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/go.mod

@@ -5,6 +5,7 @@ go 1.24
 toolchain go1.24.13
 
 require (
+	github.com/gofiber/adaptor/v2 v2.2.1
 	github.com/gofiber/fiber/v2 v2.52.0
 	github.com/golang-jwt/jwt/v5 v5.2.1
 	github.com/google/uuid v1.6.0
@@ -12,6 +13,7 @@ require (
 	github.com/ledongthuc/pdf v0.0.0-20240201131950-da5b75280b06
 	github.com/lib/pq v1.10.9
 	github.com/minio/minio-go/v7 v7.0.70
+	github.com/prometheus/client_golang v1.19.0
 	github.com/redis/go-redis/v9 v9.4.0
 	github.com/sashabaranov/go-openai v1.20.0
 	go.uber.org/zap v1.27.0