Files
gstack/test/skill-e2e-workflow.test.ts
T
Garry TanandOpenAI Codex 636175d349 v1.87.6.0 fix: make checks reliable and everyday validation faster (#2898)
* fix: acknowledge seeded plans before invoking review skills

* fix: distinguish current plan input from conversation history

* fix: keep hermetic plan reviews on manual permissions

* fix: distinguish tool discovery from file permission ownership

* fix: preserve initial plan mode in observation tests

* fix: wait for scope decisions before writing review findings

* fix: carry autoplan decisions consistently into review artifacts

* test: retain native failure context in periodic assertions

* fix: advance active file permissions before queued questions

* fix: finish red-team attempts before retry and cleanup

* fix: finalize plan format captures and judges before retry

* fix: cancel setup-gbrain SDK attempts before fixture cleanup

* test: select periodic consumers of the bounded attempt helper

* fix native Bash permission cards and queued questions

* fix: preserve independent decisions and review scope

Keep CEO approach, engineering scope and outside-review choices from approving independent remedies together. Carry declared contracts through DX polish and resolve new gaps before editing the plan. Regenerate every host and retain existing stop boundaries.

Validation: 654 focused tests passed across nine files; all-host generation passed. Full free and periodic validation pending.

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

* fix: require approval before design plan amendments

Align the Design review philosophy and rating recipe with its section protocol: resolve one proposed fix, then apply only that approved decision and retain honest scores for declined fixes.

Validation: 469 focused tests passed across four files; all-host generation passed.

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

* fix: observe native question completion before transcript persistence

Match owned completion hooks to submitted choices, reject conflicting or late answers, and retain bounded failure evidence.

* test: recognize review posture in acknowledged native questions

Require the selected mode acknowledgement, a completed follow-up question, and its current decoded display while preserving existing posture assertions.

* fix: preserve settled CEO choices and isolate pending remedies

Resolve established approach gates with cited authority and keep independent fixes out of unrelated option commitments and plan amendments.

* fix: carry approved DX choices through later review steps

Choose documentation approaches within the accepted scope and map resolved confusion points without reopening them through a bulk menu.

* test: handle native settings-file edit prompts

Keep one-time owned-file approvals and retain the actual sampled Autoplan permission frame with its matching barrier state.

* test: accept standard CEO reply directives with tuning footers

Recognize the exact trailing preference footer and letter-list directive while preserving current-display and exact acknowledgement checks.

* test: scope split reviewers to their generated plan artifacts

* test: observe native Bash permissions and invocation results

* test: handle owned Bash prompts during mode preference checks

* test: preserve synchronous subprocess rejection in Codex fixture

* Fix periodic review handoff navigation

Recognize review-first and explicit manual-next-step labels while preserving exact action families, manual preference, and ambiguous-menu rejection.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Bind pending file permissions to distinct current targets

Allow one captured file request to own the complete current dialog while unrelated file work is pending. Preserve same-path ambiguity, exact input ownership, and one-time grant checks.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Make paired CEO verification choices genuinely unresolved

Start the positive control with proposed manual checks so its unchanged oracle measures two new coverage decisions. Preserve runtime contracts, targets, count bounds, and all assertions.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Keep CEO review options and verification within approved scope

Audit every offered option for independent add-ons and keep new verification depth pending until accepted. Preserve already requested coverage and trace plan changes to the actual decision.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Assemble DX review artifacts before appending the final report

Keep early DX evidence above decisions, update artifact sections in place, and append the report using the actual current file suffix. Re-read after deleting an existing report before choosing the append anchor.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Keep outside plan reviews exclusive and invocation-owned

Follow one preflight-selected backend, terminate failed Codex work before fallback, and allocate extra prompt/output files uniquely. Consume only the current invocation’s completed output.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Select periodic completion evaluations for report writer changes

Register the shared review resolver for eight missing consumers and regress selection for all nine completion cases without changing their IDs or tiers.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Keep permission ambiguity fixtures on the same normalized target

Use distinct raw spellings of one target in the four negative fixtures so they exercise the normalized duplicate-owner guard after exact current-file disambiguation. Preserve the existing exception, no-input, diagnostic and cleanup assertions.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Clarify preserved contracts in engineering review fixture

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Recognize the offered DX follow-up handoff

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Check independent commitments before presenting review options

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Keep Codex review output and status in one shell invocation

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Distinguish seeded plans from reports written by a test attempt

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Recover clipped Autoplan file approvals with bounded viewport resizing

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Recover clipped Bash approvals before binding the complete command

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Isolate setup message tests from the shared checkout

Run the real installer in a temporary payload with private config, require successful completion, and guard source and binary contents and mtimes.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Fix periodic native permission and report completion handling

Match the pinned CLI's soft wraps and clipped headings without granting from incomplete frames. Retire completed file requests, retain mode annotations, and ask section captures for a short final acknowledgement after their full report is saved.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Preserve review approvals and validate DX comparison artifacts

Keep independent remedies and approved amendments explicit. Give the synthetic DX review its existing documentation and validate peer comparison as required analysis alongside four native decisions. Add positive and negative semantic calibrations while preserving review counts, model budgets and prompt size limits.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Make the five-finding CEO fixture's application boundary explicit

Materialize the request adapter and service composition used by the synthetic payment application. Explicitly declare the revised unregistered-event and mail-telemetry assumptions while preserving uncaught handler errors, the original invoice path and all five unresolved findings.

