test: clean up the paid eval lane (B1-B4, B6, B7)

- B1: delete paid files that assert nothing or cannot pass meaningfully:
  skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e
  (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red
  since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose
  (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys,
  scripts and census rows.
- B2: skill-llm-eval grades browse/sections/command-list.md with one union
  judge that also carries the baseline score pin; regression-vs-baseline
  deleted (paid run: pass, c4/c4/a4).
- B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral
  make no model calls; renamed out of the paid glob so they run on every
  PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted.
- B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI
  image; excluded from the weekly lane with a tracked re-entry condition.
- B6: fold opus-47's negative routing controls into skill-routing-e2e
  journey-negatives (paid run: 3/3 unrouted) and delete the file.
- B7: delete the never-green brain-privacy-gate eval; a free
  gstack-skill-start test now proves consent precedes artifacts egress.
This commit is contained in:
garrytan committed 2026-09-29 06:08:49 +00:00
1 parent 5d032ef299
commit 53e7f3212f
58 files changed
+273 -2594

No files matched your search

+5 -5
View File
@@ -18,7 +18,7 @@ import { resolveModuleSelection } from './helpers/e2e-helpers';
const ROOT = path.resolve(import.meta.dir, '..');
const CEO_FILES = [
'test/skill-e2e-plan.test.ts', 'test/skill-e2e-ask-user-question-format-compliance.test.ts',
'test/skill-e2e-opus-47.test.ts', 'test/skill-llm-eval.test.ts',
'test/skill-e2e-retro.test.ts', 'test/skill-llm-eval.test.ts',
];
const ceoManifest = () => buildRunManifest({ tier: 'gate', profile: 'pr', sliceCount: 1,
evalsAll: false, env: {}, changedFiles: ['plan-ceo-review/SKILL.md.tmpl'], discovered: CEO_FILES });
@@ -70,7 +70,7 @@ describe('PR profile paid-runner integration', () => {
expect(manifest.selection?.e2e).toContain('plan-ceo-review-benefits');
expect(manifest.selection?.e2e).not.toContain('plan-ceo-review-plan-mode');
expect(manifest.selection?.judges).toContain('plan-ceo-review/SKILL.md modes');
expect(manifest.entries.find(entry => entry.file.includes('opus-47'))?.status).toBe('skipped-by-diff');
expect(manifest.entries.find(entry => entry.file.includes('skill-e2e-retro'))?.status).toBe('skipped-by-diff');
expect(manifest.entries.find(entry => entry.file.includes('ask-user-question'))?.status).toBe('planned');
expect(manifest.prCoverage?.deferred.some(item => item.id === 'plan-ceo-review-plan-mode')).toBe(true);
expect(parseRunManifest(JSON.stringify(manifest))).toEqual(manifest);
@@ -145,8 +145,8 @@ describe('PR profile paid-runner integration', () => {
broad.selection!.e2e!.push('qa-only-no-fix'); broad.prCoverage!.e2e.push('qa-only-no-fix');
expect(() => parseRunManifest(JSON.stringify(broad))).toThrow('broad-only');
const injected = structuredClone(manifest);
injected.entries.find(entry => entry.file.includes('opus-47'))!.status = 'planned';
injected.entries.find(entry => entry.file.includes('opus-47'))!.slice = 1;
injected.entries.find(entry => entry.file.includes('skill-e2e-retro'))!.status = 'planned';
injected.entries.find(entry => entry.file.includes('skill-e2e-retro'))!.slice = 1;
expect(() => parseRunManifest(JSON.stringify(injected))).toThrow('outside its PR case selection');
for (const action of ['remove', 'skip', 'duplicate'] as const) {
const missing = structuredClone(manifest);
@@ -184,7 +184,7 @@ describe('PR profile paid-runner integration', () => {
const judge = new RegExp(prProfileTestNamePattern('test/skill-llm-eval.test.ts', selection));
expect(judge.test('LLM-as-judge plan-ceo-review/SKILL.md modes')).toBe(true);
expect(judge.test('LLM-as-judge plan-ceo-review/SKILLxmd modes')).toBe(false);
expect(prProfileFileSelected('test/skill-e2e-opus-47.test.ts', selection)).toBe(false);
expect(prProfileFileSelected('test/skill-e2e-retro.test.ts', selection)).toBe(false);
});
test('real Bun child executes only the persisted case through the actual registered helper', async () => {