refactor: improve model_config implementation based on code review

- Simplify _get_model_config method logic
- Add more descriptive comment about model_config usage
- Clarify when model_config is used (assistant type apps)

Co-authored-by: RockChinQ <45992437+RockChinQ@users.noreply.github.com>

src/langbot/libs/dify_service_api/v1/client.py

@@ -53,6 +53,8 @@ class AsyncDifyServiceClient:
             }
 
             # Add model_config if provided
+            # model_config allows overriding model settings (temperature, max_tokens, etc.)
+            # for assistant type apps in Dify's open-source version
             if model_config is not None:
                 payload['model_config'] = model_config
 

src/langbot/pkg/provider/runners/difysvapi.py

@@ -41,12 +41,11 @@ class DifyServiceAPIRunner(runner.RequestRunner):
         """获取模型配置参数
 
         Returns:
-            模型配置字典，如果未配置则返回None
+            模型配置字典，如果未配置或为空则返回None
         """
         model_config = self.pipeline_config['ai']['dify-service-api'].get('model-config')
-        if model_config:
-            return model_config
-        return None
+        # Return None if model_config is None or empty dict to avoid sending unnecessary parameters
+        return model_config if model_config else None
 
     def _process_thinking_content(
         self,