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

@@ -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
 

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=$(git merge-base origin/<base> HEAD) && git diff "$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.

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 (`<diff-base>`: 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.

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=<diff-base> && git diff "$DIFF_BASE"` to get the diff (`<diff-base>`: 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.

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
   }
 }