Merge origin/main (v1.64.0.0) into garrytan/time-attack-fork-review

Both waves fixed several of the same bugs; resolutions keep whichever
shape this branch's tests pin (#2018 jq bind, #1798 set-- pattern,
stop-ack, lock errors, polyfill windowsHide) and take main's richer
codex Step 2A (it absorbed the same mktemp fix). True unions: memory-
ingest keeps main's capability-probed --include-gitignored inside our
GIT_CEILING defense; setup wraps main's Playwright platform override in
our stale-healing install lock; package.json takes main's diff@^9 and
the combined test glob (design/test + ios-qa/daemon/test, 30s timeout).
Generated SKILL.md files regenerated from resolved templates, never
hand-picked. Ship goldens refreshed; parity/carve budgets re-measured
for the summed preamble growth of both waves (itemized per entry).
This commit is contained in:
Garry Tan
2026-08-15 09:57:34 -07:00
241 changed files with 7683 additions and 4716 deletions
+21 -5
View File
@@ -167,7 +167,11 @@ export function probePoisonedChromiumBundle(chromiumExecutablePath: string): voi
* restarts on backoff.
*/
export async function resolveDisconnectCause(browser: Browser | null): Promise<'clean' | 'crash'> {
const proc = browser?.process();
// `.process()` only exists on browsers we launched ourselves. A browser
// obtained via connectOverCDP() (or a stub in tests) has no such method —
// calling it blind throws inside the disconnect handler, which killed the
// whole daemon with "browser?.process is not a function".
const proc = typeof browser?.process === 'function' ? browser.process() : null;
if (proc && proc.exitCode === null && proc.signalCode === null) {
await new Promise<void>((resolve) => {
const timer = setTimeout(resolve, 1000);
@@ -869,19 +873,31 @@ export class BrowserManager {
const page = this.pages.get(tabId);
if (!page) throw new Error(`Tab ${tabId} not found`);
// Capture BEFORE close(): the page 'close' event handler wired in
// wirePageEvents() can fire while page.close() is awaited. It removes
// the tab from the maps and reassigns activeTabId (to 0 when no tabs
// remain), so a post-close `tabId === this.activeTabId` check is
// order-dependent — whether the event dispatches before or after
// close() resolves varies across Playwright/Chromium versions and
// machines, and losing the race means the last-tab auto-create below
// never runs, leaving the manager with zero tabs.
const wasActive = tabId === this.activeTabId;
await page.close();
this.pages.delete(tabId);
this.tabSessions.delete(tabId);
this.tabOwnership.delete(tabId);
// Switch to another tab if we closed the active one
if (tabId === this.activeTabId) {
if (wasActive) {
const remaining = [...this.pages.keys()];
if (remaining.length > 0) {
this.activeTabId = remaining[remaining.length - 1];
} else {
if (remaining.length === 0) {
// No tabs left — create a new blank one
await this.newTab();
} else if (!this.pages.has(this.activeTabId)) {
// The 'close' handler may have already switched to a valid tab;
// only reassign when activeTabId no longer points at a live tab.
this.activeTabId = remaining[remaining.length - 1];
}
}
}
+23 -1
View File
@@ -34,7 +34,12 @@ export function getGitRoot(): string | null {
const proc = Bun.spawnSync(['git', 'rev-parse', '--show-toplevel'], {
stdout: 'pipe',
stderr: 'pipe',
timeout: 2_000, // Don't hang if .git is broken
// Raised from 2s: under heavy machine load `git rev-parse` routinely
// takes >2s (measured 6.3s spikes). Timing out here returns null →
// resolveConfig falls back to process.cwd() → state files scatter across
// cwds (split-brain daemons; `goto` and `url` hit different servers). 8s
// still bounds a genuinely broken .git from hanging the CLI forever.
timeout: 8_000,
});
if (proc.exitCode !== 0) return null;
return proc.stdout.toString().trim() || null;
@@ -78,6 +83,20 @@ export function resolveConfig(
};
}
function isIgnoredByGit(projectDir: string, relPath: string): boolean {
try {
const proc = Bun.spawnSync(['git', 'check-ignore', '-q', '--', relPath], {
cwd: projectDir, stdout: 'pipe', stderr: 'pipe',
timeout: 2_000,
});
return proc.exitCode === 0;
} catch {
// git not found, timed out, or not a repo (exit 128). Fall through to
// the text-check path — appending is the safe default when unsure.
return false;
}
}
/**
* Create the .gstack/ state directory if it doesn't exist.
