Repository navigation
Record a failed Bug-origin session instead of ending Scoring - #1332
Merged
Merged
Conversation
The first Scoring run backfills every closed bug, one session each. One failed session ended the whole run with no window, and the staged packets holding its artifacts were deleted, so the cause was lost and a retry repeated every session. A session that fails, times out or leaves no proposal now records that bug with no commit and says why; the window keeps the other proposals and publishes the failed session's artifacts. Plan-limit stops, interrupts and tampered proposals still advance no window. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LSAzXiA6BD9neiPgVQRMKD
JacobStephens2
added
the
test:macos
Merged
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The first Scoring run on the
thirdshifthost (#1032) failed after 13 minutes withBug-origin session failed: Bug-origin proposal session failed; see private Grader artifacts, and no window was saved.Why:
JacobStephens2that's 113 bugs, each getting a session of up to 5 minutes.packets/origins/<n>/with the failed session'sstderrandstdout.jsonl, so the "private Grader artifacts" the error pointed to no longer existed.Change:
--corrector--none.docs/guide.md, the generatedsite/docs/andsite/architecture/say so.Tests:
tests/bug_origins.rshas a new test,a_failed_session_records_no_commit_keeps_its_artifacts_and_the_window_advances. It failed before this change (exit 1, no window) and passes now. All Bug-origin tests pass.🤖 Generated with Claude Code
https://claude.ai/code/session_01LSAzXiA6BD9neiPgVQRMKD