hz4th_coder
d387d5ba09
- Auto配置编辑: 粒度从提供商改为具体模型, 原生HTML5拖动排序, 修复已保存模型不显示勾选(字符串/对象混拼bug) - 历史缓存: 带历史上下文的auto请求按首条消息识别会话, 优先复用上次模型命中上游前缀缓存 (可配置: prefer_cache_model + cache_ttl_seconds, 系统配置页开关 + /api/admin/routing) - 对话生图: chat页选 auto-image/Qwen-Image 直接调生图接口并在对话内展示图片 - 修复: Flask模板缓存导致改模板不生效 -> TEMPLATES_AUTO_RELOAD - 修复: 自动回退/显式有序模型列表路由, 空列表回退提供商能力选择
1971 lines
71 KiB
Python
1971 lines
71 KiB
Python
"""
|
||
大模型API中转系统
|
||
v2.1.0 - 能力(Capability)体系 + 模型管理 + 生图/语音/视频端点
|
||
兼容OpenAI API格式，支持多上游提供商优先级调度
|
||
|
||
端口: 16003
|
||
前台API: http://localhost:16003/v1/chat/completions
|
||
后台管理: http://localhost:16003/admin
|
||
"""
|
||
|
||
from flask import Flask, request, jsonify, Response, stream_with_context, render_template
|
||
from flask_cors import CORS
|
||
import requests
|
||
import json
|
||
import time
|
||
import random
|
||
import hashlib
|
||
import logging
|
||
from datetime import datetime, date
|
||
from pathlib import Path
|
||
import sys
|
||
import threading
|
||
import uuid
|
||
|
||
# 添加配置路径
|
||
sys.path.insert(0, str(Path(__file__).parent))
|
||
from config.settings import (
|
||
get_providers, get_model_aliases, get_auto_profiles, get_auto_profile,
|
||
SERVER_CONFIG, LOG_CONFIG, RETRY_CONFIG, CAPABILITY_DEFS, ROUTING_CONFIG,
|
||
load_config, save_config, get_provider, add_provider, update_provider,
|
||
delete_provider, update_priority, update_model_alias, delete_model_alias,
|
||
add_auto_profile, update_auto_profile, delete_auto_profile, load_routing_config, save_routing_config,
|
||
DEFAULT_PROVIDERS, DEFAULT_MODEL_ALIASES, DEFAULT_AUTO_PROFILES
|
||
)
|
||
|
||
app = Flask(__name__, template_folder='templates')
|
||
app.config['TEMPLATES_AUTO_RELOAD'] = True # 模板修改即时生效（无需重启）
|
||
CORS(app)
|
||
|
||
VERSION = "2.1.1"
|
||
|
||
# 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'
|
||
CHATS_FILE = DATA_DIR / 'chats.json'
|
||
LOGS_DIR = Path(__file__).parent / (LOG_CONFIG.get('log_dir', 'logs'))
|
||
LOGS_DIR.mkdir(exist_ok=True)
|
||
|
||
# 统计锁（避免并发写入冲突）
|
||
stats_lock = threading.Lock()
|
||
chats_lock = threading.Lock()
|
||
|
||
# 历史上下文→模型缓存（用于 auto 请求优先复用上次模型，命中前缀缓存）
|
||
history_model_cache = {}
|
||
history_cache_lock = threading.Lock()
|
||
|
||
|
||
def history_fingerprint(data):
|
||
"""计算会话指纹：用首条消息作为会话锚点（同一对话各轮次首条消息不变，可跨轮次复用模型）"""
|
||
messages = data.get('messages', []) if isinstance(data, dict) else []
|
||
if not messages:
|
||
return None
|
||
try:
|
||
s = json.dumps(messages[0], ensure_ascii=False, sort_keys=True)
|
||
except Exception:
|
||
return None
|
||
return hashlib.md5(s.encode('utf-8')).hexdigest()
|
||
|
||
|
||
def has_history(data):
|
||
"""请求是否带历史上下文"""
|
||
messages = data.get('messages', []) if isinstance(data, dict) else []
|
||
return len(messages) >= 2
|
||
|
||
|
||
def get_cached_history_model(fp, capability=None):
|
||
"""获取历史前缀对应的上次模型（未过期且可用才返回）"""
|
||
if not fp:
|
||
return None
|
||
with history_cache_lock:
|
||
entry = history_model_cache.get(fp)
|
||
if not entry:
|
||
return None
|
||
routing = load_routing_config()
|
||
ttl = routing.get('cache_ttl_seconds', 3600)
|
||
if time.time() - entry.get('ts', 0) > ttl:
|
||
with history_cache_lock:
|
||
history_model_cache.pop(fp, None)
|
||
return None
|
||
provider = find_provider_for_model(entry.get('model', ''), capability)
|
||
if not provider:
|
||
return None
|
||
return {'provider': provider, 'model': entry['model']}
|
||
|
||
|
||
def remember_history_model(fp, provider_name, model):
|
||
"""记录某历史前缀使用的模型"""
|
||
if not fp:
|
||
return
|
||
with history_cache_lock:
|
||
history_model_cache[fp] = {'provider': provider_name, 'model': model, 'ts': time.time()}
|
||
|
||
# 提供商状态缓存
|
||
provider_status = {}
|
||
|
||
# 配置缓存时间（秒）
|
||
CONFIG_CACHE_TTL = 3
|
||
_last_config_load = 0
|
||
_cached_providers = []
|
||
_cached_aliases = {}
|
||
_cached_auto_profiles = {}
|
||
|
||
|
||
# ============ 能力/模型 工具函数 ============
|
||
|
||
def normalize_models(models, default_caps):
|
||
"""规范化模型列表（支持字符串 或 {name,capabilities} 两种格式）"""
|
||
result = []
|
||
for m in models or []:
|
||
if isinstance(m, str):
|
||
result.append({'name': m, 'capabilities': list(default_caps)})
|
||
elif isinstance(m, dict):
|
||
caps = m.get('capabilities') or list(default_caps)
|
||
result.append({'name': m.get('name', ''), 'capabilities': caps})
|
||
return [m for m in result if m['name']]
|
||
|
||
|
||
def provider_models(provider):
|
||
"""获取提供商的有效模型列表（dict）"""
|
||
default_caps = provider.get('capabilities', ['text'])
|
||
return normalize_models(provider.get('models', []), default_caps)
|
||
|
||
|
||
def provider_model_names(provider):
|
||
"""提供商支持的模型名列表"""
|
||
return [m['name'] for m in provider_models(provider)]
|
||
|
||
|
||
def model_capabilities(provider, model_name):
|
||
"""获取某模型在该提供商下的能力"""
|
||
for m in provider_models(provider):
|
||
if m['name'] == model_name:
|
||
return m.get('capabilities') or provider.get('capabilities', ['text'])
|
||
return provider.get('capabilities', ['text'])
|
||
|
||
|
||
def model_has_capability(provider, model_name, capability):
|
||
"""判断模型是否具备某能力"""
|
||
if capability == 'all' or not capability:
|
||
return True
|
||
caps = model_capabilities(provider, model_name)
|
||
return capability in caps
|
||
|
||
|
||
def provider_supports_capability(provider, capability):
|
||
"""判断提供商下是否有模型具备某能力"""
|
||
if capability == 'all' or not capability:
|
||
return True
|
||
return any(model_has_capability(provider, m['name'], capability) for m in provider_models(provider))
|
||
|
||
|
||
def provider_capability_models(provider, capability):
|
||
"""返回提供商下具备某能力的所有模型名"""
|
||
return [m['name'] for m in provider_models(provider) if model_has_capability(provider, m['name'], capability)]
|
||
|
||
|
||
def find_default_model_for_capability(provider, capability):
|
||
"""找提供商下具备某能力的最佳模型（优先 default_model）"""
|
||
default_model = provider.get('default_model', '')
|
||
if default_model and default_model in provider_model_names(provider) and model_has_capability(provider, default_model, capability):
|
||
return default_model
|
||
for m in provider_models(provider):
|
||
if model_has_capability(provider, m['name'], capability):
|
||
return m['name']
|
||
return None
|
||
|
||
|
||
# ============ 统计 ============
|
||
|
||
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
|
||
}
|
||
|
||
|
||
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()
|
||
|
||
if stats.get('date') != today:
|
||
stats['date'] = today
|
||
stats['requests_today'] = 0
|
||
|
||
stats['total_requests'] += 1
|
||
stats['requests_today'] += 1
|
||
|
||
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
|
||
|
||
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)
|
||
|
||
|
||
# ============ 配置缓存 ============
|
||
|
||
def refresh_config():
|
||
"""动态刷新配置"""
|
||
global _last_config_load, _cached_providers, _cached_aliases, _cached_auto_profiles
|
||
|
||
current_time = time.time()
|
||
if current_time - _last_config_load > CONFIG_CACHE_TTL:
|
||
_cached_providers = get_providers()
|
||
_cached_aliases = get_model_aliases()
|
||
_cached_auto_profiles = get_auto_profiles()
|
||
_last_config_load = current_time
|
||
|
||
for provider in _cached_providers:
|
||
if provider['name'] not in provider_status:
|
||
provider_status[provider['name']] = {
|
||
'available': True,
|
||
'last_check': None,
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
}
|
||
|
||
|
||
def refresh_provider_status():
|
||
"""刷新提供商状态"""
|
||
providers = get_providers()
|
||
for provider in providers:
|
||
if provider['name'] not in provider_status:
|
||
provider_status[provider['name']] = {
|
||
'available': True,
|
||
'last_check': None,
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
'request_count': 0,
|
||
'success_count': 0,
|
||
'total_tokens': 0,
|
||
}
|
||
|
||
|
||
# ============ 熔断器（带冷却恢复） ============
|
||
|
||
def is_provider_available(provider_name):
|
||
"""判断提供商是否可用（含熔断冷却自动恢复）"""
