feat(fleet): auto-enable units on install + drift recognizes wrapped runtimes (#583)

packages/mosaic/src/commands/fleet.ts

@@ -210,6 +210,93 @@ export function buildFleetServiceCommand(action: FleetServiceAction, agentName?:
   return ['systemctl', '--user', action, service];
 }
 
+/**
+ * Returns the systemctl --user enable command for a given unit.
+ * Used by the install auto-enable step to persist units across reboots.
+ */
+export function buildSystemdEnableCommand(unit: string): string[] {
+  return ['systemctl', '--user', 'enable', unit];
+}
+
+/**
+ * Returns the loginctl enable-linger command for a given user.
+ * Linger allows user systemd services to survive logout.
+ */
+export function buildEnableLingerCommand(user: string): string[] {
+  return ['loginctl', 'enable-linger', user];
+}
+
+/**
+ * Enable fleet units for boot-survival after install.
+ * Non-fatal: if systemctl enable returns non-zero, a warning is printed and we continue.
+ * If opts.enable === false (--no-enable flag), the whole step is skipped.
+ */
+export async function enableFleetUnits(
+  runner: CommandRunner,
+  roster: FleetRoster,
+  opts: { enable?: boolean },
+): Promise<void> {
+  if (opts.enable === false) {
+    return;
+  }
+  try {
+    let succeeded = 0;
+    let failed = 0;
+
+    const holderResult = await runner(
+      ...splitCommand(buildSystemdEnableCommand('mosaic-tmux-holder.service')),
+    );
+    if (holderResult.exitCode === 0) {
+      succeeded++;
+    } else {
+      failed++;
+      process.stderr.write(
+        `Warning: could not enable mosaic-tmux-holder.service: ${holderResult.stderr || holderResult.stdout || 'non-zero exit'}\n`,
+      );
+    }
+
+    for (const agent of roster.agents) {
+      const unit = `mosaic-agent@${agent.name}.service`;
+      const result = await runner(...splitCommand(buildSystemdEnableCommand(unit)));
+      if (result.exitCode === 0) {
+        succeeded++;
+      } else {
+        failed++;
+        process.stderr.write(
+          `Warning: could not enable ${unit}: ${result.stderr || result.stdout || 'non-zero exit'}\n`,
+        );
+      }
+    }
+
+    if (succeeded > 0) {
+      console.log(`Enabled ${succeeded} unit(s) for boot-survival.`);
+    }
+    if (failed > 0) {
+      process.stderr.write(
+        `Warning: ${failed} unit(s) could not be enabled (systemctl unavailable?). Run manually if needed.\n`,
+      );
+    }
+
+    // Best-effort linger
+    let username: string;
+    try {
+      username = userInfo().username;
+    } catch {
+      username = process.env['USER'] ?? process.env['LOGNAME'] ?? 'unknown';
+    }
+    const lingerResult = await runner(...splitCommand(buildEnableLingerCommand(username)));
+    if (lingerResult.exitCode !== 0) {
+      process.stderr.write(
+        `Hint: run 'loginctl enable-linger ${username}' as root to survive logout.\n`,
+      );
+    }
+  } catch (err) {
+    process.stderr.write(
+      `Warning: auto-enable step failed unexpectedly: ${err instanceof Error ? err.message : String(err)}\n`,
+    );
+  }
+}
+
 export function buildAgentSendCommand(
   paths: FleetPaths,
   agentName: string,
@@ -437,32 +524,41 @@ export function parseTmuxListPanes(
   return { pid, command, dead, idleSeconds };
 }
 
+/**
+ * Maps each known runtime to the set of acceptable pane commands.
+ * A pane running any of these commands for the given runtime is NOT considered drifted.
+ * Runtimes launched via `mosaic yolo` wrap in node, so 'node' is acceptable for most.
+ * The dogfood runtime accepts python3/python (the canary-pi dogfood stub).
+ */
+export const RUNTIME_ACCEPTABLE_COMMANDS: Record<string, readonly string[]> = {
+  claude: ['claude', 'node'],
+  codex: ['codex', 'node'],
+  opencode: ['opencode', 'node'],
+  pi: ['pi', 'node'],
+  dogfood: ['python3', 'python'],
+};
+
 /**
  * Determine if there is a runtime drift: roster says one runtime but the pane
  * is actually running something from a different runtime. We detect this by
- * checking if the pane command doesn't match a known canonical command for the
+ * checking if the pane command doesn't match a known acceptable command for the
  * roster's declared runtime.
  *
- * Known canonical commands per runtime:
- *   claude → claude
- *   codex  → codex
- *   opencode → opencode
- *   pi     → pi
+ * Known acceptable commands per runtime (see RUNTIME_ACCEPTABLE_COMMANDS):
+ *   claude   → claude, node  (node covers mosaic yolo wrapper)
+ *   codex    → codex, node
+ *   opencode → opencode, node
+ *   pi       → pi, node      (python3 still flags drift for canary-pi dogfood stub)
+ *   dogfood  → python3, python
  *
  * If the pane is running something else (e.g., python3/dogfood-agent.py) for
  * an agent whose roster runtime is "pi", that's a drift.
  */
 export function detectDrift(rosterRuntime: string, paneCommand: string | null): boolean {
   if (!paneCommand) return false;
-  const knownCommands: Record<string, string[]> = {
-    claude: ['claude'],
-    codex: ['codex'],
-    opencode: ['opencode'],
-    pi: ['pi'],
-  };
-  const expected = knownCommands[rosterRuntime];
-  if (!expected) return false;
-  return !expected.includes(paneCommand);
+  const acceptable = RUNTIME_ACCEPTABLE_COMMANDS[rosterRuntime];
+  if (!acceptable) return false;
+  return !acceptable.includes(paneCommand);
 }
 
 /**
@@ -706,12 +802,22 @@ export function registerFleetCommand(program: Command, deps: FleetCommandDeps =
   cmd
     .command('install')
     .description('Install local fleet tools and user systemd units')
-    .action(async () => installFleet(cmd, frameworkRoot));
+    .option('--no-enable', 'Skip enabling units for boot-survival')
+    .action(async (opts: { enable?: boolean }) => {
+      await installFleet(cmd, frameworkRoot);
+      const roster = await loadRosterForCommand(cmd);
+      await enableFleetUnits(runner, roster, opts);
+    });
 
   cmd
     .command('install-systemd')
     .description('Install local fleet tools and user systemd units')
-    .action(async () => installFleet(cmd, frameworkRoot));
+    .option('--no-enable', 'Skip enabling units for boot-survival')
+    .action(async (opts: { enable?: boolean }) => {
+      await installFleet(cmd, frameworkRoot);
+      const roster = await loadRosterForCommand(cmd);
+      await enableFleetUnits(runner, roster, opts);
+    });
 
   for (const action of ['start', 'stop', 'restart'] as const) {
     cmd