mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-10 10:40:32 +01:00
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
This commit is contained in:
garrytan committed
1 parent
1e568bc5a0
commit
66c0e5f02e
20 files changed
+270
-123
No files matched your search
@@ -81,7 +81,7 @@ else
|
||||
|
||||
```bash
|
||||
_GS=""
|
||||
for _D in "${GSTACK_ROOT:-}" "$HOME/.claude/skills/gstack" "$HOME/.codex/skills/gstack" "$HOME/.factory/skills/gstack" "$HOME/.kiro/skills/gstack" "$HOME/.config/opencode/skills/gstack" "$HOME/.slate/skills/gstack" "$HOME/.cursor/skills/gstack" "$HOME/.openclaw/skills/gstack" "$HOME/.hermes/skills/gstack" "$HOME/.gbrain/skills/gstack" "$HOME/.gstack/repos/gstack"; do
|
||||
for _D in "${GSTACK_ROOT:-}" "$HOME/.claude/skills/gstack" "$HOME/.codex/skills/gstack" "$HOME/.factory/skills/gstack" "$HOME/.kiro/skills/gstack" "$HOME/.config/opencode/skills/gstack" "$HOME/.slate/skills/gstack" "$HOME/.cursor/skills/gstack" "$HOME/.openclaw/skills/gstack" "$HOME/.hermes/skills/gstack" "$HOME/.gbrain/skills/gstack" "$HOME/.copilot/skills/gstack" "$HOME/.gstack/repos/gstack"; do
|
||||
[ -z "$_GS" ] && [ -n "$_D" ] && [ -d "$_D/bin" ] && _GS="$_D"
|
||||
done
|
||||
[ -n "$_GS" ] && echo "GSTACK_OK: $_GS" || echo "GSTACK_MISSING"
|
||||
@@ -135,7 +135,7 @@ if [ "$MODE" = "required" ]; then
|
||||
# repo location. Block only when NONE exist (#2500 — hardcoding
|
||||
# ~/.claude/skills/gstack false-blocked Codex-host and migrated-repo installs).
|
||||
_GSTACK_ROOT=""
|
||||
for _D in "${GSTACK_ROOT:-}" "$HOME/.claude/skills/gstack" "$HOME/.codex/skills/gstack" "$HOME/.factory/skills/gstack" "$HOME/.kiro/skills/gstack" "$HOME/.config/opencode/skills/gstack" "$HOME/.slate/skills/gstack" "$HOME/.cursor/skills/gstack" "$HOME/.openclaw/skills/gstack" "$HOME/.hermes/skills/gstack" "$HOME/.gbrain/skills/gstack" "$HOME/.gstack/repos/gstack"; do
|
||||
for _D in "${GSTACK_ROOT:-}" "$HOME/.claude/skills/gstack" "$HOME/.codex/skills/gstack" "$HOME/.factory/skills/gstack" "$HOME/.kiro/skills/gstack" "$HOME/.config/opencode/skills/gstack" "$HOME/.slate/skills/gstack" "$HOME/.cursor/skills/gstack" "$HOME/.openclaw/skills/gstack" "$HOME/.hermes/skills/gstack" "$HOME/.gbrain/skills/gstack" "$HOME/.copilot/skills/gstack" "$HOME/.gstack/repos/gstack"; do
|
||||
[ -z "$_GSTACK_ROOT" ] && [ -n "$_D" ] && [ -d "$_D/bin" ] && _GSTACK_ROOT="$_D"
|
||||
done
|
||||
|
||||
|
||||
@@ -29,6 +29,9 @@ import {
|
||||
import { __resetRegistry } from '../src/token-registry';
|
||||
import { BrowserManager } from '../src/browser-manager';
|
||||
import { resolveConfig } from '../src/config';
|
||||
import { usePrivateStateRoot } from '../../test/helpers/private-state-root';
|
||||
|
||||
usePrivateStateRoot();
|
||||
|
||||
const PINNED_ORIGIN = `chrome-extension://${GSTACK_EXTENSION_ID}`;
|
||||
const fixtureDir = fs.realpathSync(fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-extension-token-')));
|
||||
|
||||
@@ -15,6 +15,9 @@ import * as crypto from 'crypto';
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { usePrivateStateRoot } from '../../test/helpers/private-state-root';
|
||||
|
||||
usePrivateStateRoot();
|
||||
|
||||
const fixtureDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-server-factory-'));
|
||||
const fixtureConfig = resolveConfig({ BROWSE_STATE_FILE: path.join(fixtureDir, 'state/browse.json') });
|
||||
|
||||
@@ -23,6 +23,9 @@ import { __resetRegistry, __resetConnectRateLimit, createToken } from '../src/to
|
||||
import { mintSseSessionToken, SSE_COOKIE_NAME } from '../src/sse-session-cookie';
|
||||
import { BrowserManager } from '../src/browser-manager';
|
||||
import { resolveConfig } from '../src/config';
|
||||
import { usePrivateStateRoot } from '../../test/helpers/private-state-root';
|
||||
|
||||
usePrivateStateRoot();
|
||||
|
||||
const fixtureDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-route-blackbox-'));
|
||||
const fixtureConfig = resolveConfig({ BROWSE_STATE_FILE: path.join(fixtureDir, 'state/browse.json') });
|
||||
|
||||
@@ -27,6 +27,9 @@ import { buildFetchHandler, __testInternals__ } from '../src/server';
|
||||
import { __resetRegistry } from '../src/token-registry';
|
||||
import { BrowserManager } from '../src/browser-manager';
|
||||
import { resolveConfig } from '../src/config';
|
||||
import { usePrivateStateRoot } from '../../test/helpers/private-state-root';
|
||||
|
||||
usePrivateStateRoot();
|
||||
|
||||
type Cred = 'none' | 'wrong' | 'root' | 'scoped' | 'sse-cookie' | 'extension-origin';
|
||||
const CREDS: Cred[] = ['none', 'wrong', 'root', 'scoped', 'sse-cookie', 'extension-origin'];
|
||||
|
||||
@@ -716,6 +716,25 @@ resolves (`browserAvailable()` — Aside, or the browse binary CI builds with
|
||||
`bun run build:gates`) and skip only when neither exists; the fallback
|
||||
engine's own tests run everywhere.
|
||||
|
||||
### Real-home tripwire
|
||||
|
||||
No free test may write the developer's real home. `scripts/lib/free-home-guard.ts`
|
||||
snapshots `~/.gstack`, `~/.claude`, `~/.codex`, `~/.agents` and `~/.config/gstack`
|
||||
(live session logs excluded) and fails the run when an entry changes.
|
||||
|
||||
- A shard that runs alone (`--shard`, CI, the exclusive host-state shard, the
|
||||
flaky retry) owns its window, so the failure names its files.
|
||||
- Full-suite shards run concurrently on one HOME and cannot tell whose write a
|
||||
change was. The runner guards that whole phase once and names no shard.
|
||||
- `bun run scripts/test-free-shards.ts --attribute-home` names the writer: it
|
||||
runs every file alone with a private HOME (browser cache and git identity
|
||||
still come from the real home) and reports each file that wrote a watched
|
||||
surface. The retained shard directory keeps the written files as evidence.
|
||||
|
||||
Fix a writer with `usePrivateStateRoot()` (`test/helpers/private-state-root.ts`)
|
||||
or a child HOME/GSTACK_HOME, and resolve product state paths at write time,
|
||||
never at import.
