fix: 修复高优先级提供商失败时自动切换到备用提供商

- 任何非200响应（400、429、500等）都会触发切换
- 增加 exclude_providers 参数排除已尝试的提供商
- 避免重复尝试失败的提供商
- 添加切换日志便于调试

app.py

@@ -177,10 +177,17 @@ def get_provider_for_model(model_name):
     return None, None
 
 
-def get_available_provider_for_auto(auto_name='auto'):
-    """获取auto模式下的可用提供商（支持自定义auto配置）"""
+def get_available_provider_for_auto(auto_name='auto', exclude_providers=None):
+    """获取auto模式下的可用提供商（支持自定义auto配置）
+    
+    Args:
+        auto_name: auto配置名称
+        exclude_providers: 要排除的提供商名称列表（已尝试过的）
+    """
     refresh_config()
     
+    exclude_providers = exclude_providers or []
+    
     # 获取auto配置
     profile = _cached_auto_profiles.get(auto_name, _cached_auto_profiles.get('auto', {}))
     
@@ -194,6 +201,8 @@ def get_available_provider_for_auto(auto_name='auto'):
     for provider in sorted_providers:
         if not provider['enabled']:
             continue
+        if provider['name'] in exclude_providers:
+            continue
         if not provider_status.get(provider['name'], {}).get('available', True):
             continue
         
@@ -448,26 +457,27 @@ def chat_completions():
                         increment_stats(model, provider['name'], success=True, tokens=request_tokens)
                         return jsonify(result)
                 
-                elif response.status_code == 429:
-                    # 速率限制，尝试下一个提供商
-                    mark_provider_error(provider['name'], "Rate limit")
+                else:
+                    # 任何非200响应都尝试下一个提供商
+                    error_info = response.json() if response.headers.get('content-type', '').startswith('application/json') else {"error": response.text}
+                    last_error = error_info
+                    logger.warning(f"Provider {provider['name']} returned {response.status_code}: {error_info}")
+                    mark_provider_error(provider['name'], f"HTTP {response.status_code}")
                     tried_providers.append(provider['name'])
                     
                     # 尝试下一个提供商
-                    next_provider, next_model = get_available_provider_for_auto('auto')
+                    next_provider, next_model = get_available_provider_for_auto('auto', exclude_providers=tried_providers)
                     if next_provider and next_provider['name'] not in tried_providers:
+                        logger.info(f"Switching to next provider: {next_provider['name']}")
                         provider = next_provider
                         resolved_model = next_model
                         request_provider = provider['name']
+                        time.sleep(RETRY_CONFIG['retry_delay'])
                         continue
                     
-                    increment_stats(model, provider['name'], success=False, error='Rate limit')
-                    return jsonify(response.json()), response.status_code
-                
-                else:
-                    last_error = response.json() if response.headers.get('content-type', '').startswith('application/json') else {"error": response.text}
+                    # 所有提供商都尝试过了，返回最后一个错误
                     increment_stats(model, provider['name'], success=False, error=str(last_error))
-                    return jsonify(last_error), response.status_code
+                    return jsonify(error_info), response.status_code
                     
             except Exception as e:
                 last_error = str(e)
@@ -475,7 +485,7 @@ def chat_completions():
                 tried_providers.append(provider['name'])
                 
                 # 尝试下一个提供商
-                next_provider, next_model = get_available_provider_for_auto('auto')
+                next_provider, next_model = get_available_provider_for_auto('auto', exclude_providers=tried_providers)
                 if next_provider and next_provider['name'] not in tried_providers:
                     provider = next_provider
                     resolved_model = next_model