mirror of
https://github.com/openai/codex.git
synced 2026-10-23 18:08:45 +00:00
## What changed - Replace structured numeric classifier output with a single `high` or `low` token and map those classifications to `1.0` and `0.0` risk scores. - Require the classification contract in both default and overridden prompts, including when classifier instructions are truncated. - Return the first streamed classification immediately while draining the remaining response for connection reuse and token accounting. ## Testing - Cover prompt rendering and truncation, classification parsing, early streamed results, conflicting later output, WebSocket reuse, and approval routing. GitOrigin-RevId: 31a57e4eb9bf8df2a161b84aa3d5b16ab8f2937b