ai-app/server/src/main.rs

mod auth;
mod config;
mod files;
mod media;
mod models;
mod resume;
mod routes;
mod session;
mod setups;
mod ssh;
mod usage;

use std::net::{IpAddr, SocketAddr};
use std::path::PathBuf;
use std::sync::Arc;
use std::time::Duration;

use anyhow::{Context, Result};
use axum::middleware::Next;
use clap::Parser;
use tokio::signal::unix::{SignalKind, signal};

use wg_app_link::enroll;
use wg_app_link::netif::{self, WG_INTERFACE};
use wg_app_link::xdg::{config_home, data_home};

use config::TokenEntry;
use session::SessionManager;

const DEFAULT_PORT: u16 = 8443;

#[derive(Parser)]
struct Args {
    #[arg(long, default_value_t = DEFAULT_PORT)]
    port: u16,

    #[arg(long)]
    bind: Option<IpAddr>,

    #[arg(long)]
    config: Option<PathBuf>,

    #[arg(long)]
    data_dir: Option<PathBuf>,

    #[arg(long)]
    models_dir: Option<PathBuf>,

    #[arg(long)]
    certs: Option<PathBuf>,

    #[arg(long)]
    rotate_token: bool,

    #[arg(long)]
    enroll_link: bool,

    #[arg(long, default_value_t = 0, value_name = "MS")]
    delay: u64,

    #[arg(
        long,
        default_value_t = cfg!(debug_assertions),
        action = clap::ArgAction::Set,
        num_args = 0..=1,
        default_missing_value = "true",
        value_name = "BOOL",
    )]
    throwaway_sessions: bool,
}

/// Where this run keeps its certificates: `--certs`, else the XDG default.
/// One reader because `--enroll-link` returns before the rest of startup
/// gets there, and a link minted against a different directory's CA than
/// the server presents is a handshake failure with nothing on screen
/// saying why.
fn certs_dir(certs: &Option<std::path::PathBuf>) -> std::path::PathBuf {
    certs
        .clone()
        .unwrap_or_else(|| config_home("ai-app").join("certs"))
}

fn read_ca(certs_dir: &std::path::Path) -> Result<String> {
    let path = certs_dir.join("ca.pem");
    std::fs::read_to_string(&path).with_context(|| {
        format!(
            "no CA certificate at {} -- start ai-server once so it generates one, \
             or point --certs at the directory that has it",
            path.display()
        )
    })
}

#[tokio::main]
async fn main() -> Result<()> {
    rustls::crypto::aws_lc_rs::default_provider()
        .install_default()
        .expect("no other TLS crypto provider is installed before main");

    // `info` unless RUST_LOG says otherwise. Written as a *fallback* rather than
    // as the filter, because `with_env_filter("info")` is a fixed directive that
    // never reads the environment -- so `RUST_LOG=ai_server=debug` printed
    // nothing, and the switch looked like the code it was meant to instrument.
    tracing_subscriber::fmt()
        .with_env_filter(
            tracing_subscriber::EnvFilter::try_from_default_env()
                .unwrap_or_else(|_| tracing_subscriber::EnvFilter::new("info")),
        )
        .init();
    let args = Args::parse();

    let config_path = args
        .config
        .unwrap_or_else(|| config_home("ai-app").join("config.ron"));
    if args.enroll_link {
        let bind_ip = match args.bind {
            Some(ip) => ip,
            None => netif::wg_address("ai-server")?,
        };
        let token = enroll::generate_token();
        enroll::spool_pending(
            &config::pending_enrollments_dir(&config_path),
            "phone",
            &token,
        )?;
        println!(
            "{}",
            enroll::enrollment_uri(
                "aiapp",
                bind_ip,
                args.port,
                &token,
                Some(&read_ca(&certs_dir(&args.certs))?)
            )?
        );
        return Ok(());
    }
    let data_dir = args
        .data_dir
        .unwrap_or_else(|| data_home("ai-app").join("sessions"));
    // Beside the session data rather than under it: models outlive every session
    // and are shared by all of them, so deleting a session must never take a
    // multi-gigabyte download with it.
    let models_dir = args
        .models_dir
        .unwrap_or_else(|| data_home("ai-app").join("models"));
    let models = Arc::new(models::ModelStore::new(models_dir.clone()));
    let manager = Arc::new(
        SessionManager::new(config_path.clone(), data_dir, models_dir.clone())
            .with_context(|| format!("failed to load {}", config_path.display()))?
            .marking_new_sessions_throwaway(args.throwaway_sessions),
    );
    if args.throwaway_sessions {
        tracing::warn!(
            "sessions spawned here are marked throwaway -- their processes are stopped when this \
             server exits rather than left running (--throwaway-sessions=false to keep them)"
        );
    }
    // After construction rather than inside it: seeding asks this machine what
    // it has, and a constructor that quietly runs a subprocess is a surprise to
    // every caller including the tests.
    manager.seed_setup().await?;

