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/pkg/config/config.go

@@ -79,8 +79,11 @@ type Config struct {
 	TimewebProxySource    string
 
 	// Ollama (local LLM)
-	OllamaBaseURL   string
-	OllamaModelKey  string
+	OllamaBaseURL        string
+	OllamaModelKey       string
+	OllamaEmbeddingModel string
+	OllamaNumParallel    int
+	OllamaAPIToken       string
 
 	// Timeouts
 	HTTPTimeout     time.Duration
@@ -160,8 +163,11 @@ func Load() (*Config, error) {
 		TimewebAPIKey:        getEnv("TIMEWEB_API_KEY", ""),
 		TimewebProxySource:   getEnv("TIMEWEB_X_PROXY_SOURCE", "gooseek"),
 
-		OllamaBaseURL:  getEnv("OLLAMA_BASE_URL", "http://ollama:11434"),
-		OllamaModelKey: getEnv("OLLAMA_MODEL", "llama3.2"),
+		OllamaBaseURL:        getEnv("OLLAMA_BASE_URL", "http://ollama:11434"),
+		OllamaModelKey:       getEnv("OLLAMA_MODEL", "qwen3.5:9b"),
+		OllamaEmbeddingModel: getEnv("OLLAMA_EMBEDDING_MODEL", "qwen3-embedding:0.6b"),
+		OllamaNumParallel:    getEnvInt("OLLAMA_NUM_PARALLEL", 2),
+		OllamaAPIToken:       getEnv("OLLAMA_API_TOKEN", ""),
 
 		HTTPTimeout:   time.Duration(getEnvInt("HTTP_TIMEOUT_MS", 60000)) * time.Millisecond,
 		LLMTimeout:    time.Duration(getEnvInt("LLM_TIMEOUT_MS", 120000)) * time.Millisecond,