|
||||
|
||||
## Running evals as an agent: detach
|
||||
|
||||
Moved verbatim from CLAUDE.md (#2096 size limit). The short rule stays in
|
||||
|
||||
@@ -8,6 +8,9 @@ import { join } from 'path';
|
||||
import { mintForCaller } from '../src/auth-mint';
|
||||
import { SessionTokenStore } from '../src/session-tokens';
|
||||
import { grantIdentity } from '../src/allowlist';
|
||||
import { usePrivateStateRoot } from '../../../test/helpers/private-state-root';
|
||||
|
||||
usePrivateStateRoot();
|
||||
|
||||
let tmpDir: string;
|
||||
let listPath: string;
|
||||
|
||||
@@ -6,12 +6,17 @@
|
||||
* when one of those entries changed. It watches only these surfaces; it is not
|
||||
* a universal write-containment check. Live agent-session logs that a
|
||||
* concurrently running host keeps writing are excluded, and directory mtimes
|
||||
* are ignored, so only file, link and directory-set changes count. Concurrent
|
||||
* shards whose windows overlap a change all report it.
|
||||
* are ignored, so only file, link and directory-set changes count.
|
||||
*
|
||||
* A shard that runs alone owns its window, so its guard names its files.
|
||||
* Concurrent shards share one HOME and cannot tell whose write a change was, so
|
||||
* the runner guards that phase once and names no file; `--attribute-home`
|
||||
* then runs every file alone in a private HOME, where any write is that file's.
|
||||
*/
|
||||
import * as fs from 'node:fs';
|
||||
import * as os from 'node:os';
|
||||
import * as path from 'node:path';
|
||||
import { forEachFileAlone } from './shard-engine';
|
||||
|
||||
export const FREE_HOME_SURFACES = ['.gstack', '.claude', '.codex', '.agents', '.config/gstack'] as const;
|
||||
|
||||
@@ -76,15 +81,28 @@ export function diffFreeHome(before: FreeHomeSnapshot, after: FreeHomeSnapshot):
|
||||
return [...changed].sort();
|
||||
}
|
||||
|
||||
export function formatFreeHomeChange(changed: string[], files: string[]): string {
|
||||
/** Who owns the snapshotted window: one shard, a concurrent phase, or one file in a private HOME. */
|
||||
export type FreeHomeScope = { kind: 'shard' } | { kind: 'concurrent'; shards: number } | { kind: 'private' };
|
||||
|
||||
export function formatFreeHomeChange(changed: string[], files: string[], scope: FreeHomeScope = { kind: 'shard' }): string {
|
||||
const shown = changed.slice(0, MAX_REPORTED).map(entry => `~/${entry.split(path.sep).join('/')}`);
|
||||
const more = changed.length > MAX_REPORTED ? ` (+${changed.length - MAX_REPORTED} more)` : '';
|
||||
return `real home changed while this shard ran (watches ${FREE_HOME_SURFACES.map(s => `~/${s}`).join(', ')} only): `
|
||||
+ `${shown.join(', ')}${more}. Give the writer a private HOME/GSTACK_HOME. Shard files: ${files.join(', ')}`;
|
||||
const watched = `(watches ${FREE_HOME_SURFACES.map(s => `~/${s}`).join(', ')} only): ${shown.join(', ')}${more}.`;
|
||||
const fix = 'Give the writer a private HOME/GSTACK_HOME.';
|
||||
if (scope.kind === 'concurrent') {
|
||||
return `real home changed while ${scope.shards} shards ran concurrently ${watched} They share one HOME, so no shard or file `
|
||||
+ `is named. Find the writer with \`bun run scripts/test-free-shards.ts --attribute-home\` (each file alone in a private HOME). ${fix}`;
|
||||
}
|
||||
if (scope.kind === 'private') return `${files.join(', ')} wrote its private HOME ${watched} With the real HOME it writes there. ${fix}`;
|
||||
return `real home changed while this shard ran ${watched} ${fix} Shard files: ${files.join(', ')}`;
|
||||
}
|
||||
|
||||
export interface FreeHomeGuard { verify(): string | null }
|
||||
/** How runFreeShard guards one shard; it may redirect `env` before the child starts. */
|
||||
export type FreeHomeGuardFactory = (files: string[], env: NodeJS.ProcessEnv, stateDir: string) => FreeHomeGuard;
|
||||
|
||||
/** Take the baseline now; verify() returns null or the failure to report. */
|
||||
export function guardFreeHome(files: string[], env: NodeJS.ProcessEnv = process.env): { verify(): string | null } {
|
||||
export function guardFreeHome(files: string[], env: NodeJS.ProcessEnv = process.env, scope: FreeHomeScope = { kind: 'shard' }): FreeHomeGuard {
|
||||
const home = freeHomeDir(env);
|
||||
const unreadable = (error: unknown) => `real home surfaces could not be snapshotted (${(error as NodeJS.ErrnoException).code ?? 'error'}); shard files: ${files.join(', ')}`;
|
||||
let before: FreeHomeSnapshot | undefined;
|
||||
@@ -95,8 +113,51 @@ export function guardFreeHome(files: string[], env: NodeJS.ProcessEnv = process.
|
||||
if (!before) return baselineError!;
|
||||
try {
|
||||
const changed = diffFreeHome(before, snapshotFreeHome(home));
|
||||
return changed.length ? formatFreeHomeChange(changed, files) : null;
|
||||
return changed.length ? formatFreeHomeChange(changed, files, scope) : null;
|
||||
} catch (error) { return unreadable(error); }
|
||||
},
|
||||
};
|
||||
}
|
||||
|
||||
/** For a shard inside a concurrently guarded phase: the phase guard reports, this one never does. */
|
||||
export const sharedFreeHome = (): FreeHomeGuard => ({ verify: () => null });
|
||||
|
||||
/**
|
||||
* Redirect one shard's HOME to `<stateDir>/home` and guard that instead. The
|
||||
* browser cache and git identity still come from the real home, so tests run
|
||||
* as they would there; only home writes are diverted.
|
||||
*/
|
||||
export function privateFreeHome(files: string[], env: NodeJS.ProcessEnv, stateDir: string): FreeHomeGuard {
|
||||
const real = freeHomeDir(env);
|
||||
const home = path.join(stateDir, 'home');
|
||||
fs.mkdirSync(home, { recursive: true, mode: 0o700 });
|
||||
env.PLAYWRIGHT_BROWSERS_PATH ??= path.join(real, process.platform === 'darwin' ? 'Library/Caches' : '.cache', 'ms-playwright');
|
||||
if (!env.GIT_CONFIG_GLOBAL && fs.existsSync(path.join(real, '.gitconfig'))) env.GIT_CONFIG_GLOBAL = path.join(real, '.gitconfig');
|
||||
env.HOME = home;
|
||||
if (env.USERPROFILE !== undefined) env.USERPROFILE = home;
|
||||
return guardFreeHome(files, env, { kind: 'private' });
|
||||
}
|
||||
|
||||
/**
|
||||
* `--attribute-home`: run each reader file alone with a private HOME, `jobs`
|
||||
* at a time, then each exclusive host-state file alone, and name every file
|
||||
* that wrote a watched surface. Exit 1 when any did.
