From d6b585a4c0cdf03705a19d3cd921478436d3f38e Mon Sep 17 00:00:00 2001 From: Matt Miller Date: Tue, 14 Jul 2026 16:53:34 -0700 Subject: [PATCH] ci(cursor-review): bump panel + judge to newest per-lab reasoning tiers OpenAI lane: gpt-5.3-codex-xhigh -> gpt-5.6-sol-max (GPT-5.6 Sol is the 5.6-family coding flagship; no 5.6 codex variant exists in Cursor's catalog). Anthropic lane + judge default: claude-opus-4-8-thinking-xhigh -> claude-opus-4-8-thinking-max. Fable 5 tops the catalog but every Fable entry is marked NO ZDR, so it is excluded from a panel that reviews private-repo diffs. Gemini and Kimi lanes unchanged (still the single top tier per lab). README and judge-prompt examples synced. Both new IDs validated with live cursor-agent calls; actionlint clean. --- .github/cursor-review/README.md | 6 +++--- .github/cursor-review/prompt-judge.md | 2 +- .github/workflows/cursor-review.yml | 16 ++++++++++------ 3 files changed, 14 insertions(+), 10 deletions(-) diff --git a/.github/cursor-review/README.md b/.github/cursor-review/README.md index 15e8922..7ee26ae 100644 --- a/.github/cursor-review/README.md +++ b/.github/cursor-review/README.md @@ -56,8 +56,8 @@ skipped if no Slack token is configured). | Lab | Model (Cursor catalog) | |---|---| -| OpenAI | `gpt-5.3-codex-xhigh` | -| Anthropic | `claude-opus-4-8-thinking-xhigh` | +| OpenAI | `gpt-5.6-sol-max` | +| Anthropic | `claude-opus-4-8-thinking-max` | | Google | `gemini-3.1-pro` | | Moonshot | `kimi-k2.7-code` | @@ -190,7 +190,7 @@ descriptions live in the [workflow header](../workflows/cursor-review.yml). | Input | Default | What it does | |---|---|---| -| `judge_model` | `claude-opus-4-8-thinking-xhigh` | Model that consolidates panel findings. | +| `judge_model` | `claude-opus-4-8-thinking-max` | Model that consolidates panel findings. | | `diff_size_cap` | `5000` | Max changed lines (after excludes); larger PRs are skipped. | | `review_label` | `cursor-review` | Label whose addition triggers the review. | | `diff_excludes` | lockfiles, `node_modules`, `dist`, `vendor`, minified/generated files | Pathspecs excluded from both the size count and the reviewed diff. | diff --git a/.github/cursor-review/prompt-judge.md b/.github/cursor-review/prompt-judge.md index 7af5d28..d331b73 100644 --- a/.github/cursor-review/prompt-judge.md +++ b/.github/cursor-review/prompt-judge.md @@ -50,7 +50,7 @@ object with exactly: - "body": string — concise (1-3 sentences). Do NOT prefix the body with a severity word or emoji; the severity field drives the rendered badge. END with attribution like - `_Raised by 3 of 8 reviewers (gpt-5.3-codex-xhigh adversarial, claude-opus-4-8-thinking-xhigh edge-case, gemini-3.1-pro adversarial)._` + `_Raised by 3 of 8 reviewers (gpt-5.6-sol-max adversarial, claude-opus-4-8-thinking-max edge-case, gemini-3.1-pro adversarial)._` Order the array most-severe first. If no findings rise to the bar, return []. diff --git a/.github/workflows/cursor-review.yml b/.github/workflows/cursor-review.yml index 2652047..b455dbb 100644 --- a/.github/workflows/cursor-review.yml +++ b/.github/workflows/cursor-review.yml @@ -58,7 +58,7 @@ on: the panel. type: string required: false - default: claude-opus-4-8-thinking-xhigh + default: claude-opus-4-8-thinking-max diff_size_cap: description: >- Max changed lines (added + removed, after diff_excludes). PRs over @@ -296,12 +296,16 @@ jobs: strategy: fail-fast: false matrix: - # Pinned to the highest reasoning tier available for each lab. Gemini - # and Kimi only ship a single tier in Cursor's catalog; OpenAI Codex - # and Claude expose xhigh variants we use here. + # Pinned to each lab's newest highest-reasoning tier in Cursor's + # catalog (last checked 2026-07-14). OpenAI: GPT-5.6 Sol is the + # 5.6-family coding flagship (no 5.6 codex variant exists). Anthropic: + # Fable 5 tops the catalog but all Fable entries are marked NO ZDR in + # Cursor, and this panel reviews private-repo diffs, so it is excluded; + # Opus 4.8 thinking at its max tier is the top ZDR-eligible pick. + # Gemini (Pro line) and Kimi still ship a single reasoning tier each. model: - - gpt-5.3-codex-xhigh - - claude-opus-4-8-thinking-xhigh + - gpt-5.6-sol-max + - claude-opus-4-8-thinking-max - gemini-3.1-pro - kimi-k2.7-code review_type: [adversarial, edge-case]