fix(gsd): Make task completion robust to malformed evidence JSON#3469
Closed
aryanjsingh wants to merge 1 commit intogsd-build:mainfrom
Closed
fix(gsd): Make task completion robust to malformed evidence JSON#3469aryanjsingh wants to merge 1 commit intogsd-build:mainfrom
aryanjsingh wants to merge 1 commit intogsd-build:mainfrom
Conversation
Contributor
🟢 PR Risk Report — LOW
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes a crash in the gsd_task_complete tool when smaller models generate malformed numeric values in verificationEvidence. The schema for exitCode and durationMs is updated to accept strings, and the handler now coerces these values to numbers, preventing parsing errors and improving reliability.
Changes
VerificationEvidenceSchemato allowexitCodeanddurationMsto be either a number or a string. This prevents schema validation failures when the language model provides a numeric value as a string (e.g.,"0"instead of0) or syntactically invalid JSON like a bare minus sign.handleCompleteTaskto normalizeexitCodeanddurationMsto numbers. This handles cases where the model provides a string or a malformed value (like a bare-), ensuring data consistency before it's used or stored in the database.Related Issue
Closes #3464