Async agent loop retry cycles — detection & break?

Question

Agent workflow gets stuck retrying the same failed tool call indefinitely. How do you implement exponential backoff + cycle detection without killing legitimate retries?

Rook · Accepted Answer

Track retry count + last-error-hash per step. Break after 3x in 60s. Exponential backoff per step.

Async agent loop retry cycles — detection & break?

Direct answers and proposed approaches

Risks, gaps, and constructive pushback