mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-01 06:24:41 +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>
106 lines
4.6 KiB
TypeScript
106 lines
4.6 KiB
TypeScript
/**
|
|
* Workflow action pins (supply chain, free).
|
|
*
|
|
* A tag (`@v7`) or branch ref is mutable: whoever controls the action's
|
|
* repository can repoint it, and the next CI run executes the new code with
|
|
* this repository's token and secrets. Every remote `uses:` in a workflow or
|
|
* composite action must name a full 40-character commit SHA (Dependabot's
|
|
* `github-actions` ecosystem keeps those current, with the tag in a trailing
|
|
* comment), and every `docker://` image must name a sha256 digest. Local
|
|
* actions (`./...`) are part of this checkout and need no pin.
|
|
*/
|
|
import { describe, expect, test } from 'bun:test';
|
|
import * as fs from 'node:fs';
|
|
import * as path from 'node:path';
|
|
|
|
const ROOT = path.resolve(__dirname, '..');
|
|
const GITHUB_DIR = path.join(ROOT, '.github');
|
|
|
|
/** Why a `uses:` reference is not immutable, or null when it is. */
|
|
export function pinProblem(uses: string): string | null {
|
|
if (uses.startsWith('./')) return null;
|
|
if (uses.startsWith('docker://')) {
|
|
return /@sha256:[0-9a-f]{64}$/.test(uses) ? null : 'docker image is not pinned to a sha256 digest';
|
|
}
|
|
const at = uses.lastIndexOf('@');
|
|
if (at <= 0) return 'remote action has no ref';
|
|
if (!/^[\w.-]+\/[\w.-]+(?:\/[\w./-]+)?$/.test(uses.slice(0, at))) return 'unrecognized action reference';
|
|
return /^[0-9a-f]{40}$/.test(uses.slice(at + 1)) ? null : 'ref is not a full 40-character commit SHA';
|
|
}
|
|
|
|
/** Every `uses:` in a workflow (job steps and reusable-workflow jobs) or composite action. */
|
|
export function usesReferences(document: any): string[] {
|
|
const refs: string[] = [];
|
|
const steps = (list: any) => {
|
|
for (const step of Array.isArray(list) ? list : []) if (typeof step?.uses === 'string') refs.push(step.uses);
|
|
};
|
|
for (const job of Object.values<any>(document?.jobs ?? {})) {
|
|
if (typeof job?.uses === 'string') refs.push(job.uses);
|
|
steps(job?.steps);
|
|
}
|
|
steps(document?.runs?.steps);
|
|
return refs;
|
|
}
|
|
|
|
function automationFiles(): string[] {
|
|
const files: string[] = [];
|
|
const workflows = path.join(GITHUB_DIR, 'workflows');
|
|
for (const name of fs.readdirSync(workflows).sort()) {
|
|
if (/\.ya?ml$/.test(name)) files.push(path.join(workflows, name));
|
|
}
|
|
const actions = path.join(GITHUB_DIR, 'actions');
|
|
for (const name of fs.existsSync(actions) ? fs.readdirSync(actions).sort() : []) {
|
|
for (const file of ['action.yml', 'action.yaml']) {
|
|
if (fs.existsSync(path.join(actions, name, file))) files.push(path.join(actions, name, file));
|
|
}
|
|
}
|
|
return files;
|
|
}
|
|
|
|
describe('workflow action pins', () => {
|
|
test('the classifier accepts immutable references and rejects mutable ones', () => {
|
|
for (const ok of [
|
|
'./.github/actions/restore-deps',
|
|
'actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1',
|
|
'github/codeql-action/upload-sarif@2892aa5e19bbd11bc0cff5427e3b750a04d9e3c2',
|
|
'google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@f4cfcc01edc9c8b756a9b873b7a623ca674da51e',
|
|
`docker://alpine@sha256:${'a'.repeat(64)}`,
|
|
]) expect(pinProblem(ok), ok).toBeNull();
|
|
for (const bad of [
|
|
'actions/checkout@v7',
|
|
'actions/checkout@main',
|
|
'actions/checkout@3d3c42e',
|
|
'actions/checkout',
|
|
'google/osv-scanner-action/.github/workflows/osv-scanner-reusable.yml@v2.3.8',
|
|
'docker://alpine:3.20',
|
|
'docker://alpine',
|
|
]) expect(pinProblem(bad), bad).not.toBeNull();
|
|
});
|
|
|
|
test('every remote action, reusable workflow and docker image is pinned immutably', () => {
|
|
const files = automationFiles();
|
|
const problems: string[] = [];
|
|
let scanned = 0;
|
|
for (const file of files) {
|
|
const source = fs.readFileSync(file, 'utf-8');
|
|
const refs = usesReferences(Bun.YAML.parse(source));
|
|
// A parse that misses `uses:` lines would pass vacuously; count them.
|
|
const lines = source.split('\n').filter((line) => /^\s*(?:-\s+)?uses:\s*\S/.test(line)).length;
|
|
expect(refs.length, `${path.relative(ROOT, file)}: parsed ${refs.length} of ${lines} uses: lines`).toBe(lines);
|
|
scanned += refs.length;
|
|
for (const ref of refs) {
|
|
const problem = pinProblem(ref);
|
|
if (problem) problems.push(`${path.relative(ROOT, file)}: ${ref} (${problem})`);
|
|
}
|
|
}
|
|
expect(files.length).toBeGreaterThan(10);
|
|
expect(scanned).toBeGreaterThan(100);
|
|
expect(problems, 'pin each action to a full commit SHA with the tag in a trailing comment').toEqual([]);
|
|
});
|
|
|
|
test('Dependabot keeps the pinned actions current', () => {
|
|
const config = Bun.YAML.parse(fs.readFileSync(path.join(GITHUB_DIR, 'dependabot.yml'), 'utf-8')) as any;
|
|
expect((config.updates ?? []).map((update: any) => update['package-ecosystem'])).toContain('github-actions');
|
|
});
|
|
});
|