mirror of
https://github.com/openai/codex.git
synced 2026-11-05 20:10:33 +00:00
## What changed - Evaluate recent unknown-authorization or critical-risk actions over the last five actions instead of ten. - Flag predicted high- or critical-risk actions when they are credibly expected within the next two actions, rather than treating any potential risk within ten actions as high. - Remove privileged or broad access as a standalone high-risk condition and classify a trajectory as low when none of the explicit high-risk conditions apply. - Clarify the user-authorization and reviewer terminology in the classifier instructions. GitOrigin-RevId: 1eaf63c3327f57a9c8560df085e1fe0afad99cd4