siftlode/backend/app/main.py

import logging
import sys
from contextlib import asynccontextmanager
from pathlib import Path

from fastapi import FastAPI, HTTPException

# When started via uvicorn --log-config the "siftlode" logger is already configured
# (see log_config.json). This block is a timestamped fallback for other entrypoints
# (tests, scripts) so our logs are never silently dropped.
_siftlode_logger = logging.getLogger("siftlode")
if not _siftlode_logger.handlers:
    _handler = logging.StreamHandler(sys.stdout)
    _handler.setFormatter(
        logging.Formatter("%(asctime)s %(levelname)-5s [%(name)s] %(message)s")
    )
    _siftlode_logger.addHandler(_handler)
    _siftlode_logger.setLevel(logging.INFO)
    _siftlode_logger.propagate = False

log = logging.getLogger("siftlode.app")
from fastapi.middleware.cors import CORSMiddleware
from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
from fastapi.staticfiles import StaticFiles
from starlette.middleware.sessions import SessionMiddleware

from app import auth, state
from app.config import settings
from app.db import SessionLocal
from app.routes import (
    admin,
    audit as audit_routes,
    channels,
    config as config_routes,
    downloads,
    feed,
    health,
    me,
    messages,
    notifications,
    playlists,
    plex as plex_routes,
    public as public_routes,
    quota,
    saved_views,
    scheduler as scheduler_routes,
    search as search_routes,
    setup as setup_routes,
    sync,
    tags,
    version,
)
from app.scheduler import shutdown_scheduler, start_scheduler


@asynccontextmanager
async def lifespan(app: FastAPI):
    log.info("Siftlode starting up")
    # First-run: if the instance isn't configured yet, mint a fresh one-time setup token and print
    # the wizard URL so the operator can open it (the app runs in setup mode until they finish).
    with SessionLocal() as db:
        if not state.is_configured(db):
            token = state.rotate_setup_token(db)
            url = f"{settings.app_base}/setup?token={token}"
            log.warning(
                "FIRST-RUN SETUP REQUIRED — this instance isn't configured yet.\n"
                "    Open the install wizard (internal access only):\n    %s",
                url,
            )
    start_scheduler()
    try:
        yield
    finally:
        log.info("Siftlode shutting down")
        shutdown_scheduler()


app = FastAPI(title=settings.app_name, lifespan=lifespan)

app.add_middleware(
    SessionMiddleware,
    secret_key=settings.secret_key,
    same_site="lax",  # required so the cookie rides the OAuth redirect back from Google
    https_only=settings.session_https_only,  # Secure flag when served over HTTPS (prod)
)

if settings.frontend_origin:
    app.add_middleware(
        CORSMiddleware,
        allow_origins=[settings.frontend_origin],
        allow_credentials=True,
        allow_methods=["*"],
        allow_headers=["*"],
    )

# Paths reachable while the instance is unconfigured (setup mode). Everything else under /api or
# /auth is locked until the wizard finishes; static/SPA always loads so the wizard page can render.
_SETUP_OPEN_PREFIXES = ("/api/setup", "/api/version")


@app.middleware("http")
async def setup_gate(request, call_next):
    """Lock the app to the install wizard until it's configured. Skips the DB entirely once setup
    completed in this process (the cached fast-path), so there's no steady-state overhead."""
    if not state.setup_complete():
        path = request.url.path
        if path.startswith(("/api/", "/auth/")) and not path.startswith(_SETUP_OPEN_PREFIXES):
            with SessionLocal() as db:
                configured = state.is_configured_cached(db)
            if not configured:
                return JSONResponse(
                    {"detail": "This instance isn't set up yet."}, status_code=503
                )
    return await call_next(request)