|
||||
*/
|
||||
export async function attributeFreeHomeWriters(
|
||||
readers: string[], exclusive: string[], jobs: number,
|
||||
runAlone: (file: string, index: number, homeGuard: FreeHomeGuardFactory) => Promise<unknown>,
|
||||
): Promise<number> {
|
||||
const writers: string[] = [];
|
||||
console.log(`[test:free] attributing home writes: ${readers.length + exclusive.length} files, each alone in a private HOME, ${jobs} at a time`);
|
||||
await forEachFileAlone(readers, exclusive, jobs, async (file, index) => {
|
||||
let change = null as string | null;
|
||||
await runAlone(file, index, (files, env, stateDir) => {
|
||||
const guard = privateFreeHome(files, env, stateDir);
|
||||
return { verify: () => (change = guard.verify()) };
|
||||
});
|
||||
if (change) writers.push(change);
|
||||
});
|
||||
for (const writer of writers.sort()) console.error(`[test:free] ✗ ${writer}`);
|
||||
console.log(`[test:free] ${writers.length ? `${writers.length} file(s) wrote home surfaces` : 'no file wrote a watched home surface'}`);
|
||||
return writers.length ? 1 : 0;
|
||||
}
|
||||
@@ -595,6 +595,22 @@ export async function removeShardSandbox(stateDir: string): Promise<void> {
|
||||
catch { /* a locked file must not turn a real verdict into an exception */ }
|
||||
}
|
||||
|
||||
/** Run once per file, alone: readers `jobs` at a time, then exclusive files one by one. Stops on termination. */
|
||||
export async function forEachFileAlone(
|
||||
readers: string[], exclusive: string[], jobs: number, run: (file: string, index: number) => Promise<void>,
|
||||
): Promise<void> {
|
||||
let cursor = 0;
|
||||
const worker = async (files: string[], offset: number) => {
|
||||
while (cursor < files.length && !isTerminationRequested()) {
|
||||
const index = cursor++;
|
||||
await run(files[index], offset + index);
|
||||
}
|
||||
};
|
||||
await Promise.all(Array.from({ length: Math.max(1, jobs) }, () => worker(readers, 0)));
|
||||
cursor = 0;
|
||||
await worker(exclusive, readers.length);
|
||||
}
|
||||
|
||||
let shardLogSequence = 0;
|
||||
|
||||
/** Timestamped log path; pid + sequence defeat same-millisecond collisions. */
|
||||
|
||||
+30
-30
@@ -73,6 +73,7 @@
|
||||
* bun run scripts/test-free-shards.ts --wall-timeout 600 # override the kill deadline
|
||||
* bun run scripts/test-free-shards.ts --verbose # forward the full child stream
|
||||
* bun run scripts/test-free-shards.ts --quick # explicit fast subset, not acceptance
|
||||
* bun run scripts/test-free-shards.ts --attribute-home # name real-home writers: each file alone, private HOME
|
||||
* bun run scripts/test-free-shards.ts --ci-plan plan.json --shards 20
|
||||
* bun run scripts/test-free-shards.ts --ci-run plan.json --shard 1 --result result.json
|
||||
* bun run scripts/test-free-shards.ts --ci-verify plan.json --results results/
|
||||
@@ -86,11 +87,12 @@ import { StringDecoder } from 'node:string_decoder';
|
||||
import { createHash, randomUUID } from 'node:crypto';
|
||||
import { isPaidTestFile } from '../test/helpers/paid-test-set';
|
||||
import { resolveStateRoot } from '../lib/state-root';
|
||||
import { guardFreeHome } from './lib/free-home-guard';
|
||||
import { attributeFreeHomeWriters, guardFreeHome, sharedFreeHome, type FreeHomeGuardFactory } from './lib/free-home-guard';
|
||||
import {
|
||||
BunTestOutputClassifier,
|
||||
createShardSandbox,
|
||||
exactTestFileSelectors,
|
||||
forEachFileAlone,
|
||||
isTerminationRequested,
|
||||
killProcessGroup,
|
||||
BunFailureSummaryParser,
|
||||
@@ -902,6 +904,7 @@ type CliOptions = {
|
||||
/** True when --wall-timeout was passed explicitly; full-suite mode only auto-scales the default. */
|
||||
wallTimeoutExplicit: boolean;
|
||||
quick: boolean;
|
||||
attributeHome: boolean;
|
||||
ciPlan: string | null;
|
||||
ciRun: string | null;
|
||||
ciVerify: string | null;
|
||||
@@ -920,6 +923,7 @@ export function parseCliOptions(argv: string[]): CliOptions {
|
||||
let wallTimeoutMs = DEFAULT_WALL_TIMEOUT_MS;
|
||||
let wallTimeoutExplicit = false;
|
||||
let quick = false;
|
||||
let attributeHome = false;
|
||||
const paths: Record<'ciPlan' | 'ciRun' | 'ciVerify' | 'result' | 'results', string | null> = {
|
||||
ciPlan: null, ciRun: null, ciVerify: null, result: null, results: null,
|
||||
};
|
||||
@@ -936,6 +940,7 @@ export function parseCliOptions(argv: string[]): CliOptions {
|
||||
'--windows-only': () => { windowsOnly = true; },
|
||||
'--verbose': () => { verbose = true; },
|
||||
'--quick': () => { quick = true; },
|
||||
'--attribute-home': () => { attributeHome = true; },
|
||||
'--ci-plan': pathFlag('--ci-plan', 'ciPlan'),
|
||||
'--ci-run': pathFlag('--ci-run', 'ciRun'),
|
||||
'--ci-verify': pathFlag('--ci-verify', 'ciVerify'),
|
||||
@@ -960,11 +965,11 @@ export function parseCliOptions(argv: string[]): CliOptions {
|
||||
});
|
||||
|
||||
const ciModes = [paths.ciPlan, paths.ciRun, paths.ciVerify].filter(Boolean).length;
|
||||
if (ciModes > 1 || (ciModes && (quick || listOnly || dryRun || recordDurations || windowsOnly))) throw new Error('CI modes cannot be combined with other selection modes');
|
||||
if (ciModes > 1 || (ciModes && (quick || listOnly || dryRun || recordDurations || windowsOnly || attributeHome))) throw new Error('CI modes cannot be combined with other selection modes');
|
||||
if (paths.ciRun && (shardIndex === null || !paths.result)) throw new Error('--ci-run requires --shard and --result');
|
||||
if (paths.ciVerify && !paths.results) throw new Error('--ci-verify requires --results');
|
||||
if (quick && (recordDurations || windowsOnly || shardIndex !== null)) throw new Error('--quick cannot change recording, Windows or shard selection');
|
||||
return { dryRun, listOnly, recordDurations, windowsOnly, verbose, shardCount, shardIndex, wallTimeoutMs, wallTimeoutExplicit, quick, ...paths };
|
||||
return { dryRun, listOnly, recordDurations, windowsOnly, verbose, shardCount, shardIndex, wallTimeoutMs, wallTimeoutExplicit, quick, attributeHome, ...paths };
|
||||
}
|
||||
|
||||
function formatShardSummary(shards: string[][]): string[] {
|
||||
@@ -1394,6 +1399,8 @@ export interface RunFreeShardOptions {
|
||||
/** Per-run full-stream log path (tests inject). Default: a private retained file under .context/free-test-logs. */
|
||||
logFilePath?: string;
|
||||
log?: (line: string) => void;
|
||||
/** Home tripwire for this shard. Default: guard the real home and name this shard's files. */
|
||||
homeGuard?: FreeHomeGuardFactory;
|
||||
}
|
||||
|
||||
const EPILOGUE_WORD: Record<FreeShardStatus, string> = {
|
||||
@@ -1915,6 +1922,7 @@ export async function runFreeShard(
|
||||
// shards and prior daemons replace each other's state; override inherited state.
