v3.8.0: AI Monitoring — self-healing watchdog with 3-tier response system

- HealthWatcher thread: monitors proxy /health every 5s
- LogAnalyzer thread: tails cc-debug.log for 18 failure signal patterns
- Tier 1 rule engine: 14 rules for instant auto-recovery (< 1s)
- Tier 2 incident store: JSON pattern database with success rates
- Tier 3 AI diagnostic agent: calls configurable provider/model for novel failures
- AIMonitoringWindow GUI: ON/OFF toggle, provider/model/API key selector, incident log
- 30 fault types catalogued across 5 categories (A-E)
- Enhanced /health endpoint with memory_mb, uptime_s, requests_total
- Auto-restart proxy, auto-clear schema cache, kill stale processes
- Safety: rate-limited AI calls, restart caps, cooldowns per pattern
- AI Monitoring design spec (AI-MONITORING-DESIGN.md)
- 54 self-test patterns passing

src/translate-proxy.py

@@ -3410,10 +3410,20 @@ class Handler(http.server.BaseHTTPRequestHandler):
         if self.path in ("/v1/models", "/models"):
             self.send_json(200, {"object": "list", "data": MODELS})
         elif self.path in ("/health", "/v1/health"):
+            import resource as _res
+            _mem_mb = 0
+            try:
+                _mem_mb = _res.getrusage(_res.RUSAGE_SELF).ru_maxrss / 1024
+            except Exception:
+                pass
+            _uptime = time.time() - _START_TIME if '_START_TIME' in dir() else 0
             self.send_json(200, {"ok": True, "backend": BACKEND,
                                  "target_url": TARGET_URL,
                                  "models": [m.get("id") for m in MODELS],
-                                 "bgp_routes": len(BGP_ROUTES)})
+                                 "bgp_routes": len(BGP_ROUTES),
+                                 "uptime_s": round(_uptime, 1),
+                                 "memory_mb": round(_mem_mb, 1),
+                                 "requests_total": _STATS.get("requests", 0)})
         else:
             self.send_error(404)
 
@@ -4750,10 +4760,11 @@ def _handle_shutdown_signal(sig, frame):
     _SHUTDOWN_REQUESTED = True
     print(f"[SELF-REVIVE] Signal {sig} received, shutting down cleanly", flush=True)
     if 'SERVER' in globals() and SERVER:
-        SERVER.shutdown()
-
+         SERVER.shutdown()
+ 
 def main():
-    global SERVER
+    global SERVER, _START_TIME
+    _START_TIME = time.time()
     _init_runtime()
     signal.signal(signal.SIGTERM, _handle_shutdown_signal)
     signal.signal(signal.SIGINT, _handle_shutdown_signal)