Streamlit issue AutoGen 0.4 Code Executor

[sridharratna]

I am trying to run the console based program to run inside streamlit. but getting the error as below.. which works fine when removed streamlit wrapper. Replacing MagenticOneGroupChat with RoundRobinGroupChat also have the same.
What am I missing here? I am new to python

attached the error image

`from pathlib import Path
from autogen_agentchat.agents import AssistantAgent, CodeExecutorAgent
from autogen_agentchat.conditions import MaxMessageTermination, TextMentionTermination
from autogen_agentchat.ui import Console
from autogen_agentchat.teams import MagenticOneGroupChat
from autogen_agentchat.teams import RoundRobinGroupChat
from autogen_ext.code_executors.local import LocalCommandLineCodeExecutor
from autogen_ext.models.openai import OpenAIChatCompletionClient
import asyncio
import venv
import streamlit as st

model_client = OpenAIChatCompletionClient(model="llama-3.3-70b-versatile",
base_url="https://api.groq.com/openai/v1",
api_key="xxxxxxxxxxxxxxxxxxxxxxx",
model_info={
"vision": False,
"function_calling": True,
"json_output": True
})

async def main():
st.set_page_config(page_title="CodeAgent", page_icon=":robot:")
st.title("CodeAgent 🤖")
st.write("An AI agent that can read and write code to solve programming problems.")
work_dir = Path("coding")
work_dir.mkdir(exist_ok=True)

ststem_message =  """You are a helpful AI assistant.
    Solve tasks using your coding and language skills.
    In the following cases, suggest python code (in a python coding block) or shell script (in a sh coding block) for the user to execute.
    1. When you need to collect info, use the code to output the info you need, for example, browse or search the web, download/read a file, print the content of a webpage or a file, get the current date/time, check the operating system. After sufficient info is printed and the task is ready to be solved based on your language skill, you can solve the task by yourself.
    2. When you need to perform some task with code, use the code to perform the task and output the result. Finish the task smartly.
    Solve the task step by step if you need to. If a plan is not provided, explain your plan first. Be clear which step uses code, and which step uses your language skill.
    When using code, you must indicate the script type in the code block. The user cannot provide any other feedback or perform any other action beyond executing the code you suggest. The user can't modify your code. So do not suggest incomplete code which requires users to modify. Don't use a code block if it's not intended to be executed by the user.
    If you want the user to save the code in a file before executing it, put # filename: <filename> inside the code block as the first line. Don't include multiple code blocks in one response. Do not ask users to copy and paste the result. Instead, use 'print' function for the output when relevant. Check the execution result returned by the user.
    If the result indicates there is an error, fix the error and output the code again. Suggest the full code instead of partial code or code changes. If the error can't be fixed or if the task is not solved even after the code is executed successfully, analyze the problem, revisit your assumption, collect additional info you need, and think of a different approach to try.
    When you find an answer, verify the answer carefully. Include verifiable evidence in your response if possible. Reply 'TERMINATE' in the end when everything is done.
    """

assistant = AssistantAgent(
    name="assistant",
    model_client=model_client,
    system_message=ststem_message,        
)

venv_dir = work_dir / ".venv"
venv_builder = venv.EnvBuilder(with_pip=True)
venv_builder.create(venv_dir)
venv_context = venv_builder.ensure_directories(venv_dir)

code_executor = CodeExecutorAgent(
    name="code_executor",
    code_executor=LocalCommandLineCodeExecutor(virtual_env_context=venv_context, work_dir=work_dir),
)

# The termination condition is a combination of text termination and max message termination, either of which will cause the chat to terminate.
termination = TextMentionTermination("TERMINATE") | MaxMessageTermination(10)
group_chat = MagenticOneGroupChat([assistant, code_executor], termination_condition=termination, model_client=model_client)

task_message="Today is 21-jan-2025. Write Python code get the infosys stock performance in past 6 months. plot daily candlestick chart similar to tradingview platform along with 100,200 EMA and save it to a file names 'infy-999.png'. "
# Extract the generated code
result = await Console(group_chat.run_stream(task=task_message))

if name == "main":
asyncio.run(main())`

[ekzhu]

Your platform and Python version? Looks like a streamlit issue to me. Not familiar with it, but could be that streamlit may be using an asyncio event loop that doesn't work well with asyncio.create_subprocess_exec

[sridharratna]

Windows 11 platform with python 3.12

[ekzhu]

@peterychang any opinion on this?