Mangalord/backend/src/app.rs

use std::sync::Arc;
use std::sync::atomic::{AtomicBool, AtomicU32, Ordering};

use anyhow::Context;
use async_trait::async_trait;
use axum::extract::{DefaultBodyLimit, FromRequestParts, Request, State};
use axum::http::{HeaderName, HeaderValue, Method};
use axum::middleware::{self, Next};
use axum::response::Response;
use axum::Router;
use sqlx::postgres::PgPoolOptions;
use sqlx::PgPool;
use tokio_util::sync::CancellationToken;
use tower_http::cors::{AllowOrigin, CorsLayer};
use tower_http::trace::TraceLayer;

use crate::auth::extractor::CurrentUser;
use crate::auth::rate_limit::AuthRateLimiter;
use crate::error::AppError;
use crate::config::{AuthConfig, Config, CrawlerConfig, UploadConfig};
use crate::crawler::browser_manager::{self, BrowserManager};
use crate::crawler::content::{self, SyncOutcome};
use crate::crawler::daemon::{self, ChapterDispatcher, DaemonConfig, MetadataPass};
use crate::crawler::jobs::JobPayload;
use crate::crawler::pipeline::{self, MetadataStats};
use crate::crawler::rate_limit::HostRateLimiters;
use crate::crawler::resync::{RealResyncService, ResyncService};
use crate::crawler::safety::DownloadAllowlist;
use crate::crawler::session;
use crate::repo;
use crate::storage::{LocalStorage, Storage};

#[derive(Clone)]
pub struct AppState {
    pub db: PgPool,
    pub storage: Arc<dyn Storage>,
    pub auth: AuthConfig,
    pub upload: UploadConfig,
    /// Shared rate limiter guarding the `/auth/*` mutation endpoints.
    /// One instance per AppState so tests stay isolated across the
    /// same process.
    pub auth_limiter: Arc<AuthRateLimiter>,
    /// Admin-triggered force resync. `None` when the crawler daemon
    /// is disabled (`CRAWLER_DAEMON=false`); admin handlers gate on
    /// `.is_some()` and return 503 otherwise. Set by [`build`] from the
    /// same wiring that builds the daemon's chapter dispatcher, so a
    /// force resync uses the daemon's BrowserManager + rate limiters.
    pub resync: Option<Arc<dyn ResyncService>>,
    /// Crawler observability + control handle (live status, coordinated
    /// browser restart, runtime session, manual run). `None` when the
    /// daemon is disabled; admin handlers gate on `.is_some()` → 503.
    pub crawler: Option<Arc<CrawlerControl>>,
    /// Browser origins permitted to issue mutating requests to
    /// `/api/v1/admin/*`. See [`crate::config::Config::admin_allowed_origins`]
    /// for the policy. Cloned per-request into the CSRF middleware; the
    /// `Arc` keeps the clone cheap. Empty list → check is skipped
    /// (operator opt-out documented in `.env.example`).
    pub admin_allowed_origins: Arc<Vec<String>>,
}

/// Shared handle the admin crawler endpoints use to observe and control
/// the running daemon. Bundled so the handlers take one optional field on
/// `AppState` rather than many.
pub struct CrawlerControl {
    pub browser_manager: Arc<BrowserManager>,
    pub session: Arc<crate::crawler::session_control::SessionController>,
    pub status: crate::crawler::status::StatusHandle,
    /// Used by the "run metadata pass now" endpoint; `None` when no
    /// `CRAWLER_START_URL` is configured (cron disabled).
    pub metadata_pass: Option<Arc<dyn MetadataPass>>,
    /// Drain budget for a manually-triggered coordinated browser restart.
    pub drain_deadline: std::time::Duration,
    /// Held for the duration of a `/admin/crawler/run` pass so a second
    /// click returns 409 instead of fanning N overlapping metadata passes
    /// onto the single browser lease. The daemon's daily cron does NOT
    /// take this lock — cron and operator-triggered are different
    /// trust modes (cron is single-fire by definition; the lock only
    /// dedups operator clicks). `Arc` so the spawned task can hold an
    /// owned guard past the request boundary.
    pub manual_pass_lock: Arc<tokio::sync::Mutex<()>>,
}