* Throws with a clear message on permission errors.
@@ -96,6 +115,9 @@ export function ensureStateDir(config: BrowseConfig): void {
}
// Ensure .gstack/ is in the project's .gitignore
// First, check if git already ignores .gstack/ (via global excludes, .git/info/exclude, or parent .gitignore)
if (isIgnoredByGit(config.projectDir, '.gstack/')) return;
const gitignorePath = path.join(config.projectDir, '.gitignore');
try {
const content = fs.readFileSync(gitignorePath, 'utf-8');
+48 -2
View File
@@ -42,6 +42,52 @@ import * as os from 'os';
let warnedOnce = false;
let cachedSid: string | null | undefined;
/**
* Resolve the current user's SID, cached for the process lifetime.
*
* Returns null if `whoami` is unavailable or its output cannot be parsed,
* in which case callers fall back to a domain-qualified account name.
*/
function currentUserSid(): string | null {
if (cachedSid !== undefined) return cachedSid;
try {
// Pin to the System32 binary. A bare `whoami` resolves to the MSYS/Git
// Bash build under a bash-flavoured PATH, which rejects `/user` — the
// lookup would then silently fail on one of the most common Windows
// setups for this tool.
const systemRoot = process.env.SystemRoot || process.env.windir || 'C:\\Windows';
const out = execFileSync(`${systemRoot}\\System32\\whoami.exe`, ['/user', '/fo', 'csv', '/nh'], {
encoding: 'utf8',
});
const match = out.match(/S-1-[\d-]+/);
cachedSid = match ? match[0] : null;
} catch {
cachedSid = null;
}
return cachedSid;
}
/**
* The principal to hand icacls for "the current user".
*
* An unqualified username is ambiguous: on a machine whose hostname equals
* the username, it fails to resolve to the user account and icacls silently
* writes an ACE for the machine SID instead. Combined with `/inheritance:r`
* that leaves a directory whose only ACE matches nobody — locking out the
* process that just created it.
*
* `*<SID>` is icacls' literal-SID form and is immune to that ambiguity.
* The domain-qualified name is the fallback.
*/
function currentUserPrincipal(): string {
const sid = currentUserSid();
if (sid) return `*${sid}`;
const domain = process.env.USERDOMAIN || os.hostname();
return `${domain}\\${os.userInfo().username}`;
}
function warnIcaclsFailure(fsPath: string, err: unknown): void {
if (warnedOnce) return;
warnedOnce = true;
@@ -67,7 +113,7 @@ function warnIcaclsFailure(fsPath: string, err: unknown): void {
export function restrictFilePermissions(filePath: string): void {
if (process.platform === 'win32') {
try {
const user = os.userInfo().username;
const user = currentUserPrincipal();
execFileSync(
'icacls',
[filePath, '/inheritance:r', '/grant:r', `${user}:(F)`],
@@ -97,7 +143,7 @@ export function restrictFilePermissions(filePath: string): void {
export function restrictDirectoryPermissions(dirPath: string): void {
if (process.platform === 'win32') {
try {
const user = os.userInfo().username;
const user = currentUserPrincipal();
execFileSync(
'icacls',
[dirPath, '/inheritance:r', '/grant:r', `${user}:(OI)(CI)(F)`],
+12 -1
View File
@@ -1592,8 +1592,18 @@ export function buildFetchHandler(cfg: ServerConfig): ServerHandle {
process.env.GSTACK_AGENT_WATCHDOG_TICK_MS || '60000',
10,
);
const RESPAWN_GUARD_WINDOW_MS = 60_000;
const RESPAWN_GUARD_MAX = 3;
// The guard window MUST span enough ticks for RESPAWN_GUARD_MAX respawns to
// land inside it. This was a fixed 60_000 against a 60_000 tick, so at most
// ONE respawn could ever be in the window and `respawnHistory.length >= 3`
// was unreachable — the guard could not fire at the default tick rate, and a
// steady one-per-tick leak ran unbounded instead of stopping after 3. Scale
// with the tick so the intent ("3 crashes in quick succession → stop") holds
// at any tick value: 3 respawns within 5 ticks trips it.
