ai-app/server/src/main.rs

//! A phone interface to AI coding sessions -- the backend. See PLAN.md for
//! the whole picture; this is the entry point: config + session registry,
//! token bootstrap, and the one TLS listener.
//!
//! The listener binds the WireGuard interface's address only, and fails
//! closed -- if `wg0` is down the server refuses to start rather than
//! falling back to `0.0.0.0`, because this API *is* remote code execution
//! and the tunnel is what keeps its pre-auth surface (TLS handshake, HTTP
//! parsing, auth middleware) off the open internet. `--bind` overrides
//! explicitly for development; that is a deliberate, logged choice, never a
//! fallback.
//!
//! There is no plaintext listener at all, so the bearer token can't travel
//! unencrypted by misconfiguration -- even inside the tunnel.

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

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

use anyhow::{Context, Result};
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;

/// Serves AI coding sessions (Claude Code, llama.cpp) to the phone app.
#[derive(Parser)]
struct Args {
    /// TLS port for the whole API surface.
    #[arg(long, default_value_t = DEFAULT_PORT)]
    port: u16,

    /// Address to bind instead of the wg0 interface's -- a development
    /// override (e.g. 127.0.0.1 for curl, or a LAN address for a phone
    /// before the tunnel exists). Production runs without it and fails
    /// closed when wg0 is absent.
    #[arg(long)]
    bind: Option<IpAddr>,

    /// Where the token hashes, providers, hosts, and session list live.
    /// Defaults to `$XDG_CONFIG_HOME/ai-app/config.ron`.
    #[arg(long)]
    config: Option<PathBuf>,

    /// Directory for per-session data (transcripts, attachments, images).
    /// Defaults to `$XDG_DATA_HOME/ai-app/sessions`.
    #[arg(long)]
    data_dir: Option<PathBuf>,

    /// Directory for downloaded GGUF models. Defaults to
    /// `$XDG_DATA_HOME/ai-app/models`.
    #[arg(long)]
    models_dir: Option<PathBuf>,

    /// Directory holding the TLS certificates, generated here on first
    /// start. Defaults to `$XDG_CONFIG_HOME/ai-app/certs`.
    #[arg(long)]
    certs: Option<PathBuf>,

    /// Invalidate every enrolled token, generate a fresh one, and print
    /// its enrollment QR -- the whole lost-phone story.
    #[arg(long)]
    rotate_token: bool,
}

#[tokio::main]
async fn main() -> Result<()> {
    // Both rustls crypto providers are in the dependency graph (ureq
    // brings ring, axum-server brings aws-lc-rs), so rustls refuses to
    // pick one itself; choose before anything touches TLS.
    rustls::crypto::aws_lc_rs::default_provider()
        .install_default()
        .expect("no other TLS crypto provider is installed before main");

    tracing_subscriber::fmt().with_env_filter("info").init();
    let args = Args::parse();

    let config_path = args
        .config
        .unwrap_or_else(|| config_home("ai-app").join("config.ron"));
    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()))?,
    );
    // After construction rather than inside it: seeding asks this machine
    // what it has, which is I/O, 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),
            // No parenthetical naming the local machine: the default
            // setup is *called* "this machine", and the line read
            // "setup this machine (this machine)".
            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
        );
    }

    // Before the interface check below, deliberately: the certificates are
    // also what the phone app embeds at build time, so they need to be
    // obtainable on a machine whose tunnel isn't up yet. The leaf is
    // reissued on every start, so once wg0 exists the next start covers it.
    let certs_dir = args
        .certs
        .unwrap_or_else(|| config_home("ai-app").join("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 {} -- any installed app pins the previous one and can no \
             longer reach this server. Rebuild it with app/build-apk.sh, which embeds this CA, \
             and reinstall through Dev Updater.",
            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")?,
    };

    // Token bootstrap: first run generates one; --rotate-token replaces
    // whatever exists. Either way the plaintext appears exactly once, in
    // the QR printed here.
    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)?;
    }

    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")?;

    let monitor = Arc::new(usage::UsageMonitor::new(vec![Box::new(
        usage::ClaudeUsage {
            credentials_path: std::env::home_dir()
                .unwrap_or_else(|| PathBuf::from("/"))
                .join(".claude/.credentials.json"),
        },
    )]));

    // The bearer-token middleware wraps the entire router -- routes and
    // fallback alike -- here and only here, so a new route can't forget
    // auth. Zero unauthenticated endpoints.
    let app = routes::router(Arc::clone(&manager))
        .merge(routes::usage_router(monitor))
        .merge(routes::models_router(Arc::clone(&models)))
        .layer(axum::middleware::from_fn_with_state(
            Arc::clone(&manager),
            auth::require_token,
        ));

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

    // Stop the sessions' processes on the way out. Without this a signal
    // kills this process and leaves its children running -- which for the
    // Claude CLI is untidy and for a `llama-server` holding a model is
    // gigabytes of memory belonging to nobody. Both signals, because
    // systemd and OpenRC send TERM while a terminal sends INT.
    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 -- stopping sessions"),
        _ = tokio::signal::ctrl_c() => tracing::info!("interrupted -- stopping sessions"),
    }
    manager.shutdown_all();

    Ok(())
}