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

@@ -9,9 +9,10 @@ import requests
 import json
 import time
 import logging
-from datetime import datetime
+from datetime import datetime, date
 from pathlib import Path
 import sys
+import threading
 
 # 添加配置路径
 sys.path.insert(0, str(Path(__file__).parent))
@@ -20,6 +21,75 @@ from config.settings import (
     LOG_CONFIG, RETRY_CONFIG
 )
 
+# 数据目录和统计文件
+DATA_DIR = Path(__file__).parent / 'data'
+DATA_DIR.mkdir(exist_ok=True)
+STATS_FILE = DATA_DIR / 'stats.json'
+
+# 统计锁（避免并发写入冲突）
+stats_lock = threading.Lock()
+
+def load_stats():
+    """加载统计数据"""
+    if STATS_FILE.exists():
+        try:
+            return json.loads(STATS_FILE.read_text(encoding='utf-8'))
+        except:
+            pass
+    return {
+        'total_requests': 0,
+        'total_success': 0,
+        'total_errors': 0,
+        'total_tokens': 0,
+        'requests_today': 0,
+        'requests_by_model': {},
+        'providers': {},
+        'last_updated': None,
+        'date': None  # 用于判断是否需要重置每日计数
+    }
+
+def save_stats(stats):
+    """保存统计数据"""
+    stats['last_updated'] = datetime.now().isoformat()
+    STATS_FILE.write_text(json.dumps(stats, ensure_ascii=False, indent=2), encoding='utf-8')
+
+def increment_stats(model, provider_name, success=False, tokens=0, error=None):
+    """增加统计计数"""
+    with stats_lock:
+        stats = load_stats()
+        today = date.today().isoformat()
+        
+        # 如果是新的一天，重置每日计数
+        if stats.get('date') != today:
+            stats['date'] = today
+            stats['requests_today'] = 0
+        
+        stats['total_requests'] += 1
+        stats['requests_today'] += 1
+        
+        # 模型统计
+        if model not in stats['requests_by_model']:
+            stats['requests_by_model'][model] = {'count': 0, 'success': 0, 'tokens': 0}
+        stats['requests_by_model'][model]['count'] += 1
+        if success:
+            stats['requests_by_model'][model]['success'] += 1
+            stats['requests_by_model'][model]['tokens'] += tokens
+        
+        # 提供商统计
+        if provider_name not in stats['providers']:
+            stats['providers'][provider_name] = {'requests': 0, 'success': 0, 'errors': 0, 'tokens': 0}
+        stats['providers'][provider_name]['requests'] += 1
+        if success:
+            stats['providers'][provider_name]['success'] += 1
+            stats['providers'][provider_name]['tokens'] += tokens
+            stats['total_success'] += 1
+            stats['total_tokens'] += tokens
+        else:
+            stats['providers'][provider_name]['errors'] += 1
+            stats['total_errors'] += 1
+        
+        save_stats(stats)
+
 app = Flask(__name__)
 CORS(app)
 
@@ -107,10 +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', {}))
     
@@ -124,6 +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
         
@@ -244,8 +323,27 @@ def index():
         "endpoints": {
             "chat": "/v1/chat/completions",
             "models": "/v1/models",
+            "embeddings": "/v1/embeddings",
             "health": "/health",
             "status": "/status"
+        },
+        "examples": {
+            "curl": {
+                "description": "curl 命令行",
+                "code": "curl -X POST http://localhost:19007/v1/chat/completions -H 'Content-Type: application/json' -d '{\"model\": \"auto\", \"messages\": [{\"role\": \"user\", \"content\": \"你好\"}]}'"
+            },
+            "python_openai": {
+                "description": "Python OpenAI SDK",
+                "code": "from openai import OpenAI\nclient = OpenAI(base_url='http://localhost:19007/v1', api_key='any')\nresponse = client.chat.completions.create(model='auto', messages=[{'role': 'user', 'content': '你好'}])\nprint(response.choices[0].message.content)"
+            },
+            "python_requests": {
+                "description": "Python requests",
+                "code": "import requests\nresponse = requests.post('http://localhost:19007/v1/chat/completions', json={'model': 'auto', 'messages': [{'role': 'user', 'content': '你好'}]})\nprint(response.json()['choices'][0]['message']['content'])"
+            },
+            "javascript": {
+                "description": "JavaScript fetch",
+                "code": "fetch('http://localhost:19007/v1/chat/completions', {method: 'POST', headers: {'Content-Type': 'application/json'}, body: JSON.stringify({model: 'auto', messages: [{role: 'user', content: '你好'}]})}).then(r => r.json()).then(d => console.log(d.choices[0].message.content))"
+            }
         }
     })
 
@@ -292,19 +390,29 @@ def list_models():
 @app.route('/v1/chat/completions', methods=['POST'])
 def chat_completions():
     """聊天完成API"""
+    # 用于统计的变量
+    request_model = None
+    request_provider = None
+    request_success = False
+    request_tokens = 0
+    
     try:
         data = request.get_json()
         
         if not data:
+            increment_stats('unknown', 'unknown', success=False, error='Invalid request body')
             return jsonify({"error": "Invalid request body"}), 400
         
         model = data.get('model', 'auto')
         stream = data.get('stream', False)
         
+        request_model = model
+        
         # 获取提供商
         provider, resolved_model = get_provider_for_model(model)
         
         if not provider:
+            increment_stats(model, 'unknown', success=False, error=f'No provider for model: {model}')
             return jsonify({
                 "error": {
                     "message": f"No available provider for model: {model}",
@@ -312,6 +420,8 @@ def chat_completions():
                 }
             }), 400
         
+        request_provider = provider['name']
+        
         logger.info(f"Request: model={model} -> provider={provider['name']}, resolved_model={resolved_model}, stream={stream}")
         
         # 重试逻辑
@@ -324,9 +434,11 @@ def chat_completions():
                 
                 if response.status_code == 200:
                     mark_provider_success(provider['name'])
+                    request_success = True
                     
                     if stream:
-                        # 流式响应
+                        # 流式响应 - 统计流式请求
+                        increment_stats(model, provider['name'], success=True, tokens=0)
                         return Response(
                             stream_with_context(stream_response(response)),
                             content_type='text/event-stream',
@@ -336,26 +448,36 @@ def chat_completions():
                             }
                         )
                     else:
-                        # 非流式响应
-                        return jsonify(response.json())
+                        # 非流式响应 - 提取token统计
+                        result = response.json()
+                        # 尝试提取usage信息
+                        usage = result.get('usage', {})
+                        request_tokens = usage.get('total_tokens', 0)
+                        
+                        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
                     
-                    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}
-                    return jsonify(last_error), response.status_code
+                    # 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(error_info), response.status_code
                     
             except Exception as e:
                 last_error = str(e)
@@ -363,14 +485,16 @@ 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
+                    request_provider = provider['name']
                     time.sleep(RETRY_CONFIG['retry_delay'])
                     continue
         
         # 所有重试都失败
+        increment_stats(model, request_provider or 'unknown', success=False, error=str(last_error))
         return jsonify({
             "error": {
                 "message": f"All providers failed. Last error: {last_error}",
@@ -380,6 +504,7 @@ def chat_completions():
         
     except Exception as e:
         logger.error(f"Unexpected error: {e}")
+        increment_stats(request_model or 'unknown', request_provider or 'unknown', success=False, error=str(e))
         return jsonify({
             "error": {
                 "message": str(e),