|
||||
env.BROWSE_STATE_FILE = path.join(stateDir, '.gstack', 'browse.json');
|
||||
env.GSTACK_FREE_SHARD_ID = randomUUID();
|
||||
const home = options.homeGuard ? options.homeGuard(files, env, stateDir) : guardFreeHome(files, env);
|
||||
|
||||
const startedAt = Date.now();
|
||||
const classifier = new BunTestOutputClassifier();
|
||||
@@ -1952,7 +1960,7 @@ export async function runFreeShard(
|
||||
child = await runShardChild({
|
||||
command, args, cwd: rootDir, env, timeoutMs: wallTimeoutMs,
|
||||
attach: () => {
|
||||
const browser = trackShardBrowser(stateDir, env), home = guardFreeHome(files, env);
|
||||
const browser = trackShardBrowser(stateDir, env);
|
||||
return { signal: (force) => browser.signal(force), settle: async () => { cleanupError = await browser.settle() ?? home.verify(); } };
|
||||
},
|
||||
hookStreams: (spawned) => [consumeStream(spawned.stdout, 'stdout'), consumeStream(spawned.stderr, 'stderr')],
|
||||
@@ -2053,30 +2061,18 @@ async function recordFreeTestDurations(files: string[], jobs: number): Promise<n
|
||||
const durations: Record<string, number> = {};
|
||||
const failed: string[] = [];
|
||||
const expectedCount = files.length;
|
||||
let cursor = 0;
|
||||
console.log(`[test:free] recording per-file durations: ${files.length} files across ${jobs} workers`);
|
||||
const worker = async (): Promise<void> => {
|
||||
for (;;) {
|
||||
if (isTerminationRequested()) return;
|
||||
const index = cursor;
|
||||
cursor += 1;
|
||||
if (index >= files.length) return;
|
||||
const file = files[index];
|
||||
const outcome = await runFreeShard([file], index + 1, files.length, {
|
||||
wallTimeoutMs: wallTimeoutForShard(1),
|
||||
quiet: true,
|
||||
});
|
||||
durations[normalizeRelativePath(file)] = outcome.elapsedMs;
|
||||
if (outcome.status !== 'passed') failed.push(file);
|
||||
}
|
||||
};
|
||||
const phaseHome = guardFreeHome(files, process.env, { kind: 'concurrent', shards: jobs });
|
||||
// As in full-suite mode, finish parallel work before exclusive host-state fixtures.
|
||||
const exclusive = files.filter(file => file in TREE_MUTATING);
|
||||
files = files.filter(file => !(file in TREE_MUTATING));
|
||||
await Promise.all(Array.from({ length: Math.max(1, jobs) }, () => worker()));
|
||||
files = exclusive;
|
||||
cursor = 0;
|
||||
await worker();
|
||||
await forEachFileAlone(files.filter(file => !(file in TREE_MUTATING)), files.filter(file => file in TREE_MUTATING), jobs, async (file, index) => {
|
||||
const outcome = await runFreeShard([file], index + 1, files.length, {
|
||||
wallTimeoutMs: wallTimeoutForShard(1), quiet: true, homeGuard: sharedFreeHome,
|
||||
});
|
||||
durations[normalizeRelativePath(file)] = outcome.elapsedMs;
|
||||
if (outcome.status !== 'passed') failed.push(file);
|
||||
});
|
||||
const homeChange = phaseHome.verify();
|
||||
if (homeChange) console.error(`[test:free] ${homeChange}`);
|
||||
if (Object.keys(durations).length !== expectedCount) {
|
||||
throw new Error('Duration recording was interrupted; the seed was not replaced.');
|
||||
}
|
||||
@@ -2085,7 +2081,7 @@ async function recordFreeTestDurations(files: string[], jobs: number): Promise<n
|
||||
// Atomic: a killed recorder never leaves a truncated seed behind.
|
||||
writeDurationSeed(target, durations);
|
||||
console.log(`[test:free] wrote ${Object.keys(durations).length} durations to ${path.relative(ROOT, target)}`);
|
||||
if (failed.length > 0) {
|
||||
if (failed.length > 0 || homeChange) {
|
||||
// Failures still recorded (a red file's duration is still a real cost),
|
||||
// but surfaced loudly — recording from a broken tree deserves a look.
|
||||
console.error(`[test:free] WARNING: ${failed.length} file(s) failed while recording:`);
|
||||
@@ -2245,6 +2241,8 @@ async function main(): Promise<number> {
|
||||
if (options.recordDurations) {
|
||||
return recordFreeTestDurations(files, fullSuiteJobs());
|
||||
}
|
||||
if (options.attributeHome) return attributeFreeHomeWriters(files.filter(file => !(file in TREE_MUTATING)), files.filter(file => file in TREE_MUTATING),
|
||||
fullSuiteJobs(), (file, index, homeGuard) => runFreeShard([file], index + 1, files.length, { wallTimeoutMs: wallTimeoutForShard(1), quiet: true, log: () => {}, homeGuard }));
|
||||
|
||||
if (options.dryRun) {
|
||||
const shards = assignFilesToShards(files, options.shardCount);
|
||||
@@ -2305,8 +2303,10 @@ async function main(): Promise<number> {
|
||||
}
|
||||
const shardTimeout = (fileCount: number): number =>
|
||||
options.wallTimeoutExplicit ? options.wallTimeoutMs : wallTimeoutForShard(fileCount, options.wallTimeoutMs);
|
||||
const phaseHome = guardFreeHome(readers, process.env, { kind: 'concurrent', shards: shards.length });
|
||||
const outcomes = await Promise.all(
|
||||
shards.map((shardFiles, index) => runFreeShard(shardFiles, index + 1, totalShards, {
|
||||
homeGuard: sharedFreeHome,
|
||||
// Packed shards get duration-aware walls: LPT decouples file count from
|
||||
// cost BY DESIGN, so the 5s/file heuristic would undersize a shard
|
||||
// holding few expensive files.
|
||||
@@ -2316,7 +2316,8 @@ async function main(): Promise<number> {
|
||||
verbose: options.verbose,
|
||||
})),
|
||||
);
|
||||
let worst = Math.max(...outcomes.map((o) => exitCodeFor(o.status)));
|
||||
const homeChange = phaseHome.verify();
|
||||
if (homeChange) console.error(`[test:free] ${homeChange}`);
|
||||
// Cancellation stops the run: don't launch the exclusive host-state shard
|
||||
// after a SIGINT/SIGTERM already killed the parallel phase.
