Add artwork self-hosting: local-disk download worker + storage

Section 10: every image API responses reference has pointed straight
at TMDb's CDN since day one -- Aurora never actually downloaded or
served artwork itself, despite storing dimensions/checksum/local_path
columns for exactly that. Closes the gap:

- is_primary was declared on the Artwork model but never actually set
  anywhere -- every row defaulted to False. Now the normalizer marks
  the one image each provider designates as *the* image for an entity
  (TMDb's poster_path/backdrop_path/profile_path) as primary,
  distinct from the dozens of alternates also ingested, including
  correctly marking an existing row primary (not inserting a
  duplicate) when that image already appears in the alternates list.
- app/services/artwork/: an ArtworkStorage interface with a
  LocalDiskStorage implementation (checksum-named files, single-host
  deployment via a Docker volume shared between api and worker -- see
  docs/architecture.md for the S3/R2 upgrade path), and a download
  pipeline with content-type validation, a size cap, and path-traversal
  protection.
- After movie/series/person ingestion succeeds, tasks.py cascades one
  download_artwork_task per primary artwork id via arq's ctx['redis']
  (same fan-out pattern as the season cascade) -- fire-and-forget, not
  tracked in ingestion_jobs, since a failed image cache is a
  known-safe fallback to the provider URL, not a user-facing failure.
- app/main.py serves MEDIA_ROOT at MEDIA_URL_PREFIX; local_path is
  preferred over original_url once set (already-existing fallback
  logic in app/services/common.py:artwork_url, now actually exercised).

Also fixes a real interaction bug this surfaced: every ingestion
pipeline deleted and recreated all of an entity's Artwork rows on each
re-sync, which would have silently wiped local_path/checksum on every
re-ingestion, forcing a full re-download every time and defeating the
point of caching locally at all. app/repositories/polymorphic.py's new
sync_artwork upserts by provider_asset_id (TMDb's stable per-image
path) instead, preserving downloaded copies across re-sync, and
replaces three near-identical delete+recreate helpers that used to
live separately in movie_ingestion.py, series_ingestion.py, and
person_ingestion.py.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

app/services/artwork/download.py

@@ -0,0 +1,110 @@
+"""Downloads one Artwork row's original_url and stores it locally
+(section 10; the "Artwork processing" background worker from section 1's
+architecture diagram).
+
+Deliberately narrow: only ever called for artwork already marked
+`is_primary` (see `app/services/ingestion/runner.py:get_primary_artwork_ids`
+and `app/workers/tasks.py`, which cascade a download job per primary image
+after each ingestion succeeds) — TMDb returns dozens of backdrop/logo
+alternates per title, and downloading every one of them automatically would
+be a lot of unnecessary storage and bandwidth for images Aurora's own
+clients are unlikely to ever show. Downloading on request for anything
+beyond the primary image is a reasonable follow-up if that's ever needed.
+"""
+
+from __future__ import annotations
+
+import hashlib
+import uuid
+
+import httpx
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.core.config import get_settings
+from app.core.logging import get_logger
+from app.models.artwork import Artwork
+from app.services.artwork.storage import ArtworkStorage
+
+logger = get_logger(__name__)
+
+_EXTENSION_BY_CONTENT_TYPE = {
+    "image/jpeg": "jpg",
+    "image/jpg": "jpg",
+    "image/png": "png",
+    "image/webp": "webp",
+    "image/gif": "gif",
+    "image/svg+xml": "svg",
+}
+
+
+class ArtworkDownloadError(Exception):
+    """Raised for any download-side failure (bad content-type, too large,
+    network error, ...). Callers (the arq task) let this propagate so the
+    job gets retried like any other ingestion failure — see
+    app/services/ingestion/runner.py."""
+
+
+async def download_artwork(
+    session: AsyncSession,
+    storage: ArtworkStorage,
+    artwork_id: uuid.UUID,
+    *,
+    client: httpx.AsyncClient | None = None,
+    force: bool = False,
+) -> bool:
+    """Fetch `artwork.original_url`, store it, and set `local_path` +
+    `checksum`. Returns False (no-op) if the row is gone or already has a
+    local copy (unless `force=True`); True if it downloaded something.
+    """
+
+    artwork = await session.get(Artwork, artwork_id)
+    if artwork is None:
+        return False
+    if artwork.local_path and not force:
+        return False
+
+    settings = get_settings()
+    owns_client = client is None
+    http_client = client or httpx.AsyncClient(timeout=20.0, follow_redirects=True)
+    try:
+        content, content_type = await _fetch(http_client, artwork.original_url, settings.ARTWORK_DOWNLOAD_MAX_BYTES)
+    finally:
+        if owns_client:
+            await http_client.aclose()
+
+    checksum = hashlib.sha256(content).hexdigest()
+    extension = _EXTENSION_BY_CONTENT_TYPE.get(content_type, "jpg")
+    relative_path = f"{artwork.artwork_type.value}/{checksum[:2]}/{checksum}.{extension}"
+
+    local_url = await storage.save(relative_path, content)
+
+    artwork.local_path = local_url
+    artwork.checksum = checksum
+    await session.flush()
+    logger.info(
+        "artwork_downloaded",
+        artwork_id=str(artwork_id),
+        checksum=checksum,
+        bytes=len(content),
+    )
+    return True
+
+
+async def _fetch(client: httpx.AsyncClient, url: str, max_bytes: int) -> tuple[bytes, str]:
+    try:
+        async with client.stream("GET", url) as response:
+            response.raise_for_status()
+            content_type = response.headers.get("content-type", "").split(";")[0].strip().lower()
+            if not content_type.startswith("image/"):
+                raise ArtworkDownloadError(f"expected an image, got content-type={content_type!r}")
+
+            body = bytearray()
+            async for chunk in response.aiter_bytes():
+                body.extend(chunk)
+                if len(body) > max_bytes:
+                    raise ArtworkDownloadError(
+                        f"artwork at {url} exceeds ARTWORK_DOWNLOAD_MAX_BYTES ({max_bytes} bytes)"
+                    )
+            return bytes(body), content_type
+    except httpx.HTTPError as exc:
+        raise ArtworkDownloadError(f"failed to download {url}: {exc}") from exc