/// Bundle returned by [`build`]. The router is what `axum::serve` consumes;
/// the daemon (when enabled) outlives the HTTP server and is awaited via
/// [`AppHandle::shutdown`] after the listener has finished gracefully.
pub struct AppHandle {
    pub router: Router,
    pub daemon: Option<daemon::DaemonHandle>,
}

impl AppHandle {
    pub async fn shutdown(self) {
        if let Some(d) = self.daemon {
            d.shutdown().await;
        }
    }
}

pub async fn build(config: Config) -> anyhow::Result<AppHandle> {
    let db = PgPoolOptions::new()
        .max_connections(10)
        .connect(&config.database_url)
        .await?;
    sqlx::migrate!("./migrations").run(&db).await?;

    if let Some((username, password)) = config.admin_bootstrap.as_ref() {
        repo::user::bootstrap_admin(&db, username, password)
            .await
            .context("bootstrap_admin from ADMIN_USERNAME/ADMIN_PASSWORD env")?;
        tracing::info!(admin_username = %username, "admin bootstrap ensured");
    }

    let storage: Arc<dyn Storage> = Arc::new(LocalStorage::new(config.storage_dir.clone()));

    let (daemon, resync, crawler) = if config.crawler.daemon_enabled {
        let spawned = spawn_crawler_daemon(db.clone(), Arc::clone(&storage), &config.crawler).await?;
        (Some(spawned.handle), Some(spawned.resync), Some(spawned.crawler))
    } else {
        tracing::info!("crawler daemon disabled (CRAWLER_DAEMON=false)");
        (None, None, None)
    };

    let auth_limiter = Arc::new(AuthRateLimiter::new(config.auth.rate_limit));
    let state = AppState {
        db,
        storage,
        auth: config.auth.clone(),
        upload: config.upload.clone(),
        auth_limiter,
        resync,
        crawler,
        admin_allowed_origins: Arc::new(config.admin_allowed_origins.clone()),
    };
    let router = router(state).layer(cors_layer(&config.cors_allowed_origins));
    Ok(AppHandle { router, daemon })
}

/// Bundle returned by [`spawn_crawler_daemon`]. The handle owns the
/// daemon's tasks; `resync` is the operator-trigger service shared with
/// `AppState` so admin endpoints can call into the same browser /
/// rate-limit machinery.
struct SpawnedDaemon {
    handle: daemon::DaemonHandle,
    resync: Arc<dyn ResyncService>,
    crawler: Arc<CrawlerControl>,
}

async fn spawn_crawler_daemon(
    db: PgPool,
    storage: Arc<dyn Storage>,
    cfg: &CrawlerConfig,
) -> anyhow::Result<SpawnedDaemon> {
    // Reqwest client with a shared cookie jar so CDN image fetches include
    // PHPSESSID. The same `Arc<Jar>` is held by the SessionController, so a
    // runtime session refresh rewrites it in place. Initial value: a
    // persisted runtime session (survives restart) takes precedence over
    // CRAWLER_PHPSESSID env.
    let cookie_jar = Arc::new(reqwest::cookie::Jar::default());
    let initial_sid = crate::crawler::session_control::SessionController::load_persisted(&db)
        .await
        .or_else(|| cfg.phpsessid.clone());
    if let (Some(sid), Some(domain), Some(start_url)) =
        (&initial_sid, &cfg.cookie_domain, &cfg.start_url)
    {
        let cookie_str = format!("PHPSESSID={sid}; Domain={domain}; Path=/");
        let seed_url = reqwest::Url::parse(start_url)
            .context("parse CRAWLER_START_URL for cookie seed")?;
        cookie_jar.add_cookie_str(&cookie_str, &seed_url);
    }
    let mut http_builder = reqwest::Client::builder()
        .timeout(std::time::Duration::from_secs(30))
        .no_proxy()
        .cookie_provider(Arc::clone(&cookie_jar));
    if let Some(ua) = &cfg.user_agent {
        http_builder = http_builder.user_agent(ua);
    }
    if let Some(proxy) = &cfg.proxy {
        http_builder = http_builder
            .proxy(reqwest::Proxy::all(proxy).with_context(|| format!("parse proxy: {proxy}"))?);
    }
    let http = http_builder.build().context("build crawler reqwest")?;