|
||||
if (exclusive.length > 0 && !isTerminationRequested()) {
|
||||
@@ -2324,7 +2325,6 @@ async function main(): Promise<number> {
|
||||
wallTimeoutMs: shardTimeout(exclusive.length),
|
||||
verbose: options.verbose,
|
||||
});
|
||||
worst = Math.max(worst, exitCodeFor(exclusiveOutcome.status));
|
||||
if (exclusiveOutcome.status !== 'passed') {
|
||||
// Fixture safety rests on each test restoring default state itself; a
|
||||
// SIGKILL at the wall deadline (or a mid-regeneration crash) defeats
|
||||
@@ -2340,7 +2340,7 @@ async function main(): Promise<number> {
|
||||
outcomes.push(exclusiveOutcome);
|
||||
}
|
||||
|
||||
return (await retryFailedFreeFiles(outcomes, totalShards, options)).exitCode;
|
||||
return Math.max(homeChange ? 1 : 0, (await retryFailedFreeFiles(outcomes, totalShards, options)).exitCode);
|
||||
}
|
||||
|
||||
/** Dirty generated artifacts (SKILL.md / host outputs) after a failed exclusive shard. */
|
||||
|
||||
+2
@@ -27,6 +27,8 @@ export const FREE_CASES: string[][] = [
|
||||
['--ci-verify', 'plan.json'],
|
||||
['--quick', '--shard', '1'],
|
||||
['--quick', '--windows-only'],
|
||||
['--attribute-home'],
|
||||
['--ci-plan', 'a.json', '--attribute-home'],
|
||||
];
|
||||
|
||||
export const PAID_CASES: Array<{ argv: string[]; env?: Record<string, string> }> = [
|
||||
|
||||
+46
-1
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"recordedFrom": "96764e80 (pre-engine base runners); paid lane re-recorded at v1.91.12.0 for the marathon tier and the --slice-budget, --max-parallel, --case and --trials flags (PR 2999)",
|
||||
"recordedFrom": "96764e80 (pre-engine base runners); paid lane re-recorded at v1.91.12.0 for the marathon tier and the --slice-budget, --max-parallel, --case and --trials flags (PR 2999); free lane re-recorded for the --attribute-home flag (PR 3014)",
|
||||
"free": [
|
||||
{
|
||||
"argv": [],
|
||||
@@ -15,6 +15,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -41,6 +42,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -66,6 +68,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -90,6 +93,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -114,6 +118,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": true,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -141,6 +146,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -166,6 +172,7 @@
|
||||
"wallTimeoutMs": 600000,
|
||||
"wallTimeoutExplicit": true,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -193,6 +200,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": "plan.json",
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
@@ -222,6 +230,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": "plan.json",
|
||||
"ciVerify": null,
|
||||
@@ -249,6 +258,7 @@
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": false,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": "plan.json",
|
||||
@@ -381,6 +391,41 @@
|
||||
"result": {
|
||||
"error": "--quick cannot change recording, Windows or shard selection"
|
||||
}
|
||||
},
|
||||
{
|
||||
"argv": [
|
||||
"--attribute-home"
|
||||
],
|
||||
"result": {
|
||||
"ok": {
|
||||
"dryRun": false,
|
||||
"listOnly": false,
|
||||
"recordDurations": false,
|
||||
"windowsOnly": false,
|
||||
"verbose": false,
|
||||
"shardCount": 20,
|
||||
"shardIndex": null,
|
||||
"wallTimeoutMs": 360000,
|
||||
"wallTimeoutExplicit": false,
|
||||
"quick": false,
|
||||
"attributeHome": true,
|
||||
"ciPlan": null,
|
||||
"ciRun": null,
|
||||
"ciVerify": null,
|
||||
"result": null,
|
||||
"results": null
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"argv": [
|
||||
"--ci-plan",
|
||||
"a.json",
|
||||
"--attribute-home"
|
||||
],
|
||||
"result": {
|
||||
"error": "CI modes cannot be combined with other selection modes"
|
||||
}
|
||||
}
|
||||
],
|
||||
"paid": [
|
||||
|
||||
@@ -2,7 +2,7 @@ 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 { diffFreeHome, guardFreeHome, snapshotFreeHome } from '../scripts/lib/free-home-guard';
|
||||
import { attributeFreeHomeWriters, diffFreeHome, guardFreeHome, snapshotFreeHome } from '../scripts/lib/free-home-guard';
|
||||
import { runFreeShard } from '../scripts/test-free-shards';
|
||||
|
||||
const homes: string[] = [];
|
||||
@@ -78,6 +78,47 @@ describe('free-suite home-write tripwire (#2895)', () => {
|
||||
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+)$/.exec(line)?.[1] ?? [])) {
|
||||
if (/^gstack-free-shard-/.test(path.basename(retained))) fs.rmSync(retained, { recursive: true, force: true });
|
||||
}
|
||||
}
|
||||
});
|
||||
|
||||
test.skipIf(process.platform === 'win32')('a free shard that writes the real home fails and names its files', async () => {
|
||||
const home = fakeHome();
|
||||
const writer = `require('fs').writeFileSync(require('path').join(process.env.HOME, '.gstack', '.last-setup-version'), '7.7.7\\n');`
|
||||
|
||||
@@ -14,14 +14,26 @@ const LATER_BROWSER_EDITS: Array<[string, string]> = [
|
||||
[' Opera and Opera GX are Windows-only and read from `%APPDATA%\\Opera Software\\Opera Stable` or `Opera GX Stable`, in `Default` or `Profile N` directories; legacy root-level layouts, Opera side profiles and portable or relocated installs are not detected. Opera has no native extraction, so its App-Bound cookies (if any) need manual sign-in.', ''],
|
||||
];
|
||||
|
||||
// The judged SKILL.md excerpt follows the generated preamble, so later preamble
|
||||
// edits move its line range without changing its bytes. The approved request
|
||||
// named lines from 153; the parallel-waves one-line skill start (#2763) removed
|
||||
// three preamble lines. A raw SKILL.md gets those lines back, and a built prompt,
|
||||
// which has no preamble, gets the approved start line.
