* feat: run the cli ai evals on codex and deepseek
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci: pick cli eval models from the harness and install codex
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: stop counting wmill in a file name as a cli eval mutation
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: harden the codex and deepseek cli eval runtimes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: keep codex tool order and keep other keys from deepseek
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
