mirror of
https://github.com/openai/codex.git
synced 2026-08-23 13:09:46 +00:00
## Why MultiAgent V2 workers can be reviewed after the root conversation has received new user authorization that is absent from the worker's own transcript. Guardian reviews need that genuine user context without treating forwarded or assistant-authored claims as authorization. ## What changed - Add the bounded root conversation to Guardian prompts for worker reviews. - Preserve user and assistant roles, and explicitly treat only root user messages as authorization evidence. - Exclude summaries, review artifacts, and assistant commentary from the root conversation evidence. - Apply the same evidence to both core Guardian prompts and Guardian V2 classification. ## Testing Add an integration test covering late root-user authorization, forged role text, forwarded agent claims, and filtered synthetic authorization. GitOrigin-RevId: 8846de69ba214a88f58f70675798d324e213427c