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Keep CEO state-path checks scoped to directory preparation

Co-authored-by: OpenAI Codex <noreply@openai.com>

* Use checked ports and bounded cleanup in pair-agent tests

Discover the daemon port from its owned state file, retain startup diagnostics, and await failed-start cleanup. Add occupied-port, early-exit, deadline, and foreign-state regressions while preserving the existing HTTP assertions and hook budgets.

Co-authored-by: Codex <noreply@openai.com>

* Preserve queued edit identity and recover clipped Bash permissions

Distinguish separately queued unfinished edits from mutation of one native tool ID. Keep grants bound to an exact owned request and reject reused IDs, ambiguous inputs, and competing owners.

Support the pinned renderer's literal em dash and request a repaint when only the Bash card's top rule is clipped. Grants still require the complete fresh card and an exact native acknowledgment.

Validation: 413 integrated parser/event tests passed; private repaint controls and joint source review passed. Full canonical suite and native periodic rerun remain pending.

Co-authored-by: Codex <noreply@openai.com>

* Keep periodic reviews within their approved contracts and deliverables

Carry exact approvals through engineering review, preserve declared contracts when amending CEO plans, and keep prioritization at the requested decision level. Materialize the revised synthetic SDK reference contract while retaining the five original documentation gaps.

Accept the observed semicolon in the finite DX handoff menu and register the direct source dependencies used by the engineering cases. Regenerate canonical review documents without changing model budgets, retries, count bands, or native completion assertions.

Validation: all-host generation and 275 review, fixture, selection and parity tests passed. Full free-suite and native periodic validation remain pending.

Co-authored-by: Codex <noreply@openai.com>

* Keep Eng approval cadence and independence guards explicit

* Accept ordinary punctuation in manual review handoffs

* Recover file permissions alongside queued Bash calls

* Carry approved DX work through later review findings

* Clarify the synthetic auth internal failure decision

* Bound the periodic DX fixture to onboarding changes

* Recognize native Design review handoff labels

* Hold scope in the integration-choice review fixture

* Carry approved Design decisions through review evidence

* Capture listener state when feedback reload fails

* Exclude workspace caches before checking deprecated flags

* Verify Design UI scope against a seeded review plan

* Clarify plan review decisions and outside-voice approval flow

* Reject setup menus in the Design UI gate

* docs: require focused repair validation before final acceptance

* fix: separate review commitments within existing prompt budgets

* docs: align generation and contributor validation guidance

* fix: advance native review prompts and count acknowledged findings

* chore: bump version and changelog (v1.87.1.0)

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

* chore: enforce cheap checks and side-effect-free validation previews

* fix: handle owned Fetch permissions and oversized native cards

* test: ground review fixtures in independent executable contracts

* fix: preserve review decisions and verify reports before completion

* test: construct the synthetic credential URL without a scanner false positive

* test: materialize DX examples and verify their actual local behavior

* fix: clarify CEO review decisions and execution order

* fix: clarify review workflow ordering and select Design quality checks

* Fix review decision gates and incomplete evaluation fixtures

Persist CEO and engineering commitment ledgers before menus, preserve exact
approvals, and distinguish implementation structure from feature scope.
Route Autoplan through the canonical CEO Step 0 ordering. Classify DX findings
before requesting approval and ground runtime claims in actual evidence.

Complete neutral non-target fixture contracts and accept the captured Design
handoff purpose without relaxing its ownership or acknowledgment checks.
Record runtime-capability verification in AGENTS.md validation discipline.

Validation: 1,335 focused tests passed across 21 files; build, all-host freshness,
skill validation (647 artifacts / 107 tracked), and credential checks passed.
Prior paid failures are preserved; behavioral acceptance remains pending.

* Fix review decision boundaries and owned Read prompts

Preserve exact approvals across review options, compare consistent DX milestones,
and keep proposed implementation separate from review evidence. Bind modern
Read prompts to one immutable native request and wait for its result.

Retain captured regression verdicts, correct fixture error names, improve import
probe diagnostics, and record focused-first validation discipline in AGENTS.md.

* Clarify CEO and engineering review decisions

Use explicit decision steps, one engineering ledger, and clear scope/write transitions. Preserve exact approvals and distinguish pending test requirements. Keep unrelated generated content unchanged.