    let mut rate = HostRateLimiters::new(std::time::Duration::from_millis(cfg.rate_ms));
    if let Some(host) = &cfg.cdn_host {
        rate = rate.with_override(host, std::time::Duration::from_millis(cfg.cdn_rate_ms));
    }
    let rate = Arc::new(rate);

    let tor = crate::crawler::tor::TorController::from_parts(
        cfg.tor_control_url.as_deref(),
        cfg.tor_control_password.as_deref(),
        cfg.tor_control_cookie_path.as_deref(),
    )
    .context("build TorController from CRAWLER_TOR_CONTROL_* env")?
    .map(Arc::new);
    if let Some(t) = &tor {
        tracing::info!(?t, "TOR control configured; transient pages will trigger NEWNYM");
    }
    let tor_recircuit_max = cfg.tor_recircuit_max_attempts;

    // Session controller + sticky session-expired flag. Created before the
    // browser so the on_launch hook can read the *current* session value
    // (rather than a value captured at startup), and so a runtime refresh
    // updates the cookie everywhere.
    let session_expired = Arc::new(AtomicBool::new(false));
    let session_controller = crate::crawler::session_control::SessionController::new(
        initial_sid,
        Arc::clone(&cookie_jar),
        cfg.cookie_domain.clone(),
        cfg.start_url.clone(),
        db.clone(),
        Arc::clone(&session_expired),
    );

    // Live status surface, sized to the worker count.
    let status = crate::crawler::status::StatusHandle::new(cfg.chapter_workers);

    // Browser manager. on_launch re-injects PHPSESSID on every fresh
    // chromium spawn so an idle teardown followed by re-launch stays
    // authenticated without operator action.
    let mut launch_opts = cfg.browser.clone();
    if let Some(proxy) = &cfg.proxy {
        let chromium_proxy = crate::crawler::url_utils::chromium_proxy_arg(proxy);
        launch_opts.extra_args.push(format!("--proxy-server={chromium_proxy}"));
    }
    let on_launch = match (&cfg.cookie_domain, &cfg.start_url) {
        (Some(domain), Some(start_url)) => {
            let domain = domain.clone();
            let start_url = start_url.clone();
            let tor_for_launch = tor.as_ref().map(Arc::clone);
            let sc = Arc::clone(&session_controller);
            let on_launch: browser_manager::OnLaunch = Arc::new(move |browser| {
                let domain = domain.clone();
                let start_url = start_url.clone();
                let tor_for_launch = tor_for_launch.as_ref().map(Arc::clone);
                let sc = Arc::clone(&sc);
                Box::pin(async move {
                    // Read the *current* session each launch so a runtime
                    // refresh is picked up on the next (re)launch. No session
                    // configured → run unauthenticated (metadata needs no auth).
                    let Some(sid) = sc.current().await else {
                        tracing::info!("on_launch: no session set — skipping inject + probe");
                        return Ok(());
                    };
                    session::inject_phpsessid(&browser, &sid, &domain)
                        .await
                        .context("on_launch: inject_phpsessid")?;
                    session::verify_session_with_recircuit(
                        &browser,
                        &start_url,
                        tor_for_launch.as_deref(),
                        tor_recircuit_max,
                    )
                    .await
                    .context("on_launch: verify_session")?;
                    Ok(())
                })
            });
            on_launch
        }
        _ => browser_manager::noop_on_launch(),
    };
    let browser_manager = BrowserManager::new(launch_opts, cfg.idle_timeout, on_launch);

