From cf1d862fa0e18b4496a1efa2b1dcdcbb0b1fa46e Mon Sep 17 00:00:00 2001
From: Garry Tan <garrytan@gmail.com>
Date: Sat, 30 May 2026 11:32:23 -0700
Subject: [PATCH] test: rebaseline parity-suite v1.44.1 -> v1.53.0.0

The frozen v1.44.1 anchor went stale: five planning skills (plan-ceo-review,
plan-eng-review, plan-design-review, investigate, office-hours) crept past the
1.05x ceiling via legitimate v1.49-v1.53 growth (brain-aware planning + the
v1.53 redaction guard), so `bun test` was red on a clean checkout of main.

Capture a fresh baseline at HEAD (bun run scripts/capture-baseline.ts --tag
v1.53.0.0) and re-point the test at it. The per-skill 1.05 ratio is kept, so
future bloat is still caught; only the anchor moved. Mirrors the earlier
skill-size-budget rebase (v1.44.1 -> v1.47.0.0). Historical v1.44.1 / v1.46.0.0
/ v1.47.0.0 baselines are retained for the v1->v2 audit trail. The captured
skill bytes equal origin/main exactly (this branch left every SKILL.md
untouched). Clears the pre-existing failures noted in the v1.53.0.0 CHANGELOG.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 test/parity-suite.test.ts | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/test/parity-suite.test.ts b/test/parity-suite.test.ts
index 9d6da4868..32ce49f12 100644
--- a/test/parity-suite.test.ts
+++ b/test/parity-suite.test.ts
@@ -2,9 +2,16 @@
  * Cathedral parity suite — gate-tier (free, structural + content checks).
  *
  * Runs every PARITY_INVARIANTS check against the current SKILL.md output
- * vs the v1.44.1 baseline. Failures get an actionable, per-skill report
+ * vs the v1.53.0.0 baseline. Failures get an actionable, per-skill report
  * showing missing phrases, missing headings, and size ratios.
  *
+ * Baseline rebased v1.44.1 → v1.53.0.0: the brain-aware-planning releases
+ * (v1.49–v1.52) plus the v1.53 redaction guard pushed five planning skills
+ * past the 5% ratchet on the frozen v1.44.1 anchor. Rebasing absorbs that
+ * legitimate growth at HEAD while keeping the per-skill 1.05 ratio so future
+ * bloat is still caught. Historical v1.44.1 / v1.46.0.0 / v1.47.0.0 baselines
+ * are retained in test/fixtures/ for the v1→v2 audit trail.
+ *
  * Periodic-tier LLM-judge parity (paid) lands in Phase B (v2.0.0.0)
  * alongside the sections/ extraction. Plumbing is in parity-harness.ts.
  */
@@ -16,9 +23,9 @@ import { runParityChecks, PARITY_INVARIANTS } from './helpers/parity-harness';
 import type { ParityBaseline } from './helpers/capture-parity-baseline';
 
 const REPO_ROOT = path.resolve(import.meta.dir, '..');
-const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.44.1.json');
+const BASELINE_PATH = path.join(REPO_ROOT, 'test', 'fixtures', 'parity-baseline-v1.53.0.0.json');
 
-describe('parity suite vs v1.44.1 baseline (gate, free)', () => {
+describe('parity suite vs v1.53.0.0 baseline (gate, free)', () => {
   test('baseline exists', () => {
     expect(fs.existsSync(BASELINE_PATH)).toBe(true);
   });
@@ -43,7 +50,7 @@ describe('parity suite vs v1.44.1 baseline (gate, free)', () => {
       .map(d => `  ${d.skill}:\n    - ${d.failures.join('\n    - ')}`)
       .join('\n');
     throw new Error(
-      `${report.failed} skill(s) failed parity checks vs v1.44.1:\n${failureMessages}`,
+      `${report.failed} skill(s) failed parity checks vs ${baseline.tag}:\n${failureMessages}`,
     );
   });
 });