fix(ai): remove 188 ollama provider

ops/monitoring/generated/blackbox-targets-generated.yaml

@@ -26,8 +26,18 @@
 - labels:
     criticality: P0
     owner: ai-team
-    service: ollama
-  url: http://192.168.0.188:11434/api/tags
+    service: ollama-gcp-a
+  url: http://192.168.0.110:11435/api/tags
+- labels:
+    criticality: P0
+    owner: ai-team
+    service: ollama-gcp-b
+  url: http://192.168.0.110:11436/api/tags
+- labels:
+    criticality: P0
+    owner: ai-team
+    service: ollama-local
+  url: http://192.168.0.110:11437/api/tags
 - labels:
     criticality: P0
     owner: ai-team

ops/monitoring/generated/prometheus-scrape-generated.yaml

@@ -92,7 +92,9 @@ scrape_configs:
       service: ollama
       type: docker
     targets:
-    - 192.168.0.188:11434
+    - 192.168.0.110:11435
+    - 192.168.0.110:11436
+    - 192.168.0.110:11437
 - job_name: openclaw
   static_configs:
   - labels:

ops/monitoring/grafana/dashboards/ollama_failover.json

@@ -82,11 +82,11 @@
         "textMode": "auto"
       },
       "title": "Ollama 可用性",
-      "description": "up{job=~\"ollama_111|ollama_188\"} × 100\n- 綠色 100% = 主機在線\n- 紅色 0% = 主機離線（容災應已觸發）\n\n資料來源: Prometheus scrape job ollama_111 / ollama_188",
+      "description": "up{job=~\"ollama_gcp_a|ollama_gcp_b|ollama_local|ollama_111\"} × 100\n- 綠色 100% = 主機在線\n- 紅色 0% = 主機離線（容災應已觸發）\n\n資料來源: Prometheus scrape job ollama_gcp_a / ollama_gcp_b / ollama_local",
       "targets": [
         {
           "datasource": { "type": "prometheus", "uid": "${datasource}" },
-          "expr": "up{job=~\"ollama_111|ollama_188\"} * 100",
+          "expr": "up{job=~\"ollama_gcp_a|ollama_gcp_b|ollama_local|ollama_111\"} * 100",
           "legendFormat": "{{ job }}",
           "refId": "A"
         }
@@ -188,7 +188,7 @@
         "tooltip": { "mode": "single", "sort": "none" }
       },
       "title": "AI Provider 路由分布",
-      "description": "sum by (provider) (rate(ai_router_selected_provider_total[5m]))\n- 正常狀態: ollama 佔大多數\n- failover 中: gemini / ollama_188 比例上升\n- 全走 gemini = 111 完全 offline\n\n資料來源: OLLAMA_FAILOVER_TRIGGERED_TOTAL + AI_ROUTER_PROVIDER_TOTAL (src/core/metrics.py)",
+      "description": "sum by (provider) (rate(ai_router_selected_provider_total[5m]))\n- 正常狀態: ollama / ollama_gcp_a 佔大多數\n- failover 中: ollama_gcp_b / ollama_local / gemini 比例上升\n- 全走 gemini = Ollama provider pool 完全 offline\n\n資料來源: OLLAMA_FAILOVER_TRIGGERED_TOTAL + AI_ROUTER_PROVIDER_TOTAL (src/core/metrics.py)",
       "targets": [
         {
           "datasource": { "type": "prometheus", "uid": "${datasource}" },

ops/monitoring/ollama_health_rules.yaml

@@ -6,7 +6,7 @@
 # 部署方式: 手動合併至 alerts-unified.yml，或 scripts/ops/deploy-alerts.sh 支援多檔時直接引用
 #
 # 標籤規範 (對齊 alerts-unified.yml):
-#   layer: systemd-188 | docker-188 (Ollama 跑在 188 主機)
+#   layer: ai-provider
 #   team: ai
 #   auto_repair: "true" | "false"
 #
@@ -28,16 +28,16 @@ groups:
 
       # -----------------------------------------------------------------------
       # 🔴 [ACTIVE] Ollama 主機離線
-      # metric: up{job=~"ollama_111|ollama_188"}
-      # 前置條件: Prometheus scrape job 命名為 ollama_111 / ollama_188
+      # metric: up{job=~"ollama_gcp_a|ollama_gcp_b|ollama_local|ollama_111"}
+      # 前置條件: Prometheus scrape job 命名對齊 ADR-110 provider pool
       #   (設定位於 ops/monitoring/generated/prometheus-scrape-generated.yaml)
       # -----------------------------------------------------------------------
       - alert: OllamaInstanceDown
-        expr: up{job=~"ollama_111|ollama_188"} == 0
+        expr: up{job=~"ollama_gcp_a|ollama_gcp_b|ollama_local|ollama_111"} == 0
         for: 2m
         labels:
           severity: critical
-          layer: systemd-188
+          layer: ai-provider
           team: ai
           auto_repair: "false"
           alert_category: "ollama_failover"
@@ -57,7 +57,7 @@ groups:
         for: 10m
         labels:
           severity: warning
-          layer: systemd-188
+          layer: ai-provider
           team: ai
           auto_repair: "false"
           alert_category: "ollama_failover"