    let metadata_pass: Option<Arc<dyn MetadataPass>> = cfg.start_url.as_ref().map(|url| {
        let m: Arc<dyn MetadataPass> = Arc::new(RealMetadataPass {
            browser_manager: Arc::clone(&browser_manager),
            db: db.clone(),
            storage: Arc::clone(&storage),
            http: http.clone(),
            rate: Arc::clone(&rate),
            start_url: url.clone(),
            manga_limit: cfg.manga_limit,
            download_allowlist: cfg.download_allowlist.clone(),
            max_image_bytes: cfg.max_image_bytes,
            metadata_max_consecutive_failures: cfg.metadata_max_consecutive_failures,
            status: status.clone(),
            tor: tor.as_ref().map(Arc::clone),
        });
        m
    });

    let dispatcher: Arc<dyn ChapterDispatcher> = Arc::new(RealChapterDispatcher {
        browser_manager: Arc::clone(&browser_manager),
        db: db.clone(),
        storage: Arc::clone(&storage),
        http: http.clone(),
        rate: Arc::clone(&rate),
        download_allowlist: cfg.download_allowlist.clone(),
        max_image_bytes: cfg.max_image_bytes,
        transient_failures: Arc::new(AtomicU32::new(0)),
        restart_threshold: cfg.browser_restart_threshold,
        drain_deadline: cfg.job_timeout,
        status: status.clone(),
        tor: tor.as_ref().map(Arc::clone),
    });

    let resync: Arc<dyn ResyncService> = Arc::new(RealResyncService {
        browser_manager: Arc::clone(&browser_manager),
        db: db.clone(),
        storage: Arc::clone(&storage),
        http,
        rate: Arc::clone(&rate),
        download_allowlist: cfg.download_allowlist.clone(),
        max_image_bytes: cfg.max_image_bytes,
        tor: tor.as_ref().map(Arc::clone),
    });

    // Shared cancellation: daemon shutdown cancels the BrowserManager's
    // idle reaper too. Reaper itself is added to the daemon's extra_tasks
    // so DaemonHandle::shutdown awaits its completion.
    let cancel = CancellationToken::new();
    let reaper_task = browser_manager::spawn_idle_reaper(
        Arc::clone(&browser_manager),
        cancel.clone(),
    );
    // Also close the browser explicitly on shutdown so we don't rely on
    // kill-on-drop when other Arc<Browser> holders may still exist.
    let shutdown_task = {
        let cancel = cancel.clone();
        let mgr = Arc::clone(&browser_manager);
        tokio::spawn(async move {
            cancel.cancelled().await;
            mgr.shutdown().await;
        })
    };

    let daemon_handle = daemon::spawn(
        db,
        cancel,
        DaemonConfig {
            metadata_pass: metadata_pass.clone(),
            dispatcher,
            chapter_workers: cfg.chapter_workers,
            daily_at: cfg.daily_at,
            tz: cfg.tz,
            retention_days: cfg.retention_days,
            session_expired,
            status: status.clone(),
            job_timeout: cfg.job_timeout,
            extra_tasks: vec![reaper_task, shutdown_task],
        },
    );

    let crawler = Arc::new(CrawlerControl {
        browser_manager: Arc::clone(&browser_manager),
        session: session_controller,
        status,
        metadata_pass,
        drain_deadline: cfg.job_timeout,
        manual_pass_lock: Arc::new(tokio::sync::Mutex::new(())),
    });

    Ok(SpawnedDaemon {
        handle: daemon_handle,
        resync,
        crawler,
    })
}

// Real impls of the daemon traits, owning the browser manager + I/O. Kept
// in app.rs because they need the same builder-side env wiring that
// AppState gets — the daemon module itself stays free of reqwest / storage
// details so its tests don't pull them in.

