mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 05:56:37 +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>
79 lines
3.7 KiB
TypeScript
79 lines
3.7 KiB
TypeScript
/**
|
|
* Resolver failure is fail-stop (W1). With bin/gstack-state-root.sh removed
|
|
* from an install, a real bash block copied from a generated SKILL.md and a
|
|
* migrated executable both stop with the reinstall message, and nothing is
|
|
* written outside the test's temp root.
|
|
*/
|
|
import { describe, test, expect } from 'bun:test';
|
|
import { spawnSync } from 'child_process';
|
|
import * as fs from 'fs';
|
|
import * as os from 'os';
|
|
import * as path from 'path';
|
|
import { resolveStateRoot } from '../lib/state-root';
|
|
|
|
const ROOT = path.resolve(import.meta.dir, '..');
|
|
|
|
/** The Eureka ```bash block of a generated SKILL.md: it resolves the state root through gstack-paths. */
|
|
function eurekaBlock(): string {
|
|
const md = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
|
|
const start = md.indexOf('**Eureka:**');
|
|
const open = md.indexOf('```bash\n', start) + '```bash\n'.length;
|
|
return md.slice(open, md.indexOf('\n```', open));
|
|
}
|
|
|
|
/** Every path under dir, except a host git wrapper's own log dir (not gstack's). */
|
|
function listTree(dir: string): string[] {
|
|
const out: string[] = [];
|
|
for (const e of fs.readdirSync(dir, { withFileTypes: true })) {
|
|
if (e.name === '.capy') continue;
|
|
const p = path.join(dir, e.name);
|
|
out.push(p);
|
|
if (e.isDirectory() && !e.isSymbolicLink()) out.push(...listTree(p));
|
|
}
|
|
return out;
|
|
}
|
|
|
|
describe('state-root resolver failure', () => {
|
|
test('a generated SKILL.md block and a migrated bin stop with the reinstall message when the twin is missing', () => {
|
|
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-resolver-fail-'));
|
|
try {
|
|
const home = path.join(tmp, 'home');
|
|
const bin = path.join(home, '.claude', 'skills', 'gstack', 'bin');
|
|
const cwd = path.join(tmp, 'cwd');
|
|
fs.mkdirSync(bin, { recursive: true });
|
|
fs.mkdirSync(cwd);
|
|
for (const b of ['gstack-paths', 'gstack-slug', 'gstack-config', 'gstack-context-recovery']) {
|
|
fs.copyFileSync(path.join(ROOT, 'bin', b), path.join(bin, b));
|
|
fs.chmodSync(path.join(bin, b), 0o755);
|
|
}
|
|
const env = {
|
|
PATH: process.env.PATH ?? '', HOME: home, TMPDIR: path.join(tmp, 'tmp'),
|
|
GSTACK_HOME: '', GSTACK_STATE_ROOT: '', GSTACK_STATE_DIR: '', CLAUDE_PLUGIN_DATA: '',
|
|
};
|
|
expect(resolveStateRoot(env)).toBe(`${home}/.gstack`);
|
|
const before = listTree(tmp).sort();
|
|
|
|
const block = eurekaBlock();
|
|
expect(block).toContain('GSTACK_STATE_ROOT=$(~/.claude/skills/gstack/bin/gstack-paths --get GSTACK_STATE_ROOT); : "${GSTACK_STATE_ROOT:?gstack-paths failed; reinstall with ./setup or /gstack-upgrade}"');
|
|
const skill = spawnSync('bash', ['-c', block + '\necho REACHED_END'], { cwd, env, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(skill.status).not.toBe(0);
|
|
expect(skill.stderr).toContain('gstack-paths failed; reinstall with ./setup or /gstack-upgrade');
|
|
expect(skill.stdout).not.toContain('REACHED_END');
|
|
|
|
const recovery = spawnSync('bash', [path.join(bin, 'gstack-context-recovery')], { cwd, env, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(recovery.status).toBe(1);
|
|
expect(recovery.stdout).toBe('');
|
|
expect(recovery.stderr).toContain('reinstall with ./setup or /gstack-upgrade');
|
|
|
|
const config = spawnSync('bash', [path.join(bin, 'gstack-config'), 'set', 'telemetry', 'off'], { cwd, env, encoding: 'utf-8', timeout: 30_000 });
|
|
expect(config.status).toBe(1);
|
|
expect(config.stderr).toContain('cannot resolve the gstack state root');
|
|
expect(config.stderr).toContain('reinstall with ./setup or /gstack-upgrade');
|
|
|
|
expect(listTree(tmp).sort()).toEqual(before);
|
|
} finally {
|
|
fs.rmSync(tmp, { recursive: true, force: true });
|
|
}
|
|
});
|
|
});
|