From 6b62227b057e131521852098523c9dc4e9b4f244 Mon Sep 17 00:00:00 2001 From: garrytan Date: Wed, 28 Oct 2026 00:30:17 +0000 Subject: [PATCH] fix(review): 400-word findings cap fits the /review size pins (five host pins lowered by 2); CHANGELOG max_rounds wording Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- CHANGELOG.md | 2 +- review/sections/review-army.md | 2 +- scripts/resolvers/review-army.ts | 2 +- ship/sections/review-army.md | 2 +- test/fixtures/skill-md-size-allowlist.json | 10 +++++----- 5 files changed, 9 insertions(+), 9 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9456d2b6b..f728f7076 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -19,7 +19,7 @@ ### Gate integrity - Ship union cap 1.7529 → 1.7631 and ship skeleton cap 60,913 → 60,960 bytes in `test/helpers/carve-guards.ts`, each pinned at the measured size (330,941 / 187,706 = 1.76308; 60,960 bytes). GSTA-132's size ledger replaces these re-pins once it lands. -- `test/autoplan-token-efficiency.test.ts` gives its subprocess-driven cases a 30-second timeout; the resumed `max_rounds` case in that file now expects the new default of 1. +- `test/autoplan-token-efficiency.test.ts` gives its subprocess-driven cases a 30-second timeout; its resumed-run case persists `max_rounds: 1` instead of 3, a value inside the new cap of 2. ## [1.91.284.0] - 2026-10-27 diff --git a/review/sections/review-army.md b/review/sections/review-army.md index 0211058bd..fa3d1de5b 100644 --- a/review/sections/review-army.md +++ b/review/sections/review-army.md @@ -101,7 +101,7 @@ Every other specialist, including Testing, reads the full diff with fixtures. "You are a specialist code reviewer. Read the checklist at {checklist path}, then run `DIFF_BASE=$(git merge-base origin/ HEAD) && git diff "$DIFF_BASE"` to get the full diff. Apply the checklist against the diff. -`NO FINDINGS` alone is the expected, complete result for a clean diff; never invent an item to show work. Otherwise output one JSON object per finding, on its own line, at most 400 words of findings in all: +`NO FINDINGS` alone is the expected, complete result for a clean diff; never invent an item. Otherwise output one JSON object per finding per line, 400 words at most: {\"severity\":\"CRITICAL|INFORMATIONAL\",\"confidence\":N,\"path\":\"file\",\"line\":N,\"category\":\"category\",\"summary\":\"description\",\"fix\":\"recommended fix\",\"fingerprint\":\"path:line:category\",\"specialist\":\"name\"} Required fields: severity, confidence, path, category, summary, specialist. diff --git a/scripts/resolvers/review-army.ts b/scripts/resolvers/review-army.ts index fe40ab069..1c174ac94 100644 --- a/scripts/resolvers/review-army.ts +++ b/scripts/resolvers/review-army.ts @@ -141,7 +141,7 @@ Every other specialist, including Testing, reads the full diff with fixtures. "You are a specialist code reviewer. Read the checklist at {checklist path}, then run \`${diffBase(ctx)} && git diff "$DIFF_BASE"\` to get the ${ctx.skillName === 'ship' ? 'diff (``: write the sha in before dispatch, the merge base on pass 1 and `RANGE_BASE` from pass 2 on; never a shell variable)' : 'full diff'}. Apply the checklist against the diff. -\`NO FINDINGS\` alone is the expected, complete result for a clean diff; never invent an item to show work. Otherwise output one JSON object per finding, on its own line, at most 400 words of findings in all: +\`NO FINDINGS\` alone is the expected, complete result for a clean diff; never invent an item. Otherwise output one JSON object per finding per line, 400 words at most: {\\"severity\\":\\"CRITICAL|INFORMATIONAL\\",\\"confidence\\":N,\\"path\\":\\"file\\",\\"line\\":N,\\"category\\":\\"category\\",\\"summary\\":\\"description\\",\\"fix\\":\\"recommended fix\\",\\"fingerprint\\":\\"path:line:category\\",\\"specialist\\":\\"name\\"} Required fields: severity, confidence, path, category, summary, specialist. diff --git a/ship/sections/review-army.md b/ship/sections/review-army.md index 9b446e515..daff334ee 100644 --- a/ship/sections/review-army.md +++ b/ship/sections/review-army.md @@ -392,7 +392,7 @@ Every other specialist, including Testing, reads the full diff with fixtures. "You are a specialist code reviewer. Read the checklist at {checklist path}, then run `DIFF_BASE= && git diff "$DIFF_BASE"` to get the diff (``: write the sha in before dispatch, the merge base on pass 1 and `RANGE_BASE` from pass 2 on; never a shell variable). Apply the checklist against the diff. -`NO FINDINGS` alone is the expected, complete result for a clean diff; never invent an item to show work. Otherwise output one JSON object per finding, on its own line, at most 400 words of findings in all: +`NO FINDINGS` alone is the expected, complete result for a clean diff; never invent an item. Otherwise output one JSON object per finding per line, 400 words at most: {\"severity\":\"CRITICAL|INFORMATIONAL\",\"confidence\":N,\"path\":\"file\",\"line\":N,\"category\":\"category\",\"summary\":\"description\",\"fix\":\"recommended fix\",\"fingerprint\":\"path:line:category\",\"specialist\":\"name\"} Required fields: severity, confidence, path, category, summary, specialist. diff --git a/test/fixtures/skill-md-size-allowlist.json b/test/fixtures/skill-md-size-allowlist.json index 96af070f1..c27dc55e6 100644 --- a/test/fixtures/skill-md-size-allowlist.json +++ b/test/fixtures/skill-md-size-allowlist.json @@ -27,14 +27,14 @@ "cursor/gstack-plan-design-review": 120746, "cursor/gstack-plan-devex-review": 115228, "cursor/gstack-plan-eng-review": 145996, - "cursor/gstack-review": 121628, + "cursor/gstack-review": 121626, "factory/gstack-autoplan": 110763, "factory/gstack-design-review": 124191, "factory/gstack-land-and-deploy": 100105, "factory/gstack-plan-design-review": 123521, "factory/gstack-plan-devex-review": 118591, "factory/gstack-plan-eng-review": 149104, - "factory/gstack-review": 125401, + "factory/gstack-review": 125399, "gbrain/gstack-autoplan": 108892, "gbrain/gstack-design-review": 112612, "gbrain/gstack-plan-design-review": 109503, @@ -48,7 +48,7 @@ "kiro/gstack-plan-design-review": 120598, "kiro/gstack-plan-devex-review": 115080, "kiro/gstack-plan-eng-review": 145858, - "kiro/gstack-review": 121452, + "kiro/gstack-review": 121450, "openclaw/gstack-autoplan": 108715, "openclaw/gstack-design-review": 111535, "openclaw/gstack-plan-design-review": 108472, @@ -58,12 +58,12 @@ "opencode/gstack-plan-design-review": 122033, "opencode/gstack-plan-devex-review": 115836, "opencode/gstack-plan-eng-review": 147265, - "opencode/gstack-review": 122250, + "opencode/gstack-review": 122248, "slate/gstack-autoplan": 108372, "slate/gstack-design-review": 122320, "slate/gstack-plan-design-review": 120672, "slate/gstack-plan-devex-review": 115154, "slate/gstack-plan-eng-review": 145927, - "slate/gstack-review": 121540 + "slate/gstack-review": 121538 } }