@app.middleware("http")
async def static_cache_headers(request, call_next):
    """Long-cache the content-hashed SPA bundles. Vite hashes their filename, so a given
    /assets URL never changes content and a browser can hold it forever — this is what makes
    repeat loads instant and clears the Lighthouse "efficient cache lifetimes" audit. index.html
    stays no-cache (set on its own FileResponse) so a deploy is picked up at once; other
    SPA-root static files (welcome images, favicon, robots.txt) get a moderate TTL in the SPA
    fallback below."""
    response = await call_next(request)
    if request.url.path.startswith("/assets/"):
        response.headers["Cache-Control"] = "public, max-age=31536000, immutable"
    return response


app.include_router(health.router)
app.include_router(auth.router)
app.include_router(sync.router)
app.include_router(tags.router)
app.include_router(feed.router)
app.include_router(search_routes.router)
app.include_router(me.router)
app.include_router(notifications.router)
app.include_router(messages.router)
app.include_router(channels.router)
app.include_router(playlists.router)
app.include_router(saved_views.router)
app.include_router(plex_routes.router)
app.include_router(downloads.router)
app.include_router(downloads.admin_router)
app.include_router(public_routes.router)
app.include_router(admin.router)
app.include_router(config_routes.router)
app.include_router(scheduler_routes.router)
app.include_router(audit_routes.router)
app.include_router(quota.router)
app.include_router(version.router)
app.include_router(setup_routes.router)

# Ensure modern image types resolve to the right Content-Type when FileResponse guesses from the
# filename (the runtime's mimetypes db doesn't always know .webp → it'd fall back to octet-stream).
import mimetypes

mimetypes.add_type("image/webp", ".webp")
mimetypes.add_type("image/avif", ".avif")

# The built SPA (populated by the Docker frontend build stage).
STATIC_DIR = Path(__file__).parent / "static_spa"
# index.html is unhashed and references the content-hashed /assets bundles, so it MUST NOT be
# heuristically cached — otherwise, after a deploy, a browser keeps serving the old index.html
# (pointing at the previous bundle) and runs stale code until a hard refresh. `no-cache` lets it
# stay cached but forces revalidation (cheap 304 via the FileResponse ETag) on every load. The
# hashed bundles under /assets can cache forever (a new build changes their filename).
INDEX_HTML = STATIC_DIR / "index.html"
INDEX_HEADERS = {"Cache-Control": "no-cache"}
app.mount(
    "/assets",
    StaticFiles(directory=STATIC_DIR / "assets", check_dir=False),
    name="assets",
)


@app.get("/")
async def index() -> FileResponse:
    return FileResponse(INDEX_HTML, headers=INDEX_HEADERS)


@app.get("/watch/{token}")
async def watch_page(token: str):
    """Serve the SPA for a public share link, but with per-video Open Graph tags injected so the
    link unfurls richly (title/channel/thumbnail) in Messenger/social crawlers. A real browser
    ignores the extra tags and hydrates WatchPage as usual; invalid/expired/password links fall
    back to the generic card."""
    from app.downloads import og

    with SessionLocal() as db:
        rendered = og.render_watch_html(token, INDEX_HTML, db)
    if rendered is None:
        return FileResponse(INDEX_HTML, headers=INDEX_HEADERS)
    return HTMLResponse(rendered, headers=INDEX_HEADERS)


@app.get("/{full_path:path}")
async def spa_fallback(full_path: str) -> FileResponse:
    # Client-side routes fall back to index.html; real API/asset paths are matched above.
    if full_path.startswith(("api/", "auth/", "healthz", "assets/")):
        raise HTTPException(status_code=404)
    # Serve real files that live at the SPA root (Vite copies public/ there — e.g. the landing
    # screenshots under /welcome/, favicon). /assets is already mounted above; everything else
    # that isn't a real file is a client-side route → index.html. Guard against path traversal.
    if full_path:
        candidate = (STATIC_DIR / full_path).resolve()
        if candidate.is_file() and STATIC_DIR.resolve() in candidate.parents:
            # Real SPA-root assets (welcome images, favicon, robots.txt) rarely change and have
            # stable names, so a moderate cache is safe and satisfies the cache-lifetime audit.
            return FileResponse(candidate, headers={"Cache-Control": "public, max-age=604800"})
    return FileResponse(INDEX_HTML, headers=INDEX_HEADERS)