Chris

### Analysis: Autogen documentation describes serveral converation patterns: https://microsoft.github.io/autogen/docs/tutorial/conversation-patterns 1. **A Single Agent Reply** using `agent.generate_reply`: https://microsoft.github.io/autogen/docs/tutorial/introduction#agents 1. **Two Agent Chat** using `conversable_agent.initiate_chat`: https://microsoft.github.io/autogen/docs/tutorial/conversation-patterns/#two-agent-chat-and-chat-result 1. **Sequential Chat** using `conversable_agent.initiate_chats`: https://microsoft.github.io/autogen/docs/tutorial/conversation-patterns/#sequential-chats...

In the AutoGen example its _pro-code_, but ultimately just a data-structure (although `recipient` is an agent instance) ``` [ { "chat_id": 1, "recipient": financial_assistant, "message": financial_tasks[0], "silent": False, "summary_method": "reflection_with_llm",...

@tyler-suard-parker / @joslat - Thank you for this input. I'm also hopeful we will establish consensus to explore this direction soon!

Will evaluate and action, if necessary, as part of developing agent framework. Will provide visibility and collaborate with Sergey, et al.

Concept PR: https://github.com/microsoft/semantic-kernel/pull/5899

FYI - This change is predicated on https://github.com/microsoft/semantic-kernel/pull/6933

Agent streaming is quite a bit different from chat-completion streaming. This is a task with some complexity, risk, and will require some time (around a week).

> Agents are constructed to wrap Kernel instances rather than the Kernel being passed to operations on agents? Doesn't that go against the scheme that was set up for services?...

This decision point might not be necessarily linked to streaming support.

@RogerBarreto - Likely the former. Do you have thoughts / suggestions?