@yemi33/minions 0.1.2269 → 0.1.2270

package/dashboard/js/render-dispatch.js

@@ -103,7 +103,11 @@ function renderEngineStatus(engine) {
   // against a possibly-cached heartbeat — the bug pattern that produced false-
   // positive STALE banners after control.json was dropped from the mtime tracker.
   const staleMs = engine?.heartbeatAgeMs || 0;
-  if (state === 'running' && engine?.heartbeatStale) state = 'stale';
+  // Map running→stale and degraded→stale when both heartbeat signals are stale.
+  // degraded is set by the dashboard watchdog (issue #423) when the engine PID
+  // is alive but the tick loop is frozen; treat it identically to stale so the
+  // Restart Engine banner fires in both cases.
+  if ((state === 'running' || state === 'degraded') && engine?.heartbeatStale) state = 'stale';
 
   // Clear restart grace as soon as the engine reports a fresh heartbeat — the
   // new engine has caught up, so STALE/restart banners should vanish.

package/dashboard.js

@@ -5951,6 +5951,35 @@ function restartEngine() {
   return newPid;
 }
 
+// ── Frozen-engine detection (issue #423) ─────────────────────────────────────
+// Called by the 30s watchdog when the engine PID is still alive. If both
+// control.heartbeat AND control.lastTickAt have aged past their thresholds,
+// the tick loop is frozen (event-loop blocked). Flip state to 'degraded' so:
+//   • The dashboard UI surfaces a hard warning with a Restart Engine button.
+//   • When the engine eventually unhangs, tickInner reads state !== 'running'
+//     and calls process.exit(0); the PID-dead watchdog then auto-restarts it.
+// The restarted engine reclaims state:'running' on its next boot.
+// Returns true if it wrote the degraded state, false otherwise.
+function _markEngineAsDegradedIfFrozen() {
+  const control = getEngineState();
+  if (control.state !== 'running' || !control.pid) return false;
+
+  const hbAge = control.heartbeat ? Date.now() - control.heartbeat : 0;
+  const tickInterval = Number(CONFIG?.engine?.tickInterval) || shared.ENGINE_DEFAULTS.tickInterval;
+  const tickStaleThresholdMs = Math.max(ENGINE_HEARTBEAT_STALE_MS, 2 * tickInterval);
+  const tickAge = control.lastTickAt ? Date.now() - control.lastTickAt : Infinity;
+
+  const bothStale = !!(control.heartbeat
+    && hbAge > ENGINE_HEARTBEAT_STALE_MS
+    && tickAge > tickStaleThresholdMs);
+  if (!bothStale) return false;
+
+  shared.mutateControl(c => ({ ...c, state: 'degraded' }));
+  console.log(`[watchdog] Engine tick frozen (heartbeat ${Math.round(hbAge / 1000)}s old, last tick ${Math.round(tickAge / 1000)}s old) — marking state as degraded`);
+  try { invalidateStatusCache(); } catch { /* best effort */ }
+  return true;
+}
+
 // -- Server --
 
 // Mutating HTTP methods that require Origin and Content-Type gating.
@@ -14415,6 +14444,8 @@ module.exports = {
   // staleness verdict it stamps on engine.heartbeatStale is the contract under
   // test. No production caller imports this; it is a test seam.
   _buildStatusFastState,
+  // #423 — exported for unit testing the frozen-engine watchdog logic.
+  _markEngineAsDegradedIfFrozen,
   // W-mq5xg5e9000nec0e — exported for direct unit testing of the slim shape
   // produced by GET /api/work-items. Production callers go through the
   // route's `builder` closure (getWorkItems().map(slimWorkItemForList)).
@@ -14643,6 +14674,8 @@ if (require.main === module) {
         if (!alive) {
           console.log(`[watchdog] Engine PID ${control.pid} is dead — auto-restarting...`);
           restartEngine();
+        } else {
+          _markEngineAsDegradedIfFrozen();
         }
       } catch (e) {
         console.error(`[watchdog] Error: ${e.message}`);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@yemi33/minions",
-  "version": "0.1.2269",
+  "version": "0.1.2270",
   "description": "Multi-agent AI dev team that runs from ~/.minions/ — five autonomous agents share a single engine, dashboard, and knowledge base",
   "bin": {
     "minions": "bin/minions.js"