mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-06 17:04:27 +01:00
* fix(make-pdf,design): real TOC page numbers and anchors; design models move to gpt-5.5 + gpt-image-2 (#2903, #2807) * ci: pin every action to a SHA, Scorecard, checksummed Bun, scoped Codex CLI in the CI image, macOS named-regressions job (#1948, #1706, #1997) * fix(cso,browse): Windows/macOS lease identity, retention skips bad runs, truthful 'not assessed' reports, env.kv false positive, Windows browse spawn fixes (#2894, #2912, #2048, #2637, #2805) * fix(outside-voice): one Codex model precedence for probe and dispatch, bounded timeouts with KILL escalation, probe cache identity, guarded mktemp, skills hidden in nested Codex (#2776, #2914, #2787, #2881, #2847) * feat(setup): install registry, ./setup --status, staged activation, per-scope migrations, host tiers and conformance kit, OpenCode/Hermes fixes, Copilot CLI (experimental), disabled_skills, slimmer CLAUDE.md (#1925, #2879, #2347, #2338, #2626, #2629, #2825, #2015, #393, #1206, #2096) Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com> * fix(preamble): skills start in worktree-isolated Claude Code sessions — one literal skill-start line, context-recovery helper, no eval in skill blocks, $N token tripwire, honest plan-mode precedence (#2763, #2896, #2851) * fix(setup): per-install renders for renamed, vendored and custom-config installs, space-safe alias roots, per-host /cso launcher path (#1882, #2906) * test: free tests never write the real HOME (home-write tripwire), no orphaned browse daemons, symlinked-TMPDIR (macOS) fixes, gbrain-on-PATH isolation (#2895, #2816, #2829, #2841, #2982, #2911, #2909, #2908, #2910) * chore: integrate wave follow-ups — regenerate all hosts, README model docs, TODOS, touchfiles, duration seeds, Bun 1.3 telemetry test fix, replay fixtures pinned to their recorded bytes * v1.91.14.0: release metadata * test(browse): group-kill cleanup falls back to the leader when macOS returns EPERM for a live group * ci: Codex login steps run under bash (the CI container's default sh rejects pipefail) * fix: full-suite repairs — private state roots for 7 real-HOME writers, truthful home-guard attribution with --attribute-home, gstack-paths shim in ship-hook fixtures, Copilot in team-init probes, test-of-test detector, cookie review fixture pinned to the approved excerpt * fix(windows): LF for Dockerfiles, normalized home-guard exclusions, path.relative fixture containment, ship push test spawn timeouts * test(design-detect): widen the whole-scan budget test's timing margins so a loaded macOS runner can't time out the single-batch call * fix(evals): qa protocol names defined for the judge, async PTY judge so overlapping sessions keep their cleanup deadline, bws setup cases use the standard JUDGE_MS tier * test(pty): the non-blocking judge case is POSIX-only (its fake judge is a shebang script, like the PTY harness it covers) * test(evals): ship-coverage-audit names absolute skill paths, uses Read, and skips the Step 7 artifact nothing consumes (removes the mechanism behind 3 of 4 historical timeouts) * test: deflake terminal-agent concurrent startup (write the placeholder record before spawning, like the product) and qa-evidence resumed pipe (barrier on a full high-water mark instead of a sleep) * fix(design): daemon log stream handles open errors instead of crashing the daemon; shutdown test awaits the stubbed exit * test(evals): skillify checks the product's resolved state root (no GSTACK_HOME bypass), negative cases check every root; tpa shims live outside the agent's cwd and answer consistently * test(evals): coverage-audit detector splits parallel columns at │ rails and [+] groups; coverage prompts name absolute skill paths; TODOs from the gate eval census * fix(plan-eng-review): scope gate always sends the menu (no headless 'Scope pending' exit); PTY harness ends idle turn-ends and API-error panels promptly with a precise diagnostic * test(evals): one position-bound coverage-read rule credits read-only && chains (labels, context ranges, git displays in either order) and still rejects forged output * fix(ship): documentation section has one saved source inserted by cat (never retyped); spawned-marker evidence is the child output; refreshed codex/factory ship goldens * test(docsync): the byte-exact insert positive is POSIX-only (the bash-command observer refuses backslash paths by design) * test(evals): plan-design-with-ui focus-title rule accepts the comma-less 'dimensions or focus' wording (replayed on the captured CI run, negative controls kept) * fix(qa-callers): exploratory preflight says the scope/method Reads come after exploratory.md; design-review scan check credits an executed scan proven by one engine run over the changed files --------- Co-authored-by: Andrey Esipov <61357035+andrey-esipov@users.noreply.github.com> Co-authored-by: Matthew Williams <5863886+ridermw@users.noreply.github.com> Co-authored-by: Rocky Wu <92764750+lolisaigao1234@users.noreply.github.com>
