mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-31 22:14:25 +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>
168 lines
8.1 KiB
TypeScript
168 lines
8.1 KiB
TypeScript
/**
|
|
* Static tripwire for #1835: child spawns reachable on Windows must pass
|
|
* windowsHide, or every daemon relaunch / taskkill / icacls / powershell
|
|
* invocation flashes a black console window (and can steal focus).
|
|
*
|
|
* Source-level, same style as server-auth.test.ts / cdp-session-cleanup.test.ts:
|
|
* cheap, deterministic, runs on every platform.
|
|
*/
|
|
|
|
import { describe, expect, test } from 'bun:test';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
|
|
const SRC = (f: string) => fs.readFileSync(path.join(import.meta.dir, '../src', f), 'utf-8');
|
|
|
|
/** Every occurrence of `needle` in `src` must have `windowsHide` within the
|
|
* next `window` chars (the spawn's options object). */
|
|
function expectHideNearEvery(src: string, needle: string, window = 400): void {
|
|
let idx = src.indexOf(needle);
|
|
expect(idx).toBeGreaterThanOrEqual(0);
|
|
while (idx !== -1) {
|
|
const slice = src.slice(idx, idx + window);
|
|
expect(slice).toMatch(/windowsHide:\s*true/);
|
|
idx = src.indexOf(needle, idx + needle.length);
|
|
}
|
|
}
|
|
|
|
describe('windowsHide on Windows-reachable spawns (#1835)', () => {
|
|
test('daemon launch paths in cli.ts pass windowsHide', () => {
|
|
const cli = SRC('cli.ts');
|
|
// Installed path: node -e launcher — both the outer spawnSync and the
|
|
// inner detached daemon spawn (inside the launcher code string).
|
|
expect(cli).toContain('detached:true,windowsHide:true');
|
|
expectHideNearEvery(cli, "'-e', launcherCode]");
|
|
// Dev fallback: detached bun spawn.
|
|
expectHideNearEvery(cli, "nodeSpawn('bun'");
|
|
// taskkill (killServer).
|
|
expectHideNearEvery(cli, "'taskkill'");
|
|
});
|
|
|
|
test('Windows-only process probes pass windowsHide', () => {
|
|
// isProcessAlive no longer spawns anything (signal-0 on every platform,
|
|
// #1952) — process-liveness-windows.test.ts pins that it stays
|
|
// subprocess-free, which is stronger than hiding a window.
|
|
const cookie = SRC('cookie-import-browser.ts');
|
|
expectHideNearEvery(cookie, "'powershell'");
|
|
expect(cookie).not.toContain("'tasklist'");
|
|
expectHideNearEvery(SRC('cookie-import-native.ts'), 'spawn(bunExecutable');
|
|
const worker = SRC('cookie-import-native-worker.ts');
|
|
expectHideNearEvery(worker, 'spawn(process.execPath');
|
|
expectHideNearEvery(worker, 'spawn(input.request.nodeExecutable');
|
|
});
|
|
|
|
test('icacls calls in file-permissions.ts pass windowsHide', () => {
|
|
const perms = SRC('file-permissions.ts');
|
|
expect((perms.match(/'icacls'/g) || []).length).toBeGreaterThanOrEqual(3);
|
|
expectHideNearEvery(perms, "'icacls'");
|
|
});
|
|
|
|
test('terminal-agent respawn in terminal-agent-control.ts passes windowsHide', () => {
|
|
// The CLI cold-start + v1.44 watchdog respawn path. On Windows it runs
|
|
// through the Node polyfill (dist/bun-polyfill.cjs) whose host default is
|
|
// the opposite of Bun's — a visible console window on every watchdog
|
|
// respawn is the symptom when the flag is dropped. Wider window: the
|
|
// spawn's options object carries the full env wiring before the flag.
|
|
expectHideNearEvery(SRC('terminal-agent-control.ts'), '(Bun as any).spawn(', 700);
|
|
});
|
|
|
|
test('terminal-agent spawn is detached on Windows so it outlives the CLI that started it (#2637)', () => {
|
|
const control = SRC('terminal-agent-control.ts');
|
|
const at = control.indexOf('(Bun as any).spawn(');
|
|
expect(control.slice(at, at + 1000)).toContain("detached: process.platform === 'win32'");
|
|
});
|
|
|
|
test('SWEEP: every direct child_process call in src/ passes windowsHide (#2160, #2415)', () => {
|
|
// Full-census tripwire: a NEW child_process call site without windowsHide
|
|
// fails CI. Each exemption carries a reason — an interactive console
|
|
// child must NOT get CREATE_NO_WINDOW.
|
|
const EXEMPT: Array<{ file: string; needle: string; reason: string }> = [
|
|
{
|
|
file: 'domain-skill-commands.ts',
|
|
// tripwire-exempt: grep NEEDLE string for this census, not a call
|
|
needle: 'spawnSync(editor',
|
|
reason: "interactive $EDITOR with stdio:'inherit' — windowsHide would detach a console editor into an invisible console",
|
|
},
|
|
];
|
|
|
|
const srcDir = path.join(import.meta.dir, '../src');
|
|
const offenders: string[] = [];
|
|
for (const file of fs.readdirSync(srcDir).filter((f) => f.endsWith('.ts'))) {
|
|
const raw = fs.readFileSync(path.join(srcDir, file), 'utf-8');
|
|
if (!raw.includes('child_process')) continue;
|
|
// Strip comments so documented history doesn't trip the census.