|
||||
const APPROVED_ENTRYPOINT_START = 153;
|
||||
const LATER_PREAMBLE_EDITS: Array<[string, string]> = [
|
||||
['~/.claude/skills/gstack/bin/gstack-skill-start --skill "setup-browser-cookies" --model "claude"\n', '_SS="$HOME/.claude/skills/gstack/bin/gstack-skill-start"\n[ -x "$_SS" ] || _SS=".claude/skills/gstack/bin/gstack-skill-start"\n"$_SS" --skill "setup-browser-cookies" --model "claude" --parent-pid "$PPID" \\\n || echo "SKILL_START: unavailable — stale install; run ./setup or /gstack-upgrade (preamble degraded, continue the user\'s task)"\n'],
|
||||
];
|
||||
|
||||
export function approvedCookieWorkflowSource(source: string): string {
|
||||
let removedLines = 0;
|
||||
let historical = source
|
||||
.replace('sha256sum < "$tmpfile" | awk \'{print $(1)}\'', 'sha256sum "$tmpfile" | awk \'{print $1}\'')
|
||||
.replace('shasum -a 256 < "$tmpfile" | awk \'{print $(1)}\'', 'shasum -a 256 "$tmpfile" | awk \'{print $1}\'')
|
||||
.replace(LATER_BROWSER_BLOCK, block => { removedLines = block.split('\n').length - 1; return ''; });
|
||||
for (const [later, earlier] of LATER_BROWSER_EDITS) historical = historical.replace(later, earlier);
|
||||
return historical.replace(/(--- BEGIN FILE "BROWSER\.md" \(lines \d+-)(\d+)(; section\) ---)/, (_, head, end, tail) => `${head}${Number(end) - removedLines}${tail}`);
|
||||
for (const [later, earlier] of [...LATER_BROWSER_EDITS, ...LATER_PREAMBLE_EDITS]) historical = historical.replace(later, earlier);
|
||||
return historical
|
||||
.replace(/(--- BEGIN FILE "BROWSER\.md" \(lines \d+-)(\d+)(; section\) ---)/, (_, head, end, tail) => `${head}${Number(end) - removedLines}${tail}`)
|
||||
.replace(/(--- BEGIN FILE "setup-browser-cookies\/SKILL\.md" \(lines )(\d+)-(\d+)(; entrypoint\) ---)/, (_, head, start, end, tail) => `${head}${APPROVED_ENTRYPOINT_START}-${APPROVED_ENTRYPOINT_START + Number(end) - Number(start)}${tail}`);
|
||||
}
|
||||
|
||||
export function manualReviewFixture(root = resolve(import.meta.dir, '../..')): EvalTestEntry {
|
||||
|
||||
@@ -50,6 +50,7 @@ export function createShipHookFixture(id: ShipHookCase, root = fs.mkdtempSync(pa
|
||||
write(path.join(state, 'config.yaml'), 'redact_prepush_hook: true\n');
|
||||
write(path.join(installed, 'gstack-config'), `#!/bin/sh\nprintf 'CONFIG:%s\\n' "$*" >> ${quote(receipts)}\nexec bash ${quote(path.join(ROOT, 'bin/gstack-config'))} "$@"\n`, true);
|
||||
write(path.join(installed, 'gstack-redact'), `#!/bin/sh\nprintf 'INSTALL:%s\\n' "$*" >> ${quote(receipts)}\nexec ${quote(process.execPath)} ${quote(path.join(ROOT, 'bin/gstack-redact'))} "$@"\n`, true);
|
||||
write(path.join(installed, 'gstack-paths'), `#!/bin/sh\nexec bash ${quote(path.join(ROOT, 'bin/gstack-paths'))} "$@"\n`, true);
|
||||
const workflow = readWorkflowExcerpt('ship/SKILL.md', '**Credential pre-push guard', '**Idempotency check');
|
||||
write(path.join(repo, 'workflow.md'), workflow);
|
||||
const guard = workflow.match(/```bash\n([\s\S]*?)```/)![1].trim();
|
||||
|
||||
@@ -114,6 +114,7 @@ function run(
|
||||
...process.env,
|
||||
PATH: pathEnv,
|
||||
GSTACK_DIR: ROOT,
|
||||
GSTACK_HOME: join(tmp, "state"),
|
||||
GSTACK_SUPABASE_URL: "https://stub.supabase.test",
|
||||
GSTACK_SUPABASE_ANON_KEY: "stub-key",
|
||||
STUB_CURL_MODE: opts.mode,
|
||||
|
||||
@@ -43,6 +43,7 @@ beforeEach(() => {
|
||||
mkdirSync(bin, { recursive: true });
|
||||
writeFixture(join(bin, 'gstack-config'), `#!/bin/sh\nexec bash "${join(ROOT, 'bin/gstack-config')}" "$@"\n`);
|
||||
writeFixture(join(bin, 'gstack-redact'), `#!/bin/sh\nexec "${process.execPath}" "${join(ROOT, 'bin/gstack-redact')}" "$@"\n`);
|
||||
writeFixture(join(bin, 'gstack-paths'), `#!/bin/sh\nexec bash "${join(ROOT, 'bin/gstack-paths')}" "$@"\n`);
|
||||
expect(shell('~/.claude/skills/gstack/bin/gstack-config set redact_prepush_hook true').status).toBe(0);
|
||||
});
|
||||
|
||||
|
||||
@@ -5,6 +5,7 @@ import { SNAPSHOT_FLAGS } from '../browse/src/snapshot';
|
||||
import * as fs from 'fs';
|
||||
import * as os from 'os';
|
||||
import * as path from 'path';
|
||||
import { usePrivateStateRoot } from './helpers/private-state-root';
|
||||
|
||||
const ROOT = path.resolve(import.meta.dir, '..');
|
||||
|
||||
@@ -1096,6 +1097,7 @@ describe('CEO review mode validation', () => {
|
||||
|
||||
describe('gstack-slug', () => {
|
||||
const SLUG_BIN = path.join(ROOT, 'bin', 'gstack-slug');
|
||||
usePrivateStateRoot();
|
||||
|
||||
test('binary exists and is executable', () => {
|
||||
expect(fs.existsSync(SLUG_BIN)).toBe(true);
|
||||
@@ -1104,7 +1106,7 @@ describe('gstack-slug', () => {
|
||||
});
|
||||
|
||||
test('outputs SLUG and BRANCH lines in a git repo', () => {
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
expect(result.exitCode).toBe(0);
|
||||
const output = result.stdout.toString();
|
||||
expect(output).toContain('SLUG=');
|
||||
@@ -1112,21 +1114,21 @@ describe('gstack-slug', () => {
|
||||
});
|
||||
|
||||
test('SLUG does not contain forward slashes', () => {
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const slug = result.stdout.toString().match(/SLUG=(.*)/)?.[1] ?? '';
|
||||
expect(slug).not.toContain('/');
|
||||
expect(slug.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
test('BRANCH does not contain forward slashes', () => {
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const branch = result.stdout.toString().match(/BRANCH=(.*)/)?.[1] ?? '';
|
||||
expect(branch).not.toContain('/');
|
||||
expect(branch.length).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
test('output is eval-compatible (KEY=VALUE format)', () => {
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const lines = result.stdout.toString().trim().split('\n');
|
||||
expect(lines.length).toBe(2);
|
||||
expect(lines[0]).toMatch(/^SLUG=.+/);
|
||||
@@ -1134,7 +1136,7 @@ describe('gstack-slug', () => {
|
||||
});
|
||||
|
||||
test('output values contain only safe characters (no shell metacharacters)', () => {
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const result = Bun.spawnSync([SLUG_BIN], { cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 });
|
||||
const slug = result.stdout.toString().match(/SLUG=(.*)/)?.[1] ?? '';
|
||||
const branch = result.stdout.toString().match(/BRANCH=(.*)/)?.[1] ?? '';
|
||||
