archy/core/archipelago/src/main.rs

// Archipelago Bitcoin Node OS - Native Backend
// Pure Archipelago implementation, no StartOS dependencies

use anyhow::{Context, Result};
use std::net::SocketAddr;
use tracing::info;
use tokio::signal;

mod api;
mod auth;
mod backup;
mod constants;
mod bitcoin_rpc;
mod config;
mod content_server;
mod crash_recovery;
mod credentials;
mod disk_monitor;
mod health_monitor;
mod electrs_status;
mod container;
mod port_allocator;
mod data_model;
mod federation;
mod identity;
mod identity_manager;
mod marketplace;
mod mesh;
mod monitoring;
mod transport;
mod node_message;
mod nostr_discovery;
mod nostr_handshake;
mod peers;
mod server;
mod rate_limit;
mod session;
mod state;
mod totp;
mod wallet;
mod names;
mod network;
pub mod seed;
mod nostr_relays;
mod update;
mod vpn;
mod webhooks;

use config::Config;
use server::Server;

#[tokio::main]
async fn main() -> Result<()> {
    let startup_start = std::time::Instant::now();
    crash_recovery::init_start_time();

    // Initialize tracing
    tracing_subscriber::fmt()
        .with_env_filter(
            tracing_subscriber::EnvFilter::try_from_default_env()
                .unwrap_or_else(|_| "archipelago=debug,info".into()),
        )
        .init();

    info!("Starting Archipelago Bitcoin Node OS");

    // Load configuration
    let config = Config::load().await?;
    info!("📁 Data directory: {}", config.data_dir.display());

    // Write PID marker early so we can detect crashes on next startup
    crash_recovery::write_pid_marker(&config.data_dir).await?;

    // Crash recovery runs in background so health endpoint is available immediately
    {
        let data_dir = config.data_dir.clone();
        tokio::spawn(async move {
            // Check if previous instance shut down cleanly
            match crash_recovery::check_for_crash(&data_dir).await {
                Ok(Some(containers)) => {
                    info!("🔧 Recovering {} containers from previous crash...", containers.len());
                    let report = crash_recovery::recover_containers(&containers).await;
                    info!(
                        "🔧 Recovery complete: {}/{} containers restarted (failed: {:?})",
                        report.recovered, report.total, report.failed
                    );
                }
                Ok(None) => {}
                Err(e) => {
                    tracing::warn!("Crash recovery check failed: {}", e);
                }
            }

            // Start any stopped containers (handles clean reboot)
            // Skips user-stopped containers, uses tier ordering
            let boot_report = crash_recovery::start_stopped_containers(&data_dir).await;
            if boot_report.total > 0 {
                info!(
                    "🔄 Boot startup: {}/{} containers started (failed: {:?})",
                    boot_report.recovered, boot_report.total, boot_report.failed
                );
            }

            // Signal to health monitor that boot recovery is done
            crash_recovery::mark_recovery_complete();

            // Reconcile containers against canonical specs (fixes config drift)
            crash_recovery::run_boot_reconciliation().await;
        });
    }

    // Ensure a default user exists so login works after install/onboarding.
    // In production, the default password is "password123" (shown during install).
    // In dev mode, the dev default password is used.
    // Don't auto-create default user — let onboarding flow handle password setup
    // via auth.setup RPC. The Login page detects is_setup=false and shows
    // "Create Password" form instead of login form.

    // Create server
    let server = Server::new(config.clone()).await?;

    // Start server
    let addr: SocketAddr = format!("{}:{}", config.bind_host, config.bind_port)
        .parse()
        .context("Invalid bind address")?;

    // Spawn background update scheduler
    let update_data_dir = config.data_dir.clone();
    tokio::spawn(async move {
        update::run_update_scheduler(update_data_dir).await;
    });

    // Spawn periodic container snapshot (for crash recovery)
    crash_recovery::spawn_snapshot_task(config.data_dir.clone());

    // Spawn disk space monitor (warns at 85%, auto-cleans at 90%)
    disk_monitor::spawn_disk_monitor(config.data_dir.clone());

    let startup_ms = startup_start.elapsed().as_millis();
    info!("Server listening on http://{} (startup: {}ms)", addr, startup_ms);
    info!("RPC API: http://{}/rpc/v1", addr);
    info!("WebSocket: ws://{}/ws", addr);

    // Notify systemd that we're ready (Type=notify)
    // Note: first param `false` keeps NOTIFY_SOCKET so watchdog pings work
    let _ = sd_notify::notify(false, &[sd_notify::NotifyState::Ready]);

    // Spawn systemd watchdog ping (WatchdogSec=300, ping every 120s)
    tokio::spawn(async {
        let mut interval = tokio::time::interval(std::time::Duration::from_secs(120));
        loop {
            interval.tick().await;
            let _ = sd_notify::notify(false, &[sd_notify::NotifyState::Watchdog]);
        }
    });

    // Graceful shutdown: wait for SIGTERM or SIGINT
    let mut sigterm = signal::unix::signal(signal::unix::SignalKind::terminate())
        .context("Failed to register SIGTERM handler")?;
    let shutdown = async move {
        tokio::select! {
            _ = signal::ctrl_c() => {
                info!("Received SIGINT (Ctrl+C), initiating graceful shutdown...");
            }
            _ = sigterm.recv() => {
                info!("Received SIGTERM, initiating graceful shutdown...");
            }
        }
    };

    server.serve_with_shutdown(addr, shutdown).await?;

    // Clean shutdown: remove PID marker so next startup doesn't trigger recovery
    crash_recovery::remove_pid_marker(&config.data_dir).await;

    info!("Archipelago shut down cleanly");
    Ok(())
}