Claude final-message extractor returns the first result event, not the terminal one#488
Open
clkao wants to merge 1 commit into
Open
Claude final-message extractor returns the first result event, not the terminal one#488clkao wants to merge 1 commit into
clkao wants to merge 1 commit into
Conversation
…not the first The extractor returned on the first non-error success result event instead of scanning to the terminal one, contradicting its own doc comment. A transcript with an early status-update result and a later actual-final result silently returned the wrong text to scenario assertions. Now retains the last non-error success result while keeping is_error/401 short-circuit failure unmaskable by any preceding success.
4 tasks
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Claude live-CI oracle returned a transcript's first success result instead of the last, making shared-scenario assertions flake independent of actual FO behavior.
What changed
is_error/401 launch-failure detection unchanged and unmaskable in either directionEvidence
TestExtractClaudeFinalMessage: 7/7 passed6h