|
||
status = provider_status.get(provider_name)
|
||
if not status:
|
||
return True
|
||
if status.get('available', True):
|
||
return True
|
||
# 熔断中：检查冷却期是否已过，过了则半开恢复一次
|
||
open_at = status.get('circuit_open_at')
|
||
if open_at:
|
||
cooldown = RETRY_CONFIG.get('cooldown_seconds', 60)
|
||
if time.time() - open_at > cooldown:
|
||
status['error_count'] = 0
|
||
status['available'] = True
|
||
status['circuit_open_at'] = None
|
||
logger.info(f"Provider {provider_name} circuit breaker recovered (cooldown passed)")
|
||
return True
|
||
return False
|
||
|
||
|
||
def mark_provider_error(provider_name, error):
|
||
"""标记提供商错误（连续3次熔断）"""
|
||
if provider_name in provider_status:
|
||
status = provider_status[provider_name]
|
||
status['error_count'] = status.get('error_count', 0) + 1
|
||
status['last_error'] = str(error)
|
||
status['last_check'] = datetime.now()
|
||
|
||
if status['error_count'] >= 3:
|
||
status['available'] = False
|
||
status['circuit_open_at'] = time.time()
|
||
logger.warning(f"Provider {provider_name} marked as unavailable (circuit open)")
|
||
|
||
|
||
def mark_provider_success(provider_name):
|
||
"""标记提供商成功（复位熔断）"""
|
||
if provider_name in provider_status:
|
||
provider_status[provider_name]['error_count'] = 0
|
||
provider_status[provider_name]['available'] = True
|
||
provider_status[provider_name]['circuit_open_at'] = None
|
||
provider_status[provider_name]['last_check'] = datetime.now()
|
||
|
||
|
||
# ============ 提供商/模型路由 ============
|
||
|
||
def resolve_model_name(model_name):
|
||
"""解析模型别名"""
|
||
refresh_config()
|
||
return _cached_aliases.get(model_name, model_name)
|
||
|
||
|
||
def is_auto_model(model_name):
|
||
"""判断是否为auto类模型（auto 或 auto-xxx 配置）"""
|
||
return model_name == 'auto' or model_name.startswith('auto-')
|
||
|
||
|
||
def sorted_providers():
|
||
"""按优先级排序的启用提供商"""
|
||
refresh_config()
|
||
return sorted(_cached_providers, key=lambda x: x['priority'])
|
||
|
||
|
||
def find_provider_for_model(model_name, capability=None, exclude=None):
|
||
"""精确查找托管某模型的提供商（保持模型名不变，仅用于切换时的同模型替换）"""
|
||
exclude = exclude or set()
|
||
for provider in sorted_providers():
|
||
if not provider['enabled']:
|
||
continue
|
||
if provider['name'] in exclude:
|
||
continue
|
||
if not is_provider_available(provider['name']):
|
||
continue
|
||
if model_name in provider_model_names(provider):
|
||
if model_has_capability(provider, model_name, capability):
|
||
return provider
|
||
return None
|
||
|
||
|
||
def get_auto_provider(profile_name='auto', capability=None, exclude=None):
|
||
"""获取auto模式下可用的提供商与模型
|
||
|
||
优先级：
|
||
1. 配置了显式有序 models 列表 → 按列表顺序逐个找能托管该模型的提供商
|
||
2. 否则按提供商能力 + 优先级选择（旧逻辑回退）
|
||
"""
|
||
refresh_config()
|
||
exclude = exclude or set()
|
||
profile = _cached_auto_profiles.get(profile_name, _cached_auto_profiles.get('auto', {}))
|
||
req_cap = profile.get('capability') or capability or 'text'
|
||
allowed_providers = profile.get('providers', ['*'])
|
||
strategy = profile.get('strategy', 'priority')
|
||
ordered_models = profile.get('models') or []
|
||
|
||
# 方式1：显式有序模型列表（粒度=具体模型，用户可拖动排序）
|
||
if ordered_models:
|
||
candidates = []
|
||
for mname in ordered_models:
|
||
provider = find_provider_for_model(mname, req_cap, exclude=exclude)
|
||
if provider:
|
||
candidates.append((provider, mname))
|
||
if candidates:
|
||
if strategy == 'random':
|
||
return random.choice(candidates)
|
||
return candidates[0]
|
||
return None, None # 显式列表全不可用时，不悄悄换成别的模型
|
||
|
||
# 方式2：按提供商能力 + 优先级
|
||
candidates = []
|
||
for provider in sorted_providers():
|
||
if not provider['enabled']:
|
||
continue
|
||
if provider['name'] in exclude:
|
||
continue
|
||
if not is_provider_available(provider['name']):
|
||
continue
|
||
if not ('*' in allowed_providers or provider.get('id') in allowed_providers or provider['name'] in allowed_providers):
|
||
continue
|
||
chosen_model = find_default_model_for_capability(provider, req_cap)
|
||
if chosen_model:
|
||
candidates.append((provider, chosen_model))
|
||
|
||
if not candidates:
|
||
return None, None
|
||
if strategy == 'random':
|
||
return random.choice(candidates)
|
||
return candidates[0]
|
||
|
||
|
||
def get_provider_for_model(model_name, capability=None):
|
||
"""根据模型名获取提供商与解析后的模型名"""
|
||
resolved_model = resolve_model_name(model_name)
|
||
|
||
if is_auto_model(resolved_model):
|
||
return get_auto_provider(resolved_model, capability)
|
||
|
||
# 精确匹配：提供商托管该模型
|
||
provider = find_provider_for_model(resolved_model, capability)
|
||
if provider:
|
||
return provider, resolved_model
|
||
|
||
# 兜底：匹配提供商 default_model
|
||
for provider in sorted_providers():
|
||
if not provider['enabled']:
|
||
continue
|
||
if not is_provider_available(provider['name']):
|
||
continue
|
||
if provider.get('default_model') == resolved_model:
|
||
if model_has_capability(provider, resolved_model, capability):
|
||
return provider, resolved_model
|
||
|
||
# 最后：模糊匹配（仅当请求模型是提供商某个模型名的子串或反向，避免误路由）
|
||
for provider in sorted_providers():
|
||
if not provider['enabled']:
|
||
continue
|
||
if not is_provider_available(provider['name']):
|
||
continue
|
||
for m in provider_model_names(provider):
|
||
if resolved_model.lower() == m.lower():
|
||
return provider, m
|
||
|
||
return None, None
|
||
|
||
|
||
def detect_capability(data):
|
||
"""根据请求内容判断所需能力（含图片则 vision，否则 text）"""
|
||
messages = data.get('messages', []) if isinstance(data, dict) else []
|
||
for msg in messages:
|
||
content = msg.get('content')
|
||
if isinstance(content, list):
|
||
for part in content:
|
||
if isinstance(part, dict) and part.get('type') in ('image_url', 'image', 'input_image'):
|
||
return 'vision'
|
||
return 'text'
|
||
|
||
|
||
def is_image_gen_request(model):
|
||
"""判断请求是否为图片生成（auto-image 配置或具备 image_gen 能力的模型）"""
|
||
resolved = resolve_model_name(model)
|
||
if is_auto_model(resolved):
|
||
return _cached_auto_profiles.get(resolved, {}).get('capability') == 'image_gen'
|
||
return find_provider_for_model(resolved, 'image_gen') is not None
|
||
|
||
|
||
# ============ 上游转发 ============
|
||
|
||
def build_headers(provider, content_type='application/json', extra=None):
|
||
headers = {
|
||
"Authorization": f"Bearer {provider['api_key']}",
|
||
"Content-Type": content_type,
|
||
}
|
||
if extra:
|
||
headers.update(extra)
|
||
return headers
|
||
|
||
|
||
def proxy_chat(provider, model, request_data, stream=False):
|
||
"""转发聊天请求到上游"""
|
||
url = f"{provider['base_url'].rstrip('/')}/chat/completions"
|
||
data = request_data.copy()
|
||
data['model'] = model
|
||
|
||
try:
|
||
if stream:
|
||
return requests.post(url, headers=build_headers(provider), json=data, stream=True, timeout=provider.get('timeout', 120))
|
||
return requests.post(url, headers=build_headers(provider), json=data, timeout=provider.get('timeout', 120))
|
||
except requests.exceptions.Timeout:
|
||
mark_provider_error(provider['name'], "Timeout")
|
||
raise Exception(f"Provider {provider['name']} timeout")
|
||
except requests.exceptions.ConnectionError:
|
||
mark_provider_error(provider['name'], "Connection error")
|
||
raise Exception(f"Provider {provider['name']} connection error")
|
||
except Exception as e:
|
||
mark_provider_error(provider['name'], str(e))
|
||
raise
|
||
|
||
|
||
def proxy_json(provider, path, request_data, timeout=None):
|
||
"""通用JSON转发"""
|
||
url = f"{provider['base_url'].rstrip('/')}/{path.lstrip('/')}"
|
||
timeout = timeout or provider.get('timeout', 120)
|
||
try:
|
||
return requests.post(url, headers=build_headers(provider), json=request_data, timeout=timeout)
|
||
except requests.exceptions.Timeout:
|
||
mark_provider_error(provider['name'], "Timeout")
|
||
raise Exception(f"Provider {provider['name']} timeout")
|
||
except requests.exceptions.ConnectionError:
|
||
mark_provider_error(provider['name'], "Connection error")
|
||
raise Exception(f"Provider {provider['name']} connection error")
