fix(predictions): cooldown fallback cascade + circuit breaker tuning

- Add 4-level fallback when AI circuit breaker fires cooldown:
  1) In-memory cache (10min TTL)
  2) DB stored prediction (no TTL filter)
  3) DB cached prediction (with model version check)
  4) Wait out cooldown + retry once (max 20s wait)
- Raise circuit breaker threshold from 3 to 5 consecutive failures
- Reduce cooldown duration from 30s to 15s for faster recovery
- Add extractCooldownMs helper to parse remaining ms from error detail

src/common/utils/ai-engine-client.ts

@@ -69,8 +69,8 @@ export class AiEngineClient {
     this.defaultTimeoutMs = options.timeoutMs ?? 30000;
     this.maxRetries = options.maxRetries ?? 2;
     this.retryDelayMs = options.retryDelayMs ?? 750;
-    this.circuitBreakerThreshold = options.circuitBreakerThreshold ?? 3;
-    this.circuitBreakerCooldownMs = options.circuitBreakerCooldownMs ?? 30000;
+    this.circuitBreakerThreshold = options.circuitBreakerThreshold ?? 5;
+    this.circuitBreakerCooldownMs = options.circuitBreakerCooldownMs ?? 15000;
 
     this.axiosClient = axios.create({
       baseURL: options.baseUrl,