fix(cli): 1.31.1 — reaper no longer blocks the daemon event loop

1.31.0 introduced a session reaper that called execFileSync(ps) once
per registered session every 5s. With many sessions registered, the
daemon's event loop stalled for hundreds of ms — long enough that
incoming /v1/version probes from the CLI timed out against a healthy
daemon and the new service-managed warning fired.

Fix:

- getProcessStartTime is now async (execFile + promisify); never
  blocks the event loop
- New getProcessStartTimes(pids) issues one batched ps for all
  survivors instead of N separate forks. Sweep cost is fixed
  regardless of session count.
- registerSession stays sync; start-time capture is fire-and-forget
- reapDead is now async; the setInterval wrapper voids it so a
  rejected sweep cannot crash the daemon

Behavior is otherwise unchanged from 1.31.0: same 5s cadence, same
PID-reuse guard semantics, same broker-WS teardown via the registry
hook. 83/83 tests still green.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

apps/cli/src/daemon/process-info.ts

@@ -9,31 +9,83 @@
  * sweep — if it changed, treat the original process as dead.
  *
  * macOS + Linux both expose `ps -o lstart=` returning a fixed-format
- * timestamp ("Sun May  4 09:14:00 2026"). Equality is the only operation
- * the reaper needs, so we keep the value as an opaque string.
+ * timestamp ("Sun May  4 09:14:00 2026"). Equality is the only
+ * operation the reaper needs, so we keep the value as an opaque string.
+ *
+ * IMPORTANT (1.31.1): every fork / execFile blocks the daemon's event
+ * loop until ps completes (~30-80 ms per call on macOS). The first
+ * 1.31.0 implementation called execFileSync once per registered
+ * session every 5 s, and with 10+ sessions that stalled IPC for hundreds
+ * of milliseconds at a time — long enough that probes against
+ * /v1/version were declared "stale" and the CLI fell back to the cold
+ * path with the misleading "service-managed daemon not responding"
+ * warning. This module now exposes:
+ *
+ *   - `getProcessStartTime(pid)`: async, single-pid, used at register.
+ *   - `getProcessStartTimes(pids)`: async, batched, used by the reaper.
+ *     One ps invocation handles N pids, so the per-sweep cost is fixed
+ *     and tiny regardless of how many sessions are registered.
  */
 
-import { execFileSync } from "node:child_process";
+import { execFile } from "node:child_process";
+import { promisify } from "node:util";
+
+const execFileAsync = promisify(execFile);
 
 /**
  * Returns a stable process-start identifier for `pid`, or null if the
- * process is dead or unreachable. Cheap (~1 ms per call) — safe to use
- * inside the 5-second reaper sweep.
+ * process is dead or unreachable. Async — never blocks the event loop.
  */
-export function getProcessStartTime(pid: number): string | null {
+export async function getProcessStartTime(pid: number): Promise<string | null> {
   if (!Number.isFinite(pid) || pid <= 0) return null;
   try {
-    const out = execFileSync("ps", ["-o", "lstart=", "-p", String(pid)], {
+    const { stdout } = await execFileAsync("ps", ["-o", "lstart=", "-p", String(pid)], {
       encoding: "utf8",
       timeout: 1_000,
-      stdio: ["ignore", "pipe", "ignore"],
-    }).trim();
+    });
+    const out = stdout.trim();
     return out.length > 0 ? out : null;
   } catch {
     return null;
   }
 }
 
+/**
+ * Batched form: returns a Map<pid, lstart> for every pid that is still
+ * alive. Pids that ps doesn't return (i.e. dead) are absent from the
+ * map. One ps fork handles all pids — O(1) sweep cost regardless of
+ * session count.
+ */
+export async function getProcessStartTimes(pids: number[]): Promise<Map<number, string>> {
+  const result = new Map<number, string>();
+  const valid = pids.filter((p) => Number.isFinite(p) && p > 0);
+  if (valid.length === 0) return result;
+  // ps -o pid,lstart= -p p1,p2,...  emits one row per live pid:
+  //   "  12345 Sun May  4 09:14:00 2026"
+  // Dead pids are silently omitted.
+  try {
+    const { stdout } = await execFileAsync(
+      "ps",
+      ["-o", "pid=,lstart=", "-p", valid.join(",")],
+      { encoding: "utf8", timeout: 2_000 },
+    );
+    for (const raw of stdout.split("\n")) {
+      const line = raw.trim();
+      if (!line) continue;
+      const m = /^(\d+)\s+(.+)$/.exec(line);
+      if (!m) continue;
+      const pid = Number.parseInt(m[1]!, 10);
+      const lstart = m[2]!.trim();
+      if (Number.isFinite(pid) && lstart.length > 0) result.set(pid, lstart);
+    }
+  } catch {
+    // ps failure (timeout, ENOENT) — treat as "no info available" and
+    // let the reaper fall back to bare liveness for these pids. Better
+    // to keep entries than to nuke them on a transient ps error.
+  }
+  return result;
+}
+
 /** Liveness-only probe (signal 0). Use together with start-time guard. */
 export function isPidAlive(pid: number): boolean {
   if (!Number.isFinite(pid) || pid <= 0) return false;