ci: bump cursor-review panel and judge to Opus 4.8

[mattmillerai]

Summary

Bumps the cursor-review panel's Anthropic leg and the judge from Opus 4.7 to Opus 4.8.

Changes

• judge_model default: claude-opus-4-7-thinking-xhigh → claude-opus-4-8-thinking-xhigh (the judge is the final arbiter that reads files and adjudicates, so it gets the strongest tier).
• Panel Anthropic leg in the review matrix: same 4.7 → 4.8 bump. Panel diversity comes from running four labs, not from the Opus point version, so there's no coverage reason to hold it back.
• Docs (.github/cursor-review/README.md) and the judge prompt example (prompt-judge.md) updated to match.

Model ID verified against Cursor's catalog (agent --list-models): claude-opus-4-8-thinking-xhigh = "Opus 4.8 1M Extra High Thinking", the direct equivalent of the prior 4.7 ID.

Review Focus

Both roles move to 4.8. A split (4.8 judge + 4.7 panel leg) was considered for mild version-diversity between judge and the Anthropic reviewer, but with three other labs in the panel and a file-reading judge, the benefit is marginal — not worth carrying a stale model ID.

[coderabbitai]

Warning

Review limit reached

@mattmillerai, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 1 minute and 59 seconds. Learn how PR review limits work.

Your organization has used up its prepaid credits, and credit purchases are no longer available. Enable the review add-on in the billing tab to keep reviews running — you're only billed for reviews past your plan's rate limits ($0.25/file).

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

We recommend that you space out your commits to avoid hitting the rate limit.

🚦 How do rate limits work?

CodeRabbit enforces hourly rate limits for each developer per organization.

Our paid plans include higher PR review limits than trial, open-source, and free plans. In all cases, reviews become available again over time. During sustained high-volume PR review activity, CodeRabbit may temporarily slow when the next review becomes available.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: fe229aed-58b4-4ebe-a2c4-0248d6afcb4a

📥 Commits

Reviewing files that changed from the base of the PR and between 41d1201 and 9f33c5e.

📒 Files selected for processing (3)

• .github/cursor-review/README.md
• .github/cursor-review/prompt-judge.md
• .github/workflows/cursor-review.yml

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch chore/cursor-review-opus-4-8

✨ Simplify code

• Create PR with simplified code
• Commit simplified code in branch chore/cursor-review-opus-4-8

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}