147 lines
8.0 KiB
TypeScript
147 lines
8.0 KiB
TypeScript
import { afterEach, describe, expect, spyOn, test } from 'bun:test';
|
|
import * as fs from 'node:fs';
|
|
import * as os from 'node:os';
|
|
import * as path from 'node:path';
|
|
import { attributeFreeHomeWriters, diffFreeHome, guardFreeHome, snapshotFreeHome } from '../scripts/lib/free-home-guard';
|
|
import { runFreeShard } from '../scripts/test-free-shards';
|
|
|
|
const homes: string[] = [];
|
|
afterEach(() => { for (const home of homes.splice(0)) fs.rmSync(home, { recursive: true, force: true }); });
|
|
|
|
function fakeHome(): string {
|
|
const home = fs.mkdtempSync(path.join(os.tmpdir(), 'free-home-guard-'));
|
|
homes.push(home);
|
|
for (const dir of ['.gstack/security', '.claude/skills', '.claude/projects/p', '.codex/skills', '.agents/skills', '.config/gstack']) {
|
|
fs.mkdirSync(path.join(home, dir), { recursive: true });
|
|
}
|
|
fs.writeFileSync(path.join(home, '.gstack/.last-setup-version'), '1.0.0\n');
|
|
fs.writeFileSync(path.join(home, '.claude/projects/p/session.jsonl'), '{}\n');
|
|
return home;
|
|
}
|
|
|
|
const bump = (file: string) => {
|
|
const later = new Date(Date.now() + 5_000);
|
|
fs.utimesSync(file, later, later);
|
|
};
|
|
|
|
describe('free-suite home-write tripwire (#2895)', () => {
|
|
test.skipIf(process.platform === 'win32')('names install and state writes on every watched surface', () => {
|
|
const home = fakeHome();
|
|
const before = snapshotFreeHome(home);
|
|
fs.writeFileSync(path.join(home, '.gstack/.last-setup-version'), '9.9.9\n');
|
|
bump(path.join(home, '.gstack/.last-setup-version'));
|
|
fs.appendFileSync(path.join(home, '.gstack/security/prepush-skip.jsonl'), '{"reason":"env-skip"}\n');
|
|
fs.symlinkSync(path.join(home, 'checkout'), path.join(home, '.claude/skills/gstack'));
|
|
fs.mkdirSync(path.join(home, '.codex/skills/gstack-qa'));
|
|
fs.writeFileSync(path.join(home, '.agents/skills/marker'), 'x');
|
|
fs.writeFileSync(path.join(home, '.config/gstack/config.yaml'), 'a: b\n');
|
|
expect(diffFreeHome(before, snapshotFreeHome(home)).map(entry => entry.split(path.sep).join('/'))).toEqual([
|
|
'.agents/skills/marker',
|
|
'.claude/skills/gstack',
|
|
'.codex/skills/gstack-qa',
|
|
'.config/gstack/config.yaml',
|
|
'.gstack/.last-setup-version',
|
|
'.gstack/security/prepush-skip.jsonl',
|
|
]);
|
|
});
|
|
|
|
test('ignores live session logs and directory-only mtime churn', () => {
|
|
const home = fakeHome();
|
|
const before = snapshotFreeHome(home);
|
|
fs.appendFileSync(path.join(home, '.claude/projects/p/session.jsonl'), '{"more":true}\n');
|
|
fs.writeFileSync(path.join(home, '.claude/history.jsonl'), 'line\n');
|
|
fs.writeFileSync(path.join(home, '.claude/.tmp-write'), 'x');
|
|
fs.rmSync(path.join(home, '.claude/.tmp-write'));
|
|
expect(diffFreeHome(before, snapshotFreeHome(home))).toEqual([]);
|
|
});
|
|
|
|
test.skipIf(process.platform === 'win32')('a removed entry and a retargeted link count as changes', () => {
|
|
const home = fakeHome();
|
|
fs.symlinkSync('/one', path.join(home, '.claude/skills/link'));
|
|
const before = snapshotFreeHome(home);
|
|
fs.rmSync(path.join(home, '.gstack/.last-setup-version'));
|
|
fs.rmSync(path.join(home, '.claude/skills/link'));
|
|
fs.symlinkSync('/two', path.join(home, '.claude/skills/link'));
|
|
expect(diffFreeHome(before, snapshotFreeHome(home)).map(entry => entry.split(path.sep).join('/')))
|
|
.toEqual(['.claude/skills/link', '.gstack/.last-setup-version']);
|
|
});
|
|
|
|
test('the guard reports nothing for an untouched home and names the shard files otherwise', () => {
|
|
const home = fakeHome();
|
|
expect(guardFreeHome(['test/a.test.ts'], { HOME: home }).verify()).toBeNull();
|
|
const guard = guardFreeHome(['test/a.test.ts', 'test/b.test.ts'], { HOME: home });
|
|
