Our approach is to save LLM conversations but to not have them be part of the context.
have they though? I feel like 50% of the chat history is gettin in the way of the model that just created it half the time, let alone any future LLM.
Humans wont re-read an old chat history either unless very desperate for clues.
The few valuable nuggets of information in the chat history can probably be summarize into 3 bullet points and put in the docs or in code comments.
I really dont see the value.
Much of the knowledge of writing the software is manifest and captured in those chats. and we share them so that we can learn from each other.
I work in data and machine learning, it's pretty common to attach artifacts like charts, images, data outputs to a PR for me, but not include them in the codebase.
I'd only want to do that if it was going to be useful at some future point - do you go back to chats / transcripts etc months after a PR is merged to understand its design? (that sounds rhetorical, but I promise it's a genuine question!)
Why don't your chatbots just write clear, well documented code?