    tracing::info!("config: {}", config_path.display());
    tracing::info!("models: {}", models_dir.display());
    for setup in manager.setups() {
        match &setup.ssh {
            Some(ssh) => tracing::info!("  setup \"{}\" -> {}", setup.name, ssh.address),
            None => tracing::info!("  setup \"{}\" runs here", setup.name),
        }
        for provider in &setup.providers {
            tracing::info!("    provider {} ({:?})", provider.name, provider.kind);
        }
    }
    for info in manager.sessions() {
        tracing::info!(
            "  session {} ({}, {:?})",
            info.id,
            info.provider,
            info.status
        );
    }

    let certs_dir = certs_dir(&args.certs);
    let certificates = wg_app_link::certs::ensure("ai-app", &certs_dir, &netif::local_addresses())
        .with_context(|| format!("failed to prepare certificates in {}", certs_dir.display()))?;
    if certificates.ca_is_new {
        tracing::warn!(
            "a new CA was generated in {} -- existing enrollments pin the previous one and can no \
             longer reach this server. Enroll each client again with a newly minted link.",
            certs_dir.display(),
        );
    }

    let bind_ip = match args.bind {
        Some(ip) => {
            tracing::warn!(
                "binding {ip} by explicit --bind override -- production binds {WG_INTERFACE} only"
            );
            ip
        }
        None => netif::wg_address("ai-server")?,
    };

    if args.rotate_token || manager.tokens().is_empty() {
        let rotating = args.rotate_token && !manager.tokens().is_empty();
        let token = enroll::generate_token();
        manager.set_tokens(vec![TokenEntry {
            name: "phone".to_string(),
            sha256: enroll::token_hash_hex(&token),
        }])?;
        if rotating {
            tracing::info!("rotated the enrolled token; the previous one is now invalid");
        }
        enroll::print_enrollment(
            "aiapp",
            bind_ip,
            args.port,
            &token,
            Some(&read_ca(&certs_dir)?),
        )?;
    }

    let tls_config = axum_server::tls_rustls::RustlsConfig::from_pem_file(
        &certificates.leaf_cert,
        &certificates.leaf_key,
    )
    .await
    .context("failed to load TLS cert/key")?;

    // No providers listed here any more: which machines can be asked, and about
    // what, comes from the setups at the moment the screen is opened -- so a
    // machine added from the phone reports its limits without a restart.
    // The fixture is the manager's, because that is where the `/usage` command
    // that sets it is typed; the monitor is what serves it.
    let monitor = Arc::new(usage::UsageMonitor::new(manager.usage_fixture()));

    tokio::spawn(resume::run(Arc::clone(&manager), Arc::clone(&monitor)));

    let app = routes::router(Arc::clone(&manager))
        .merge(routes::usage_router(monitor, Arc::clone(&manager)))
        .merge(routes::models_router(Arc::clone(&models)))
        .layer(axum::middleware::from_fn_with_state(
            Arc::clone(&manager),
            auth::require_token,
        ));

    let app = match args.delay {
        0 => app,
        ms => {
            tracing::warn!("delaying every response by {ms}ms -- development override");
            app.layer(axum::middleware::from_fn(
                move |request, next: Next| async move {
                    tokio::time::sleep(Duration::from_millis(ms)).await;
                    next.run(request).await
                },
            ))
        }
    };

    let addr = SocketAddr::new(bind_ip, args.port);
    tracing::info!("serving https://{addr}");

    let serving = axum_server::bind_rustls(addr, tls_config)
        .serve(app.into_make_service_with_connect_info::<SocketAddr>());
    let mut terminate = signal(SignalKind::terminate()).context("listening for SIGTERM")?;
    tokio::select! {
        served = serving => served.context("TLS listener failed")?,
        _ = terminate.recv() => tracing::info!("SIGTERM -- letting go of sessions"),
        _ = tokio::signal::ctrl_c() => tracing::info!("interrupted -- letting go of sessions"),
    }
    manager.stop_throwaway_sessions();
    manager.detach_all();

    Ok(())
}