# Recover a failed run 1. Read `pipelines inspect ID --json`, the failed stage's actual input/result, retained tool evidence, artifacts and Git diff. A timeout is not proof of lost work. 2. Separate code failure, environment/setup failure and result-format failure. Missing evidence is not a passing check; a failed result does not erase edits. 3. Fix the specific cause directly or continue the original pipeline from the necessary stage. Preserve completed work and original history. Do not create another pipeline simply to merge a prepared commit. 4. Verify the repair with a focused regression; run broader checks once relevant inputs settle. Do not raise retry/time budgets to hide a reproducible defect. Use `pipelines help retry` to discover the installed options. When supported, select a recorded stage/visit, bounded input correction and explicit compatible version of the same pipeline. Verify actual retained stage input, not merely successful admission. Do not silently restart from entry. A clean preparation stage succeeds without an empty commit. A committer with a delivery gate succeeds with a clean checked candidate; the server lands afterward. Read-only, nonvisual work does not require device screenshots. Visual acceptance requires a ready fixture, verified connection and actual captured interactions. Preserve exclusive fixture ownership; inspect tool/process termination before reuse. Stop and await exact owned fixture processes, not just a go-run parent. Do not disrupt another active fixture or restart a shared service over running work. Report the exact blocker and next action briefly. Keep independent work moving.