// Only alphanumeric, dot, dash, underscore are allowed (#133)
|
||||
@@ -1144,7 +1146,7 @@ describe('gstack-slug', () => {
|
||||
test('eval sets variables under bash with set -euo pipefail', () => {
|
||||
const result = Bun.spawnSync(
|
||||
['bash', '-c', 'set -euo pipefail; eval "$(./bin/gstack-slug 2>/dev/null)"; echo "SLUG=$SLUG"; echo "BRANCH=$BRANCH"'],
|
||||
{ cwd: ROOT, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 }
|
||||
{ cwd: ROOT, env: { ...process.env }, stdout: 'pipe', stderr: 'pipe', timeout: 30_000 }
|
||||
);
|
||||
expect(result.exitCode).toBe(0);
|
||||
const output = result.stdout.toString();
|
||||
|
||||
@@ -247,8 +247,9 @@ describe('/spec --no-gate keeps redacting', () => {
|
||||
});
|
||||
|
||||
describe('/spec archive (carved: gate-and-file section)', () => {
|
||||
test('uses eval $(gstack-paths) not hardcoded ~/.gstack/', () => {
|
||||
expect(SEC_TMPL).toMatch(/eval "\$\(.+gstack-paths\)"/);
|
||||
test('resolves the state root with gstack-paths --get, not hardcoded ~/.gstack/', () => {
|
||||
expect(SEC_TMPL).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}"');
|
||||
expect(SEC_TMPL).not.toMatch(/eval "\$\(.+gstack-paths\)"/);
|
||||
expect(SEC_TMPL).toMatch(/\$GSTACK_STATE_ROOT\/projects\/\$SLUG\/specs/);
|
||||
// No hardcoded ~/.gstack/projects path anywhere in /spec:
|
||||
expect(TMPL_UNION).not.toMatch(/~\/\.gstack\/projects\/\$SLUG\/specs/);
|
||||
|
||||
@@ -18,9 +18,7 @@ const ROOT = path.resolve(import.meta.dir, '..');
|
||||
/** Recorded after workstream D. Add a path only with a one-line reason comment, reviewed in the diff. */
|
||||
const BASELINE = [
|
||||
'test/anthropic-preflight.test.ts',
|
||||
'test/artifacts-allowlist-decisions.test.ts',
|
||||
'test/artifacts-init-migration.test.ts',
|
||||
'test/auto-decide-fixture.test.ts',
|
||||
'test/autoplan-artifact-recorder.test.ts',
|
||||
'test/autoplan-artifact-windows-argv.test.ts',
|
||||
'test/autoplan-edit-digests-al.test.ts',
|
||||
@@ -29,15 +27,12 @@ const BASELINE = [
|
||||
'test/autoplan-pending-question.test.ts',
|
||||
'test/autoplan-phase-observer.test.ts',
|
||||
'test/autoplan-public-narration.test.ts',
|
||||
'test/benchmark-cli.test.ts',
|
||||
'test/bootstrap-retention-shard.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/bootstrap-retention.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/bootstrap-session-lifecycle.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/brain-sync-windows-paths.test.ts',
|
||||
'test/build-script-shell-compat.test.ts',
|
||||
'test/builder-profile.test.ts',
|
||||
'test/bun-subprocess-fd-lifetime.test.ts',
|
||||
'test/bun-version-drift.test.ts',
|
||||
'test/carve-guard-completeness.test.ts',
|
||||
'test/carve-plan-fixture.test.ts',
|
||||
'test/carve-section-ordering.test.ts',
|
||||
@@ -51,20 +46,14 @@ const BASELINE = [
|
||||
'test/ceo-mode-pending-submit.test.ts',
|
||||
'test/ceo-mode-posture-native.test.ts',
|
||||
'test/ceo-mode-prerequisite.test.ts',
|
||||
'test/ceo-mode-routing-fixture.test.ts',
|
||||
'test/ceo-plan-mode-fixture.test.ts',
|
||||
'test/ceo-posture-packet.test.ts',
|
||||
'test/ceo-section-loading-fixture.test.ts',
|
||||
'test/ceo-split-collection.test.ts',
|
||||
'test/ceo-split-question-policy.test.ts',
|
||||
'test/changed-files-union.test.ts',
|
||||
'test/ci-image-cli-pin.test.ts',
|
||||
'test/ci-image-tag-binding.test.ts',
|
||||
'test/claude-provider-keychain.test.ts',
|
||||
'test/code-intelligence-cli.test.ts',
|
||||
'test/codex-carve-fixture.test.ts',
|
||||
'test/codex-eval-recording.test.ts',
|
||||
'test/codex-model-probe.test.ts',
|
||||
'test/codex-resume-flag-semantics.test.ts',
|
||||
'test/cso-ntfs-fixture.test.ts',
|
||||
'test/cso-windows-build-contract.test.ts',
|
||||
@@ -75,11 +64,7 @@ const BASELINE = [
|
||||
'test/design-html-section-completion.test.ts',
|
||||
'test/devex-peer-comparison-calibration.test.ts',
|
||||
'test/diagram-render-drift.test.ts',
|
||||
'test/diff-scope.test.ts',
|
||||
'test/disabled-dated-record-at.test.ts',
|
||||
'test/distill-apply.test.ts',
|
||||
'test/distill-free-text.test.ts',
|
||||
'test/docs-config-keys.test.ts',
|
||||
'test/docsync-atomic-writes.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/docsync-command-grammar.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/docsync-nested-writes.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
@@ -97,40 +82,11 @@ const BASELINE = [
|
||||
'test/eng-semantic-terminal.test.ts',
|
||||
'test/eng-test-plan-edit-approval.test.ts',
|
||||
'test/eval-list-cli.test.ts',
|
||||
'test/evidence.test.ts',
|
||||
'test/explain-level-config.test.ts',
|
||||
'test/extension-pty-inject-invariant.test.ts',
|
||||
'test/founder-resources-optout.test.ts',
|
||||
'test/free-tests-workflow-wiring.test.ts',
|
||||
'test/gbrain-lib-validate-varname.test.ts',
|
||||
'test/gbrain-lib-verify.test.ts',
|
||||
'test/gbrain-refresh-install-render.test.ts',
|
||||
'test/gbrain-repo-policy.test.ts',
|
||||
'test/gbrain-source-worktree-advance.test.ts',
|
||||
'test/gbrain-sync-skip.test.ts',
|
||||
'test/gbrain-sync-voyage-code-3-integration.test.ts',
|
||||
'test/gstack-artifacts-url.test.ts',
|
||||
'test/gstack-codex-session-import.test.ts',
|
||||
'test/gstack-config-cross-project.test.ts',
|
||||
'test/gstack-config-defaults.test.ts',
|
||||
'test/gstack-config-key-locale.test.ts',
|
||||
'test/gstack-config-memorable-key.test.ts',
|
||||
'test/gstack-config-redact-keys.test.ts',
|
||||
'test/gstack-detach.test.ts',
|
||||
'test/gstack-developer-profile.test.ts',
|
||||
'test/gstack-gbrain-mcp-verify.test.ts',
|
||||
'test/gstack-gbrain-source-wireup.test.ts',
|
||||
'test/gstack-home-module-scope.test.ts',
|
||||
'test/gstack-learnings-search.test.ts',
|
||||
'test/gstack-question-log.test.ts',
|
||||
'test/gstack-question-preference.test.ts',
|
||||
'test/gstack-redact-cli.test.ts',
|
||||
'test/gstack-repo-mode.test.ts',
|
||||
'test/gstack-session-kind.test.ts',
|
||||
'test/gstack-slug-parity.test.ts',
|
||||
'test/gstack-slug-sanitize.test.ts',
|
||||
'test/gstack-state-root-override.test.ts',
|
||||
'test/gstack-team-init-hook-schema.test.ts',
|
||||
'test/gstack-upgrade-migration-v1_17_0_0.test.ts',
|
||||
'test/gstack-upgrade-migration-v1_37_0_0.test.ts',
|