* Fix review decision ordering and native evaluation interactions

* Clarify engineering decisions and test artifact order

* Clarify pending choices and approvals in CEO reviews

* Make CEO review phases sequential and clarify completion

* Fix Design board submission intent matching

* Seed an existing browser test baseline for Autoplan

* Document decision-log payloads before state initialization

* Preserve exact review scope and decide one change before drafting options

* Require input identity before repeating passing model judges

* Honor permitted storage throughout CEO review completion

* Match complete native permission text within the pinned renderer contract

* Align review approvals, independent choices, and bounded validation

* fix: preserve reopened approvals and declare fixture interfaces

* fix: isolate review artifacts and audit complete questions

* fix: match detector artifact permissions to configured storage

* fix: complete native permissions and review fixture workflows

* fix: order CEO review work and separate engineering guarantees

* fix: preserve native validation and separate review choices

* fix: clarify review decisions and judge complete report context

* fix: constrain review judgments and retain parse failures

* fix: compare each affected value before review decisions

* fix: make engineering review decisions and completion order explicit

* fix: give the complete Autoplan evaluation a bounded chain budget

* fix(cso): diagnose forbidden Docker endpoints before tool lookup

* fix(reviews): reconcile workflow contracts and generated artifacts after main integration

* fix(evals): migrate retained regressions to the native review harness

* fix(tests): close native harness and workflow integration regressions

* fix(evals): preserve complete permission context and native menu contracts

* fix(tests): capture synchronous command output without pipe drain stalls

* fix(reviews): clarify decision and completion ordering

* fix(reviews): separate decision readiness from final completion checks

* refactor(reviews): consolidate decision rules and completion branches

* fix(plan-eng-review): order preparation and clarify decision routing

* fix(plan-eng-review): restore size and question-format guard parity

* fix(plan-eng-review): clarify scope phases and blocked completion

* fix(plan-eng-review): unify review flow and report destination

* fix(plan-eng-review): define bootstrap and question stage ownership

* fix(plan-eng-review): clarify review structure and design lookup

* fix(plan-eng-review): render report examples and show saved decisions

* fix: consolidate Eng review decisions and select their evaluations

* test: cover overlapping terminal attachments and clean merged runner type

* fix: preserve Office Hours relationship closings during review updates

* fix: retain pasted review targets across slash invocations

* docs: preserve validation traces and correct release scope

* test: cover pasted targets in both review skills

* fix: validate report artifacts before recording success

* fix: redact source roots at CSO report boundaries

* fix: bind native Design questions before answering

* test: select report privacy and native recovery regressions

* test: bind rejection predicate in extracted observers

* fix: bind complete boxed native questions

* test: keep the Design UI fixture on native review

* fix: preserve review decisions and evaluation completion outcomes

* fix: clarify CEO approval and report completion order

* fix: align native review evaluation ownership and completion

* fix: bind review evaluators to native decisions and owned artifacts

* fix: validate review decisions against native outcomes

* fix: preserve review evidence and Autoplan phase handoffs

* test: bind review evidence to owned decisions and completion

* fix: retain owned native history across compaction

* fix(evals): validate current review decisions and setup choices

* fix: bind Autoplan reviews and phase completion to current amended input

* fix: reconcile native review evidence and close Autoplan phases

* test: recognize owned whole-candidate complexity decisions

* test: preserve report freshness for approved investigation handoffs

* fix: recognize scoped review findings and isolate dual voice fixtures

* fix: make review handoffs and question dispatch self-contained

* test: recognize complete CEO decisions and procedural pauses

* fix: bind current CEO comparison options and risk intervals

* test: bind engineering decisions and completion to owned evidence

* fix: publish Autoplan phase reports before continuing tools

* test: verify actual Autoplan dual-review dispatch evidence

* test: select dual review when shared evidence fixtures change

* fix: clarify plan review decisions and completion gates

* fix: make CEO review decisions and return paths explicit

* test: keep Autoplan prompt files inside attempt state

* test: preserve source whitespace across permission dialog wraps

* fix: publish Autoplan phase reports before continuing

* test: recognize current CEO comparisons and reject inactive records

* fix: reconcile engineering decision states before completion

* test: recognize complete Design decisions and reports

* test: verify current engineering decisions before navigation

* Recognize source-owned component reduction choices

* fix: recognize current CEO ledger and commitment grids

* test: supply RequestPolicy context to Eng count fixture

* fix: save complete engineering decisions before asking

* fix: bind Autoplan publication to the complete phase readback

* chore: prepare 1.87.5.0 reliability release

* fix: clarify engineering review completion and preserve log failures

* fix: bind CEO saved choices and current section ancestry

* fix(evals): bind review execution and completion evidence

* fix(plan-ceo-review): verify complete decisions before asking

* fix(evals): preserve complete engineering choice records

* fix(evals): preserve complete review outcomes and bounded fixtures

* fix(autoplan): publish phase reports before advancing

* fix(plan-ceo-review): validate option fields before asking

* fix(plan-eng-review): verify current decisions after answers

* fix(evals): bind review decisions and bound fixture scope

* fix(plan-ceo-review): verify decision rows and edit saved checkpoints

* fix(evals): bind review evidence and scope document lookup

* fix(plan-eng-review): update resolution state with its answer

* fix(reviews): preserve complete questions through dispatch

* fix(evals): recognize completed mode declarations

* fix(evals): define cache consistency at wrapper completion

* fix(evals): validate owned initial scope and completed review handoffs

* fix: assemble complete CEO decision fields before saving

* fix: authenticate automatic mode decisions without guessing selectors

* fix: bind engineering coverage to approved regression contracts

* fix(evals): supply review helpers to native Eng capture

* fix(plan-eng-review): preserve the full selected option scope

* fix(evals): recognize owned engineering seed and regression evidence

* fix(evals): bind engineering retry reports to native approvals

* docs: clarify release guarantees (v1.87.5.0)

