Comment by whh
10 days ago
I'm trying it out now. If it works, I think it'd be great for my agentic workflows where I need to figure out why something was done a specific way.
I have a lot of concurrent agents working on things at the same time, so I'm not always sure why a piece of code is the way it is months later.
I've used it for a couple of hours. A few observations:
- It's nice to see conversation context alongside the change itself. - I wasn't able to see Claude Code utilise past commit context in understanding code. - It's a tad unclear (and possible unreliable) in what is called 'checkpointing'. - It mucked up my commit messages by replacing the first line with a sort of AI request title or similar.
Sadly, because of the last point (we use semantic release and git-cz) I've had to uninstall it.
This sounds like you're using the auto-commit strategy instead of the default manual-commit strategy. manual-commit does not automatically commit. It just adds a trailer to the git commit message to link the checkpoint to the commit.