fix(browse): tame the macOS headless GPU spin + reap the lock-less headless Chromium on stop (#2709)

Two defects in one report. On macOS 26 / Apple Silicon the headless-shell GPU
process pegs ~800% CPU indefinitely after real page work and --disable-gpu
alone is not enough; the reporter validated that adding
--disable-software-rasterizer/--disable-gpu-compositing/--disable-gpu-watchdog
drops it to 0.0% with screenshots still working. The flag block is a pure
platform-parameterized function (unit-tested on any host), darwin-gated,
headless-only (buildGStackLaunchArgs feeds the headed/GBrowser paths where
GPU-off is wrong), with a GSTACK_DISABLE_GPU=off escape.

Separately: the headless launch has no userDataDir, so it never writes the
SingletonLock that killOrphanChromium walks — 'browse stop' reported success
while the orphan kept spinning. The daemon now records the launched child's
pid + wall-clock start time in the state file (the xvfbPid/xvfbStartTime
contract), and stop paths reap a survivor only after verifying BOTH the
recorded start time and a Chromium-looking cmdline — a recycled PID, even one
running a different legitimate Chromium, is never killed (identity tests
include the coreutils-shebang trap that defeats argv0 renames).

macOS efficacy is per the reporter's validation; live re-verification on
Apple silicon is tracked in TODOS.md.

Refs #2709

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

browse/src/browser-manager.ts

@@ -23,6 +23,30 @@ import { validateNavigationUrl } from './url-validation';
 import { TabSession, type RefEntry } from './tab-session';
 import { resolveChromiumProfile, cleanSingletonLocks } from './config';
 import { launchWithXProtectHeal } from './xprotect-heal';
+import { readPidStartTime } from './xvfb';
+
+/**
+ * Headless GPU flags (#2709): on macOS 26 / Apple Silicon the headless-shell
+ * GPU process can peg ~800% CPU indefinitely after real page work, and
+ * --disable-gpu alone is not enough — the software-compositing GPU process
+ * still spawns and still spins. The reporter validated this exact flag set
+ * drops it to 0.0% with screenshots still working. darwin-gated: on Linux CI
+ * and Windows the GPU process behaves, and the flags are a mild automation
+ * tell. GSTACK_DISABLE_GPU=off opts out. Pure function (platform + env
+ * injected) so the darwin behavior is unit-testable on any host. Deliberately
+ * NOT in buildGStackLaunchArgs: that feeds the headed/GBrowser paths too,
+ * where GPU-off is user-visibly wrong.
+ */
+export function headlessGpuArgs(platform: string, env: NodeJS.ProcessEnv): string[] {
+  if (platform !== 'darwin') return [];
+  if ((env.GSTACK_DISABLE_GPU || '').toLowerCase() === 'off') return [];
+  return [
+    '--disable-gpu',
+    '--disable-software-rasterizer',
+    '--disable-gpu-compositing',
+    '--disable-gpu-watchdog',
+  ];
+}
 import { withCdpSession } from './cdp-bridge';
 import type { MemorySnapshot, MemoryStructureStats, MemoryTabSnapshot, MemoryProcess } from './memory-snapshot';
 
@@ -261,6 +285,17 @@ export class BrowserManager {
   private nextTabId: number = 1;
   private extraHeaders: Record<string, string> = {};
   private customUserAgent: string | null = null;
+  // #2709: identity of the Chromium child WE launched (headless path). The
+  // headless launch has no userDataDir, so killOrphanChromium's SingletonLock
+  // walk is a structural no-op for it — `browse stop` reported success while
+  // the orphaned GPU process kept spinning. PID alone is not identity (reuse);
+  // start time makes the later reap safe (same contract as xvfbPid/xvfbStartTime).
+  private chromiumProcInfo: { pid: number; startTime: string } | null = null;
+
+  /** PID + start-time of the launched Chromium child, when we own one. */
+  getChromiumProcInfo(): { pid: number; startTime: string } | null {
+    return this.chromiumProcInfo;
+  }
 
   // ─── Viewport + deviceScaleFactor (context options) ──────────
   // Tracked at the manager level so recreateContext() preserves them.
@@ -479,6 +514,12 @@ export class BrowserManager {
       console.log(`[browse] Extensions loaded from: ${extensionsDir}`);
     }
 
+    // #2709: headless-only — the extensions path above forces headed mode,
+    // and headed/GBrowser sessions must keep the GPU.
+    if (useHeadless) {
+      launchArgs.push(...headlessGpuArgs(process.platform, process.env));
+    }
+
     // XProtect self-heal wrapper (P0 #2554): a macOS definition update can
     // start SIGKILLing the pinned Chromium at spawn. On the classified
     // signature, clear quarantine on the Playwright cache + force-reinstall
@@ -519,6 +560,15 @@ export class BrowserManager {
       void handleChromiumDisconnect(this.browser);
     });
 
