How do you break AI agents out of endless fix-and-break debugging loops?

We’ve all been there: an agent makes a mistake, you paste the error, it "fixes" it, introduces a new error, and 5 turns later it reintroduces the original bug you started with. It gets trapped in a cycle of surface-level trial and error instead of stepping back to analyze the root cause.

It feels like the model loses critical reasoning capacity once the context turns into a wall of error logs.

What’s your hard rule for stopping an agent mid loop? Do you wipe the chat context drop to a lower tier model, or force a specific step-by-step diagnostic prompt?