upstream llama_backend {
    least_conn;
    server 127.0.0.1:9000 max_fails=3 fail_timeout=30s;
    server 127.0.0.1:9001 max_fails=3 fail_timeout=30s;
    server 127.0.0.1:9002 max_fails=3 fail_timeout=30s;
    server 127.0.0.1:9003 max_fails=3 fail_timeout=30s;
}

server {
    listen 8090;
    server_name _;
    
    client_max_body_size 512M;
    
    location / {
        proxy_pass http://llama_backend;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection "upgrade";
        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;
        proxy_buffering off;
        proxy_request_buffering off;
        proxy_read_timeout 600s;
        proxy_connect_timeout 30s;
    }
    
    location /health {
        access_log off;
        return 200 "healthy\n";
        add_header Content-Type text/plain;
    }
}