|
|
const code = raw.replace(/\/\*[\s\S]*?\*\//g, '').replace(/^\s*\/\/.*$/gm, '');
|
|
|
|
// Collect the callable names this file binds to child_process:
|
|
// import { spawn as nodeSpawn } from 'child_process'
|
|
// const { execSync } = await import('child_process') / require(...)
|
|
// import * as cp from 'child_process' → cp.<fn>( pattern
|
|
const names = new Set<string>();
|
|
const namespaces = new Set<string>();
|
|
const importRe = /import\s*\{([^}]*)\}\s*from\s*['"](?:node:)?child_process['"]/g;
|
|
const dynRe = /(?:const|let|var)\s*\{([^}]*)\}\s*=\s*(?:await\s+import\(|require\()['"](?:node:)?child_process['"]\)/g;
|
|
const nsRe = /import\s*\*\s*as\s*(\w+)\s*from\s*['"](?:node:)?child_process['"]/g;
|
|
for (const m of code.matchAll(importRe)) {
|
|
for (const part of m[1].split(',')) {
|
|
const alias = part.split(/\s+as\s+/).map((s) => s.trim()).filter(Boolean);
|
|
const name = alias[alias.length - 1];
|
|
if (name && /^(spawn|spawnSync|exec|execSync|execFile|execFileSync|nodeSpawn|cpSpawn)/.test(alias[0].trim())) names.add(name);
|
|
}
|
|
}
|
|
for (const m of code.matchAll(dynRe)) {
|
|
for (const part of m[1].split(',')) {
|
|
const alias = part.split(':').map((s) => s.trim()).filter(Boolean);
|
|
const name = alias[alias.length - 1];
|
|
if (name && /^(spawn|spawnSync|exec|execSync|execFile|execFileSync)/.test(alias[0].trim())) names.add(name);
|
|
}
|
|
}
|
|
for (const m of code.matchAll(nsRe)) namespaces.add(m[1]);
|
|
|
|
const patterns: RegExp[] = [];
|
|
for (const n of names) patterns.push(new RegExp(`(?<![.\\w'"\`])${n}\\(`, 'g'));
|
|
for (const ns of namespaces) {
|
|
patterns.push(new RegExp(`(?<![\\w'"\`])${ns}\\.(?:spawn|spawnSync|exec|execSync|execFile|execFileSync)\\(`, 'g'));
|
|
}
|
|
|
|
for (const re of patterns) {
|
|
for (const m of code.matchAll(re)) {
|
|
const slice = code.slice(m.index!, m.index! + 700);
|
|
const exempt = EXEMPT.some((e) => e.file === file && slice.startsWith(e.needle));
|
|
if (exempt) continue;
|
|
if (!/windowsHide:\s*true/.test(slice)) {
|
|
offenders.push(`${file}: ${slice.split('\n')[0].slice(0, 100)}`);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
expect(offenders).toEqual([]);
|
|
});
|
|
|
|
test('SWEEP: every Bun.spawn call in src/ passes windowsHide (#2575 residual)', () => {
|
|
// Bun.spawn sites are structurally outside the child_process sweep above.
|
|
// Native Bun hides consoles by default and the Node polyfill
|
|
// (bun-polyfill.cjs) defaults windowsHide !== false since #2523/#2539 —
|
|
// this census exists so an explicit flag documents the intent at every
|
|
// site AND catches a regression if either default ever flips. Exemptions
|
|
// carry reasons, same contract as the child_process sweep.
|
|
const EXEMPT: Array<{ file: string; needle: string; reason: string }> = [];
|
|
|
|
const srcDir = path.join(import.meta.dir, '../src');
|
|
const offenders: string[] = [];
|
|
for (const file of fs.readdirSync(srcDir).filter((f) => f.endsWith('.ts'))) {
|
|
const raw = fs.readFileSync(path.join(srcDir, file), 'utf-8');
|
|
const code = raw.replace(/\/\*[\s\S]*?\*\//g, '').replace(/^\s*\/\/.*$/gm, '');
|
|
const re = /(?:\(Bun as any\)|Bun)\.spawn(?:Sync)?\(/g;
|
|
for (const m of code.matchAll(re)) {
|
|
const slice = code.slice(m.index!, m.index! + 900);
|
|
const exempt = EXEMPT.some((e) => e.file === file && slice.includes(e.needle));
|
|
if (exempt) continue;
|
|
if (!/windowsHide:\s*true/.test(slice)) {
|
|
offenders.push(`${file}: ${slice.split('\n')[0].slice(0, 100)}`);
|
|
}
|
|
}
|
|
}
|
|
expect(offenders).toEqual([]);
|
|
});
|
|
});
|