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>
70 lines
3.4 KiB
TypeScript
70 lines
3.4 KiB
TypeScript
/**
|
|
* #2847: a nested gstack Codex call is a one-shot review, but Codex injects every
|
|
* installed skill (gstack's own `review` included) into its context, and the
|
|
* reviewer re-ran whole skill workflows inside its timeout. A read-only sandbox
|
|
* does not stop that. Verified against codex-cli 0.152.0 and 0.160.0 with a local
|
|
* Responses API stub: without `skills.include_instructions=false` the request
|
|
* carried the full gstack catalog; with it, none (exec and native review alike).
|
|
* Every gstack-owned Codex call therefore carries the isolation flag, and the
|
|
* prompt boundary names the Codex skill roots.
|
|
*/
|
|
import { describe, expect, test } from 'bun:test';
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import { CODEX_MODEL_CONFIG_FLAG, CODEX_REVIEW_MODEL_CONFIG_FLAG, CODEX_SKILLS_ISOLATION_FLAG } from '../scripts/resolvers/constants';
|
|
|
|
const ROOT = path.join(import.meta.dir, '..');
|
|
|
|
function renderedSkillFiles(): string[] {
|
|
const files: string[] = [];
|
|
const pending = [ROOT];
|
|
const excluded = new Set(['node_modules', '.git', '.context', '.claude', 'fixtures']);
|
|
while (pending.length) {
|
|
const dir = pending.pop()!;
|
|
for (const entry of fs.readdirSync(dir, { withFileTypes: true })) {
|
|
if (excluded.has(entry.name)) continue;
|
|
const full = path.join(dir, entry.name);
|
|
if (entry.isDirectory()) pending.push(full);
|
|
else if (entry.name.endsWith('.md') && !entry.name.endsWith('.tmpl')) files.push(full);
|
|
}
|
|
}
|
|
return files;
|
|
}
|
|
|
|
describe('Codex skill isolation (#2847)', () => {
|
|
test('the model flags carry the isolation flag, so every model-flag site is isolated', () => {
|
|
expect(CODEX_SKILLS_ISOLATION_FLAG).toBe('-c skills.include_instructions=false');
|
|
expect(CODEX_MODEL_CONFIG_FLAG).toContain(CODEX_SKILLS_ISOLATION_FLAG);
|
|
expect(CODEX_REVIEW_MODEL_CONFIG_FLAG).toContain(CODEX_SKILLS_ISOLATION_FLAG);
|
|
});
|
|
|
|
test('every wrapped Codex exec/review call in generated skills disables the skill catalog', () => {
|
|
const calls: string[] = [];
|
|
for (const file of renderedSkillFiles()) {
|
|
for (const line of fs.readFileSync(file, 'utf8').split('\n')) {
|
|
if (/_gstack_codex_timeout_wrapper\s+\d+\s+codex\s+(exec|review)\b/.test(line)) calls.push(`${path.relative(ROOT, file)}: ${line}`);
|
|
}
|
|
}
|
|
expect(calls.length).toBeGreaterThan(10);
|
|
expect(calls.filter(call => !call.includes("skills.include_instructions=false"))).toEqual([]);
|
|
});
|
|
|
|
test('the probe round trip does not pay for the skill catalog either', () => {
|
|
const probe = fs.readFileSync(path.join(ROOT, 'bin', 'gstack-codex-probe'), 'utf8');
|
|
const roundTrip = probe.split('\n').find(line => line.includes('"reply OK"'));
|
|
expect(roundTrip).toContain("skills.include_instructions=false");
|
|
});
|
|
|
|
test('outside-voice and /codex prompt boundaries name the Codex skill roots and forbid skill use', () => {
|
|
const sources = ['scripts/resolvers/outside-voice-steps.ts', ...['review-mode', 'challenge-mode', 'consult-mode'].map(m => `codex/sections/${m}.md.tmpl`)];
|
|
for (const rel of sources) {
|
|
const text = fs.readFileSync(path.join(ROOT, rel), 'utf8');
|
|
const boundaries = text.split('\n').filter(line => line.includes('IMPORTANT: Do NOT read or execute any files under'));
|
|
expect(boundaries.length, rel).toBeGreaterThan(0);
|
|
for (const line of boundaries) {
|
|
expect(line, rel).toContain('Do not invoke any installed skill (Codex home skills/, .agents/)');
|
|
}
|
|
}
|
|
});
|
|
});
|