# chat.lan - HTTPS reverse proxy to LLeMbas (127.0.0.1:8080).
# Deployed to /etc/nginx/conf.d/chat.lan.conf. Self-signed cert (chat.lan).
#
# Mirrors the comfy.lan and llama.lan vhosts on this box.

server {
    listen 80;
    listen [::]:80;
    server_name chat.lan;
    return 301 https://$host$request_uri;
}

server {
    listen 443 ssl;
    listen [::]:443 ssl;
    http2 on;
    server_name chat.lan;

    ssl_certificate     /etc/nginx/ssl/chat.lan.crt;
    ssl_certificate_key /etc/nginx/ssl/chat.lan.key;
    ssl_protocols       TLSv1.2 TLSv1.3;

    # File uploads land here once that feature exists; 0 = no limit.
    client_max_body_size 0;

    location / {
        proxy_pass http://127.0.0.1:8080;
        proxy_http_version 1.1;
        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;

        # Streamed replies are server-sent events. Every one of these matters:
        # with buffering on, nginx holds the whole reply and delivers it in one
        # lump at the end, which looks exactly like streaming being broken.
        proxy_buffering         off;
        proxy_request_buffering off;
        proxy_cache             off;
        # SSE is plain HTTP/1.1 chunked, so the connection header must not be
        # the websocket upgrade dance -- it must simply stay open.
        proxy_set_header Connection "";

        # A model can think for minutes before the first token. The default
        # 60s read timeout would cut long generations off mid-sentence.
        proxy_read_timeout 3600s;
        proxy_send_timeout 3600s;
    }

    # Static assets are immutable per release and never need revalidating.
    location /static/ {
        proxy_pass http://127.0.0.1:8080;
        proxy_set_header Host $host;
        expires 1h;
        add_header Cache-Control "public";
    }
}