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

* fix(evals): recognize owned engineering decisions and handoffs

* fix(evals): bind engineering decisions and completion evidence

* fix(tests): align review contracts and selection fixtures

* fix(skills): restore review prompt size limits

* fix(plan-eng-review): clarify review execution and completion

* fix(evals): preserve configured retries through all supervision layers

* Clarify Engineering decisions and report completion

* Keep native decision assertions within their source boundary

* fix: recognize owned engineering decisions and completed navigation

* fix: bind completed auto decisions to their current review

* fix: recognize explicit CEO source attribution

* fix: dispatch verified CEO decisions without recomposing fields

* test: expose existing execution deadlines to review actors

* fix: distinguish CEO decision records from incidental headings

* test: bind split-scope choices to the registered native actor

* test: connect reviewed regressions to required evaluation coverage

* Clarify CEO decision routing and completion stages

* test: expose existing section review deadlines to fixture actors

* test: recognize complete native CEO pacing inventories

* test: exclude answered history from current CEO payloads

* test: detect phase entry through owned skill HOME aliases

* test: validate native review completion and owned report permissions

* fix: make Autoplan close packets carry the parent handoff steps

* test: assess source-bound HOLD decisions within the existing deadline

* fix: keep CEO native decision fields under one formatting authority

* test: register integrated review and permission dependencies

* test: align native review adapters and finding coverage

Preserve explicit AUTO decisions, apply native single-select defaults, and bind complete cropped questions and report permissions to their owned requests. Require seeded review findings instead of crediting setup menus.

Keep captured failure controls and additive selection dependencies. The integrated candidate passed 3,099 focused tests across 65 files; affected paid validation remains required before publication.

* fix(autoplan): require phase reports before advancing

* fix(evals): bind setup and evidence to complete attempts

* fix(evals): bind native answers and pending writes to fixture scope

Preserve complete option rows when native descriptions wrap, retain current
owned Write arguments before journal publication, and keep engineering and
DX answers within their declared fixture interfaces. Add captured free
regressions without increasing model budgets or relaxing completion checks.

* fix(autoplan): verify phase reports across native tool paths

Guard owned methodology reads and reviewer dispatches, detect complete driver
loads through Bash, and distinguish report-only edits from implementation
changes. Follow authenticated native UUID ancestry when journal writes arrive
out of order and verify earlier native content for cached phase reads.

Keep current close acknowledgment and parent publication in order, require CEO
entry before later phases, and register captured failure regressions.

* fix(evals): honor native input and collection lifecycles

Match complete native Edit panes and truncated question borders, reject stderr close before EOF, and stop the CEO split fixture once its acknowledged scope decisions are collected. Keep semantic validation, process failures, report requirements, and absolute deadlines authoritative.

Add captured-event and real-process regressions with selection dependencies. Focused checks pass; final integrated paid and full-suite acceptance remain pending.

* fix(autoplan): retain native session ownership across directory changes

Recover missed native UUID ancestry through the existing strict graph while preserving ordinary event order and legacy scoping. Bind publication hooks to Claude's original project directory while retaining current cwd for requested file paths.

Captured public-event regressions, existing caller checks, and a pinned native CLI loopback verify both fixes. Preserve failed attempts and require fresh paid and final full-suite acceptance.

* docs: align evaluation limits and completion version

* fix(autoplan): allow authenticated phase reads during journal streaming

* fix(evals): bind clipped native questions and owned edit dialogs

* fix: preserve overlay retries and bounded cleanup

* fix: recognize owned planning preludes in native questions

* docs: explain overlay scheduling and cleanup guarantees

* fix: require fresh publication after Autoplan phase reruns

* Release gstack 1.87.6

* fix: preserve CI paths, process identity, and test deadlines

* fix: keep informational setup commands independent of install probes

* fix: clarify plan review decisions and bound source audit reports

* Fix remaining Windows identity and native path CI failures

* Clarify CEO review decision and reviewer-result routing

* test: accept no-install planner in retry supervision

* fix(ceo-review): make review decisions and report completion explicit

* perf(test): add fast PR gates, input-keyed judge reuse and isolated free shards

