentchat/teams/_group_chat/_selector_group_chat.py", line 139, in select_speaker
    response = await self._model_client.create(messages=select_speaker_messages)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/autogen_ext/models/openai/_openai_client.py", line 518, in create
    result: Union[ParsedChatCompletion[BaseModel], ChatCompletion] = await future
                                                                     ^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/openai/resources/chat/completions.py", line 1727, in create
    return await self._post(
           ^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/openai/_base_client.py", line 1849, in post
    return await self.request(cast_to, opts, stream=stream, stream_cls=stream_cls)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/openai/_base_client.py", line 1543, in request
    return await self._request(
           ^^^^^^^^^^^^^^^^^^^^
  File "/Users/naarang/projects/paisa/paisa-backend-autogen/paisa_autogen/.venv/lib/python3.11/site-packages/openai/_base_client.py", line 1644, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.BadRequestError: Error code: 400 - [{'error': {'code': 400, 'message': '* GenerateContentRequest.contents: contents is not specified\n', 'status': 'INVALID_ARGUMENT'}}]

What did you expect to happen?

Working as the other models

How can we reproduce it (as minimally and precisely as possible)?

agents.py

from autogen_agentchat.agents import AssistantAgent, UserProxyAgent
from models import model_client

user_agent = UserProxyAgent(name="user_confirmation_agent", description="You are a user confirmation agent to get confirmation from the user for the input provided by the assistant.")

assistant_agent = AssistantAgent(name="assistant_agent", system_message="You are an assistant to get the input from the user.", model_client=model_client)

models.py

from autogen_core.models import ModelFamily
from dotenv import load_dotenv
load_dotenv()
from autogen_ext.models.openai import OpenAIChatCompletionClient
import os

model_client = OpenAIChatCompletionClient(
    model="gemini-2.0-flash-exp",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/",
    api_key=os.environ.get("GEMINI_API_KEY"),
    model_info={
        "family": "unknown",
        "function_calling": True,
        "json_output": True,
        "vision": False
    }
)

main.py

from autogen_agentchat.teams import SelectorGroupChat
from agents import user_agent, assistant_agent
from models import model_client
from autogen_agentchat.conditions import TextMentionTermination
from autogen_agentchat.ui import Console
import asyncio

async def main():
    team = SelectorGroupChat([user_agent, assistant_agent], model_client=model_client, termination_condition=TextMentionTermination("STOP"))

    await Console(team.run_stream(task="Draft an email for me to send to my boss."))


if __name__ == "__main__":
    asyncio.run(main())

AutoGen version

0.4.5

Which package was this bug in

AgentChat

Model used

gemini-2.0-flash-exp, gemini-1.5-flash

Python version

3.11.3

Operating system

macOS 15.1

Any additional info you think would be helpful for fixing this bug

No response

[ekzhu]

Thanks for the issue. PR #5334

[vishal-android-freak]

Thanks for the quick fix @ekzhu I have added a small review in the PR :)

[vishal-android-freak]

Nevermind, I read the code. Looks good :)