Limit the maximum number of tokens in an entire conversation

[ArturDev42]

Thanks a lot for this cool framework! From the docs, I understand that it is possible to set the maximum number of tokens that can be generated in a single response when making API calls to models. I need to limit the tokens used across an entire interaction between user proxy and assisant, i.e. multiple messages and responses. I am using user_proxy.initiate_chat(assistant, message=message, max_turns=max_turns). Once the pre-defined token limit has been reached, the conversation should be terminated. Is this possible? Thanks!