* fix(test): start isolated CEO smoke from its existing project plan

* fix(test): repair CI fixture races and preserve retry evidence

* fix(ceo-review): clarify approvals, depth and saved completion

---------

Co-authored-by: OpenAI Codex <noreply@openai.com>
2026-09-22 14:57:52 -04:00

493 lines
22 KiB
TypeScript

import { describe, test, expect, beforeAll, afterAll } from 'bun:test';
import { JUDGE_MS, CAPTURE_MS, CAPTURE_LONG_MS } from './helpers/eval-budgets';
import { runSkillTest } from './helpers/session-runner';
import {
ROOT, browseBin, runId, evalsEnabled,
describeIfSelected, testConcurrentIfSelected,
copyDirSync, setupBrowseShims, logCost, recordE2E,
createEvalCollector, finalizeEvalCollector,
} from './helpers/e2e-helpers';
import { spawnSync } from 'child_process';
import { randomUUID } from 'node:crypto';
import * as fs from 'fs';
import * as path from 'path';
import * as os from 'os';
import { extractSkillBody } from './helpers/skill-fixture';
import { createCoverageAuditFixture } from './fixtures/coverage-audit-fixture';
import { validateCoverageAudit, type CoverageFile } from './helpers/coverage-audit';
import { runRecordedOfficeHoursAttempt, OFFICE_HOURS_BUN_GRACE_MS } from './helpers/office-hours-attempt';
import { resolveEvalModel } from '../lib/eval-model';
const evalCollector = createEvalCollector('e2e');
// --- Document-Release skill E2E ---
describeIfSelected('Document-Release skill E2E', ['document-release'], () => {
let docReleaseDir: string;
beforeAll(() => {
docReleaseDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-doc-release-'));
// Copy document-release skill files
copyDirSync(path.join(ROOT, 'document-release'), path.join(docReleaseDir, 'document-release'));
// Init git repo with initial docs
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: docReleaseDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
// Create initial README with a features list
fs.writeFileSync(path.join(docReleaseDir, 'README.md'),
'# Test Project\n\n## Features\n\n- Feature A\n- Feature B\n\n## Install\n\n```bash\nnpm install\n```\n');
// Create initial CHANGELOG that must NOT be clobbered
fs.writeFileSync(path.join(docReleaseDir, 'CHANGELOG.md'),
'# Changelog\n\n## 1.0.0 — 2026-03-01\n\n- Initial release with Feature A and Feature B\n- Setup CI pipeline\n');
// Create VERSION file (already bumped)
fs.writeFileSync(path.join(docReleaseDir, 'VERSION'), '1.1.0\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial']);
// Create feature branch with a code change
run('git', ['checkout', '-b', 'feat/add-feature-c']);
fs.writeFileSync(path.join(docReleaseDir, 'feature-c.ts'), 'export function featureC() { return "C"; }\n');
fs.writeFileSync(path.join(docReleaseDir, 'VERSION'), '1.1.1\n');
fs.writeFileSync(path.join(docReleaseDir, 'CHANGELOG.md'),
'# Changelog\n\n## 1.1.1 — 2026-03-16\n\n- Added Feature C\n\n## 1.0.0 — 2026-03-01\n\n- Initial release with Feature A and Feature B\n- Setup CI pipeline\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'feat: add feature C']);
});
afterAll(() => {
try { fs.rmSync(docReleaseDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('document-release', async () => {
const result = await runSkillTest({
prompt: `Read the file document-release/SKILL.md for the document-release workflow instructions.
Run the /document-release workflow on this repo. The base branch is "main".
IMPORTANT:
- Do NOT use AskUserQuestion — auto-approve everything or skip if unsure.
- Do NOT push or create PRs (there is no remote).
- Do NOT run gh commands (no remote).
- Focus on updating README.md to reflect the new Feature C.
- Do NOT overwrite or regenerate CHANGELOG entries.
- Skip VERSION bump (it's already bumped).
- After editing, just commit the changes locally.`,
workingDirectory: docReleaseDir,
maxTurns: 30,
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Grep', 'Glob'],
// 300s, not 180s: a 30-turn multi-step doc workflow under 40-way
// in-shard CI concurrency timed out at exactly 180s on its final
// attempt twice on PR #2593 (rounds 4 and 13) while passing four
// other rounds — marginal at 180s, same contention story as
// review-dashboard-via and retro-base-branch. Outer bun timeout
// rises to 360s for headroom.
timeout: CAPTURE_MS,
testName: 'document-release',
runId,
});
logCost('/document-release', result);
// Read CHANGELOG to verify it was NOT clobbered
const changelog = fs.readFileSync(path.join(docReleaseDir, 'CHANGELOG.md'), 'utf-8');
const hasOriginalEntries = changelog.includes('Initial release with Feature A and Feature B')
&& changelog.includes('Setup CI pipeline')
&& changelog.includes('1.0.0');
if (!hasOriginalEntries) {
console.warn('CHANGELOG CLOBBERED — original entries missing!');
}
// Check if README was updated
const readme = fs.readFileSync(path.join(docReleaseDir, 'README.md'), 'utf-8');
const readmeUpdated = readme.includes('Feature C') || readme.includes('feature-c') || readme.includes('feature C');
const exitOk = ['success', 'error_max_turns'].includes(result.exitReason);
