//! 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 off the open internet. `--bind` overrides
//! explicitly for development; 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 files;
mod machines;
mod media;
mod models;
mod provider_auth;
mod resume;
mod routes;
mod session;
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;

/// Serves AI coding sessions (Codex, 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
    /// (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,

    /// Enroll one more device without touching the running server: mint a
    /// token, print its enrollment link (one line, stdout, nothing else) and
    /// exit. The server adopts the token the first time that device uses it.
    /// For a tool that opens the link on the phone, where a QR printed here
    /// cannot be scanned.
    #[arg(long)]
    enroll_link: bool,

    /// Hold every response back by this many milliseconds.
    ///
    /// A development aid, and a specific one: over the tunnel a phone's requests
    /// take tens to hundreds of milliseconds, and several faults live entirely
    /// in what the app does *while* one is outstanding. On a loopback server
    /// those windows close before anything can be observed and the bug looks
    /// like it is not there.
    #[arg(long, default_value_t = 0, value_name = "MS")]
    delay: u64,

    /// Mark every session spawned here as throwaway: its process is stopped
    /// when this server exits, instead of being left running for the next start
    /// to adopt. On by default in a debug build.
    ///
    /// Sessions outlive the backend on purpose, which is right for the ones
    /// somebody is using and wrong for the ones a test made -- twelve of those
    /// accumulated on this machine in a day, each holding a conversation open.
    ///
    /// The flag decides only what *new* sessions are marked as. What happens on
    /// the way out is decided by the mark, which outlives the server that made
    /// it.
    #[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,
}

#[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.
    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"));
    // Before the manager exists, on purpose: constructing it and seeding machines
    // touches sessions and subprocesses this invocation has no business with
    // while another instance is serving. Only the hash reaches disk, in the
    // spool `auth.rs` reads; the link goes to stdout alone.
    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)
        );
        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_machine().await?;

    tracing::info!("config: {}", config_path.display());
    tracing::info!("models: {}", models_dir.display());
    for machine in manager.machines() {
        match &machine.ssh {
            Some(ssh) => tracing::info!("  machine \"{}\" -> {}", machine.name, ssh.address),
            // No parenthetical naming the local machine: the default machine is
            // *called* "this machine", so repeating a local qualifier read
            // like a stutter.
            None => tracing::info!("  machine \"{}\" runs here", machine.name),
        }
        for provider in &machine.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.
    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.
    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")?;

    // No providers listed here any more: which machines can be asked, and about
    // what, comes from the machines 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()));
    let provider_logins = Arc::new(provider_auth::LoginManager::new(Arc::clone(&monitor)));

    // The one thing in here that acts without a request behind it: a session
    // switched to auto-resume waits out its account's usage limit and picks
    // itself back up. Started whether or not any session has it on, because
    // the setting is per session and changes from the phone -- see
    // `resume::run`.
    tokio::spawn(resume::run(Arc::clone(&manager), Arc::clone(&monitor)));

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

    // Outside the auth layer, so an unauthenticated request is refused at the
    // speed it always was: this is here to slow the app down, not to widen the
    // window on anything guessing at tokens.
    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 go of the sessions on the way out rather than stopping them: their
    // processes are meant to outlive this one. Each is recorded in its session
    // directory and adopted again on the way back up. The exception is the
    // sessions marked throwaway, which are stopped first. 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 -- letting go of sessions"),
        _ = tokio::signal::ctrl_c() => tracing::info!("interrupted -- letting go of sessions"),
    }
    // Stopped before the rest are let go of, and on every way out of the select
    // above: a throwaway session is one nobody meant to keep, and the whole point
    // is that nothing has to remember to clean it up.
    manager.stop_throwaway_sessions();
    provider_logins.cancel_all();
    manager.detach_all();

    Ok(())
}