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/cmd/api-gateway/main.go

@@ -15,6 +15,7 @@ import (
 	"github.com/gofiber/fiber/v2/middleware/cors"
 	"github.com/gofiber/fiber/v2/middleware/logger"
 	"github.com/gooseek/backend/pkg/config"
+	"github.com/gooseek/backend/pkg/metrics"
 	"github.com/gooseek/backend/pkg/middleware"
 	"github.com/redis/go-redis/v9"
 )
@@ -73,6 +74,11 @@ func main() {
 		AllowHeaders: "Origin, Content-Type, Accept, Authorization",
 		AllowMethods: "GET, POST, PUT, PATCH, DELETE, OPTIONS",
 	}))
+	app.Use(metrics.PrometheusMiddleware(metrics.MetricsConfig{
+		ServiceName: "api-gateway",
+	}))
+
+	app.Get("/metrics", metrics.MetricsHandler())
 
 	app.Use(middleware.JWT(middleware.JWTConfig{
 		Secret:     cfg.JWTSecret,