recordE2E(evalCollector, '/document-release', 'Document-Release skill E2E', result, {
passed: exitOk && hasOriginalEntries,
});
// Critical guardrail: CHANGELOG must not be clobbered
expect(hasOriginalEntries).toBe(true);
// Accept error_max_turns — thorough doc review is not a failure
expect(['success', 'error_max_turns']).toContain(result.exitReason);
// Informational: did it update README?
if (readmeUpdated) {
console.log('README updated to include Feature C');
} else {
console.warn('README was NOT updated — agent may not have found the feature');
}
}, CAPTURE_LONG_MS);
});
// --- Ship workflow with local bare remote ---
describeIfSelected('Ship workflow E2E', ['ship-local-workflow'], () => {
let shipWorkDir: string;
let shipRemoteDir: string;
beforeAll(() => {
shipRemoteDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ship-remote-'));
shipWorkDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-ship-work-'));
// Create bare remote
spawnSync('git', ['init', '--bare'], { cwd: shipRemoteDir, stdio: 'pipe' });
// Clone it as working repo
spawnSync('git', ['clone', shipRemoteDir, shipWorkDir], { stdio: 'pipe' });
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: shipWorkDir, stdio: 'pipe', timeout: 5000 });
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
// Initial commit on main
fs.writeFileSync(path.join(shipWorkDir, 'app.ts'), 'console.log("v1");\n');
fs.writeFileSync(path.join(shipWorkDir, 'VERSION'), '0.1.0.0\n');
fs.writeFileSync(path.join(shipWorkDir, 'CHANGELOG.md'), '# Changelog\n');
run('git', ['add', '.']);
run('git', ['commit', '-m', 'initial']);
run('git', ['push', '-u', 'origin', 'main']);
// Feature branch
run('git', ['checkout', '-b', 'feature/ship-test']);
fs.writeFileSync(path.join(shipWorkDir, 'app.ts'), 'console.log("v2");\n');
run('git', ['add', 'app.ts']);
run('git', ['commit', '-m', 'feat: update to v2']);
});
afterAll(() => {
try { fs.rmSync(shipWorkDir, { recursive: true, force: true }); } catch {}
try { fs.rmSync(shipRemoteDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('ship-local-workflow', async () => {
const result = await runSkillTest({
prompt: `You are in a git repo on branch feature/ship-test. Do these steps in order:
1. Read VERSION file and bump the last digit by 1 (e.g. 0.1.0.0 → 0.1.0.1). Write the new version back.
2. Add a CHANGELOG.md entry: "## [NEW_VERSION] - TODAY" with a bullet "- Ship test feature".
3. Stage all changes, commit with message "ship: vNEW_VERSION".
4. Push to origin: git push origin feature/ship-test`,
workingDirectory: shipWorkDir,
maxTurns: 8,
timeout: JUDGE_MS,
testName: 'ship-local-workflow',
runId,
});
logCost('/ship local workflow', result);
// Check push succeeded — verify the feature branch exists on the bare remote
const branchCheck = spawnSync('git', ['branch', '--list', 'feature/ship-test'], { cwd: shipRemoteDir, stdio: 'pipe', timeout: 30_000 });
const branchExists = branchCheck.stdout.toString().trim().length > 0;
// Check VERSION was bumped locally (even if push failed, this shows the LLM did the work)
const versionContent = fs.existsSync(path.join(shipWorkDir, 'VERSION'))
? fs.readFileSync(path.join(shipWorkDir, 'VERSION'), 'utf-8').trim() : '';
const versionBumped = versionContent !== '0.1.0.0';
recordE2E(evalCollector, '/ship local workflow', 'Ship workflow E2E', result, {
passed: branchExists && versionBumped && ['success', 'error_max_turns'].includes(result.exitReason),
});
expect(['success', 'error_max_turns']).toContain(result.exitReason);
expect(branchExists).toBe(true);
expect(versionBumped).toBe(true);
console.log(`Branch pushed: ${branchExists}, VERSION: ${versionContent}, bumped: ${versionBumped}`);
}, CAPTURE_MS);
});
// setup-cookies-detect REMOVED: The cookie-import-browser module has 30+ thorough
// unit tests in browse/test/cookie-import-browser.test.ts (decryption, profile
// detection, error handling, path traversal). The E2E just tested LLM instruction-
// following ("write a file saying no browsers") on a CI box with no browsers.
// --- gstack-upgrade E2E ---
describeIfSelected('gstack-upgrade E2E', ['gstack-upgrade-happy-path'], () => {
let upgradeDir: string;
let remoteDir: string;
beforeAll(() => {
upgradeDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-upgrade-'));
remoteDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-remote-'));
const run = (cmd: string, args: string[], cwd: string) =>
spawnSync(cmd, args, { cwd, stdio: 'pipe', timeout: 5000 });
// Init the "project" repo
run('git', ['init'], upgradeDir);
run('git', ['config', 'user.email', 'test@test.com'], upgradeDir);
run('git', ['config', 'user.name', 'Test'], upgradeDir);
// Create mock gstack install directory (local-git type)
const mockGstack = path.join(upgradeDir, '.claude', 'skills', 'gstack');
fs.mkdirSync(mockGstack, { recursive: true });
// Init as a git repo
run('git', ['init'], mockGstack);
run('git', ['config', 'user.email', 'test@test.com'], mockGstack);
run('git', ['config', 'user.name', 'Test'], mockGstack);
// Create bare remote
run('git', ['init', '--bare'], remoteDir);
run('git', ['remote', 'add', 'origin', remoteDir], mockGstack);
