This is a good idea but I feel like you could get something similar by just adding an instruction for the agent to summarize the context for the commit into a .context/commit/<sha> file as a git hook.
Exactly. I don't want to wade through a whole session log just to get to reasoning, and more importantly, I don't want to taint my current agent context with a bunch of old context.
Context management is still an important human skill in working with an agent, and this makes it harder.
