fix(ollama): increase timeout and add default max_tokens for large models

- Increase Ollama timeout to 5m for larger models (e.g. gemma4)
- Set default max_tokens to 4096 for common Ollama models
- Expand stream scanner buffer to 10MB to prevent truncation
- Improve model routing and prefix stripping in server

internal/server/server.go

@@ -310,15 +310,15 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 
 	// Select provider based on model name
 	providerName := "openai" // default
-	if strings.Contains(req.Model, "gemini") {
+	if strings.HasPrefix(req.Model, "gemini/") || strings.Contains(req.Model, "gemini") || strings.HasPrefix(req.Model, "google/") {
 		providerName = "gemini"
-	} else if strings.Contains(req.Model, "deepseek") {
+	} else if strings.HasPrefix(req.Model, "deepseek/") || strings.Contains(req.Model, "deepseek") {
 		providerName = "deepseek"
-	} else if strings.Contains(req.Model, "kimi") || strings.Contains(req.Model, "moonshot") {
+	} else if strings.HasPrefix(req.Model, "moonshot/") || strings.Contains(req.Model, "kimi") || strings.Contains(req.Model, "moonshot") {
 		providerName = "moonshot"
-	} else if strings.Contains(req.Model, "grok") {
+	} else if strings.HasPrefix(req.Model, "grok/") || 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") {
+	} else if strings.HasPrefix(req.Model, "ollama/") || 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"
 	}
 
@@ -330,10 +330,12 @@ func (s *Server) handleChatCompletions(c *gin.Context) {
 
 	// 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/")
+	prefixes := []string{"gemini/", "google/", "openai/", "deepseek/", "moonshot/", "grok/", "ollama/"}
+	for _, p := range prefixes {
+		if strings.HasPrefix(modelID, p) {
+			modelID = strings.TrimPrefix(modelID, p)
+			break
+		}
 	}
 
 	// Convert ChatCompletionRequest to UnifiedRequest