||||
'test/gstack-upgrade-migration-v1_40_0_0.test.ts',
|
||||
@@ -139,7 +95,6 @@ const BASELINE = [
|
||||
'test/helpers/budget-override.test.ts',
|
||||
'test/helpers/capture-parity-baseline.test.ts',
|
||||
'test/helpers/claude-pty-runner.auq.unit.test.ts', // W4: moved from claude-pty-runner.unit.test.ts (exempt via its design SKILL.md.tmpl read), split along the pty/ module seams
|
||||
'test/helpers/claude-pty-runner.classify.unit.test.ts', // W4: moved from claude-pty-runner.unit.test.ts (exempt via its design SKILL.md.tmpl read), split along the pty/ module seams
|
||||
'test/helpers/claude-pty-runner.launch.unit.test.ts', // W4: moved from claude-pty-runner.unit.test.ts (exempt via its design SKILL.md.tmpl read), split along the pty/ module seams
|
||||
'test/helpers/claude-pty-runner.plan-native.unit.test.ts', // W4: moved from claude-pty-runner.unit.test.ts (exempt via its design SKILL.md.tmpl read), split along the pty/ module seams
|
||||
'test/helpers/claude-pty-runner.runners.unit.test.ts', // W4 fake-driver regressions: the PTY harness is itself the subject (plan-mode paid evals stand on it)
|
||||
@@ -152,22 +107,16 @@ const BASELINE = [
|
||||
'test/helpers/session-runner.test.ts',
|
||||
'test/helpers/sync-command-capture.test.ts',
|
||||
'test/hooks-windows-paths.test.ts',
|
||||
'test/hostile-path-writers.test.ts',
|
||||
'test/ios-debug-bridge-release-guard.test.ts',
|
||||
'test/ios-qa-stateserver-hardening.test.ts',
|
||||
'test/ios-qa-swift-build.test.ts',
|
||||
'test/jargon-list.test.ts',
|
||||
'test/jsonl-merge.test.ts',
|
||||
'test/learnings-injection.test.ts',
|
||||
'test/llm-judge-frontier.test.ts',
|
||||
'test/llm-judge-stream.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/memory-cache-injection.test.ts',
|
||||
'test/memory-ingest-include-gitignored.test.ts',
|
||||
'test/migrations-v1.27.0.0.test.ts',
|
||||
'test/module-size-ratchet.test.ts', // ratchet (c) source scanner (W2): measures product modules as text; its counter is test tooling
|
||||
'test/native-auto-decide-pty.test.ts',
|
||||
'test/no-suicide-exit.test.ts',
|
||||
'test/osv-config-wiring.test.ts',
|
||||
'test/outside-voice-fixture.test.ts',
|
||||
'test/overlay-measurement.test.ts',
|
||||
'test/overlay-recording-order.test.ts',
|
||||
@@ -200,19 +149,14 @@ const BASELINE = [
|
||||
'test/plan-create-combined-permission.test.ts',
|
||||
'test/plan-create-permission.test.ts',
|
||||
'test/plan-create-prepublication.test.ts',
|
||||
'test/plan-design-floor-fixture.test.ts',
|
||||
'test/plan-edit-cropped-permission.test.ts',
|
||||
'test/plan-floor-dx-actor.test.ts',
|
||||
'test/plan-floor-review.test.ts',
|
||||
'test/plan-floor-target.test.ts',
|
||||
'test/plan-mode-evidence.test.ts',
|
||||
'test/plan-pending-question-pty.test.ts',
|
||||
'test/plan-seed-submission.test.ts',
|
||||
'test/plan-skill-read-permission.test.ts',
|
||||
'test/plan-skill-webfetch-permission.test.ts',
|
||||
'test/plan-tune-cathedral.test.ts',
|
||||
'test/pr-title-rewrite.test.ts',
|
||||
'test/pr-title-sync-workflow-safety.test.ts',
|
||||
'test/pty-askuserquestion-single-line.test.ts',
|
||||
'test/pty-numbered-option-indent-native.test.ts',
|
||||
'test/pty-option-selection.test.ts',
|
||||
@@ -229,12 +173,9 @@ const BASELINE = [
|
||||
'test/qa-functional-fixture.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/qa-functional-observer-atomic.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/qa-functional-observer.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/qa-only-capability.test.ts',
|
||||
'test/qa-supervision-selection.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/question-log-hook.test.ts',
|
||||
'test/readme-throughput.test.ts',
|
||||
'test/redact-prepush-rebase-force-push.test.ts',
|
||||
'test/redact-prepush-scan-range.test.ts',
|
||||
'test/review-army-budget.test.ts',
|
||||
'test/review-consensus-lifecycle.test.ts',
|
||||
'test/review-count-markdown.test.ts',
|
||||
@@ -246,29 +187,17 @@ const BASELINE = [
|
||||
'test/setup-browser-hint.test.ts',
|
||||
'test/setup-bun-cmd-and-pipe-bugs.test.ts',
|
||||
'test/setup-conductor-worktree.test.ts',
|
||||
'test/setup-plan-tune-hooks-noninteractive.test.ts',
|
||||
'test/setup-playwright-platform.test.ts',
|
||||
'test/setup-sections-linking.test.ts',
|
||||
'test/setup-timeline-hook-gate.test.ts',
|
||||
'test/shared-libs-cancellation.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals
|
||||
'test/shared-libs-plan-actor.test.ts',
|
||||
'test/shared-libs-revalidation-prompt.test.ts',
|
||||
'test/shared-libs-source-reads.test.ts',
|
||||
'test/ship-coverage-audit-af.test.ts',
|
||||
'test/ship-pr-liveness-policy.test.ts',
|
||||
'test/ship-section-fixture.test.ts',
|
||||
'test/skill-budget-regression.test.ts',
|
||||
'test/skill-parser.test.ts',
|
||||
'test/spawnsync-timeout-tripwire.test.ts',
|
||||
'test/tasks-section-jq.test.ts',
|
||||
'test/taste-engine.test.ts',
|
||||
'test/telemetry-repo-strip.test.ts',
|
||||
'test/test-free-shards-capture.test.ts',
|
||||
'test/timeline.test.ts',
|
||||
'test/ubicloud-runner.test.ts',
|
||||
'test/update-check-crash-sentinel.test.ts',
|
||||
'test/verify-gate.test.ts',
|
||||
'test/workflow-concurrency.test.ts',
|
||||
];
|
||||
|
||||
function freeTests(): string[] {
|
||||
@@ -280,7 +209,8 @@ function testsOnlyTestCode(file: string): { counted: boolean; helper?: string }
|
||||
const source = fs.readFileSync(path.join(ROOT, file), 'utf8');
|
||||
const targets = directSpecifiers(source).map(specifier => resolveRepoSpecifier(ROOT, file, specifier)).filter(Boolean) as string[];
|
||||
if (targets.some(target => !target.startsWith('test/') && !target.startsWith('node_modules/'))) return { counted: false };
|
||||
if (/(['"`])[^'"`\n]*(?:\bbin\/|SKILL\.md|\.tmpl)[^'"`\n]*\1/.test(source)) return { counted: false };
|
||||
if (/(['"`])[^'"`\n]*(?:\bbin\/|SKILL\.md|CLAUDE\.md|\.tmpl)[^'"`\n]*\1/.test(source)) return { counted: false };
|
||||
if (/(['"`])(?:\.\/)?\.github\b[^'"`\n]*\1|(['"`])bin\2\s*,\s*(['"`])[\w.-]+\3/.test(source)) return { counted: false };
|
||||
return { counted: true, helper: targets.find(target => target.startsWith('test/helpers/') && !target.endsWith('.test.ts')) };
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user