Hey guys, I’ve been testing a failure mode in agent authorization that I’m not sure is getting enough attention. We usually model the flow as: agent proposes → human approves → tool executes But I think there are actually three separate questions: What action was shown to the human? What action did the human approve (including any edits)? What exact action actually reached the executor? A system can have a perfectly good HITL flow and still have a gap between #2 and #3 if the exec...