feat(self-update): launchd-daemon supervisor — rootless restart on headless Macs

A KeepAlive system-level LaunchDaemon (the right setup for headless Macs,
where no GUI login means LaunchAgents never start) is now detected as
supervisor 'launchd-daemon': the updater kills the server PID (passed via
--server-pid) and launchd respawns it on the new dist/ — no root needed.
Detection requires the daemon plist to be bootstrapped AND KeepAlive=true.

Also: on boot, a 'completed-needs-manual-restart' status auto-completes
when the running version matches the staged target, so the stale
'restart Codeman to apply' instruction no longer lingers in the UI.

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

CLAUDE.md

@@ -163,7 +163,7 @@ Codeman is a Claude Code session manager with web interface and autonomous Ralph
 
 **Circuit breaker**: Prevents respawn thrashing. States: `CLOSED` → `HALF_OPEN` → `OPEN`. Reset: `/api/sessions/:id/ralph-circuit-breaker/reset`.
 
-**Self-update** (App Settings → Updates): in-app updater for **git-clone installs** supervised by systemd/launchd. The update restarts the very process running it, so the real work runs in a DETACHED `scripts/self-update.sh` (`git checkout <release tag> && npm install && npm run build && restart`) that outlives the restart; it writes progress to `dataPath('update-status.json')`, which the browser polls across the connection drop. Channel = latest `codeman@X.Y.Z` release tag; dirty trees are auto-stashed. `src/web/self-update.ts` splits PURE helpers (semver/tag parsing, reconcile decision — unit-tested) from IO wrappers (`getInstallInfo`/`checkForUpdate`/`startUpdate`/`reconcileUpdateOnBoot`). Routes: `GET /api/system/update/check`, `POST /api/system/update`, `GET /api/system/update/status`. Types: `src/types/update.ts`. npm installs report as non-updatable.
+**Self-update** (App Settings → Updates): in-app updater for **git-clone installs** supervised by systemd/launchd. Supervisors: `systemd` (user unit), `launchd` (GUI LaunchAgent, gui-domain kickstart), `launchd-daemon` (KeepAlive system LaunchDaemon on headless Macs — restarts rootlessly by killing the server PID and letting launchd respawn it; detected only when the daemon is bootstrapped AND KeepAlive), else `none` → "restart manually" message; on next boot a manual-restart status auto-completes when the running version matches the target. The update restarts the very process running it, so the real work runs in a DETACHED `scripts/self-update.sh` (`git checkout <release tag> && npm install && npm run build && restart`) that outlives the restart; it writes progress to `dataPath('update-status.json')`, which the browser polls across the connection drop. Channel = latest `codeman@X.Y.Z` release tag; dirty trees are auto-stashed. `src/web/self-update.ts` splits PURE helpers (semver/tag parsing, reconcile decision — unit-tested) from IO wrappers (`getInstallInfo`/`checkForUpdate`/`startUpdate`/`reconcileUpdateOnBoot`). Routes: `GET /api/system/update/check`, `POST /api/system/update`, `GET /api/system/update/status`. Types: `src/types/update.ts`. npm installs report as non-updatable.
 
 **Port interfaces**: Routes declare dependencies via port interfaces (`src/web/ports/`). Routes use intersection types (e.g., `SessionPort & EventPort`).
 

scripts/self-update.sh

@@ -31,6 +31,7 @@ export PUPPETEER_SKIP_DOWNLOAD="${PUPPETEER_SKIP_DOWNLOAD:-1}"
 REPO=""
 TAG=""
 SUPERVISOR="none"
+SERVER_PID=""
 STATUS_FILE=""
 UPDATE_ID=""
 FROM_VERSION=""
@@ -50,6 +51,7 @@ while [[ $# -gt 0 ]]; do
     --node) NODE="$2"; shift 2 ;;
     --log) LOG="$2"; shift 2 ;;
     --prev-sha) PREV_SHA="$2"; shift 2 ;;
+    --server-pid) SERVER_PID="$2"; shift 2 ;;
     --stash) DO_STASH=1; shift ;;
     *) shift ;;
   esac
@@ -198,6 +200,19 @@ case "$SUPERVISOR" in
         || fail "Build succeeded but launchd restart failed" "launchctl"
     }
     ;;
+  launchd-daemon)
+    # System-level KeepAlive LaunchDaemon (headless Mac): kickstarting the system
+    # domain needs root, but we don't need it — kill the server and launchd
+    # respawns it on the new dist/ within ThrottleInterval seconds.
+    if [[ -n "$SERVER_PID" ]] && kill "$SERVER_PID" 2>/dev/null; then
+      : # respawn is launchd's job from here
+    else
+      MANUAL_CMD="sudo launchctl kickstart -k system/com.codeman.web"
+      write_status "completed-needs-manual-restart" "Update staged — restart Codeman to apply v$TO_VERSION."
+      echo "[self-update] launchd-daemon: could not signal server pid '$SERVER_PID' — manual restart required"
+      exit 0
+    fi
+    ;;
   *)
     MANUAL_CMD="pkill -f 'codeman.*web'; codeman web &"
     write_status "completed-needs-manual-restart" "Update staged — restart Codeman to apply v$TO_VERSION."

