I would assume it's the harness sending the model a notification toward the end. At least Claude Code is designed to attach reminders with tool call output as a way for the harness itself to steer the model slightly.
Relatively sure it's not. I'm using pi and I can't find any place it's doing any such thing. My current theory is that it's behavior trained into the model either accidentally or intentionally, probably during post-training in some harness that _does_ give hints of that sort?
