feat: add Watchdog recovery and drift rebuild workflows

src/lib/server/pipeline/sweep.ts

@@ -41,7 +41,8 @@ async function runSweep(): Promise<SweepResult> {
     }
     db().prepare(`UPDATE deployments SET finished_at = ? WHERE finished_at IS NULL AND NOT EXISTS (
         SELECT 1 FROM deployment_servers WHERE deployment_id = deployments.id AND restart_state IN ('pending','failed','held'))`).run(nowIso());
-    db().prepare(`DELETE FROM deployments WHERE started_at < ? AND NOT EXISTS (
+    db().prepare(`DELETE FROM deployments WHERE started_at < ?
+        AND NOT EXISTS (SELECT 1 FROM watchdog_actions WHERE campaign_id = deployments.id) AND NOT EXISTS (
         SELECT 1 FROM deployment_servers WHERE deployment_id = deployments.id AND restart_state IN ('pending','failed','held'))`)
         .run(new Date(Date.now() - config.deployKeepDays * 86_400_000).toISOString());
     emit({ type: 'sweep-tick', frozen: false });

src/lib/server/pipeline/worker.ts

@@ -14,6 +14,7 @@ import { STATUS_REFRESH_MS } from '../../server-freshness.js';
 import { recordMetrics } from '../fleet/metrics.js';
 import { selectedZombieMap } from '../../map-aliases.js';
 import { maintenanceTick } from '../fleet/plutonium.js';
+import { watchdogTick } from '../watchdog/index.js';
 
 const TICK_MS = 15_000;
 // Cap concurrent UDP RCON calls so a 15-server fleet doesn't blast the
@@ -36,6 +37,7 @@ async function reconcileRequesters(): Promise<void> {
     try { await sweep(); } catch (err) { console.error('[worker] campaign error:', err); }
     try { await betaTick(); } catch (err) { console.error('[worker] beta error:', err); }
     try { await maintenanceTick(); } catch (err) { console.error('[worker] maintenance error:', err); }
+    try { await watchdogTick(); } catch (err) { console.error('[worker] watchdog error:', err); }
 }
 
 async function runTick(): Promise<void> {