src/types/update.ts

@@ -13,8 +13,12 @@
  * @module types/update
  */
 
-/** Which init system supervises the running server (decides how we restart it). */
-export type SupervisorKind = 'systemd' | 'launchd' | 'none';
+/**
+ * Which init system supervises the running server (decides how we restart it).
+ * `launchd-daemon` = a KeepAlive system-level LaunchDaemon (headless Macs, no GUI
+ * login): restart works by killing the server and letting launchd respawn it.
+ */
+export type SupervisorKind = 'systemd' | 'launchd' | 'launchd-daemon' | 'none';
 
 /** How Codeman was installed — only `git` installs can self-update in place. */
 export type InstallKind = 'git' | 'npm' | 'unknown';

src/web/self-update.ts

@@ -161,7 +161,9 @@ export function parseGitHubRepo(remoteUrl: string): { owner: string; repo: strin
  * persist — or null to leave it untouched.
  *
  * Rules (see plan "Hardening"):
- * - Terminal phases → untouched.
+ * - Terminal phases → untouched, EXCEPT `completed-needs-manual-restart`: once we
+ *   boot into the staged target version the manual restart evidently happened, so
+ *   it flips to `completed` (otherwise the stale instruction lingers in the UI).
  * - Only the `restarting` marker (written right before the updater triggers our
  *   restart) flips to completed/failed by comparing running version vs. target.
  * - Other in-flight phases are owned by the still-running updater scope — leave
@@ -174,6 +176,17 @@ export function reconcileStatusDecision(
   now: number
 ): UpdateStatus | null {
   if (!status) return null;
+
+  // A staged update that asked for a manual restart: if we're now running the
+  // target version, the user (or supervisor) did restart — mark it completed so
+  // the UI stops showing the stale "restart Codeman to apply" instruction.
+  if (status.phase === 'completed-needs-manual-restart') {
+    if (status.toVersion && runningVersion === status.toVersion) {
+      return { ...status, phase: 'completed', message: `Updated to v${runningVersion}`, updatedAt: now };
+    }
+    return null;
+  }
+
   if (!IN_FLIGHT_PHASES.has(status.phase)) return null;
 
   if (status.phase === 'restarting') {
@@ -275,6 +288,16 @@ function detectInstallKind(dir: string): InstallKind {
 export function detectSupervisor(): SupervisorKind {
   if (process.platform === 'darwin') {
     if (existsSync(join(homedir(), 'Library', 'LaunchAgents', `${LAUNCHD_LABEL}.plist`))) return 'launchd';
+    // Headless Macs (no GUI login → no gui domain) run Codeman as a system-level
+    // LaunchDaemon instead. Restarting one needs no root IF it has KeepAlive: the
+    // updater just kills the server and launchd respawns it on the new build. Only
+    // claim this supervisor when the daemon is actually bootstrapped and KeepAlive.
+    const daemonPlist = join('/Library/LaunchDaemons', `${LAUNCHD_LABEL}.plist`);
+    if (existsSync(daemonPlist)) {
+      const loaded = tryExec('launchctl', ['print', `system/${LAUNCHD_LABEL}`]) !== null;
+      const keepAlive = tryExec('plutil', ['-extract', 'KeepAlive', 'raw', '-o', '-', daemonPlist]);
+      if (loaded && keepAlive === 'true') return 'launchd-daemon';
+    }
     return 'none';
   }
   if (process.platform === 'linux') {
@@ -535,6 +558,10 @@ export async function startUpdate(): Promise<StartUpdateResult> {
     process.execPath,
     '--log',
     logFile,
+    // For the launchd-daemon restart path: the updater kills this PID and the
+    // KeepAlive daemon respawns the server on the freshly built dist/.
+    '--server-pid',
+    String(process.pid),
   ];
   if (prevSha) args.push('--prev-sha', prevSha);
   if (info.dirty) args.push('--stash');

test/self-update.test.ts

@@ -153,4 +153,17 @@ describe('reconcileStatusDecision (boot handoff state machine)', () => {
     expect(out?.phase).toBe('failed');
     expect(out?.error).toContain('building');
   });
+
+  it('needs-manual-restart + now running the target version → completed', () => {
+    const out = reconcileStatusDecision(base({ phase: 'completed-needs-manual-restart' }), '0.9.4', NOW);
+    expect(out?.phase).toBe('completed');
+    expect(out?.message).toContain('0.9.4');
+    expect(out?.updatedAt).toBe(NOW);
+  });
+
+  it('needs-manual-restart + still on the old version → untouched (restart pending)', () => {
+    expect(reconcileStatusDecision(base({ phase: 'completed-needs-manual-restart' }), '0.9.3', NOW)).toBeNull();
+    const noTarget = base({ phase: 'completed-needs-manual-restart', toVersion: undefined });
+    expect(reconcileStatusDecision(noTarget, '0.9.4', NOW)).toBeNull();
+  });
 });