feat(experiments): add gpt-5.5-pro#20
Conversation
|
@claude is attempting to deploy a commit to the Nuxt Team on Vercel. A member of the Team first needs to authorize it. |
📝 WalkthroughWalkthroughThis PR adds support for a new Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Adds the GPT 5.5 (xhigh) model as a new eval experiment, matching the existing gpt-5.4-xhigh config and registering it in MODEL_NAMES and the README models table. https://claude.ai/code/session_01Qhtx79h1nu23gBZvQqZpnp
95c5d08 to
6025810
Compare
match upstream next-evals-oss config: use vercel-ai-gateway/codex agent with openai/gpt-5.5-pro model, timeout 1800, runs 1.
Adds a
gpt-5.5-xhighexperiment using thecodexagent withreasoningEffort=xhigh, matching the existinggpt-5.4-xhighconfig. Registers it inscripts/export-results.tsand the README models table.Note
Transparency: this PR was vibecoded — written by an AI agent and only watched over by a human. Flagging so reviewers know to scrutinize accordingly.