test: dedicated-tools overlay case pinned to claude-opus-5-5 (E2)

scripts/paid-test-durations.json

@@ -157,6 +157,7 @@
       "test/skill-e2e-outside-plan-disabled.test.ts": 53292,
       "test/skill-e2e-outside-voice.test.ts": 1000,
       "test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts": 85282,
+      "test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts": 85282,
       "test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash.test.ts": 80465,
       "test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts": 49282,
       "test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts": 318532,

test/fixtures/overlay-nudges.ts

@@ -324,6 +324,34 @@ export const OVERLAY_FIXTURES: OverlayFixture[] = [
     comparison: { direction: 'lower_is_better', minimum: 0 },
     pass: lowerIsBetter20Pct,
   },
+  {
+    id: 'claude-dedicated-tools-vs-bash-opus-5-5',
+    overlayPath: 'model-overlays/claude.md',
+    model: 'claude-opus-5-5',
+    trials: 10,
+    concurrency: 3,
+    direction: 'lower_is_better',
+    maxTurns: 15,
+    setupWorkspace: (dir) => {
+      fs.mkdirSync(path.join(dir, 'src'), { recursive: true });
+      fs.writeFileSync(path.join(dir, 'src', 'index.ts'), "export const x = 1;\n");
+      fs.writeFileSync(path.join(dir, 'src', 'util.ts'), "export function util() { return 42; }\n");
+      fs.writeFileSync(path.join(dir, 'src', 'types.ts'), "export type Foo = { a: number };\n");
+      fs.writeFileSync(path.join(dir, 'src', 'config.ts'), "export const c = { n: 'demo' };\n");
+      fs.writeFileSync(path.join(dir, 'src', 'api.ts'), "export async function fetchFoo() { return null; }\n");
+    },
+    userPrompt:
+      "List every TypeScript file under src/ and tell me what each exports. " +
+      "Return only a JSON object mapping each src/ path to an array of its exported symbol names. " +
+      "The final message is consumed directly by JSON.parse: return the exact JSON object, with no Markdown fences and no other prose. " +
+      "You may use any tools available.",
+    metric: bashToolCallCount,
+    metricName: 'bash_tool_calls',
+    verify: (r) => assertFinalJson(r, { 'src/index.ts': ['x'], 'src/util.ts': ['util'], 'src/types.ts': ['Foo'], 'src/config.ts': ['c'], 'src/api.ts': ['fetchFoo'] }),
+    gate: lowerIsBetter20PctOrZeroBaseline,
+    comparison: { direction: 'lower_is_better', minimum: 0 },
+    pass: lowerIsBetter20Pct,
+  },
 
 ];
 

test/helpers/overlay-case-policy.ts

@@ -23,4 +23,5 @@ export const OVERLAY_CASE_FILES: Record<string, string> = {
   'test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts': 'opus-4-7-effort-match-trivial',
   'test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts': 'opus-4-7-literal-interpretation',
   'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts': 'claude-dedicated-tools-vs-bash-sonnet',
+  'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts': 'claude-dedicated-tools-vs-bash-opus-5-5',
 };

test/helpers/touchfiles-data.ts

@@ -1096,6 +1096,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
   'overlay-harness-opus-4-7-effort-match-trivial': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts',  'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts',  'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts',     'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'],
   'overlay-harness-opus-4-7-literal-interpretation': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts',  'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts',  'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts',     'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'],
   'overlay-harness-claude-dedicated-tools-vs-bash-sonnet': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts',  'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts',  'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts',     'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'],
+  'overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts',  'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts',  'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts',     'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'],
   'journey-negatives':      [
     
 
@@ -1477,6 +1478,7 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic' | 'marathon'> = {
   'overlay-harness-opus-4-7-effort-match-trivial': 'periodic',
   'overlay-harness-opus-4-7-literal-interpretation': 'periodic',
   'overlay-harness-claude-dedicated-tools-vs-bash-sonnet': 'periodic',
+  'overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5': 'periodic',
   'journey-negatives': 'periodic',
 };
 
@@ -1803,6 +1805,7 @@ export const E2E_KINDS: Record<string, 'rule' | 'behavior' | 'judge'> = {
   'overlay-harness-opus-4-7-effort-match-trivial': 'rule',
   'overlay-harness-opus-4-7-literal-interpretation': 'rule',
   'overlay-harness-claude-dedicated-tools-vs-bash-sonnet': 'rule',
+  'overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5': 'rule',
   'journey-negatives': 'rule',
   'review/SKILL.md workflow': 'judge',
   'setup-browser-cookies/SKILL.md workflow': 'judge',

test/overlay-measurement.test.ts

@@ -255,11 +255,12 @@ describe('literal fixture task correctness', () => {
     expect(() => assertReadOnlyWorkspace(before, snapshotWorkspace(dir))).toThrow('b');
   }));
   test('registry retires absent-nudge fanout cases and preserves remaining model/trial budgets', () => {
-    expect(OVERLAY_FIXTURES).toHaveLength(4);
+    expect(OVERLAY_FIXTURES).toHaveLength(5);
     expect(OVERLAY_FIXTURES.some((f) => f.id.includes('fanout') || f.comparison?.unsupportedHypothesis)).toBe(false);
     expect(OVERLAY_FIXTURES.every((f) => f.trials === 10 && f.comparison)).toBe(true);
     expect(OVERLAY_FIXTURES.filter((f) => f.model === 'claude-opus-4-7')).toHaveLength(3);
     expect(OVERLAY_FIXTURES.filter((f) => f.model === 'claude-sonnet-4-6')).toHaveLength(1);
+    expect(OVERLAY_FIXTURES.filter((f) => f.model === 'claude-opus-5-5')).toHaveLength(1);
   });
 });
 

test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts

@@ -0,0 +1,6 @@
+import { describeE2ETier } from './helpers/e2e-gate';
+import { registerOverlayCase } from './helpers/overlay-case';
+
+describeE2ETier('periodic')('overlay behavior contract v2 (SDK)', () => {
+  registerOverlayCase('claude-dedicated-tools-vs-bash-opus-5-5');
+});