mirror of
https://github.com/openai/codex.git
synced 2026-11-05 20:10:33 +00:00
## What changed Introduce `GuardianReviewResponse` to retain both the parsed assessment and the original response text. Reuse the stored result for authorization checks, denial reconsideration, review record capture, and final assessment extraction instead of reparsing the response. Preserve raw text for review records and keep invalid responses as completed turns so history and session reuse remain unchanged. ## Testing Extend review record coverage to wrapped denials and invalid responses, and verify that invalid assessments remain retryable while missing assessments do not. GitOrigin-RevId: 50c19e788a8d57f951c6140d66306b3538515adc