I’m pretty new to using AutoGen so I don’t know for sure if this is a simple problem to fix but I created two simple agents with the user_proxy to communicate with each other through the “GroupChat” function. However, after the first response from the first agent, it leads to an error code 400 from openai. The following below is the exact error code and I don’t really know what the issue is.

openai.BadRequestError: Error code: 400 – {‘error’: {‘message’: “Invalid ‘messages[2].name’: string does not match pattern. Expected a string that matches the pattern ‘^[a-zA-Z0-9_-]+$’.”, ‘type’: ‘invalid_request_error’, ‘param’: ‘messages[2].name’, ‘code’: ‘invalid_value’}}

I’ve been following the tutorials on the AutoGen Github repo and I don’t think I’ve seen anyone really run into this problem.

At first I thought it was just an issue between using different LLMs so I decided to keep it to one LLM (GPT-4) and the issue is still recurring. Any insight?