Leonardo Pinheiro

@ekzhu @jackgerrits , this is a very early draft, I have some questions before proceeding further. 1. What to do w.r.t. model client? The chat completion client abstraction doesn't seem...

@ekzhu , this is ready for review. I tested it with the script below. I haven't added unit tests as mocking the assistants api will take a lot of effort...

@asheeshgarg @natemellendorf , can you post the full error trace you currently have? Currently I'm unable to reproduce due to an issue with cross-inference endpoints in SK: https://github.com/microsoft/semantic-kernel/issues/10738

> Chatted with @victordibia API is nice and clean and I agree with its usefulness. > > It would be useful to have following somewhere in the repo but not...

> Excellent conversation .. thanks [@abhinav-aegis](https://github.com/abhinav-aegis) , [@EItanya](https://github.com/EItanya) . > > FWIW, I think the implementations above are in line with some minimal experiments I have tried - e.g., simply...

> Agree that communication based on edges makes sense. I think this is what [@ekzhu](https://github.com/ekzhu) and [@victordibia](https://github.com/victordibia) are mentioning as well. Looks like it should be feasible where the correct...

@EItanya , what I recall is that the chat agent container broadcasts to a single topic and the behavior is currently hardcoded so every participant will see all messages, I...

I will try to have a look soon.

@ekzhu , can you have a look and tag the relevant people for feedback?

> Thanks for the draft PR! It presents a good starting point. For `create_stream` the caller will be consume the output as an async generator. By wrapping the `create_stream` method,...