feat(ollama): improve configuration and dashboard integration

internal/server/server.go

@@ -154,6 +154,7 @@ func (s *Server) RefreshProviders() error {
 			s.providers["grok"] = providers.NewGrokProvider(cfg, apiKey)
 		case "ollama":
 			cfg := s.cfg.Providers.Ollama
+			fmt.Printf("[DEBUG] Ollama config: Enabled=%v, BaseURL=%s, Models=%v\n", cfg.Enabled, baseURL, cfg.Models)
 			cfg.BaseURL = baseURL
 			s.providers["ollama"] = providers.NewOllamaProvider(cfg)
 		}
@@ -271,6 +272,28 @@ func (s *Server) handleListModels(c *gin.Context) {
 		}
 	}
 
+	// Add configured Ollama models
+	if s.cfg.Providers.Ollama.Enabled {
+		for _, mID := range s.cfg.Providers.Ollama.Models {
+			// Check if already added
+			exists := false
+			for _, d := range data {
+				if d.ID == mID {
+					exists = true
+					break
+				}
+			}
+			if !exists {
+				data = append(data, OpenAIModel{
+					ID:      mID,
+					Object:  "model",
+					Created: 1700000000,
+					OwnedBy: "ollama",
+				})
+			}
+		}
+	}
+
 	c.JSON(http.StatusOK, gin.H{
 		"object": "list",
 		"data":   data,
@@ -305,9 +328,17 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 		return
 	}
 
+	// Strip common prefixes
+	modelID := req.Model
+	if strings.HasPrefix(modelID, "gemini/") {
+		modelID = strings.TrimPrefix(modelID, "gemini/")
+	} else if strings.HasPrefix(modelID, "google/") {
+		modelID = strings.TrimPrefix(modelID, "google/")
+	}
+
 	// Convert ChatCompletionRequest to UnifiedRequest
 	unifiedReq := &models.UnifiedRequest{
-		Model:            req.Model,
+		Model:            modelID,
 		Messages:         []models.UnifiedMessage{},
 		Temperature:      req.Temperature,
 		TopP:             req.TopP,