|
||
except Exception as e:
|
||
mark_provider_error(provider['name'], str(e))
|
||
raise
|
||
|
||
|
||
def proxy_raw(provider, path, timeout=None):
|
||
"""通用原始体转发（用于 multipart 表单，如语音识别）"""
|
||
url = f"{provider['base_url'].rstrip('/')}/{path.lstrip('/')}"
|
||
timeout = timeout or provider.get('timeout', 180)
|
||
data = request.get_data()
|
||
headers = build_headers(provider, content_type=request.headers.get('Content-Type', 'application/octet-stream'))
|
||
try:
|
||
return requests.post(url, headers=headers, data=data, timeout=timeout)
|
||
except requests.exceptions.Timeout:
|
||
mark_provider_error(provider['name'], "Timeout")
|
||
raise Exception(f"Provider {provider['name']} timeout")
|
||
except requests.exceptions.ConnectionError:
|
||
mark_provider_error(provider['name'], "Connection error")
|
||
raise Exception(f"Provider {provider['name']} connection error")
|
||
except Exception as e:
|
||
mark_provider_error(provider['name'], str(e))
|
||
raise
|
||
|
||
|
||
def stream_response(response):
|
||
"""流式响应生成器"""
|
||
try:
|
||
for line in response.iter_lines():
|
||
if line:
|
||
yield line + b'\n'
|
||
except Exception as e:
|
||
logger.error(f"Stream error: {e}")
|
||
yield b'data: {"error": "' + str(e).encode() + b'"}\n\n'
|
||
|
||
|
||
# ============ 日志 ============
|
||
|
||
logging.basicConfig(
|
||
level=logging.INFO,
|
||
format='%(asctime)s - %(name)s - %(levelname)s - %(message)s',
|
||
handlers=[
|
||
logging.FileHandler(LOGS_DIR / 'proxy.log', encoding='utf-8'),
|
||
logging.StreamHandler()
|
||
]
|
||
)
|
||
logger = logging.getLogger(__name__)
|
||
|
||
# 初始化配置与提供商状态
|
||
refresh_config()
|
||
refresh_provider_status()
|
||
|
||
# ============ 前台 API 路由 ============
|
||
|
||
@app.route('/')
|
||
def index():
|
||
"""首页"""
|
||
return jsonify({
|
||
"name": "LLM Proxy",
|
||
"version": VERSION,
|
||
"description": "OpenAI-compatible LLM API Proxy with capability routing",
|
||
"endpoints": {
|
||
"chat": "/v1/chat/completions",
|
||
"models": "/v1/models",
|
||
"embeddings": "/v1/embeddings",
|
||
"images": "/v1/images/generations",
|
||
"audio_speech": "/v1/audio/speech",
|
||
"audio_transcriptions": "/v1/audio/transcriptions",
|
||
"video": "/v1/video/generations",
|
||
"health": "/health",
|
||
"status": "/status",
|
||
"admin": "/admin"
|
||
},
|
||
"capabilities": CAPABILITY_DEFS,
|
||
})
|
||
|
||
|
||
@app.route('/v1/models', methods=['GET'])
|
||
def list_models():
|
||
"""列出可用模型（含auto配置与能力标签）"""
|
||
refresh_config()
|
||
|
||
models_list = []
|
||
added_models = set()
|
||
|
||
for profile_name, profile in _cached_auto_profiles.items():
|
||
if profile_name not in added_models:
|
||
models_list.append({
|
||
"id": profile_name,
|
||
"object": "model",
|
||
"created": int(time.time()),
|
||
"owned_by": "proxy",
|
||
"kind": "auto",
|
||
"capability": profile.get('capability', 'text'),
|
||
"description": f"[{CAPABILITY_DEFS.get(profile.get('capability', 'text'), profile.get('capability', 'text'))}] {profile.get('description', '')}"
|
||
})
|
||
added_models.add(profile_name)
|
||
|
||
for provider in _cached_providers:
|
||
if not provider['enabled']:
|
||
continue
|
||
for m in provider_models(provider):
|
||
if m['name'] not in added_models:
|
||
models_list.append({
|
||
"id": m['name'],
|
||
"object": "model",
|
||
"created": int(time.time()),
|
||
"owned_by": provider['name'],
|
||
"kind": "model",
|
||
"capabilities": m['capabilities'],
|
||
})
|
||
added_models.add(m['name'])
|
||
|
||
return jsonify({"object": "list", "data": models_list})
|
||
|
||
|
||
@app.route('/v1/chat/completions', methods=['POST'])
|
||
def chat_completions():
|
||
"""聊天完成API"""
|
||
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
|
||
capability = detect_capability(data)
|
||
|
||
# 历史上下文缓存：auto 请求始终记录会话锚点（首条消息），带历史时优先复用上次模型
|
||
history_fp = None
|
||
routing_cfg = load_routing_config()
|
||
if routing_cfg.get('prefer_cache_model', True) and is_auto_model(model):
|
||
history_fp = history_fingerprint(data)
|
||
if has_history(data):
|
||
cached = get_cached_history_model(history_fp, capability)
|
||
if cached:
|
||
provider = cached['provider']
|
||
resolved_model = cached['model']
|
||
request_provider = provider['name']
|
||
logger.info(f"History cache hit: model={model} -> provider={provider['name']}, resolved_model={resolved_model}, stream={stream}, capability={capability}")
|
||
else:
|
||
provider, resolved_model = get_provider_for_model(model, capability)
|
||
else:
|
||
provider, resolved_model = get_provider_for_model(model, capability)
|
||
else:
|
||
provider, resolved_model = get_provider_for_model(model, capability)
|
||
|
||
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} (capability: {capability})", "type": "invalid_request_error"}}), 400
|
||
|
||
request_provider = provider['name']
|
||
if not history_fp or not routing_cfg.get('prefer_cache_model', True):
|
||
logger.info(f"Request: model={model} -> provider={provider['name']}, resolved_model={resolved_model}, stream={stream}, capability={capability}")
|
||
|
||
last_error = None
|
||
tried_providers = set()
|
||
|
||
for attempt in range(RETRY_CONFIG['max_retries']):
|
||
try:
|
||
response = proxy_chat(provider, resolved_model, data, stream)
|
||
|
||
if response.status_code == 200:
|
||
mark_provider_success(provider['name'])
|
||
request_success = True
|
||
|
||
if stream:
|
||
increment_stats(model, provider['name'], success=True, tokens=0)
|
||
remember_history_model(history_fp, provider['name'], resolved_model)
|
||
return Response(
|
||
stream_with_context(stream_response(response)),
|
||
content_type='text/event-stream',
|
||
headers={'Cache-Control': 'no-cache', 'Connection': 'keep-alive'}
|
||
)
|
||
else:
|
||
result = response.json()
|
||
usage = result.get('usage', {})
|
||
request_tokens = usage.get('total_tokens', 0)
|
||
increment_stats(model, provider['name'], success=True, tokens=request_tokens)
|
||
remember_history_model(history_fp, provider['name'], resolved_model)
|
||
return jsonify(result)
|
||
|
||
else:
|
||
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.add(provider['name'])
|
||
|
||
# 切换到下一个能托管同一模型的提供商（保持模型名不变）
|
||
next_provider = find_provider_for_model(resolved_model, capability, exclude=tried_providers)
|
||
if next_provider:
|
||
logger.info(f"Switching to next provider: {next_provider['name']}")
|
||
provider = next_provider
|
||
request_provider = provider['name']
|
||
time.sleep(RETRY_CONFIG['retry_delay'])
|
||
continue
|
||
|
||
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)
|
||
logger.error(f"Attempt {attempt + 1} failed: {e}")
|
||
tried_providers.add(provider['name'])
|
||
|
||
# 非auto模型：优先切换到能托管同一模型的其他提供商
|
||
next_provider = find_provider_for_model(resolved_model, capability, exclude=tried_providers)
|
||
if next_provider:
|
||
provider = next_provider
|
||
request_provider = provider['name']
|
||
time.sleep(RETRY_CONFIG['retry_delay'])
|
||
continue
|
||
|
||
# auto模型：按auto配置切换到下一个候选（模型可随能力重选）
|
||
if is_auto_model(model):
|
||
next_provider, next_model = get_auto_provider(model, capability, exclude=tried_providers)
|
||
if next_provider:
|
||
provider = next_provider
|
||
resolved_model = next_model
|
||
request_provider = provider['name']
|
||
time.sleep(RETRY_CONFIG['retry_delay'])
|
||
continue
|
||
|
||
# 没有更多可切换提供商，立即结束（不再重试同一个失败提供商）
|
||
break
|
||
|
||
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}", "type": "api_error"}}), 503
|
||
|
||
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), "type": "internal_error"}}), 500
|
||
|
||
|
||
@app.route('/v1/embeddings', methods=['POST'])
|
||
def embeddings():
|
||
"""嵌入API（按模型路由，不再固定第一个提供商）"""
|
||
refresh_config()
|
||
|
||
try:
|
||
data = request.get_json()
|
||
if not data:
|
||
return jsonify({"error": "Invalid request body"}), 400
|
||
|
||
model = data.get('model')
|
||
provider = None
|
||
|
||
if model:
|
||
provider = find_provider_for_model(model)
|
||
if not provider:
|
||
# 按名字匹配（如 embedding 模型名可能不在托管列表）
|
||
for p in sorted_providers():
|
||
if p['enabled'] and is_provider_available(p['name']):
|
||
provider = p
|
||
break
|
||
else:
|
||
for p in sorted_providers():
|
||
if p['enabled'] and is_provider_available(p['name']):
|
||
provider = p
|
||
break
|
||
|
||
if not provider:
|
||
return jsonify({"error": "No available provider for embeddings"}), 503
|
||
|
||
response = proxy_json(provider, 'embeddings', data, timeout=60)
|
||
return jsonify(response.json()), response.status_code
|
||
except Exception as e:
|
||
return jsonify({"error": str(e)}), 500
|
||
|
||
|
||
def _generic_capability_endpoint(capability, path, error_msg="No available provider"):
|
||
"""通用能力端点路由"""
|
||
refresh_config()
|
||
try:
|
||
data = request.get_json() if request.is_json else {}
|
||
if not isinstance(data, dict):
|
||
data = {}
|
||
model = data.get('model', 'auto')
|
||
|
||
if is_auto_model(model):
|
||
provider, resolved_model = get_auto_provider(model, capability)
|
||
else:
|
||
resolved_model = resolve_model_name(model)
|
||
provider = find_provider_for_model(resolved_model, capability)
|
||
if not provider:
|
||
# 允许提供商默认模型具备该能力
|
||
for p in sorted_providers():
|
||
if not p['enabled'] or not is_provider_available(p['name']):
|
||
continue
|
||
if p.get('default_model') == resolved_model and model_has_capability(p, resolved_model, capability):
|
||
provider = p
|
||
break
|
||
|
||
if not provider:
|
||
return jsonify({"error": {"message": f"{error_msg} (capability: {capability})", "type": "invalid_request_error"}}), 400
|
||
|
||
data['model'] = resolved_model if resolved_model else data.get('model')
|
||
response = proxy_json(provider, path, data)
|
||
return Response(
|
||
response.content,
|
||
status=response.status_code,
|
||
content_type=response.headers.get('Content-Type', 'application/json')
|
||
)
|
||
except Exception as e:
|
||
return jsonify({"error": str(e)}), 500
|
||
|
||
|
||
@app.route('/v1/images/generations', methods=['POST'])
|
||
def images_generations():
|
||
"""图片生成API（OpenAI兼容）"""
|
||
return _generic_capability_endpoint('image_gen', 'images/generations', "No image generation provider available")
|
||
|
||
|
||
@app.route('/v1/audio/speech', methods=['POST'])
|
||
def audio_speech():
|
||
"""语音合成API（TTS，OpenAI兼容）"""
|
||
return _generic_capability_endpoint('audio_out', 'audio/speech', "No TTS provider available")
|
||
|
||
|
||
@app.route('/v1/audio/transcriptions', methods=['POST'])
|
||
def audio_transcriptions():
|
||
"""语音识别API（ASR，OpenAI兼容，multipart转发）"""
|
||
refresh_config()
|
||
try:
|
||
model = request.form.get('model', 'auto')
|
||
|
||
if is_auto_model(model):
|
||
provider, resolved_model = get_auto_provider(model, 'audio_in')
|
||
else:
|
||
resolved_model = resolve_model_name(model)
|
||
provider = find_provider_for_model(resolved_model, 'audio_in')
|
||
if not provider:
|
||
for p in sorted_providers():
|
||
if not p['enabled'] or not is_provider_available(p['name']):
|
||
continue
|
||
if p.get('default_model') == resolved_model and model_has_capability(p, resolved_model, 'audio_in'):
|
||
provider = p
|
||
break
|
||
|
||
if not provider:
|
||
return jsonify({"error": {"message": "No ASR provider available (capability: audio_in)", "type": "invalid_request_error"}}), 400
|
||
|
||
response = proxy_raw(provider, 'audio/transcriptions')
|
||
return Response(
|
||
response.content,
|
||
status=response.status_code,
|
||
content_type=response.headers.get('Content-Type', 'application/json')
|
||
)
|
||
except Exception as e:
|
||
return jsonify({"error": str(e)}), 500
|
||
|
||
|
||
@app.route('/v1/video/generations', methods=['POST'])
|
||
def video_generations():
|
||
"""视频生成API"""
|
||
return _generic_capability_endpoint('video_gen', 'video/generations', "No video generation provider available")
|
||
|
||
|
||
@app.route('/health', methods=['GET'])
|
||
def health():
|
||
"""健康检查"""
|
||
available_count = sum(1 for name, s in provider_status.items() if is_provider_available(name))
|
||
total_count = len(provider_status)
|
||
|
||
return jsonify({
|
||
"status": "healthy" if available_count > 0 else "degraded",
|
||
"providers": {"available": available_count, "total": total_count},
|
||
"timestamp": datetime.now().isoformat()
|
||
})
|
||
|
||
|
||
@app.route('/status', methods=['GET'])
|
||
def status():
|
||
"""详细状态"""
|
||
refresh_config()
|
||
|
||
providers_detail = []
|
||
for provider in _cached_providers:
|
||
status_info = provider_status.get(provider['name'], {})
|
||
providers_detail.append({
|
||
"name": provider['name'],
|
||
"priority": provider['priority'],
|
||
"enabled": provider['enabled'],
|
||
"available": is_provider_available(provider['name']),
|
||
"error_count": status_info.get('error_count', 0),
|
||
"last_error": status_info.get('last_error'),
|
||
"capabilities": provider.get('capabilities', ['text']),
|
||
"models": [{'name': m['name'], 'capabilities': m['capabilities']} for m in provider_models(provider)],
|
||
})
|
||
|
||
return jsonify({
|
||
"version": VERSION,
|
||
"uptime": time.time(),
|
||
"providers": providers_detail,
|
||
"model_aliases": _cached_aliases,
|
||
"auto_profiles": _cached_auto_profiles,
|
||
})
|
||
|
||
|
||
# 兼容旧版端点
|
||
@app.route('/v1/engines', methods=['GET'])
|
||
def list_engines():
|
||
return list_models()
|
||
|
||
|
||
@app.route('/v1/engines/<model>/completions', methods=['POST'])
|
||
def engine_completions(model):
|
||
data = request.get_json()
|
||
if data is None:
|
||
data = {}
|
||
if not isinstance(data, dict):
|
||
return jsonify({"error": {"message": "Invalid request body", "type": "invalid_request_error"}}), 400
|
||
data['model'] = model
|
||
return chat_completions()
|
||
|
||
|
||
# ============ 后台管理页面路由 ============
|
||
|
||
@app.route('/admin')
|
||
def admin_index():
|
||
return render_template('index.html')
|
||
|
||
|
||
@app.route('/admin/providers')
|
||
def admin_providers_page():
|
||
return render_template('providers.html')
|
||
|
||
|
||
@app.route('/admin/models')
|
||
def admin_models_page():
|
||
return render_template('models.html')
|
||
|
||
|
||
@app.route('/admin/logs')
|
||
def admin_logs_page():
|
||
return render_template('logs.html')
|
||
|
||
|
||
@app.route('/admin/config')
|
||
def admin_config_page():
|
||
return render_template('config.html')
|
||
|
||
|
||
@app.route('/admin/chat')
|
||
def admin_chat_page():
|
||
return render_template('chat.html')
|
||
|
||
|
||
@app.route('/admin/auto-profiles')
|
||
def admin_auto_profiles_page():
|
||
return render_template('auto-profiles.html')
|
||
|
||
|
||
# ============ 后台管理 API：能力 ============
|
||
|
||
@app.route('/api/admin/capabilities')
|
||
def api_admin_capabilities():
|
||
"""获取能力定义"""
|
||
return jsonify(CAPABILITY_DEFS)
|
||
|
||
|
||
# ============ 后台管理 API：统计 ============
|
||
|
||
@app.route('/api/admin/stats')
|
||
def api_admin_stats():
|
||
"""获取统计数据"""
|
||
stats = load_stats()
|
||
providers = get_providers()
|
||
refresh_provider_status()
|
||
|
||
available_count = sum(1 for p in providers if is_provider_available(p['name']))
|
||
|
||
return jsonify({
|
||
'total_requests': stats.get('total_requests', 0),
|
||
'total_success': stats.get('total_success', 0),
|
||
'total_errors': stats.get('total_errors', 0),
|
||
'total_tokens': stats.get('total_tokens', 0),
|
||
'requests_today': stats.get('requests_today', 0),
|
||
'providers_count': len(providers),
|
||
'available_providers': available_count,
|
||
'models_count': sum(len(provider_model_names(p)) for p in providers),
|
||
'uptime': time.time(),
|
||
})
|
||
|
||
|
||
# ============ 后台管理 API：提供商 ============
|
||
|
||
def _provider_public(p):
|
||
"""提供商对外数据结构（含能力与模型详情）"""
|
||
return {
|
||
'id': p.get('id', p['name'].lower().replace(' ', '-')),
|
||
'name': p['name'],
|
||
'priority': p['priority'],
|
