fix(server): add Ollama model detection and registry support

- Add Ollama to allowed providers in model list endpoint
- Add model pattern detection for Ollama models (glm-, qwen, gemma, llama, mistral, codellama)
- This fixes 500 errors when using Ollama models via /v1/chat/completions

internal/server/server.go

@@ -252,6 +252,7 @@ func (s *Server) handleListModels(c *gin.Context) {
 		"deepseek": true,
 		"moonshot": true,
 		"xai":      true, // Models from models.dev use 'xai' ID for Grok
+		"ollama":   true,
 	}
 
 	if s.registry != nil {
@@ -294,6 +295,8 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 		providerName = "moonshot"
 	} else if strings.Contains(req.Model, "grok") {
 		providerName = "grok"
+	} else if strings.Contains(req.Model, "glm-") || strings.Contains(req.Model, "qwen") || strings.Contains(req.Model, "gemma") || strings.Contains(req.Model, "llama") || strings.Contains(req.Model, "mistral") || strings.Contains(req.Model, "codellama") {
+		providerName = "ollama"
 	}
 
 	provider, ok := s.providers[providerName]