struct RealMetadataPass {
    browser_manager: Arc<BrowserManager>,
    db: PgPool,
    storage: Arc<dyn Storage>,
    http: reqwest::Client,
    rate: Arc<HostRateLimiters>,
    start_url: String,
    manga_limit: usize,
    download_allowlist: DownloadAllowlist,
    max_image_bytes: usize,
    metadata_max_consecutive_failures: u32,
    status: crate::crawler::status::StatusHandle,
    tor: Option<Arc<crate::crawler::tor::TorController>>,
}

#[async_trait]
impl MetadataPass for RealMetadataPass {
    async fn run(&self) -> anyhow::Result<MetadataStats> {
        let result = pipeline::run_metadata_pass(
            &self.browser_manager,
            &self.db,
            self.storage.as_ref(),
            &self.http,
            &self.rate,
            &self.start_url,
            self.manga_limit,
            false,
            &self.download_allowlist,
            self.max_image_bytes,
            self.metadata_max_consecutive_failures,
            Some(&self.status),
            self.tor.as_deref(),
        )
        .await;
        if let Err(e) = &result {
            if crate::crawler::nav::anyhow_looks_browser_dead(e) {
                self.browser_manager.invalidate().await;
            }
        }
        // Cover backfill follows the metadata pass even when the pass
        // errored — the early-stop walk can complete its work and bail
        // late, and a transient browser failure shouldn't cancel the
        // residual cover backlog. The backfill has its own per-call cap
        // so a runaway error stream can't monopolise the tick. It sets the
        // CoverBackfill{index,total} phase + current_cover per entry.
        match pipeline::backfill_missing_covers(
            &self.browser_manager,
            &self.db,
            self.storage.as_ref(),
            &self.http,
            &self.rate,
            pipeline::COVER_BACKFILL_DEFAULT_MAX,
            &self.download_allowlist,
            self.max_image_bytes,
            Some(&self.status),
            self.tor.as_deref(),
        )
        .await
        {
            Ok(stats) => {
                if stats.considered > 0 {
                    tracing::info!(?stats, "cover backfill complete");
                }
            }
            Err(e) => {
                tracing::warn!(error = ?e, "cover backfill failed");
                if crate::crawler::nav::anyhow_looks_browser_dead(&e) {
                    self.browser_manager.invalidate().await;
                }
            }
        }
        result
    }
}

struct RealChapterDispatcher {
    browser_manager: Arc<BrowserManager>,
    db: PgPool,
    storage: Arc<dyn Storage>,
    http: reqwest::Client,
    rate: Arc<HostRateLimiters>,
    download_allowlist: DownloadAllowlist,
    max_image_bytes: usize,
    /// Consecutive transient chapter failures; resets on any success.
    /// Drives the automatic coordinated browser restart.
    transient_failures: Arc<std::sync::atomic::AtomicU32>,
    /// Consecutive-failure count that triggers an auto restart.
    restart_threshold: u32,
    /// How long a coordinated restart waits for in-flight leases to drain.
    drain_deadline: std::time::Duration,
    /// Live status surface — the dispatcher registers each chapter it
    /// crawls (with a realtime page count) here.
    status: crate::crawler::status::StatusHandle,
    tor: Option<Arc<crate::crawler::tor::TorController>>,
}