const RESPAWN_GUARD_WINDOW_MS = Math.max(
60_000,
AGENT_WATCHDOG_TICK_MS * (RESPAWN_GUARD_MAX + 2),
);
let agentRespawnGuardTripped = false;
if (ownsTerminalAgent) {
@@ -1626,6 +1636,7 @@ export function buildFetchHandler(cfg: ServerConfig): ServerHandle {
const pid = spawnTerminalAgent({
stateFile: cfg.config.stateFile,
serverPort: cfg.browsePort,
ownerPid: process.pid,
cwd: cfg.config.projectDir,
});
if (pid) {
+4 -2
View File
@@ -48,12 +48,13 @@ export function resolveTerminalAgentScript(searchHints: { metaDir?: string; exec
*
* Used by both the CLI cold-start path (cli.ts) and the v1.44 watchdog in
* server.ts. Centralizing here removes a copy-paste between them and means
* future spawn-env additions (e.g. BROWSE_OWNER_PID for the generation
* counter rollout) land in one place.
* spawn-env additions (BROWSE_OWNER_PID being the first) land in one place.
*/
export function spawnTerminalAgent(opts: {
stateFile: string;
serverPort: number;
/** PID of the browse server that owns this agent. */
ownerPid: number;
cwd?: string;
/** Optional extra env vars to add to the agent's process env. */
extraEnv?: Record<string, string>;
@@ -74,6 +75,7 @@ export function spawnTerminalAgent(opts: {
...process.env,
BROWSE_STATE_FILE: opts.stateFile,
BROWSE_SERVER_PORT: String(opts.serverPort),
BROWSE_OWNER_PID: String(opts.ownerPid),
...(opts.extraEnv || {}),
},
stdio: ['ignore', 'ignore', 'ignore'],
+30 -7
View File
@@ -30,6 +30,11 @@ import { writeAgentRecord, clearAgentRecord } from './terminal-agent-control';
const STATE_FILE = process.env.BROWSE_STATE_FILE || path.join(process.env.HOME || '/tmp', '.gstack', 'browse.json');
const PORT_FILE = path.join(path.dirname(STATE_FILE), 'terminal-port');
const BROWSE_SERVER_PORT = parseInt(process.env.BROWSE_SERVER_PORT || '0', 10);
const BROWSE_OWNER_PID = parseInt(process.env.BROWSE_OWNER_PID || '0', 10);
const OWNER_WATCHDOG_MS = parseInt(
process.env.GSTACK_TERMINAL_OWNER_WATCHDOG_MS || '15000',
10,
);
const EXTENSION_ID = process.env.BROWSE_EXTENSION_ID || ''; // optional: tighten Origin check
const INTERNAL_TOKEN = crypto.randomBytes(32).toString('base64url'); // shared with parent server via env at spawn
/**
@@ -598,12 +603,10 @@ function buildServer() {
// first that matches a known token.
const protoHeader = req.headers.get('sec-websocket-protocol') || '';
let token: string | null = null;
let acceptedProtocol: string | null = null;
for (const raw of protoHeader.split(',').map(s => s.trim()).filter(Boolean)) {
const candidate = raw.startsWith('gstack-pty.') ? raw.slice('gstack-pty.'.length) : raw;
if (validTokens.has(candidate)) {
token = candidate;
acceptedProtocol = raw;
break;
}
}
@@ -632,13 +635,13 @@ function buildServer() {
// sessionsById so /internal/restart and (Commit 3) re-attach
// lookups can find it.
const sessionId = validTokens.get(token) ?? null;
// No explicit Sec-WebSocket-Protocol echo: Bun >= 1.3 auto-echoes the
// first offered protocol in the 101 response, so setting the header
// here produced a DUPLICATE header — strict clients (Chromium, python
// websockets) reject the handshake per RFC 6455 and the sidebar
// terminal could never connect. Verified on Bun 1.3.6.
const upgraded = server.upgrade(req, {
data: { cookie: token, sessionId },
// Echo the protocol back so the browser accepts the upgrade.
// Required when the client sends Sec-WebSocket-Protocol — the
// server MUST select one of the offered protocols, otherwise
// the browser closes the connection immediately.