||
'enabled': p.get('enabled', True),
|
||
'available': is_provider_available(p['name']),
|
||
'base_url': p['base_url'],
|
||
'api_key': p['api_key'],
|
||
'capabilities': p.get('capabilities', ['text']),
|
||
'models': [{'name': m['name'], 'capabilities': m['capabilities']} for m in provider_models(p)],
|
||
'default_model': p.get('default_model', ''),
|
||
'timeout': p.get('timeout', 120),
|
||
'request_count': 0,
|
||
'success_count': 0,
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
'last_check': None,
|
||
}
|
||
|
||
|
||
@app.route('/api/admin/providers')
|
||
def api_admin_providers():
|
||
"""获取提供商列表"""
|
||
providers = get_providers()
|
||
refresh_provider_status()
|
||
stats = load_stats()
|
||
|
||
providers_data = []
|
||
for provider in sorted(providers, key=lambda x: x['priority']):
|
||
p_stats = stats.get('providers', {}).get(provider['name'], {})
|
||
p_status = provider_status.get(provider['name'], {})
|
||
item = _provider_public(provider)
|
||
item.update({
|
||
'request_count': p_stats.get('requests', 0),
|
||
'success_count': p_stats.get('success', 0),
|
||
'error_count': p_status.get('error_count', 0),
|
||
'last_error': p_status.get('last_error'),
|
||
'last_check': p_status.get('last_check'),
|
||
})
|
||
providers_data.append(item)
|
||
|
||
return jsonify(providers_data)
|
||
|
||
|
||
@app.route('/api/admin/providers/<provider_id>', methods=['GET'])
|
||
def api_admin_provider_detail(provider_id):
|
||
"""获取提供商详情"""
|
||
provider = get_provider(provider_id)
|
||
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
stats = load_stats()
|
||
p_stats = stats.get('providers', {}).get(provider['name'], {})
|
||
p_status = provider_status.get(provider['name'], {})
|
||
|
||
item = _provider_public(provider)
|
||
item['status'] = {
|
||
'available': is_provider_available(provider['name']),
|
||
'error_count': p_status.get('error_count', 0),
|
||
'last_error': p_status.get('last_error'),
|
||
'request_count': p_stats.get('requests', 0),
|
||
'success_count': p_stats.get('success', 0),
|
||
}
|
||
return jsonify(item)
|
||
|
||
|
||
def _sanitize_provider_input(data):
|
||
"""清洗提供商输入"""
|
||
new_provider = {}
|
||
if 'id' in data:
|
||
new_provider['id'] = data['id']
|
||
if 'name' in data:
|
||
new_provider['name'] = data['name'].strip()
|
||
if 'priority' in data:
|
||
try:
|
||
new_provider['priority'] = int(data['priority'])
|
||
except:
|
||
pass
|
||
if 'base_url' in data:
|
||
new_provider['base_url'] = data['base_url'].rstrip('/')
|
||
if 'api_key' in data:
|
||
new_provider['api_key'] = data['api_key']
|
||
if 'timeout' in data:
|
||
try:
|
||
new_provider['timeout'] = int(data['timeout'])
|
||
except:
|
||
pass
|
||
if 'enabled' in data:
|
||
new_provider['enabled'] = bool(data['enabled'])
|
||
if 'capabilities' in data:
|
||
caps = data['capabilities']
|
||
if isinstance(caps, str):
|
||
caps = [c.strip() for c in caps.split(',') if c.strip()]
|
||
new_provider['capabilities'] = list(caps)
|
||
if 'models' in data:
|
||
models = data['models']
|
||
if isinstance(models, str):
|
||
models = [m.strip() for m in models.split(',') if m.strip()]
|
||
# 统一为 dict 形式，新模型默认继承提供商能力
|
||
default_caps = new_provider.get('capabilities') or data.get('capabilities', ['text'])
|
||
norm = []
|
||
for m in models:
|
||
if isinstance(m, dict):
|
||
norm.append({'name': m['name'], 'capabilities': m.get('capabilities', list(default_caps))})
|
||
else:
|
||
norm.append({'name': m, 'capabilities': list(default_caps)})
|
||
new_provider['models'] = norm
|
||
if 'default_model' in data and data['default_model']:
|
||
new_provider['default_model'] = data['default_model']
|
||
return new_provider
|
||
|
||
|
||
@app.route('/api/admin/providers', methods=['POST'])
|
||
def api_admin_add_provider():
|
||
"""添加新提供商"""
|
||
data = request.get_json()
|
||
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
required = ['name', 'base_url', 'api_key', 'models']
|
||
for field in required:
|
||
if not data.get(field):
|
||
return jsonify({'error': f'Missing required field: {field}'}), 400
|
||
|
||
providers = get_providers()
|
||
max_priority = max([p['priority'] for p in providers]) if providers else 0
|
||
|
||
new_provider = _sanitize_provider_input(data)
|
||
new_provider.setdefault('id', data['name'].lower().replace(' ', '-').replace('.', '-'))
|
||
new_provider.setdefault('priority', max_priority + 1)
|
||
new_provider.setdefault('enabled', True)
|
||
new_provider.setdefault('capabilities', ['text'])
|
||
if not new_provider.get('default_model'):
|
||
names = [m['name'] for m in new_provider.get('models', [])]
|
||
new_provider['default_model'] = names[0] if names else ''
|
||
new_provider['priority'] = data.get('priority', max_priority + 1)
|
||
|
||
result = add_provider(new_provider)
|
||
|
||
provider_status[result['name']] = {
|
||
'available': True,
|
||
'last_check': None,
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
}
|
||
|
||
return jsonify({'success': True, 'provider': _provider_public(result)})
|
||
|
||
|
||
@app.route('/api/admin/providers/<provider_id>', methods=['PUT'])
|
||
def api_admin_update_provider(provider_id):
|
||
"""更新提供商"""
|
||
data = request.get_json()
|
||
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
result = update_provider(provider_id, _sanitize_provider_input(data))
|
||
|
||
if not result:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
return jsonify({'success': True, 'provider': _provider_public(result)})
|
||
|
||
|
||
@app.route('/api/admin/providers/<provider_id>', methods=['DELETE'])
|
||
def api_admin_delete_provider(provider_id):
|
||
"""删除提供商"""
|
||
provider = get_provider(provider_id)
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
result = delete_provider(provider_id)
|
||
|
||
if provider['name'] in provider_status:
|
||
del provider_status[provider['name']]
|
||
|
||
return jsonify({'success': True})
|
||
|
||
|
||
@app.route('/api/admin/providers/priority', methods=['POST'])
|
||
def api_admin_update_priority():
|
||
"""更新优先级顺序"""
|
||
data = request.get_json()
|
||
|
||
if not data or 'order' not in data:
|
||
return jsonify({'error': 'Missing order field'}), 400
|
||
|
||
provider_ids = data['order']
|
||
result = update_priority(provider_ids)
|
||
|
||
return jsonify({'success': True, 'providers': result})
|
||
|
||
|
||
@app.route('/api/admin/providers/<provider_id>/toggle', methods=['POST'])
|
||
def api_admin_toggle_provider(provider_id):
|
||
"""切换提供商启用状态"""
|
||
provider = get_provider(provider_id)
|
||
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
new_enabled = not provider.get('enabled', True)
|
||
result = update_provider(provider_id, {'enabled': new_enabled})
|
||
|
||
return jsonify({'success': True, 'enabled': new_enabled})
|
||
|
||
|
||
@app.route('/api/admin/providers/<provider_id>/test', methods=['POST'])
|
||
def api_admin_test_provider(provider_id):
|
||
"""测试提供商连接（优先 /models，失败则用聊天探测，适配 new-api 等无 /models 的服务）"""
|
||
provider = get_provider(provider_id)
|
||
|
||
if not provider:
|
||
return jsonify({'success': False, 'error': 'Provider not found'}), 404
|
||
|
||
# 方式1: GET /models
|
||
try:
|
||
url = f"{provider['base_url'].rstrip('/')}/models"
|
||
headers = {"Authorization": f"Bearer {provider['api_key']}"}
|
||
|
||
response = requests.get(url, headers=headers, timeout=10)
|
||
|
||
if response.status_code == 200:
|
||
provider_status[provider['name']] = {
|
||
'available': True,
|
||
'last_check': datetime.now().isoformat(),
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
}
|
||
models_data = []
|
||
try:
|
||
resp_json = response.json()
|
||
models_data = resp_json.get('data', [])
|
||
except:
|
||
pass
|
||
|
||
return jsonify({'success': True, 'message': 'Connection successful', 'models_count': len(models_data)})
|
||
except Exception as e:
|
||
pass # 继续尝试聊天探测
|
||
|
||
# 方式2: 能力探测（用 default_model 发一条最小请求，按能力选择探测端点）
|
||
try:
|
||
default_model = provider.get('default_model') or ''
|
||
probe_model = default_model if default_model in provider_model_names(provider) else (provider_model_names(provider) or [''])[0]
|
||
if probe_model:
|
||
caps = model_capabilities(provider, probe_model)
|
||
if 'image_gen' in caps:
|
||
# 生图提供商：探测 /images/generations
|
||
url = f"{provider['base_url'].rstrip('/')}/images/generations"
|
||
headers = {"Authorization": f"Bearer {provider['api_key']}", "Content-Type": "application/json"}
|
||
payload = {"model": probe_model, "prompt": "a tiny red dot", "n": 1}
|
||
probe_name = 'image generation'
|
||
else:
|
||
url = f"{provider['base_url'].rstrip('/')}/chat/completions"
|
||
headers = {"Authorization": f"Bearer {provider['api_key']}", "Content-Type": "application/json"}
|
||
payload = {"model": probe_model, "messages": [{"role": "user", "content": "hi"}], "max_tokens": 1, "stream": False}
|
||
probe_name = 'chat'
|
||
resp = requests.post(url, headers=headers, json=payload, timeout=20)
|
||
if resp.status_code in (200, 201):
|
||
provider_status[provider['name']] = {
|
||
'available': True,
|
||
'last_check': datetime.now().isoformat(),
|
||
'error_count': 0,
|
||
'last_error': None,
|
||
}
|
||
return jsonify({'success': True, 'message': f'Connection successful ({probe_name} probe, model={probe_model})', 'models_count': None})
|
||
provider_status[provider['name']] = {
|
||
'available': False,
|
||
'last_check': datetime.now().isoformat(),
|
||
'error_count': provider_status.get(provider['name'], {}).get('error_count', 0) + 1,
|
||
'last_error': f'HTTP {resp.status_code}',
|
||
}
|
||
return jsonify({'success': False, 'error': f'HTTP {resp.status_code}: {resp.text[:200]}'})
|
||
except Exception as e:
|
||
provider_status[provider['name']] = {
|
||
'available': False,
|
||
'last_check': datetime.now().isoformat(),
|
||
'error_count': provider_status.get(provider['name'], {}).get('error_count', 0) + 1,
|
||
'last_error': str(e),
|
||
}
|
||
return jsonify({'success': False, 'error': str(e)})
|
||
|
||
provider_status[provider['name']] = {
|
||
'available': False,
|
||
'last_check': datetime.now().isoformat(),
|
||
'error_count': provider_status.get(provider['name'], {}).get('error_count', 0) + 1,
|
||
'last_error': 'Connection failed',
|
||
}
|
||
return jsonify({'success': False, 'error': 'Connection failed'})
|
||
|
||
|
||
# ============ 后台管理 API：模型管理 ============
|
||
|
||
@app.route('/api/admin/models')
|
||
def api_admin_models():
|
||
"""获取所有模型（按提供商分组，含能力）"""
|
||
providers = get_providers()
|
||
aliases = get_model_aliases()
|
||
|
||
result = []
|
||
for provider in sorted(providers, key=lambda x: x['priority']):
|
||
default_model = provider.get('default_model', '')
|
||
model_aliases = {}
|
||
for alias, target in aliases.items():
|
||
if alias == 'auto' or alias.startswith('auto-'):
|
||
continue
|
||
if target in provider_model_names(provider):
|
||
model_aliases.setdefault(target, []).append(alias)
|
||
for m in provider_models(provider):
|
||
result.append({
|
||
'name': m['name'],
|
||
'capabilities': m['capabilities'],
|
||
'provider_id': provider.get('id'),
|
||
'provider_name': provider['name'],
|
||
'provider_priority': provider['priority'],
|
||
'provider_enabled': provider.get('enabled', True),
|
||
'is_default': m['name'] == default_model,
|
||
'aliases': model_aliases.get(m['name'], []),
|
||
})
|
||
|
||
return jsonify(result)
|
||
|
||
|
||
@app.route('/api/admin/models', methods=['POST'])
|
||
def api_admin_add_model():
|
||
"""向提供商添加模型"""
|
||
data = request.get_json()
|
||
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
provider_id = data.get('provider_id')
|
||
name = (data.get('name') or '').strip()
|
||
if not provider_id or not name:
|
||
return jsonify({'error': 'provider_id and name are required'}), 400
|
||
|
||
provider = get_provider(provider_id)
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
caps = data.get('capabilities') or provider.get('capabilities', ['text'])
|
||
if isinstance(caps, str):
|
||
caps = [c.strip() for c in caps.split(',') if c.strip()]
|
||
|
||
if name in provider_model_names(provider):
|
||
return jsonify({'error': 'Model already exists in this provider'}), 400
|
||
|
||
models = provider.get('models', [])
|
||
models.append({'name': name, 'capabilities': list(caps)})
|
||
result = update_provider(provider_id, {'models': models})
|
||
|
||
return jsonify({'success': True, 'model': {'name': name, 'capabilities': list(caps)}})
|
||
|
||
|
||
@app.route('/api/admin/models/<provider_id>', methods=['PUT'])
|
||
def api_admin_update_model(provider_id):
|
||
"""更新模型（能力、名称）——模型名放 body，避免路径斜杠问题"""
|
||
data = request.get_json()
|
||
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
old_name = data.get('name') or data.get('old_name')
|
||
if not old_name:
|
||
return jsonify({'error': 'Model name is required'}), 400
|
||
|
||
provider = get_provider(provider_id)
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
models = provider.get('models', [])
|
||
found = False
|
||
for m in models:
|
||
mname = m['name'] if isinstance(m, dict) else m
|
||
if mname == old_name:
|
||
found = True
|
||
if 'new_name' in data and data['new_name']:
|
||
m['name'] = data['new_name']
|
||
if 'capabilities' in data:
|
||
caps = data['capabilities']
|
||
if isinstance(caps, str):
|
||
caps = [c.strip() for c in caps.split(',') if c.strip()]
|
||
m['capabilities'] = list(caps)
|
||
break
|
||
|
||
if not found:
|
||
return jsonify({'error': 'Model not found'}), 404
|
||
|
||
# 同步 default_model
|
||
if provider.get('default_model') == old_name and 'new_name' in data and data['new_name']:
|
||
provider['default_model'] = data['new_name']
|
||
|
||
result = update_provider(provider_id, {'models': models, 'default_model': provider.get('default_model', '')})
|
||
return jsonify({'success': True, 'provider': _provider_public(result)})
|
||
|
||
|
||
@app.route('/api/admin/models/<provider_id>', methods=['DELETE'])
|
||
def api_admin_delete_model(provider_id):
|
||
"""删除模型——模型名放 query，避免路径斜杠问题"""
|
||
name = request.args.get('name', '')
|
||
if not name:
|
||
return jsonify({'error': 'Model name is required (query param name=)'}), 400
|
||
|
||
provider = get_provider(provider_id)
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
models = [m for m in provider.get('models', []) if (m['name'] if isinstance(m, dict) else m) != name]
|
||
|
||
update_data = {'models': models}
|
||
if provider.get('default_model') == name:
|
||
names = [m['name'] for m in provider_models({'models': models, 'capabilities': provider.get('capabilities', ['text'])})]
|
||
update_data['default_model'] = names[0] if names else ''
|
||
update_provider(provider_id, update_data)
|
||
|
||
return jsonify({'success': True})
|
||
|
||
|
||
@app.route('/api/admin/models/<provider_id>/default', methods=['POST'])
|
||
def api_admin_set_default_model(provider_id):
|
||
"""设置默认模型"""
|
||
data = request.get_json() or {}
|
||
name = data.get('name', '')
|
||
if not name:
|
||
return jsonify({'error': 'Model name is required'}), 400
|
||
|
||
provider = get_provider(provider_id)
|
||
if not provider:
|
||
return jsonify({'error': 'Provider not found'}), 404
|
||
|
||
if name not in provider_model_names(provider):
|
||
return jsonify({'error': 'Model not found in provider'}), 404
|
||
|
||
result = update_provider(provider_id, {'default_model': name})
|
||
return jsonify({'success': True, 'default_model': name})
|
||
|
||
|
||
# ============ 后台管理 API：模型别名 ============
|
||
|
||
@app.route('/api/admin/aliases')
|
||
def api_admin_aliases():
|
||
"""获取模型别名"""
|
||
return jsonify(get_model_aliases())
|
||
|
||
|
||
@app.route('/api/admin/aliases', methods=['POST'])
|
||
def api_admin_add_alias():
|
||
"""添加/更新模型别名"""
|
||
data = request.get_json()
|
||
|
||
if not data or not data.get('alias') or not data.get('target'):
|
||