#[async_trait]
impl ChapterDispatcher for RealChapterDispatcher {
    async fn dispatch(&self, payload: JobPayload) -> anyhow::Result<SyncOutcome> {
        match payload {
            JobPayload::SyncChapterContent {
                source_id: _,
                chapter_id,
                source_chapter_key: _,
            } => {
                let row = repo::chapter::dispatch_target(&self.db, chapter_id)
                    .await
                    .context("look up chapter for dispatch")?;
                let Some((manga_id, source_url, manga_title, chapter_number)) = row else {
                    // Chapter (or its source row) is gone — ack done.
                    return Ok(SyncOutcome::Skipped);
                };
                // Register the chapter as crawling now (live status). The
                // guard removes it on every exit path — success, panic, or
                // the worker's outer-timeout drop.
                let _active = self.status.begin_chapter(crate::crawler::status::ActiveChapter {
                    manga_id,
                    manga_title,
                    chapter_id,
                    chapter_number,
                    pages_done: 0,
                    pages_total: None,
                });
                let lease = self.browser_manager.acquire().await?;
                let result = content::sync_chapter_content(
                    &lease,
                    &self.db,
                    self.storage.as_ref(),
                    &self.http,
                    &self.rate,
                    chapter_id,
                    manga_id,
                    &source_url,
                    false,
                    &self.download_allowlist,
                    self.max_image_bytes,
                    self.tor.as_deref(),
                    Some(&self.status),
                )
                .await;
                drop(lease);
                match result {
                    Ok(outcome) => {
                        // Any successful dispatch (including a clean Skipped)
                        // means the browser is healthy — reset the streak.
                        self.transient_failures.store(0, Ordering::Release);
                        Ok(outcome)
                    }
                    Err(e) => {
                        let streak = self.transient_failures.fetch_add(1, Ordering::AcqRel) + 1;
                        if crate::crawler::nav::anyhow_looks_browser_dead(&e) {
                            // Hard browser-dead: lazy invalidate (next acquire
                            // relaunches). Reset the streak — we're recovering.
                            self.browser_manager.invalidate().await;
                            self.transient_failures.store(0, Ordering::Release);
                        } else if self.restart_threshold > 0 && streak >= self.restart_threshold {
                            // Persistent transients that TOR recircuit couldn't
                            // fix — proactively restart Chromium.
                            tracing::warn!(
                                streak,
                                threshold = self.restart_threshold,
                                "auto browser restart: consecutive transient chapter failures"
                            );
                            let _ = self
                                .browser_manager
                                .coordinated_restart(self.drain_deadline)
                                .await;
                            self.transient_failures.store(0, Ordering::Release);
                        }
                        Err(e)
                    }
                }
            }
            // Other payload kinds aren't dispatched by this daemon yet —
            // SyncManga / SyncChapterList are handled inline by the cron's
            // metadata pass.
            _ => Ok(SyncOutcome::Skipped),
        }
    }
}

/// Build a router from a pre-assembled state. Used by integration tests
/// so they can swap in a test DB pool and a `tempfile`-backed storage.
pub fn router(state: AppState) -> Router {
    let max_request_bytes = state.upload.max_request_bytes;
    Router::new()
        .nest("/api/v1", crate::api::routes())
        .layer(middleware::from_fn(admin_no_store_guard))
        .layer(middleware::from_fn_with_state(
            state.clone(),
            admin_csrf_guard,
        ))
        .layer(middleware::from_fn_with_state(
            state.clone(),
            private_mode_guard,
        ))
        .layer(DefaultBodyLimit::max(max_request_bytes))
        .with_state(state)
        .layer(TraceLayer::new_for_http())
}

/// Path prefix the admin-only middlewares scope themselves to. The router
/// already nests `/api/v1`, so callers see `/api/v1/admin/...`.
const ADMIN_PATH_PREFIX: &str = "/api/v1/admin/";

/// CSRF defence for cookie-authenticated admin mutations. The session
/// cookie is `SameSite=Lax`, which still permits top-level form-POSTs
/// from a malicious page — this middleware rejects such requests by
/// comparing the request's `Origin` (with `Referer` as fallback) against
/// the configured allowlist. Safe methods (`GET`/`HEAD`/`OPTIONS`) are
/// always allowed. Requests with neither `Origin` nor `Referer` are
/// allowed (non-browser callers like curl can't be a CSRF vector). When
/// the allowlist is empty the check is skipped entirely (operator
/// opt-out — documented in `.env.example`).
async fn admin_csrf_guard(
    State(state): State<AppState>,
    req: Request,
    next: Next,
) -> Result<Response, AppError> {
    if !req.uri().path().starts_with(ADMIN_PATH_PREFIX) {
        return Ok(next.run(req).await);
    }
    if matches!(
        *req.method(),
        Method::GET | Method::HEAD | Method::OPTIONS
    ) {
        return Ok(next.run(req).await);
    }
    if state.admin_allowed_origins.is_empty() {
        return Ok(next.run(req).await);
    }
    let headers = req.headers();
    let origin = headers.get("origin").and_then(|v| v.to_str().ok());
    let referer = headers.get("referer").and_then(|v| v.to_str().ok());
    // No Origin AND no Referer → server-to-server / curl / extension.
    // Browsers always send one or the other on a cross-site POST.
    let Some(candidate) = origin.or(referer) else {
        return Ok(next.run(req).await);
    };
    if origin_in_allowlist(candidate, &state.admin_allowed_origins) {
        return Ok(next.run(req).await);
    }
    tracing::warn!(
        candidate = %truncate_for_log(candidate, 64),
        path = %req.uri().path(),
        "admin CSRF: rejecting mutation with disallowed origin"
    );
    Err(AppError::Forbidden)
}