// Write old version files
fs.writeFileSync(path.join(mockGstack, 'VERSION'), '0.5.0\n');
fs.writeFileSync(path.join(mockGstack, 'CHANGELOG.md'),
'# Changelog\n\n## 0.5.0 — 2026-03-01\n\n- Initial release\n');
fs.writeFileSync(path.join(mockGstack, 'setup'),
'#!/bin/bash\necho "Setup completed"\n', { mode: 0o755 });
// Initial commit + push
run('git', ['add', '.'], mockGstack);
run('git', ['commit', '-m', 'initial'], mockGstack);
run('git', ['push', '-u', 'origin', 'HEAD:main'], mockGstack);
// Create new version (simulate upstream release)
fs.writeFileSync(path.join(mockGstack, 'VERSION'), '0.6.0\n');
fs.writeFileSync(path.join(mockGstack, 'CHANGELOG.md'),
'# Changelog\n\n## 0.6.0 — 2026-03-15\n\n- New feature: interactive design review\n- Fix: snapshot flag validation\n\n## 0.5.0 — 2026-03-01\n\n- Initial release\n');
run('git', ['add', '.'], mockGstack);
run('git', ['commit', '-m', 'release 0.6.0'], mockGstack);
run('git', ['push', 'origin', 'HEAD:main'], mockGstack);
// Reset working copy back to old version
run('git', ['reset', '--hard', 'HEAD~1'], mockGstack);
// Copy gstack-upgrade skill
fs.mkdirSync(path.join(upgradeDir, 'gstack-upgrade'), { recursive: true });
fs.copyFileSync(
path.join(ROOT, 'gstack-upgrade', 'SKILL.md'),
path.join(upgradeDir, 'gstack-upgrade', 'SKILL.md'),
);
// Commit so git repo is clean
run('git', ['add', '.'], upgradeDir);
run('git', ['commit', '-m', 'initial project'], upgradeDir);
});
afterAll(() => {
try { fs.rmSync(upgradeDir, { recursive: true, force: true }); } catch {}
try { fs.rmSync(remoteDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('gstack-upgrade-happy-path', async () => {
const mockGstack = path.join(upgradeDir, '.claude', 'skills', 'gstack');
const result = await runSkillTest({
prompt: `Read gstack-upgrade/SKILL.md for the upgrade workflow.
You are running /gstack-upgrade standalone. The gstack installation is at ./.claude/skills/gstack (local-git type — it has a .git directory with an origin remote).
Current version: 0.5.0. A new version 0.6.0 is available on origin/main.
Follow the standalone upgrade flow:
1. Detect install type (local-git)
2. Run git fetch origin && git reset --hard origin/main in the install directory
3. Run the setup script
4. Show what's new from CHANGELOG
Skip any AskUserQuestion calls — auto-approve the upgrade. Write a summary of what you did to stdout.
IMPORTANT: The install directory is at ./.claude/skills/gstack — use that exact path.`,
workingDirectory: upgradeDir,
maxTurns: 20,
timeout: CAPTURE_MS,
testName: 'gstack-upgrade-happy-path',
runId,
});
logCost('/gstack-upgrade happy path', result);
// Check that the version was updated
const versionAfter = fs.readFileSync(path.join(mockGstack, 'VERSION'), 'utf-8').trim();
const output = result.output || '';
const mentionsUpgrade = output.toLowerCase().includes('0.6.0') ||
output.toLowerCase().includes('upgrade') ||
output.toLowerCase().includes('updated');
recordE2E(evalCollector, '/gstack-upgrade happy path', 'gstack-upgrade E2E', result, {
passed: versionAfter === '0.6.0' && ['success', 'error_max_turns'].includes(result.exitReason),
});
expect(['success', 'error_max_turns']).toContain(result.exitReason);
expect(versionAfter).toBe('0.6.0');
}, CAPTURE_MS);
});
// --- Test Coverage Audit E2E ---
describeIfSelected('Test Coverage Audit E2E', ['ship-coverage-audit'], () => {
testConcurrentIfSelected('ship-coverage-audit', async () => {
let coverageDir: string | undefined;
let files: CoverageFile[] = [];
try {
await runRecordedOfficeHoursAttempt({
collector: evalCollector, name: 'ship-coverage-audit', suite: 'Test Coverage Audit E2E',
model: process.env.EVALS_MODEL ?? resolveEvalModel('capture'),
// Keep the original 300s Bun cap and 120s runner work budget, including
// the existing helper's bounded abort/drain/record reserve in that cap.
budgetMs: CAPTURE_MS - OFFICE_HOURS_BUN_GRACE_MS,
run: async signal => {
coverageDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-coverage-'));
copyDirSync(path.join(ROOT, 'ship'), path.join(coverageDir, 'ship'));
copyDirSync(path.join(ROOT, 'review'), path.join(coverageDir, 'review'));
fs.writeFileSync(path.join(coverageDir, 'ship', 'SKILL.md'), extractSkillBody(path.join(ROOT, 'ship')));
createCoverageAuditFixture(coverageDir);
files = ['src/billing.ts', 'test/billing.test.ts'].map(relative => {
const file = path.join(coverageDir!, relative);
// The complete contents and fresh marker must occur in successful
// native tool output; the prompt does not disclose the marker.
fs.appendFileSync(file, `\n// coverage-read-evidence: ${randomUUID()}\n`);
return { path: file, content: fs.readFileSync(file, 'utf8') };
});
return runSkillTest({
prompt: `Read ship/SKILL.md and ship/sections/test-coverage.md for the current ship workflow.
You are on the feature/billing branch. The base branch is main.
This is a test project — there is no remote, no PR to create.
Run ONLY Step 7 (Test Coverage Audit), applying the section's audit instructions directly
to the two supplied billing functions. This is a targeted audit with no branch diff.
