test: pin landed judge schemas to the recorded calibration; record W2 results (W2 T8)

A free test ties each inline judge's schema wiring to its committed
comparison-1 result, so a schema cannot be sent without a complete,
landing calibration. The corpus README records every configuration's
flips, agreement, false passes, errors, latency, cost and decision.

test/fixtures/judge-calibration/README.md

@@ -20,3 +20,28 @@ defines each configuration. Run outputs land in `<config>/runs/`:
 and priced usage, and `comparison-1.result.json` holds the flip rates, agreement,
 false passes, error rates, p95 latency, landing decision and the UC3 prose-step
 trigger. `manifest.json` prices every planned call before dispatch.
+
+## Comparison (1) results (2026-10-03, `claude-fable-5-1`)
+
+Flips are panel-verdict differences on items where both panels completed: old-vs-old
+is `old-a` vs `old-b`, new-vs-old is `new` vs `old-a`. Agreement is items whose panel
+verdict matches `expected`. A configuration lands when new flips are at most old flips
+plus one, agreement does not drop, there are zero new false passes and the new p95 is at
+most 80% of `JUDGE_MS` (96 s).
+
+| Config | Old-vs-old flips | New-vs-old flips | Agreement old / new | New false passes | Errored samples old / new | p95 s old / new | Held-out new flips, agreement | Cost | Decision |
+|---|---|---|---|---|---|---|---|---|---|
+| `arm` | 0/24 | 0/24 | 24 / 24 | 0 | 0 / 0 | 7.6 / 5.9 | 0/8, 8/8 | $6.16 | lands |
+| `qa-workflow` | 2/24 | 4/24 | 17 / 17 | 1 (a06) | 0 / 0 | 26.7 / 27.6 | 1/8, 6/8 | $18.94 | held: new flips above old + 1, one new false pass |
+| `qa-health-rubric` | 0/24 | 1/24 | 22 / 23 | 0 | 0 / 0 | 17.0 / 18.7 | 0/8, 8/8 | $10.62 | lands |
+| `qa-anti-refusal` | 0/24 | 0/24 | 23 / 23 | 0 | 0 / 0 | 12.5 / 13.4 | 0/8, 8/8 | $7.02 | lands |
+| `cross-skill` | 0/24 | 0/24 | 23 / 23 | 0 | 0 / 0 | 19.7 / 22.6 | 0/8, 8/8 | $19.86 | lands |
+| `voice` | 0/24 | 0/24 | 22 / 22 | 0 | 0 / 0 | 13.3 / 13.7 | 0/8, 8/8 | $8.09 | lands |
+
+No sample errored (refusal, truncation, parse, schema or transport) under either prompt.
+`workflow-default` has a corpus but was not dispatched: its priced cost (about $20) exceeded
+what remained of the W2 reservation after the higher-priority configurations, so the shared
+workflow judge stays on today's request (only `ship` sends `WORKFLOW_JUDGE_RESPONSE_SCHEMA`,
+as before). The frontier (`review`) and cookie workflow configurations have no corpus yet.
+A $0.12 two-call pilot sized output tokens before the manifest was priced. Total W2 spend:
+$70.81 of $90.

test/judge-calibration.test.ts

@@ -253,3 +253,35 @@ describe('committed calibration configurations and corpora', () => {
     expect(byId.voice!.verdict([voice(4), voice(4), voice(3)])).toBe('fail');
   });
 });
+
+describe('landed schemas match the recorded calibration', () => {
+  const evalSource = fs.readFileSync(path.join(import.meta.dir, 'skill-llm-eval.test.ts'), 'utf8');
+  const judgeSource = fs.readFileSync(path.join(import.meta.dir, 'helpers', 'llm-judge.ts'), 'utf8');
+  const result = (id: string) => JSON.parse(fs.readFileSync(path.join(import.meta.dir, 'fixtures', 'judge-calibration', id, 'runs', 'comparison-1.result.json'), 'utf8'));
+  const wiring: Array<[string, string, string]> = [
+    ['qa-workflow', 'buildQaWorkflowJudgePrompt(section)', 'JUDGE_SCORE_SCHEMA'],
+    ['qa-health-rubric', 'buildQaHealthRubricJudgePrompt(section)', 'JUDGE_SCORE_SCHEMA'],
+    ['qa-anti-refusal', 'buildQaAntiRefusalJudgePrompt(diffAwareSection, rulesSection)', 'QA_ANTI_REFUSAL_JUDGE_SCHEMA'],
+    ['cross-skill', 'buildCrossSkillConsistencyJudgePrompt(collected)', 'CROSS_SKILL_CONSISTENCY_JUDGE_SCHEMA'],
+    ['voice', 'buildVoiceDirectiveJudgePrompt(voiceSection)', 'VOICE_DIRECTIVE_JUDGE_SCHEMA'],
+  ];
+
+  test.each(wiring)('%s sends its schema only when its complete calibration landed', (id, call, schema) => {
+    const recorded = result(id);
+    expect(recorded.complete).toBe(true);
+    const sent = evalSource.includes(`${call}, undefined, { jsonSchema: ${schema} })`);
+    expect(evalSource.includes(`${call})`) || sent).toBe(true);
+    expect(sent).toBe(recorded.landing.lands);
+  });
+
+  test('armJudge sends ARM_JUDGE_SCHEMA because its calibration landed', () => {
+    expect(result('arm').landing.lands).toBe(true);
+    expect(judgeSource).toContain('buildArmJudgePrompt(task, diff), ARM_JUDGE_MODEL, { jsonSchema: ARM_JUDGE_SCHEMA })');
+  });
+
+  test('uncalibrated workflow configurations stay on today\'s request; only ship keeps its existing schema', () => {
+    expect(fs.existsSync(path.join(import.meta.dir, 'fixtures', 'judge-calibration', 'workflow-default', 'runs'))).toBe(false);
+    expect(evalSource.match(/schemaTransport: true/g)).toHaveLength(1);
+    expect(evalSource.match(/compactReasoning: true/g)).toHaveLength(1);
+  });
+});