/// Match `candidate` (an `Origin` value, or a `Referer` URL whose
/// origin we'll extract) against `allowed`. `Origin` is `scheme://host[:port]`
/// with no path; `Referer` is a full URL — compare by parsing both and
/// matching scheme + host + port.
fn origin_in_allowlist(candidate: &str, allowed: &[String]) -> bool {
    let cand_origin = parse_origin(candidate);
    let Some(cand) = cand_origin else { return false };
    allowed
        .iter()
        .filter_map(|a| parse_origin(a))
        .any(|a| a == cand)
}

/// Extract the origin (`scheme://host[:port]`) from an `Origin` header
/// value or a `Referer` URL. Returns `None` when the input doesn't parse
/// as a URL with a host.
fn parse_origin(raw: &str) -> Option<String> {
    let url = reqwest::Url::parse(raw.trim()).ok()?;
    let host = url.host_str()?;
    let scheme = url.scheme();
    let port_str = match (url.port(), scheme) {
        (Some(p), "http") if p == 80 => String::new(),
        (Some(p), "https") if p == 443 => String::new(),
        (Some(p), _) => format!(":{p}"),
        (None, _) => String::new(),
    };
    Some(format!("{scheme}://{host}{port_str}"))
}

fn truncate_for_log(s: &str, max: usize) -> &str {
    let end = s
        .char_indices()
        .take(max)
        .last()
        .map(|(i, c)| i + c.len_utf8())
        .unwrap_or(0);
    &s[..end.min(s.len())]
}

/// Forbids intermediaries (CDN, browser bfcache, reverse proxy with a
/// permissive default) from caching admin responses. Defence-in-depth
/// for cookie-authenticated reads — even though the responses already
/// vary on cookie, a misconfigured cache layer in front of the
/// SvelteKit container could leak a logged-in admin's view to another
/// session. Headers added on response so the rest of the API is
/// unaffected.
async fn admin_no_store_guard(req: Request, next: Next) -> Response {
    let is_admin_path = req.uri().path().starts_with(ADMIN_PATH_PREFIX);
    let mut resp = next.run(req).await;
    if is_admin_path {
        resp.headers_mut().insert(
            axum::http::header::CACHE_CONTROL,
            HeaderValue::from_static("no-store"),
        );
    }
    resp
}

/// Paths reachable anonymously even when `PRIVATE_MODE=true`. Login and
/// logout are needed for the auth flow itself; `/health` is reserved
/// for load-balancer probes; `/auth/config` lets the frontend decide
/// whether to render the login form or its anonymous alternatives;
/// `/auth/register` is exempted from the gate so the handler can
/// return its informative `registration_disabled` 403 (the same code
/// public-mode deployments use when `ALLOW_SELF_REGISTER=false`) —
/// the handler itself force-blocks the request body in private mode,
/// so no account ever gets created here. Everything else demands a
/// valid session cookie or bearer token.
fn is_public_in_private_mode(path: &str) -> bool {
    matches!(
        path,
        "/api/v1/health"
            | "/api/v1/auth/config"
            | "/api/v1/auth/login"
            | "/api/v1/auth/logout"
            | "/api/v1/auth/register"
    )
}