return jsonify({'error': 'alias and target are required'}), 400
|
||
|
||
alias = data['alias'].strip()
|
||
target = data['target'].strip()
|
||
|
||
if alias != 'auto' and alias.startswith('auto-'):
|
||
return jsonify({'error': 'auto- 前缀保留给Auto配置'}), 400
|
||
|
||
result = update_model_alias(alias, target)
|
||
return jsonify({'success': True, 'aliases': result})
|
||
|
||
|
||
@app.route('/api/admin/aliases/<alias>', methods=['DELETE'])
|
||
def api_admin_delete_alias(alias):
|
||
"""删除模型别名"""
|
||
result = delete_model_alias(alias)
|
||
if not result:
|
||
return jsonify({'error': 'Cannot delete alias or alias not found'}), 400
|
||
return jsonify({'success': True})
|
||
|
||
|
||
# ============ 后台管理 API：Auto配置 ============
|
||
|
||
def _auto_profile_public(name, profile):
|
||
"""Auto配置对外结构（含能力、有序模型列表与可挑选模型详情）"""
|
||
providers = get_providers()
|
||
allowed_providers = profile.get('providers', ['*'])
|
||
capability = profile.get('capability', 'text')
|
||
ordered_models = profile.get('models') or []
|
||
|
||
# 收集所有具备该能力、且在候选提供商范围内的模型（供编辑器挑选）
|
||
matched = []
|
||
seen = set()
|
||
for p in sorted(providers, key=lambda x: x['priority']):
|
||
if not ('*' in allowed_providers or p.get('id') in allowed_providers or p['name'] in allowed_providers):
|
||
continue
|
||
for m in provider_models(p):
|
||
if model_has_capability(p, m['name'], capability) and m['name'] not in seen:
|
||
seen.add(m['name'])
|
||
matched.append({
|
||
'name': m['name'],
|
||
'provider_id': p.get('id'),
|
||
'provider_name': p['name'],
|
||
'provider_priority': p['priority'],
|
||
'capabilities': m['capabilities'],
|
||
})
|
||
|
||
# 已保存的有序模型排前面，其余可挑选模型按提供商优先级追加
|
||
by_name = {x['name']: x for x in matched}
|
||
sorted_matched = []
|
||
for mname in ordered_models:
|
||
if mname in by_name:
|
||
sorted_matched.append(by_name[mname])
|
||
for x in matched:
|
||
if x['name'] not in ordered_models:
|
||
sorted_matched.append(x)
|
||
|
||
return {
|
||
'name': name,
|
||
'display_name': profile.get('name', name),
|
||
'description': profile.get('description', ''),
|
||
'capability': capability,
|
||
'capability_label': CAPABILITY_DEFS.get(capability, capability),
|
||
'strategy': profile.get('strategy', 'priority'),
|
||
'providers': allowed_providers,
|
||
'models': ordered_models, # 有序的具体模型列表（优先级顺序）
|
||
'matched_models': [x['name'] for x in matched],
|
||
'matched_models_detail': sorted_matched, # 每个模型的提供商详情（编辑器用）
|
||
}
|
||
|
||
|
||
@app.route('/api/admin/auto-profiles')
|
||
def api_admin_auto_profiles():
|
||
"""获取所有Auto配置"""
|
||
profiles = get_auto_profiles()
|
||
result = [_auto_profile_public(name, profile) for name, profile in profiles.items()]
|
||
return jsonify(result)
|
||
|
||
|
||
@app.route('/api/admin/auto-profiles/<profile_name>', methods=['GET'])
|
||
def api_admin_auto_profile_detail(profile_name):
|
||
"""获取单个Auto配置详情"""
|
||
profile = get_auto_profile(profile_name)
|
||
|
||
if not profile:
|
||
return jsonify({'error': 'Profile not found'}), 404
|
||
|
||
return jsonify(_auto_profile_public(profile_name, profile))
|
||
|
||
|
||
@app.route('/api/admin/auto-profiles', methods=['POST'])
|
||
def api_admin_add_auto_profile():
|
||
"""添加新的Auto配置"""
|
||
data = request.get_json()
|
||
|
||
if not data or not data.get('name'):
|
||
return jsonify({'error': 'Missing profile name'}), 400
|
||
|
||
profile_name = data['name'].lower().replace(' ', '-').replace('.', '-')
|
||
|
||
if profile_name in get_auto_profiles():
|
||
return jsonify({'error': 'Profile already exists'}), 400
|
||
|
||
capability = data.get('capability', 'text')
|
||
if capability not in CAPABILITY_DEFS:
|
||
return jsonify({'error': f'Invalid capability: {capability}. Valid: {list(CAPABILITY_DEFS.keys())}'}), 400
|
||
|
||
profile_data = {
|
||
'name': data.get('display_name', data['name']),
|
||
'description': data.get('description', ''),
|
||
'capability': capability,
|
||
'models': data.get('models', []), # 有序的具体模型列表（优先级顺序）
|
||
'providers': data.get('providers', ['*']),
|
||
'strategy': data.get('strategy', 'priority'),
|
||
}
|
||
|
||
result = add_auto_profile(profile_name, profile_data)
|
||
|
||
return jsonify({'success': True, 'profile': _auto_profile_public(profile_name, profile_data)})
|
||
|
||
|
||
@app.route('/api/admin/auto-profiles/<profile_name>', methods=['PUT'])
|
||
def api_admin_update_auto_profile(profile_name):
|
||
"""更新Auto配置"""
|
||
data = request.get_json()
|
||
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
profile_data = {}
|
||
if 'display_name' in data:
|
||
profile_data['name'] = data['display_name']
|
||
if 'description' in data:
|
||
profile_data['description'] = data['description']
|
||
if 'capability' in data:
|
||
if data['capability'] not in CAPABILITY_DEFS:
|
||
return jsonify({'error': f'Invalid capability: {data["capability"]}'}), 400
|
||
profile_data['capability'] = data['capability']
|
||
if 'models' in data:
|
||
profile_data['models'] = data['models']
|
||
if 'providers' in data:
|
||
profile_data['providers'] = data['providers']
|
||
if 'strategy' in data:
|
||
profile_data['strategy'] = data['strategy']
|
||
|
||
result = update_auto_profile(profile_name, profile_data)
|
||
|
||
if not result:
|
||
return jsonify({'error': 'Profile not found'}), 404
|
||
|
||
return jsonify({'success': True, 'profile': _auto_profile_public(profile_name, result)})
|
||
|
||
|
||
@app.route('/api/admin/auto-profiles/<profile_name>', methods=['DELETE'])
|
||
def api_admin_delete_auto_profile(profile_name):
|
||
"""删除Auto配置"""
|
||
result = delete_auto_profile(profile_name)
|
||
|
||
if not result:
|
||
return jsonify({'error': 'Cannot delete default auto profile or profile not found'}), 400
|
||
|
||
return jsonify({'success': True})
|
||
|
||
|
||
# ============ 后台管理 API：日志/配置 ============
|
||
|
||
@app.route('/api/admin/logs')
|
||
def api_admin_logs():
|
||
"""获取日志"""
|
||
log_file = LOGS_DIR / 'proxy.log'
|
||
|
||
lines = []
|
||
if log_file.exists():
|
||
content = log_file.read_text(encoding='utf-8')
|
||
lines = content.strip().split('\n')[-200:]
|
||
|
||
return jsonify({'logs': lines, 'total_lines': len(lines)})
|
||
|
||
|
||
@app.route('/api/admin/config')
|
||
def api_admin_config():
|
||
"""获取配置"""
|
||
providers = get_providers()
|
||
aliases = get_model_aliases()
|
||
|
||
return jsonify({
|
||
'providers': [{
|
||
'id': p.get('id', p['name'].lower().replace(' ', '-')),
|
||
'name': p['name'],
|
||
'priority': p['priority'],
|
||
'base_url': p['base_url'],
|
||
'capabilities': p.get('capabilities', ['text']),
|
||
'models': [{'name': m['name'], 'capabilities': m['capabilities']} for m in provider_models(p)],
|
||
'default_model': p.get('default_model', ''),
|
||
'timeout': p.get('timeout', 120),
|
||
'enabled': p['enabled'],
|
||
} for p in providers],
|
||
'model_aliases': aliases,
|
||
'auto_profiles': get_auto_profiles(),
|
||
'retry_config': RETRY_CONFIG,
|
||
'routing_config': load_routing_config(),
|
||
'capabilities': CAPABILITY_DEFS,
|
||
'server_config': {'port': SERVER_CONFIG['port']}
|
||
})
|
||
|
||
|
||
@app.route('/api/admin/routing', methods=['GET'])
|
||
def api_admin_routing_get():
|
||
"""获取路由缓存配置"""
|
||
return jsonify(load_routing_config())
|
||
|
||
|
||
@app.route('/api/admin/routing', methods=['PUT'])
|
||
def api_admin_routing_put():
|
||
"""更新路由缓存配置"""
|
||
data = request.get_json()
|
||
if not data:
|
||
return jsonify({'error': 'Invalid request body'}), 400
|
||
|
||
update = {}
|
||
if 'prefer_cache_model' in data:
|
||
update['prefer_cache_model'] = bool(data['prefer_cache_model'])
|
||
if 'cache_ttl_seconds' in data:
|
||
try:
|
||
update['cache_ttl_seconds'] = max(0, int(data['cache_ttl_seconds']))
|
||
except:
|
||
pass
|
||
|
||
if not update:
|
||
return jsonify({'error': 'No valid fields'}), 400
|
||
|
||
result = save_routing_config(update)
|
||
return jsonify({'success': True, 'routing_config': result})
|
||
|
||
|
||
