Repository navigation
Detect unfinished Claude Code background turns - #188
Merged
Merged
Conversation
Qian-Cheng-nju
marked this pull request as ready for review
October 9, 2026 05:56
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
An early successful Claude Code result can be followed by background activity that is cut off, including an OOM exit. The classifier currently reuses that earlier result and reports
OK. Require a result after the last conversation activity and reject malformed event streams so unfinished follow-up turns are classified asINFRA_ERROR.Completed result sequences,
error_max_turns, runner timeout precedence, and trailing rate-limit telemetry retain their existing behavior. This independently fixes the termination issue found while reviewing #186; it can merge before or after that PR.Validation: 1,446 evaluator tests passed; Ruff lint, format, and diff checks passed. Twelve new regression cases fail on the base revision. Compatibility checks with #186 distinguish completed and truncated background sequences, and all ten stored experiment-stream snapshots retain their previous termination classification.