CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-27 07:01:54 +02:00
Code Issues Packages Projects Releases Wiki Activity

v1.89.0.0 feat: add shared-code extraction audit (#2925)

Browse Source 
* feat: bind shared-code review advice to source and branch

* feat: add shared-code extraction audit and scoped review checks

* test: recognize complete source reads and explicit coverage legends

* chore: bump version and changelog (v1.88.0.0)

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* test: capture native review questions and retain public evidence

Capture the actual first public native question with strict ownership and display matching. Preserve terminal failures and raw evidence, and retain SDK completion checks.

* test: recognize verified review evidence and complete fixtures

Recognize complete source and diagram evidence, concrete design and developer-experience decisions, and the complete planted scenario contracts. Preserve negative controls and grading thresholds.

* fix: preserve decision brief structure in native questions

Keep the required pros-and-cons heading and final Net field in native question text. Regenerate host outputs and document the release and evaluation repairs.

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* docs: update project documentation for v1.88.0.0

Co-Authored-By: OpenAI Codex <noreply@openai.com>

* fix: correct eval retry accounting and ship workflow gates

* fix: capture native eval evidence and stabilize CI fixtures

* fix: keep shared-code eval skips read-only

Choose explicit no-change answers instead of mixed fix/preservation options.
Reuse the bounded revalidation prompt for path fixtures so required review
metadata is available without repeated discovery. Preserve source checks,
retry limits, and failed native terminal outcomes.

Add captured-question and callback regressions, plus evaluation selection
coverage for the affected fixtures.