...(acceptedProtocol ? { headers: { 'Sec-WebSocket-Protocol': acceptedProtocol } } : {}),
});
return upgraded ? undefined : new Response('upgrade failed', { status: 500 });
}
@@ -987,13 +990,33 @@ function main() {
console.log(`[terminal-agent] listening on 127.0.0.1:${port} pid=${process.pid} gen=${CURRENT_GEN}`);
// Cleanup port file + agent record on exit.
let cleaningUp = false;
const cleanup = () => {
if (cleaningUp) return;
cleaningUp = true;
safeUnlink(PORT_FILE);
safeUnlink(INTERNAL_TOKEN_FILE);
clearAgentRecord(dir);
process.exit(0);
};
process.on('SIGTERM', cleanup);
process.on('SIGINT', cleanup);
// The terminal agent is intentionally detached so it survives the short-lived
// CLI launcher, but its real owner is the persistent browse server. If that
// server crashes or is killed before running normal shutdown, the agent would
// otherwise be adopted by PID 1 and live forever. Poll the server PID and use
// the same cleanup path as an intentional shutdown when it disappears.
if (BROWSE_OWNER_PID > 0) {
const ownerWatchdog = setInterval(() => {
try {
process.kill(BROWSE_OWNER_PID, 0);
} catch {
cleanup();
}
}, OWNER_WATCHDOG_MS);
(ownerWatchdog as any)?.unref?.();
}
}
// Export the internal token so cli.ts can pass the SAME value to the parent
+16 -1
View File
@@ -269,9 +269,24 @@ export async function validateNavigationUrl(url: string): Promise<string> {
return pathToFileURL(fsPath).href + parsed.search + parsed.hash;
}
// about:blank ONLY — the canonical empty page, and the one the daemon opens its own
// first tab on. Blocking it meant `browse newtab about:blank` failed, which is what
// `make-pdf setup` runs as its Chromium smoke test: make-pdf reported "Chromium failed
// to launch" against a perfectly healthy Chromium, and any browse session whose daemon
// restarted could never recreate the blank tab it starts from.
//
// Deliberately not the whole `about:` scheme. about:blank has no origin, loads nothing
// and runs nothing; about:config, about:net-internals and friends are real surfaces.
// Exact href match, not a prefix test, so `about:blankfoo` stays blocked.
// Compared lower-cased: the URL parser normalises the PROTOCOL but not the opaque part,
// so `ABOUT:BLANK` parses to href `about:BLANK` and an exact === would reject it.
if (parsed.protocol === 'about:' && parsed.href.toLowerCase() === 'about:blank') {
return 'about:blank';
}
if (parsed.protocol !== 'http:' && parsed.protocol !== 'https:') {
throw new Error(
`Blocked: scheme "${parsed.protocol}" is not allowed. Only http:, https:, and file: URLs are permitted.`
`Blocked: scheme "${parsed.protocol}" is not allowed. Only http:, https:, file:, and about:blank URLs are permitted.`
);
}
+10 -7
View File
@@ -249,11 +249,11 @@ export async function handleWriteCommand(
if (!filePath) throw new Error('Usage: browse load-html <file> [--wait-until load|domcontentloaded|networkidle] [--tab-id <N>] | load-html --from-file <payload.json> [--tab-id <N>]');
// Extension allowlist
const ALLOWED_EXT = ['.html', '.htm', '.xhtml', '.svg'];
const ALLOWED_EXT = ['.html', '.htm', '.xhtml'];
const ext = path.extname(filePath).toLowerCase();
if (!ALLOWED_EXT.includes(ext)) {
throw new Error(
`load-html: file does not appear to be HTML. Expected .html/.htm/.xhtml/.svg, got ${ext || '(no extension)'}. Rename the file if it's really HTML.`
`load-html: file does not appear to be HTML. Expected .html/.htm/.xhtml, got ${ext || '(no extension)'}. Rename the file if it's really HTML.`
);
}
@@ -377,11 +377,14 @@ export async function handleWriteCommand(
const value = valueParts.join(' ');
if (!selector || !value) throw new Error('Usage: browse fill <selector> <value>');
const resolved = await session.resolveRef(selector);
if ('locator' in resolved) {
await resolved.locator.fill(value, { timeout: 5000 });
} else {
await target.locator(resolved.selector).fill(value, { timeout: 5000 });
}
const locator = 'locator' in resolved ? resolved.locator : target.locator(resolved.selector);
await locator.fill(value, { timeout: 5000 });
// Playwright's fill() only dispatches an `input` event. Frameworks that
// validate on `change` (AngularJS ng-change, debounced strength/match
// checks — e.g. cPanel's Jupiter theme) never see the update, so a value
// that's correct in the DOM can still fail the framework's own
// validation. Dispatch `change` too so those listeners fire.
await locator.dispatchEvent('change');
// Wait for network to settle (form validation XHRs)
await page.waitForLoadState('networkidle', { timeout: 2000 }).catch(() => {});
return `Filled ${selector}`;