diff --git a/k8s/awoooi-prod/04-configmap.yaml b/k8s/awoooi-prod/04-configmap.yaml index 0272154d..20057d7a 100644 --- a/k8s/awoooi-prod/04-configmap.yaml +++ b/k8s/awoooi-prod/04-configmap.yaml @@ -17,12 +17,10 @@ data: # 服務端點 (非機密) # 2026-04-16 ogt + Claude Sonnet 4.6: 改指向 111(GPU 機,RTX) # 188 = CPU-only Ollama,推理極慢(>60s);111 有 GPU,avg 10s - # 2026-05-06 Codex: bypass the transitional 110 nginx bridge for active - # inference because /etc/nginx/conf.d/ollama-gcp-proxy.conf still has a 120s - # read timeout and returns 504 before qwen3:14b can finish. NetworkPolicy - # already allows direct GCP-A/GCP-B:11434. Target architecture remains - # ADR-125 WireGuard mesh + AwoooP Inference Gateway. - OLLAMA_URL: "http://34.143.170.20:11434" + # 2026-05-25 Codex: temporary failover while GCP-A 34.143.170.20 is + # unreachable from 110/GCP-B/office networks. Keep active inference on GCP-B + # until GCP-A VM/network is repaired, then restore ADR-110 primary. + OLLAMA_URL: "http://34.21.145.224:11434" OLLAMA_SECONDARY_URL: "http://34.21.145.224:11434" OLLAMA_FALLBACK_URL: "http://192.168.0.111:11434" OPENCLAW_URL: "http://192.168.0.188:8088" diff --git a/k8s/awoooi-prod/06-deployment-api.yaml b/k8s/awoooi-prod/06-deployment-api.yaml index 3c3ddfed..30e74ed3 100644 --- a/k8s/awoooi-prod/06-deployment-api.yaml +++ b/k8s/awoooi-prod/06-deployment-api.yaml @@ -70,7 +70,7 @@ spec: - name: TELEGRAM_ENABLE_POLLING value: "true" - name: OLLAMA_URL - value: "http://34.143.170.20:11434" # 2026-05-06 Codex: GCP-A direct; avoids 110 nginx 120s bridge timeout + value: "http://34.21.145.224:11434" # 2026-05-25 Codex: temporary primary while GCP-A 34.143.170.20 is unreachable - name: OLLAMA_SECONDARY_URL value: "http://34.21.145.224:11434" # 2026-05-06 Codex: GCP-B direct; mesh gateway remains target architecture - name: OLLAMA_FALLBACK_URL