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Garry Tan
2026-09-24 01:53:58 -04:00
committed by GitHub
co-authored by OpenAI Codex
parent b9706f3635
commit 06ed920a97
177 changed files with 13244 additions and 2477 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/touchfiles.test.ts
+64 -5
View File
@@ -19,6 +19,7 @@ import {
} from './helpers/touchfiles';
import { readWorkflowExcerpt } from './helpers/workflow-excerpt';
import { sharedLibsPlanExcerpt } from './helpers/shared-libs-plan-excerpt';
const ROOT = path.resolve(import.meta.dir, '..');
@@ -78,9 +79,9 @@ describe('selectTests', () => {
expect(fs.readFileSync(path.join(ROOT, 'plan-eng-review/sections/review-sections.md.tmpl'), 'utf8'))
.toContain('{{LEARNINGS_SEARCH}}');
const consumers = selectTests(['plan-eng-review/sections/review-sections.md'], E2E_TOUCHFILES).selected
// These cases use an outside-only excerpt or descriptive Eng metadata.
// These cases use an outside-only/Code Quality excerpt or descriptive metadata.
.filter(id => !['outside-plan-disabled-no-fallback', 'plan-ceo-review-prosons-cadence',
'plan-review-prosons-format'].includes(id));
'plan-review-prosons-format', 'shared-libs-plan-callers'].includes(id));
const existing = ['learnings-show', 'codex-plan-ceo-format-mode', 'codex-plan-ceo-format-approach',
'codex-plan-eng-format-coverage', 'codex-plan-eng-format-kind'];
const result = selectTests(['scripts/resolvers/learnings.ts'], E2E_TOUCHFILES);
@@ -161,7 +162,8 @@ describe('selectTests', () => {
const generated = selectTests(consumers.map(([output]) => output), E2E_TOUCHFILES);
// These two CEO-format cases already depend on every resolver through
// scripts/resolvers/**; keep that existing selection alongside consumers.
const expected = [...new Set([...generated.selected,
// The bounded Code Quality fixture stops before Test review.
const expected = [...new Set([...generated.selected.filter(id => id !== 'shared-libs-plan-callers'),
'codex-plan-ceo-format-mode', 'codex-plan-ceo-format-approach',
])].sort();
const actual = selectTests(['scripts/resolvers/testing.ts'], E2E_TOUCHFILES);
@@ -187,6 +189,33 @@ describe('selectTests', () => {
expect(result.selected.sort()).toEqual(['plan-eng-review/SKILL.md sections', 'ship/SKILL.md workflow']);
});
test('bounded shared-code planning selects its consumed resolvers, excluding other Eng sections', () => {
const entrypoint = fs.readFileSync(path.join(ROOT, 'plan-eng-review/SKILL.md'), 'utf8');
const review = fs.readFileSync(path.join(ROOT, 'plan-eng-review/sections/review-sections.md'), 'utf8');
const excerpt = sharedLibsPlanExcerpt(entrypoint, review);
for (const [start, end] of [
['## Prior Learnings', '## Retrospective learning'],
['### 3. Test review', '### 4. Performance review'],
]) {
const begin = review.indexOf(start), finish = review.indexOf(end, begin);
expect(begin).toBeGreaterThan(0);
expect(finish).toBeGreaterThan(begin);
const changed = review.slice(0, begin + start.length) + '\nChanged excluded instructions.\n' + review.slice(finish);
expect(sharedLibsPlanExcerpt(entrypoint, changed)).toBe(excerpt);
}
for (const source of ['scripts/resolvers/learnings.ts', 'scripts/resolvers/testing.ts']) {
expect(selectTests([source], E2E_TOUCHFILES).selected).not.toContain('shared-libs-plan-callers');
}
expect(excerpt).toContain('## Confidence Calibration');
expect(excerpt).toContain('## AskUserQuestion Format');
expect(excerpt).toContain('### Shared-code evaluation rubric');
for (const source of ['scripts/resolvers/confidence.ts',
'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/shared-libs.ts',
'test/helpers/shared-libs-plan-excerpt.ts']) {
expect(selectTests([source], E2E_TOUCHFILES).selected).toContain('shared-libs-plan-callers');
}
});
test.each([
['plan-eng-review/sections/review-sections.md', 'plan-eng-review/SKILL.md sections',
'plan-eng-review/SKILL.md', '## Scope gate', '## Section self-check', '### REGRESSION RULE (mandatory)'],
@@ -268,6 +297,36 @@ describe('selectTests', () => {
expect(result.selected).not.toContain('retro');
});
test('mode-question capture dependencies select its native gate', () => {
for (const file of [
'test/auq-mode-capture.test.ts', 'test/skill-ceo-section-ordering.test.ts',
'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts',
'test/helpers/hermetic-env.ts', 'test/helpers/eval-store.ts',
'lib/claude-bin.ts', 'test/workflow-excerpt.test.ts',
]) {
expect(selectTests([file], E2E_TOUCHFILES).selected).toContain('auq-format-gate');
}
});
test('shared-code evidence regressions select their consuming evaluations', () => {
expect(selectTests(['test/fixtures/shared-libs-readonly-substitution-ci16358.json'], E2E_TOUCHFILES).selected.sort())
.toEqual(['shared-libs-codex-read-only', 'shared-libs-opportunity-judgment', 'shared-libs-pr-coverage',
'shared-libs-read-only', 'shared-libs-unsupported-git'].sort());
for (const file of ['test/helpers/shared-libs-review-start-evidence.ts', 'test/shared-libs-review-start-evidence.test.ts',
'test/fixtures/shared-libs-review-start-public.json',
'test/fixtures/shared-libs-revalidation-max-turns-public.json']) {
expect(selectTests([file], E2E_TOUCHFILES).selected).toEqual(['shared-libs-review-revalidation']);
}
const pathCases = ['shared-libs-review-path-eligibility', 'shared-libs-review-index-flags',
'shared-libs-review-prior-coverage'];
expect(selectTests(['test/shared-libs-revalidation-prompt.test.ts'], E2E_TOUCHFILES).selected.sort())
.toEqual([...pathCases, 'shared-libs-review-revalidation'].sort());
expect(selectTests(['test/fixtures/shared-libs-index-flags-skip-question.json'], E2E_TOUCHFILES).selected.sort())
.toEqual([...pathCases, 'shared-libs-review-revalidation', 'shared-libs-review-lifecycle'].sort());
expect(selectTests(['test/fixtures/shared-libs-paths-max-turns-public.json'], E2E_TOUCHFILES).selected)
.toEqual(['shared-libs-review-index-flags']);
});
test('skill-specific change selects only that skill and related tests', () => {
const result = selectTests(['plan-ceo-review/SKILL.md'], E2E_TOUCHFILES);
expect(result.selected).toContain('plan-ceo-review');
@@ -333,10 +392,10 @@ describe('selectTests', () => {
expect(result.selected).not.toContain('retro');
});
test('session tool isolation regression selects its four capture workflows', () => {
test('session tool isolation regression selects its capture workflows', () => {
const result = selectTests(['test/session-runner-tools.test.ts'], E2E_TOUCHFILES);
expect(result.selected.sort()).toEqual([
'carve-section-loading', 'plan-ceo-section-loading', 'plan-design-review-plan-mode', 'ship-section-loading',
'auq-format-gate', 'carve-section-loading', 'plan-ceo-section-loading', 'plan-design-review-plan-mode', 'ship-section-loading',
]);
expect(result.reason).toBe('diff');
});