feat: LLM routing by tier (free→Ollama, pro→Timeweb)

- Add tier-based provider routing in llm-svc
  - free tier → Ollama (local qwen3.5:9b)
  - pro/business → Timeweb Cloud AI
- Add /api/v1/embed endpoint for embeddings via Ollama
- Update Ollama client: qwen3.5:9b default, remove auth
- Add GenerateEmbedding() function for qwen3-embedding:0.6b
- Add Ollama K8s deployment with GPU support (RTX 4060 Ti)
- Add monitoring stack (Prometheus, Grafana, Alertmanager)
- Add Grafana dashboards for LLM and security metrics
- Update deploy.sh with monitoring and Ollama deployment

Made-with: Cursor

backend/deploy/k8s/configmap.yaml

@@ -23,6 +23,10 @@ data:
   AUTH_SVC_URL: "http://auth-svc:3050"
   TRAVEL_SVC_URL: "http://travel-svc:3035"
   ADMIN_SVC_URL: "http://admin-svc:3040"
+  OLLAMA_BASE_URL: "http://ollama:11434"
+  OLLAMA_MODEL: "qwen3.5:9b"
+  OLLAMA_EMBEDDING_MODEL: "qwen3-embedding:0.6b"
+  OLLAMA_NUM_PARALLEL: "2"
   DEFAULT_LLM_MODEL: "${DEFAULT_LLM_MODEL}"
   DEFAULT_LLM_PROVIDER: "${DEFAULT_LLM_PROVIDER}"
   TIMEWEB_API_BASE_URL: "${TIMEWEB_API_BASE_URL}"
@@ -50,5 +54,6 @@ stringData:
   GEMINI_API_KEY: "${GEMINI_API_KEY}"
   JWT_SECRET: "${JWT_SECRET}"
   TIMEWEB_API_KEY: "${TIMEWEB_API_KEY}"
+  OLLAMA_API_TOKEN: "${OLLAMA_API_TOKEN}"
   POSTGRES_USER: "gooseek"
   POSTGRES_PASSWORD: "gooseek"