Tianqi Xu

> By the way, my recent commits were focused on formatting and adding comments to improve code readability and maintainability. Yeah. It makes sense not to leave every single detail...

An important modification will be support multimodal in `BaseMessage`, which is our primary data exchange format. It may require lots of code changing to refactor it.

> @dandansamax IMO it depends on how we want to store the images. If we just store the images with base64 encoded format (which is also in string format), then...

I think it is a very good solution. Just a little bit uncomfortable to use `ModelType.value` to represent "model name" for OpenAI models, while using it to represent "model path"...

Hi everyone @lightaime @camel-ai/camel-intern-team This issue becomes urgent since features like memory, storage, agent, function call, etc. are introduced. Also it will be important for our discord-frontend. Let me know...

Thank you for your feedback! BTW, #400 changes the default code interpreter to subprocess interpreter. It can be a work around. Could you please check that?

Do we really need the real output of LLM? As I checking several famous agent projects, all of them just use mock outputs. A possible reson is most of tests...

#243 How about adding this?

Hi, @lightaime! This is a fascinating feature. Are you currently working on this issue? I would love to hear your thoughts on how we could implement it. I'm particularly interested...