app/services/artwork/storage.py

@@ -0,0 +1,66 @@
+"""Artwork storage abstraction (section 10).
+
+Downloaded artwork bytes need somewhere to live that both the worker
+(writing) and the API (serving, via app/main.py's static mount) can reach.
+`ArtworkStorage` is the seam: today there's only `LocalDiskStorage` — fine
+for a single Docker host where the api and worker containers share one
+volume (see docker-compose.yml), which is this project's actual deployment
+shape (section 1: modular monolith, not a multi-host fleet). A deployment
+that outgrows a single host would swap in an S3/R2-backed implementation
+behind this same interface without touching the download pipeline that
+calls it (app/services/artwork/download.py).
+"""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+from functools import lru_cache
+from pathlib import Path
+
+from app.core.config import get_settings
+
+
+class ArtworkStorage(ABC):
+    @abstractmethod
+    async def save(self, relative_path: str, content: bytes) -> str:
+        """Persist `content` at `relative_path` (already includes an
+        extension, e.g. "poster/ab/ab34...jpg"). Returns the root-relative
+        URL clients should use to fetch it."""
+
+    @abstractmethod
+    async def exists(self, relative_path: str) -> bool: ...
+
+
+class LocalDiskStorage(ArtworkStorage):
+    def __init__(self, root: str, url_prefix: str) -> None:
+        self._root = Path(root)
+        self._url_prefix = url_prefix.rstrip("/")
+
+    def _full_path(self, relative_path: str) -> Path:
+        # relative_path is always built by us from a sha256 checksum, never
+        # from unsanitized external input — but guard anyway against ever
+        # writing outside MEDIA_ROOT.
+        root = self._root.resolve()
+        full = (self._root / relative_path).resolve()
+        if full != root and root not in full.parents:
+            raise ValueError(f"unsafe artwork path escapes MEDIA_ROOT: {relative_path!r}")
+        return full
+
+    async def save(self, relative_path: str, content: bytes) -> str:
+        full = self._full_path(relative_path)
+        full.parent.mkdir(parents=True, exist_ok=True)
+        # Blocking I/O, but artwork files are small (capped by
+        # ARTWORK_DOWNLOAD_MAX_BYTES) and this only ever runs inside the
+        # worker process, not a request handler — not worth wiring aiofiles
+        # for.
+        full.write_bytes(content)
+        return f"{self._url_prefix}/{relative_path}"
+
+    async def exists(self, relative_path: str) -> bool:
+        return self._full_path(relative_path).is_file()
+
+
+@lru_cache
+def get_artwork_storage() -> ArtworkStorage:
+    settings = get_settings()
+    return LocalDiskStorage(settings.MEDIA_ROOT, settings.MEDIA_URL_PREFIX)