# 语料采集系统 · Corpus Agent
# Nginx路由配置 —— 添加到 guanghulab-cvm.conf

# 语料采集服务 (Corpus-Agent)
# 内网地址: 127.0.0.1:8084 → 对外路径: /corpus/
# 需要替换 YOUR_CORPUS_TOKEN 为实际值

# 方案A：有独立域名的子路径
# location /corpus/ {
#     proxy_pass http://127.0.0.1:8084/;
#     proxy_set_header Host $host;
#     proxy_set_header X-Real-IP $remote_addr;
#     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
#     proxy_set_header X-Forwarded-Proto $scheme;
#     
#     # WebSocket支持（Mac客户端实时采集用）
#     proxy_http_version 1.1;
#     proxy_set_header Upgrade $http_upgrade;
#     proxy_set_header Connection "upgrade";
#     proxy_read_timeout 86400;
# }

# 方案B：直接绑定到 guanghulab.com/corpus
# 将以下代码插入到 /workspace/guanghulab/server/nginx/guanghulab-cvm.conf

"""
server {
    listen 443 ssl;
    server_name guanghulab.com;
    
    # ... 已有配置 ...
    
    # === 语料采集服务 ===
    location /corpus/ {
        proxy_pass http://127.0.0.1:8084/;
        proxy_set_header Host $host;
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
        
        # WebSocket
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        proxy_read_timeout 86400s;
        proxy_send_timeout 86400s;
    }
}
"""

# 部署步骤：
# 1. 将 corpus-agent 目录上传到服务器
# 2. 安装依赖: pip install -r requirements.txt
# 3. 配置 systemd 或 pm2 开机自启
# 4. 添加 nginx 路由
# 5. 重启 nginx

# PM2启动命令：
# pm2 start "cd /path/to/corpus-agent && python3 server.py" --name corpus-agent

# Systemd Service:
"""
[Unit]
Description=Corpus Agent Service
After=network.target

[Service]
Type=simple
User=root
WorkingDirectory=/path/to/corpus-agent
Environment=CORPUS_HOST=0.0.0.0
Environment=CORPUS_PORT=8084
Environment=CORPUS_DATA_DIR=/data/corpus
ExecStart=/usr/bin/python3 /path/to/corpus-agent/server.py
Restart=always
RestartSec=5

[Install]
WantedBy=multi-user.target
"""