test: browse reference judge gates on its stated floors; the baseline comparison is recorded, not a ratchet (W7d browse judge baseline ratchet; t08 F7)

expect(regressions).toEqual([]) compared a noisy three-sample mean against
eval-baselines.json (clarity 4), silently raising the stated clarity floor of
3. The comparison stays in judge_reasoning; pass and assertions use
BROWSE_JUDGE_FLOORS (clarity 3, completeness 4, actionability 4). Judge
prompt and schema are unchanged. Stored panel means: three known-good (two the
ratchet rejected) pass; three below-floor panels fail.

test/helpers/workflow-judge-cache.ts

@@ -135,3 +135,15 @@ export function prepareWorkflowJudgeCache(opts: WorkflowCacheOptions): {
     },
   };
 }
+
+/**
+ * Pass floors for the browse reference judge panel mean. The stored baseline
+ * is recorded for comparison only: a three-sample mean is too noisy for a
+ * no-dip ratchet, and gating on it silently raised the clarity floor to 4.
+ */
+export const BROWSE_JUDGE_FLOORS = { clarity: 3, completeness: 4, actionability: 4 } as const;
+
+export function browseJudgeFloorsMet(scores: Record<keyof typeof BROWSE_JUDGE_FLOORS, number>): boolean {
+  return (Object.keys(BROWSE_JUDGE_FLOORS) as Array<keyof typeof BROWSE_JUDGE_FLOORS>)
+    .every(dim => scores[dim] >= BROWSE_JUDGE_FLOORS[dim]);
+}