The fix loop gives up after three rounds, so an unattended run fails overnight while it is still making progress: keep going by default, with a limit in Settings #178
Loading…
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
From the user, 2026-10-16: run 66 ended
failedwith "the fix loop stopped (cap): the judge found 1 problem … after 2 fix rounds", and run 67 is heading the same way.Today
osf.pipeline.fixloop.ROUNDS = 3: a check, then up to two fix rounds.script.run-tests,.r2,.r3, withagent.judge[.rN]andagent.fix[.rN].state()returnsstop/cap, andscript.confirm-checks-passedfails the run.no_progress(a round failed exactly as the one before it) andci(the project's CI could not finish).Wanted
Questions for the design
no_progresswhen there is no limit. Stopping on "the same failure as last time" is still the right guard against an all-night loop that changes nothing. Or should it change approach, such as a fresh session, before it stops?Shipped in
35c556b(changefix-loop-keeps-going, commitb3802d2), live since 00:34Z on 2026-10-17, and archived after the verification run (run_01M53R7621CJW6PCZG7S6R94HS, thorough on cmoriarty/braid-combined-test, vLLM, succeeded and merged at 03:49Z).agent.fix.r<n-1>,script.run-tests.r<n>andagent.judge.r<n>, copies of the last round renumbered. After a restart they are read back from the step rows, and the closing check waits while the loop makes one..osf/fix/limit.json= no limit) and passed in round 2. No extra round or gate was needed there yet.Closing.