# ============ 后台管理 API：对话 ============
|
||
|
||
def load_chats():
|
||
"""加载对话数据"""
|
||
if CHATS_FILE.exists():
|
||
try:
|
||
return json.loads(CHATS_FILE.read_text(encoding='utf-8'))
|
||
except:
|
||
pass
|
||
return {'chats': []}
|
||
|
||
|
||
def save_chats(data):
|
||
"""保存对话数据"""
|
||
CHATS_FILE.write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding='utf-8')
|
||
|
||
|
||
@app.route('/api/admin/chat/models')
|
||
def api_admin_chat_models():
|
||
"""获取可用模型列表（含auto配置，标注能力）"""
|
||
providers = get_providers()
|
||
profiles = get_auto_profiles()
|
||
|
||
models = []
|
||
added = set()
|
||
|
||
for name, profile in profiles.items():
|
||
if name not in added:
|
||
cap = profile.get('capability', 'text')
|
||
models.append({'id': name, 'description': f"[{CAPABILITY_DEFS.get(cap, cap)}] {profile.get('description', 'Auto-select')}"})
|
||
added.add(name)
|
||
|
||
for provider in providers:
|
||
if not provider['enabled']:
|
||
continue
|
||
for m in provider_models(provider):
|
||
if m['name'] not in added:
|
||
caps = ','.join(CAPABILITY_DEFS.get(c, c) for c in m['capabilities'])
|
||
models.append({'id': m['name'], 'description': f"{provider['name']} ({caps})"})
|
||
added.add(m['name'])
|
||
|
||
return jsonify(models)
|
||
|
||
|
||
@app.route('/api/admin/chat/list')
|
||
def api_admin_chat_list():
|
||
"""获取对话列表"""
|
||
data = load_chats()
|
||
|
||
chats = []
|
||
for chat in data.get('chats', []):
|
||
chats.append({
|
||
'id': chat['id'],
|
||
'title': chat.get('title', '新对话'),
|
||
'model': chat.get('model', 'auto'),
|
||
'message_count': len(chat.get('messages', [])),
|
||
'created_at': chat.get('created_at'),
|
||
'updated_at': chat.get('updated_at')
|
||
})
|
||
|
||
chats.sort(key=lambda x: x.get('updated_at', ''), reverse=True)
|
||
|
||
return jsonify(chats)
|
||
|
||
|
||
@app.route('/api/admin/chat/<chat_id>')
|
||
def api_admin_chat_detail(chat_id):
|
||
"""获取对话详情"""
|
||
data = load_chats()
|
||
|
||
for chat in data.get('chats', []):
|
||
if chat['id'] == chat_id:
|
||
return jsonify(chat)
|
||
|
||
return jsonify({'error': 'Chat not found'}), 404
|
||
|
||
|
||
@app.route('/api/admin/chat/send', methods=['POST'])
|
||
def api_admin_chat_send():
|
||
"""发送消息"""
|
||
req = request.get_json()
|
||
|
||
user_message = req.get('message', '')
|
||
model = req.get('model', 'auto')
|
||
chat_id = req.get('chat_id')
|
||
|
||
if not user_message:
|
||
return jsonify({'error': 'Message is required'}), 400
|
||
|
||
with chats_lock:
|
||
data = load_chats()
|
||
|
||
chat = None
|
||
if chat_id:
|
||
for c in data['chats']:
|
||
if c['id'] == chat_id:
|
||
chat = c
|
||
break
|
||
|
||
if not chat:
|
||
chat_id = str(uuid.uuid4())[:8]
|
||
chat = {
|
||
'id': chat_id,
|
||
'title': '新对话',
|
||
'model': model,
|
||
'messages': [],
|
||
'created_at': datetime.now().isoformat(),
|
||
'updated_at': datetime.now().isoformat()
|
||
}
|
||
data['chats'].append(chat)
|
||
|
||
# 先保存用户消息，避免上游失败时丢数据
|
||
chat['messages'].append({
|
||
'role': 'user',
|
||
'content': user_message,
|
||
'time': datetime.now().isoformat()
|
||
})
|
||
save_chats(data)
|
||
|
||
try:
|
||
proxy_url = f"http://localhost:{SERVER_CONFIG['port']}/v1/chat/completions"
|
||
|
||
# 图片生成模型（auto-image / Qwen-Image）→ 走生图接口
|
||
if is_image_gen_request(model):
|
||
img_resp = requests.post(f"http://localhost:{SERVER_CONFIG['port']}/v1/images/generations", json={
|
||
'model': model,
|
||
'prompt': user_message,
|
||
'n': 1,
|
||
}, timeout=180)
|
||
|
||
if img_resp.status_code == 200:
|
||
img_result = img_resp.json()
|
||
img_url = None
|
||
img_b64 = None
|
||
if img_result.get('data') and len(img_result['data']) > 0:
|
||
img_url = img_result['data'][0].get('url')
|
||
img_b64 = img_result['data'][0].get('b64_json')
|
||
used_model = img_result.get('model', model)
|
||
|
||
with chats_lock:
|
||
data = load_chats()
|
||
for c in data['chats']:
|
||
if c['id'] == chat_id:
|
||
c['messages'].append({
|
||
'role': 'assistant',
|
||
'content': '🖼️ 图片生成成功',
|
||
'image_url': img_url,
|
||
'image_b64': img_b64,
|
||
'model': used_model,
|
||
'time': datetime.now().isoformat()
|
||
})
|
||
if len(c['messages']) == 2:
|
||
c['title'] = user_message[:30] + ('...' if len(user_message) > 30 else '')
|
||
c['updated_at'] = datetime.now().isoformat()
|
||
break
|
||
save_chats(data)
|
||
|
||
return jsonify({
|
||
'success': True,
|
||
'chat_id': chat_id,
|
||
'response': '🖼️ 图片生成成功',
|
||
'model': used_model,
|
||
'image_url': img_url,
|
||
'image_b64': img_b64,
|
||
'title': chat.get('title', '新对话')
|
||
})
|
||
else:
|
||
try:
|
||
error_msg = img_resp.json().get('error', {}).get('message', 'Unknown error')
|
||
except:
|
||
error_msg = f'HTTP {img_resp.status_code}'
|
||
return jsonify({'error': error_msg}), img_resp.status_code
|
||
|
||
messages = []
|
||
for msg in chat['messages'][-20:]:
|
||
messages.append({'role': msg['role'], 'content': msg['content']})
|
||
|
||
response = requests.post(proxy_url, json={
|
||
'model': model,
|
||
'messages': messages,
|
||
'stream': False
|
||
}, timeout=180)
|
||
|
||
if response.status_code == 200:
|
||
result = response.json()
|
||
assistant_message = result['choices'][0]['message']['content']
|
||
used_model = result.get('model', model)
|
||
|
||
with chats_lock:
|
||
data = load_chats()
|
||
for c in data['chats']:
|
||
if c['id'] == chat_id:
|
||
c['messages'].append({
|
||
'role': 'assistant',
|
||
'content': assistant_message,
|
||
'model': used_model,
|
||
'time': datetime.now().isoformat()
|
||
})
|
||
if len(c['messages']) == 2:
|
||
c['title'] = user_message[:30] + ('...' if len(user_message) > 30 else '')
|
||
c['updated_at'] = datetime.now().isoformat()
|
||
break
|
||
save_chats(data)
|
||
|
||
return jsonify({
|
||
'success': True,
|
||
'chat_id': chat_id,
|
||
'response': assistant_message,
|
||
'model': used_model,
|
||
'title': chat.get('title', '新对话')
|
||
})
|
||
else:
|
||
try:
|
||
error_msg = response.json().get('error', {}).get('message', 'Unknown error')
|
||
except:
|
||
error_msg = f'HTTP {response.status_code}'
|
||
return jsonify({'error': error_msg}), response.status_code
|
||
|
||
except Exception as e:
|
||
return jsonify({'error': str(e)}), 500
|
||
|
||
|
||
@app.route('/api/admin/chat/<chat_id>', methods=['DELETE'])
|
||
def api_admin_delete_chat(chat_id):
|
||
"""删除对话"""
|
||
with chats_lock:
|
||
data = load_chats()
|
||
data['chats'] = [c for c in data['chats'] if c['id'] != chat_id]
|
||
save_chats(data)
|
||
return jsonify({'success': True})
|
||
|
||
|
||
@app.route('/api/admin/chat/<chat_id>/clear', methods=['POST'])
|
||
def api_admin_clear_chat(chat_id):
|
||
"""清空对话消息"""
|
||
with chats_lock:
|
||
data = load_chats()
|
||
|
||
for chat in data['chats']:
|
||
if chat['id'] == chat_id:
|
||
chat['messages'] = []
|
||
chat['updated_at'] = datetime.now().isoformat()
|
||
save_chats(data)
|
||
return jsonify({'success': True})
|
||
|
||
return jsonify({'error': 'Chat not found'}), 404
|
||
|
||
|
||
if __name__ == '__main__':
|
||
refresh_config()
|
||
|
||
print("=" * 60)
|
||
print(f"大模型API中转系统 v{VERSION}")
|
||
print("=" * 60)
|
||
print(f"API地址: http://localhost:{SERVER_CONFIG['port']}")
|
||
print(f"后台管理: http://localhost:{SERVER_CONFIG['port']}/admin")
|
||
print("=" * 60)
|
||
print("上游提供商:")
|
||
for p in sorted(_cached_providers, key=lambda x: x['priority']):
|
||
caps = ','.join(CAPABILITY_DEFS.get(c, c) for c in p.get('capabilities', ['text']))
|
||
print(f" [{p['priority']}] {p['name']}: {p['base_url']} ({caps})")
|
||
for m in provider_models(p):
|
||
mcaps = ','.join(CAPABILITY_DEFS.get(c, c) for c in m['capabilities'])
|
||
marker = " [默认]" if m['name'] == p.get('default_model') else ""
|
||
print(f" - {m['name']} ({mcaps}){marker}")
|
||
print("=" * 60)
|
||
|
||
app.run(
|
||
host=SERVER_CONFIG['host'],
|
||
port=SERVER_CONFIG['port'],
|
||
debug=SERVER_CONFIG['debug'],
|
||
threaded=True
|
||
)
|