fix(rag): use bge embeddings on GCP Ollama lane

k8s/awoooi-prod/04-configmap.yaml

@@ -64,6 +64,7 @@ data:
   ALERT_AI_ENFORCE_OLLAMA_FIRST: "true"
   ALERT_OLLAMA_MODEL: "qwen3:14b"
   OLLAMA_HEALTH_CHECK_MODEL: "gemma3:4b"
+  OLLAMA_EMBEDDING_MODEL: "bge-m3:latest"
   OPENCLAW_DEFAULT_MODEL: "qwen2.5:7b-instruct"
   OPENCLAW_TIMEOUT: "120"
   INCIDENT_LLM_TIMEOUT_SECONDS: "240"

k8s/awoooi-prod/06-deployment-api.yaml

@@ -81,6 +81,8 @@ spec:
               value: "qwen3:14b"  # 2026-05-05 Codex: 告警以解決問題為目標，可等待深度診斷
             - name: OLLAMA_HEALTH_CHECK_MODEL
               value: "gemma3:4b"  # 2026-05-05 Codex: 避免 health probe 載入 qwen2.5 7B 污染 GCP alert lane
+            - name: OLLAMA_EMBEDDING_MODEL
+              value: "bge-m3:latest"
             - name: OPENCLAW_DEFAULT_MODEL
               value: "qwen2.5:7b-instruct"
             - name: OPENCLAW_TIMEOUT