/// Site-wide auth gate for `PRIVATE_MODE=true`. With the flag off this
/// is a no-op pass-through, so public deployments take no extra DB
/// hit. With it on, the guard reuses [`CurrentUser`] — the same
/// session-cookie-then-bearer-token logic the per-handler extractor
/// uses — so the two paths can never drift.
async fn private_mode_guard(
    State(state): State<AppState>,
    req: Request,
    next: Next,
) -> Result<Response, AppError> {
    if !state.auth.private_mode {
        return Ok(next.run(req).await);
    }
    if is_public_in_private_mode(req.uri().path()) {
        return Ok(next.run(req).await);
    }
    let (mut parts, body) = req.into_parts();
    match CurrentUser::from_request_parts(&mut parts, &state).await {
        Ok(_) => {
            let req = Request::from_parts(parts, body);
            Ok(next.run(req).await)
        }
        Err(_) => Err(AppError::Unauthenticated),
    }
}

pub(crate) fn cors_layer(allowed_origins: &[String]) -> CorsLayer {
    if allowed_origins.is_empty() {
        // Same-origin only — no CORS headers emitted.
        return CorsLayer::new();
    }
    let origins: Vec<HeaderValue> = allowed_origins
        .iter()
        .filter_map(|o| HeaderValue::from_str(o).ok())
        .collect();
    CorsLayer::new()
        .allow_origin(AllowOrigin::list(origins))
        .allow_credentials(true)
        .allow_methods([Method::GET, Method::POST, Method::PUT, Method::DELETE])
        .allow_headers([
            HeaderName::from_static("content-type"),
            HeaderName::from_static("authorization"),
        ])
}

#[cfg(test)]
mod tests {
    use super::*;
    use axum::body::Body;
    use axum::http::Request;
    use axum::routing::get;
    use tower::ServiceExt;

    fn test_router() -> Router {
        Router::new().route("/", get(|| async { "ok" }))
    }

    #[tokio::test]
    async fn allowlist_preflight_emits_credentialed_headers() {
        let app = test_router().layer(cors_layer(&["https://app.example.com".to_string()]));
        let resp = app
            .oneshot(
                Request::builder()
                    .method(Method::OPTIONS)
                    .uri("/")
                    .header("origin", "https://app.example.com")
                    .header("access-control-request-method", "POST")
                    .body(Body::empty())
                    .unwrap(),
            )
            .await
            .unwrap();
        assert_eq!(
            resp.headers().get("access-control-allow-origin").unwrap(),
            "https://app.example.com"
        );
        assert_eq!(
            resp.headers().get("access-control-allow-credentials").unwrap(),
            "true"
        );
    }

    #[tokio::test]
    async fn allowlist_rejects_unlisted_origin() {
        let app = test_router().layer(cors_layer(&["https://app.example.com".to_string()]));
        let resp = app
            .oneshot(
                Request::builder()
                    .method(Method::OPTIONS)
                    .uri("/")
                    .header("origin", "https://evil.example.org")
                    .header("access-control-request-method", "POST")
                    .body(Body::empty())
                    .unwrap(),
            )
            .await
            .unwrap();
        // Browsers will refuse the response when the allow-origin header
        // is absent (or doesn't echo the requesting origin).
        assert!(resp.headers().get("access-control-allow-origin").is_none());
    }

    #[tokio::test]
    async fn empty_allowlist_is_same_origin_only() {
        let app = test_router().layer(cors_layer(&[]));
        let resp = app
            .oneshot(
                Request::builder()
                    .method(Method::OPTIONS)
                    .uri("/")
                    .header("origin", "https://app.example.com")
                    .header("access-control-request-method", "POST")
                    .body(Body::empty())
                    .unwrap(),
            )
            .await
            .unwrap();
        assert!(resp.headers().get("access-control-allow-origin").is_none());
        assert!(resp.headers().get("access-control-allow-credentials").is_none());
    }
}