mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-02 17:40:02 +02:00
Garry Tan
dcaea52800
* feat: add surface-aware exploratory QA and ship documentation gates * test: preserve delegated QA setup authority after main integration * fix(qa): clarify exploration order and preserve report artifacts * test(qa): follow the shared setup reference directly * refactor(ship): make verification and recovery routes explicit * test(ship): align evidence and review guards with explicit routes * fix(workflows): clarify ship recovery and functional QA evidence * fix(workflows): clarify approval recovery and full QA coverage * refactor(workflows): order review transactions and clarify ship state * fix(ship): clarify final verification and fail closed at publication * fix(evals): attribute native atomic documentation writes * fix(ship): clarify recovery and documentation lifecycle guidance * fix(test): preserve observed native placeholder styling in CI * fix(codex): report watchdog timeouts without a process-exit race * Checkpoint functional QA implementation and workflow validation repairs * Fix documentation and shared-review fixture contracts * docs: clarify judge reuse and evaluation supervision * test: align review evidence and selected case contracts * test: verify append-only documentation checkpoints and recovery * fix: qualify QA workflows and CI validation repairs * fix: launch shared-libs fixture scripts on Windows * fix: qualify QA deadlines, fixture isolation, and shard cleanup * fix: preserve qualified QA and cancellation repairs * fix: enforce functional fixture authority and share strict event decoding * fix: retain free-test evidence and explain recovery * fix: reject malformed native evidence after decoder consolidation * test: use reliable capture for telemetry privacy filters * test: refresh measured quick coverage and document validation costs * Fix native fixture receipts and preserve VM validation evidence * Align negative judge controls with upstream clarity policy * Fix report-only QA preparation and public evidence handling * Clarify QA-only preparation and current-report preservation * Stream Ship quality judgments with an explicit 64k response contract * Validate compact judge reasoning locally with supported wire schema * Align functional QA fixture instructions with evidence acceptance * Bind native browser diagnostics to execution evidence and align review verdicts * Preserve native diagnostic line boundaries * Serialize functional QA evidence from native captures * Keep large QA evidence fixture payload out of Windows argv
43 lines
2.3 KiB
TypeScript
43 lines
2.3 KiB
TypeScript
import { expect, test } from 'bun:test';
|
|
import { E2E_TIERS, E2E_TOUCHFILES, LLM_JUDGE_TOUCHFILES, selectTests } from './helpers/touchfiles';
|
|
import { computePaidCaseSelection } from '../scripts/test-paid-shards';
|
|
|
|
const id = 'ship-skipped-queued-finding';
|
|
|
|
test.each([
|
|
'scripts/resolvers/review.ts', 'scripts/resolvers/index.ts',
|
|
'ship/sections/review-army.md.tmpl', 'ship/sections/adversarial.md.tmpl',
|
|
'ship/sections/manifest.json', 'bin/gstack-review-log', 'bin/gstack-review-read',
|
|
'bin/gstack-slug', 'bin/gstack-config', 'bin/gstack-brain-enqueue',
|
|
'lib/review-evidence.ts', 'test/helpers/ship-skip-actor.ts', 'test/helpers/scratch-repo.ts',
|
|
'test/skill-e2e-ship-skip.test.ts', 'test/ship-skip-actor.test.ts',
|
|
'test/ship-skip-selection.test.ts', '.github/docker/Dockerfile.ci',
|
|
])('%s selects the native queued-Skip regression', file => {
|
|
expect(selectTests([file], E2E_TOUCHFILES).selected).toContain(id);
|
|
expect(E2E_TIERS[id]).toBe('gate');
|
|
});
|
|
|
|
test('native-only fixture files do not select quality judges', () => {
|
|
expect(selectTests(['test/helpers/ship-skip-actor.ts', 'test/ship-skip-actor.test.ts',
|
|
'test/skill-e2e-ship-skip.test.ts', 'test/helpers/scratch-repo.ts'], LLM_JUDGE_TOUCHFILES).selected).toEqual([]);
|
|
expect(selectTests(['qa-only/SKILL.md.tmpl'], E2E_TOUCHFILES).selected).not.toContain(id);
|
|
});
|
|
|
|
test('scratch identity helper selects only queued-Skip and preserves its fast-profile deferral', () => {
|
|
const changedFiles = ['test/helpers/scratch-repo.ts'];
|
|
expect(selectTests(changedFiles, E2E_TOUCHFILES).selected).toEqual([id]);
|
|
const full = computePaidCaseSelection({ profile: 'full', env: {}, changedFiles });
|
|
expect(full.selection).toEqual({ e2e: [id], judges: [] });
|
|
const pr = computePaidCaseSelection({ profile: 'pr', env: {}, changedFiles });
|
|
expect(pr.selection).toEqual({ e2e: [], judges: [] });
|
|
expect(pr.coverage?.mode).toBe('pr');
|
|
expect(pr.coverage?.deferred).toEqual([{
|
|
id, tier: 'gate', reason: 'Broad gate census/release coverage; outside the fast PR profile',
|
|
}]);
|
|
});
|
|
|
|
test.each(['test/helpers/qa-checkpoint-evidence.ts', 'test/fixtures/qa-only-charter-public.json'])
|
|
('%s selects the native QA-only preparation gate', file => {
|
|
expect(selectTests([file], E2E_TOUCHFILES).selected).toContain('qa-only-no-fix');
|
|
});
|