fs.writeFileSync(path.join(home, '.gstack/.last-setup-version'), '2.0.0\n');
|
|
bump(path.join(home, '.gstack/.last-setup-version'));
|
|
const failure = guard.verify();
|
|
expect(failure).toContain('~/.gstack/.last-setup-version');
|
|
expect(failure).toContain('Shard files: test/a.test.ts, test/b.test.ts');
|
|
expect(failure).toContain('only');
|
|
});
|
|
|
|
test('a concurrent phase guard names no shard and points at attribution', () => {
|
|
const home = fakeHome();
|
|
const guard = guardFreeHome(['test/a.test.ts', 'test/b.test.ts'], { HOME: home }, { kind: 'concurrent', shards: 3 });
|
|
fs.writeFileSync(path.join(home, '.gstack/security/egress.jsonl'), '{}\n');
|
|
const failure = guard.verify();
|
|
expect(failure).toContain('~/.gstack/security/egress.jsonl');
|
|
expect(failure).toContain('while 3 shards ran concurrently');
|
|
expect(failure).toContain('--attribute-home');
|
|
expect(failure).not.toContain('test/a.test.ts');
|
|
});
|
|
|
|
test.skipIf(process.platform === 'win32')('attribution runs each file alone in a private HOME and names only the writer', async () => {
|
|
const home = fakeHome();
|
|
const before = snapshotFreeHome(home);
|
|
const writer = `require('fs').mkdirSync(require('path').join(process.env.HOME, '.gstack', 'security'), { recursive: true });`
|
|
+ `require('fs').writeFileSync(require('path').join(process.env.HOME, '.gstack', 'security', 'attempts.jsonl'), '{}\\n');`
|
|
+ `console.log('Ran 1 tests across 1 files. [1.00ms]')`;
|
|
const clean = `console.log('Ran 1 tests across 1 files. [1.00ms]')`;
|
|
const errors: string[] = [];
|
|
const spy = spyOn(console, 'error').mockImplementation((...args: unknown[]) => { errors.push(args.join(' ')); });
|
|
const logSpy = spyOn(console, 'log').mockImplementation(() => {});
|
|
try {
|
|
const exitCode = await attributeFreeHomeWriters(['test/clean.test.ts', 'test/writer.test.ts'], [], 2, (file, index, homeGuard) =>
|
|
runFreeShard([file], index + 1, 2, { env: { ...process.env, HOME: home }, quiet: true, log: () => {}, homeGuard,
|
|
logFilePath: path.join(home, `${index}.log`),
|
|
commandFor: () => ({ command: process.execPath, args: ['-e', file.includes('writer') ? writer : clean] }) }));
|
|
expect(exitCode).toBe(1);
|
|
const verdicts = errors.filter(line => line.startsWith('[test:free] ✗ '));
|
|
expect(verdicts).toHaveLength(1);
|
|
expect(verdicts[0]).toContain('test/writer.test.ts wrote its private HOME');
|
|
expect(verdicts[0]).toContain('~/.gstack/security/attempts.jsonl');
|
|
expect(diffFreeHome(before, snapshotFreeHome(home))).toEqual([]);
|
|
} finally {
|
|
spy.mockRestore();
|
|
logSpy.mockRestore();
|
|
for (const retained of errors.flatMap(line => /retained (\S+)$/.exec(line)?.[1] ?? [])) {
|
|
if (/^gstack-free-shard-/.test(path.basename(retained))) fs.rmSync(retained, { recursive: true, force: true });
|
|
}
|
|
}
|
|
});
|
|
|
|
test.skipIf(process.platform === 'win32')('a free shard that writes the real home fails and names its files', async () => {
|
|
const home = fakeHome();
|
|
const writer = `require('fs').writeFileSync(require('path').join(process.env.HOME, '.gstack', '.last-setup-version'), '7.7.7\\n');`
|
|
+ `console.log('Ran 1 tests across 1 files. [1.00ms]')`;
|
|
const clean = `console.log('Ran 1 tests across 1 files. [1.00ms]')`;
|
|
const errors: string[] = [];
|
|
const spy = spyOn(console, 'error').mockImplementation((...args: unknown[]) => { errors.push(args.join(' ')); });
|
|
try {
|
|
const options = (script: string) => ({ env: { ...process.env, HOME: home }, quiet: true, log: () => {},
|
|
logFilePath: path.join(home, `${script === clean ? 'clean' : 'writer'}.log`),
|
|
commandFor: () => ({ command: process.execPath, args: ['-e', script] }) });
|
|
expect((await runFreeShard(['test/clean.test.ts'], 1, 2, options(clean))).status).toBe('passed');
|
|
const outcome = await runFreeShard(['test/writer.test.ts'], 2, 2, options(writer));
|
|
expect(outcome.status).toBe('failed');
|
|
expect(outcome.unattributedFailures).toBeGreaterThan(0);
|
|
expect(errors.join('\n')).toContain('~/.gstack/.last-setup-version');
|
|
expect(errors.join('\n')).toContain('Shard files: test/writer.test.ts');
|
|
} finally {
|
|
spy.mockRestore();
|
|
for (const retained of errors.flatMap(line => /retained (\S+)$/.exec(line)?.[1] ?? [])) {
|
|
if (/^gstack-free-shard-/.test(path.basename(retained))) fs.rmSync(retained, { recursive: true, force: true });
|
|
}
|
|
}
|
|
});
|
|
});
|