Repository navigation
Honor Claude Code terminal error flags - #189
Draft
Qian-Cheng-nju wants to merge 1 commit into
Draft
Qian-Cheng-nju wants to merge 1 commit into
Qian-Cheng-nju wants to merge 1 commit into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Claude Code can end a quota-blocked background turn with
subtype: successandis_error: true. The classifier ignored the error flag and reportedOK, allowing an interrupted attempt to be treated as a normal model outcome. Honor the final result's error flag so the existing evaluator recordsINFRA_ERRORand excludes it from genuine outcomes.Preserve
error_max_turns, runner timeout precedence, and recovery followed by a later successful result. This changes classification only; it does not add quota polling or automatic recovery.Validation: 1,532 evaluator tests passed; Ruff lint, formatting, and diff checks passed. Three new regression cases fail on the base revision. Replaying 15 completed experiment streams changes only the observed quota-blocked case; the other 14 retain their classification. Original experiment artifacts remain unchanged.