[MagenticOneGroupChat] MagenticOneGroupChat takes too long to start

[smalltalkman]

What happened?

Describe the bug
MagenticOneGroupChat takes about a minute to start.

To Reproduce
Modify the code here:

            import time
            start_time = time.perf_counter()
            await self._runtime.send_message(
                GroupChatStart(messages=messages, output_task_messages=output_task_messages),
                recipient=AgentId(type=self._group_chat_manager_topic_type, key=self._team_id),
                cancellation_token=cancellation_token,
            )
            end_time = time.perf_counter()
            print(f"time：{end_time - start_time:.6f} s")

Run:

import asyncio
from autogen_ext.models.openai import OpenAIChatCompletionClient
from autogen_agentchat.agents import AssistantAgent
from autogen_agentchat.teams import MagenticOneGroupChat
from autogen_agentchat.ui import Console


async def main() -> None:
    model_client = OpenAIChatCompletionClient(
            model="deepseek-chat",
            base_url="https://api.deepseek.com/v1",
          # api_key="your_api_key",
            model_capabilities={
                "vision": False,
                "function_calling": True,
                "json_output": True,
            },
        )

    assistant = AssistantAgent(
        "Assistant",
        model_client=model_client,
    )
    team = MagenticOneGroupChat([assistant], model_client=model_client)
    await Console(team.run_stream(task="Provide a different proof to Fermat last theorem"))


asyncio.run(main())

The output includes:

time：76.192850 s

Expected behavior
shorten the startup time of MagenticOneGroupChat.

Which packages was the bug in?

Python AgentChat (autogen-agentchat>=0.4.0)

AutoGen library version.

Python 0.7.2

Other library version.

No response

Model used

deepseek-chat

Model provider

None

Other model provider

No response

Python version

3.10

.NET version

None

Operating system

Ubuntu

[zrquan]

This is not a bug. The start of MagenticOneGroupChat requires at least three conversations with LLM. So it is normal for it to take a long time.