Interesting experiment. Scheduling decisions feel like the place where unpredictability shows up first. Curious how you reason about rollback when the scheduler makes a bad call.

Great point. In a real kernel, non determinism is a bug. Here, it's a feature (or at least, a known hazard). To answer your question: There is no Ctrl+Z for SIGKILL. Once the LLM decides to kill a process, it's gone. My reasoning for 'rollback' is actually latency. I built in a 'Roasting Phase' where the agent mocks the process for a few seconds before executing the kill. That delay acts as an optimistic lock it gives me a window to veto the decision if I see it targeting something critical.

If I'm AFK and it kills my IDE? I treat that as the system telling me to touch grass.