OG T
93c3280481
feat(monitoring): Phase 20 Nemotron 完整監控整合
服務註冊表:
- 新增 nvidia-nemotron AI 服務
- 3 個 Prometheus metrics 定義
- 4 個告警規則 (circuit_breaker, timeout, error_rate, rate_limit)
- fallback 策略 (nvidia → gemini → ollama)
Alertmanager 規則:
- NvidiaCircuitBreakerOpen (P1)
- NvidiaToolCallingHighLatency (P2)
- NvidiaToolCallingHighErrorRate (P0)
- NvidiaCircuitBreakerHalfOpen (Info)
- NvidiaCircuitBreakerClosed (Info)
- NvidiaNoRequests (P3)
自動修復:
- fallback_to_gemini
- fallback_to_ollama
- switch_model
ADR: ADR-036
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-29 02:05:59 +08:00
..
2026-03-28 23:59:46 +08:00
2026-03-29 01:27:29 +08:00
2026-03-28 22:23:42 +08:00
2026-03-26 18:43:28 +08:00
2026-03-28 22:23:42 +08:00
2026-03-28 22:53:21 +08:00
2026-03-29 02:05:59 +08:00
2026-03-25 00:05:51 +08:00
2026-03-28 21:27:05 +08:00
2026-03-28 23:16:54 +08:00
2026-03-28 21:57:57 +08:00