feat: add Streamlit team example with stop-and-resume pattern

[lawcontinue]

Addresses #5626

Summary

Adds a Streamlit example demonstrating the stop-and-resume pattern for interactive multi-agent teams.

Why Not UserProxyAgent?

Issue #5626 asks for a Team(AssistantAgent + UserProxyAgent) in Streamlit. The challenge is that UserProxyAgent.input_func blocks the event loop waiting for human input, but Streamlit reruns the entire script on each interaction — making blocking calls unreliable.

The official UserProxyAgent docstring recommends:

"For typical use cases that involve slow human responses, it is recommended to use termination conditions such as HandoffTermination or SourceMatchTermination to stop the running team and return the control to the application. You can run the team again with the user input."

This example follows that guidance: MaxMessageTermination(max_messages=1) stops after the assistant responds, then Streamlit collects user input and resumes the team. The team state persists in st.session_state so the conversation continues naturally.

For frameworks with native async support (ChainLit, FastAPI), see the ChainLit example which uses UserProxyAgent directly.

Files Added

• python/samples/agentchat_streamlit_team/app.py — Streamlit app with chat UI
• python/samples/agentchat_streamlit_team/model_config.yaml — Model configuration template
• python/samples/agentchat_streamlit_team/requirements.txt — Dependencies
• python/samples/agentchat_streamlit_team/README.md — Usage instructions

Related

• Provide a Streamlit example of a Team composed by one Assistant Agent and one User Proxy Agent #5626
• ChainLit example — alternative using UserProxyAgent with native async support
• Human-in-the-loop tutorial