Run the audit inline; do not dispatch subagents.
Skip all other steps (tests, evals, review, version, changelog, commit, push, PR).
The source code is in ${coverageDir}/src/billing.ts.
Existing tests are in ${coverageDir}/test/billing.test.ts.
Produce the ASCII coverage diagram showing which code paths are tested and which have gaps.
Output the diagram directly, name both billing functions, and include a coverage summary.
Do not generate tests or modify the supplied source or tests.`,
workingDirectory: coverageDir,
maxTurns: 15,
allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
timeout: JUDGE_MS,
testName: 'ship-coverage-audit',
runId, signal,
});
},
validate: result => {
logCost('/ship coverage audit', result);
validateCoverageAudit(result, coverageDir!, files);
},
});
} finally {
// Native retries retain this case's original registration and own fresh
// fixtures, so each attempt must prove its own source and test reads.
if (coverageDir) try { fs.rmSync(coverageDir, { recursive: true, force: true }); } catch {}
}
}, CAPTURE_MS);
});
// --- Codex skill E2E ---
describeIfSelected('Codex skill E2E', ['codex-review'], () => {
let codexDir: string;
beforeAll(() => {
codexDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-codex-'));
const run = (cmd: string, args: string[]) =>
spawnSync(cmd, args, { cwd: codexDir, stdio: 'pipe', timeout: 5000 });
run('git', ['init', '-b', 'main']);
run('git', ['config', 'user.email', 'test@test.com']);
run('git', ['config', 'user.name', 'Test']);
// Commit a clean base on main
fs.writeFileSync(path.join(codexDir, 'app.rb'), '# clean base\nclass App\nend\n');
run('git', ['add', 'app.rb']);
run('git', ['commit', '-m', 'initial commit']);
// Create feature branch with vulnerable code (reuse review fixture)
run('git', ['checkout', '-b', 'feature/add-vuln']);
const vulnContent = fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'review-eval-vuln.rb'), 'utf-8');
fs.writeFileSync(path.join(codexDir, 'user_controller.rb'), vulnContent);
run('git', ['add', 'user_controller.rb']);
run('git', ['commit', '-m', 'add vulnerable controller']);
// Extract only the review-relevant content (CLAUDE.md: "extract, don't copy").
// The codex skill is carved (T9): the skeleton carries setup + dispatch and
// STOP-points to codex/sections/*-mode.md. Build the fixture from the
// skeleton's setup slices plus the review-mode section body, SKIPPING the
// Section index and STOP pointers — their install paths don't exist in this
// temp fixture dir and would burn agent turns on failed Reads.
const full = fs.readFileSync(path.join(ROOT, 'codex', 'SKILL.md'), 'utf-8');
const introStart = full.indexOf('# /codex — Multi-AI Second Opinion');
const introEnd = full.indexOf('## Section index', introStart);
const stepsStart = full.indexOf('## Step 0.4', introStart);
const stepsEnd = full.indexOf('> **STOP.**', stepsStart);
expect(introStart).toBeGreaterThan(-1);
expect(introEnd).toBeGreaterThan(introStart);
expect(stepsStart).toBeGreaterThan(introEnd);
expect(stepsEnd).toBeGreaterThan(stepsStart);
const reviewMode = fs.readFileSync(
path.join(ROOT, 'codex', 'sections', 'review-mode.md'),
'utf-8',
);
expect(reviewMode).toContain('## Step 2A: Review Mode'); // non-empty, right section
const reviewSection = [
full.slice(introStart, introEnd),
full.slice(stepsStart, stepsEnd),
reviewMode,
].join('\n');
fs.writeFileSync(path.join(codexDir, 'codex-SKILL.md'), reviewSection);
});
afterAll(() => {
try { fs.rmSync(codexDir, { recursive: true, force: true }); } catch {}
});
testConcurrentIfSelected('codex-review', async () => {
// Check codex is available — skip if not installed
const codexCheck = spawnSync('which', ['codex'], { stdio: 'pipe', timeout: 3000 });
if (codexCheck.status !== 0) {
console.warn('codex CLI not installed — skipping E2E test');
return;
}
const result = await runSkillTest({
prompt: `You are in a git repo on branch feature/add-vuln with changes against main.
Read codex-SKILL.md for the /codex review instructions (it's short — ~120 lines).
Follow those instructions to run codex review against the diff on this branch.
Write the full output (including the GATE verdict) to ${codexDir}/codex-output.md`,
workingDirectory: codexDir,
maxTurns: 25,
timeout: CAPTURE_MS,
testName: 'codex-review',
runId,
model: 'claude-opus-4-7',
});
logCost('/codex review', result);
recordE2E(evalCollector, '/codex review', 'Codex skill E2E', result);
expect(result.exitReason).toBe('success');
// Check that output file was created with review content
const outputPath = path.join(codexDir, 'codex-output.md');
if (fs.existsSync(outputPath)) {
const output = fs.readFileSync(outputPath, 'utf-8');
// Should contain the CODEX SAYS header or GATE verdict
const hasCodexOutput = output.includes('CODEX') || output.includes('GATE') || output.includes('codex');
expect(hasCodexOutput).toBe(true);
}
}, CAPTURE_LONG_MS);
});
// Module-level afterAll — finalize eval collector after all tests complete
afterAll(async () => {
await finalizeEvalCollector(evalCollector);
});