+    // #2709: record the child's identity so the CLI can reap a survivor after
+    // daemon shutdown. `.process()` exists here — we launched this browser.
+    {
+      const proc = typeof this.browser.process === 'function' ? this.browser.process() : null;
+      this.chromiumProcInfo = proc?.pid
+        ? { pid: proc.pid, startTime: readPidStartTime(proc.pid) }
+        : null;
+    }
+
     const contextOptions: BrowserContextOptions = {
       viewport: { width: this.currentViewport.width, height: this.currentViewport.height },
       deviceScaleFactor: this.deviceScaleFactor,

browse/src/cli.ts

@@ -13,6 +13,7 @@ import * as fs from 'fs';
 import * as path from 'path';
 import { spawn as nodeSpawn } from 'child_process';
 import { safeUnlink, safeUnlinkQuiet, safeKill, isProcessAlive } from './error-handling';
+import { readPidStartTime, readPidCmdline } from './xvfb';
 import { writeSecureFile, mkdirSecure } from './file-permissions';
 import { resolveConfig, ensureStateDir, readVersionHash, isPairAgentEnabled, resolveChromiumProfile } from './config';
 import { parseProxyConfig, computeConfigHash, ProxyConfigError } from './proxy-config';
@@ -131,6 +132,9 @@ interface ServerState {
   xvfbPid?: number;
   xvfbStartTime?: number;
   xvfbDisplay?: string;
+  /** Launched-Chromium identity for post-stop reaping (#2709). */
+  chromiumPid?: number;
+  chromiumStartTime?: string;
 }
 
 // ─── State File ────────────────────────────────────────────────
@@ -293,6 +297,32 @@ async function killOrphanChromium(profileDir: string = chromiumProfileDir()): Pr
   }
 }
 
+/**
+ * Reap the launched Chromium recorded in the state file (#2709). The headless
+ * launch has no userDataDir, so it never writes the SingletonLock that
+ * killOrphanChromium walks — `browse stop` reported success while the
+ * orphaned GPU process kept spinning (~800% CPU on macOS 26). Identity is
+ * verified TWO ways before any signal — start time matches the recorded
+ * value AND the executable looks like Chromium — so a recycled PID (even one
+ * now running a different, legitimate Chromium) is never killed.
+ */
+export async function reapRecordedChromium(state: {
+  chromiumPid?: number;
+  chromiumStartTime?: string;
+}): Promise<void> {
+  const pid = state.chromiumPid;
+  if (!pid || !isProcessAlive(pid)) return;
+  if (!state.chromiumStartTime || readPidStartTime(pid) !== state.chromiumStartTime) return;
+  const cmd = readPidCmdline(pid).toLowerCase();
+  if (!/chrom|headless_shell/.test(cmd)) return;
+  safeKill(pid, 'SIGTERM');
+  await new Promise(r => setTimeout(r, 1000));
+  if (isProcessAlive(pid)) {
+    safeKill(pid, 'SIGKILL');
+    await new Promise(r => setTimeout(r, 500));
+  }
+}
+
 /** Total wall-clock budget for the busy-vs-dead health probe (#2219,
  * decision F10). The old ~1s window (3 × 250ms) was shorter than how long a
  * daemon stays unresponsive while Chromium chews a heavy dev-mode page with a
@@ -1823,7 +1853,10 @@ Refs:           After 'snapshot', use @e1, @e2... as selectors:
       await killServer(stopState.pid);
       // Reap the orphaned Chromium child + clear its profile locks so the
       // NEXT launch is clean (same cleanup as the disconnect force path).
+      // The headless child has no SingletonLock — reap it via the recorded
+      // identity too (#2709).
       await killOrphanChromium();
+      await reapRecordedChromium(stopState);
       cleanChromiumProfileLocks();
       safeUnlinkQuiet(config.stateFile);
       console.log('Daemon stopped (forced — tabs/cookies/logins discarded).');
@@ -1913,6 +1946,14 @@ Refs:           After 'snapshot', use @e1, @e2... as selectors:
 
   await sendCommand(state, command, commandArgs);
 
+  // #2709: after a graceful stop, the daemon has closed Chromium via
+  // Playwright — but on macOS 26 the GPU process can survive that close and
+  // spin at ~800% CPU forever. The state snapshot read above still carries
+  // the launched child's identity; reap a verified survivor.
+  if (command === 'stop') {
+    await reapRecordedChromium(state);
+  }
+
   // #1781: `focus` means "show me the window". The server-side focus activates
   // the page via CDP, but on macOS the app can still sit on another Space — pull
   // it to the user's current Space too.

browse/src/server.ts

@@ -3188,6 +3188,14 @@ export async function start() {
     // daemon launch on this state file) can validate-then-cleanup orphans
     // without clobbering a recycled PID.
     ...(xvfb ? { xvfbPid: xvfb.pid, xvfbStartTime: xvfb.startTime, xvfbDisplay: xvfb.display } : {}),
+    // #2709: launched-Chromium identity (pid + start time) so `browse stop`
+    // can reap a survivor — the headless launch has no SingletonLock for
+    // killOrphanChromium to walk, and on macOS 26 the orphaned GPU process
+    // kept spinning at ~800% CPU after the daemon exited.
+    ...(() => {
+      const info = browserManager.getChromiumProcInfo();
+      return info ? { chromiumPid: info.pid, chromiumStartTime: info.startTime } : {};
+    })(),
   };
   const tmpFile = tmpStatePath();
   fs.writeFileSync(tmpFile, JSON.stringify(state, null, 2), { mode: 0o600 });