feat(storage): library + disk statistics endpoint (§A6)

Implement `GET /api/v1/storage`, replacing the stub. Returns aggregate
library facts (track/artist/album counts, total footprint, playtime,
per-format / per-source / metadata-status breakdowns, top genres) plus
the real capacity of the backing volume.

- domain: `LibraryStats`, `FormatBreakdown`, `DiskUsage` value objects
- ports: `FileStorage.disk_usage()` (local = shutil.disk_usage walking up
  to the nearest existing ancestor; S3 returns None — no fixed disk)
- repo: `TrackRepository.library_stats()` (single set of GROUP BYs)
- tests: storage stats API (auth, empty library, upload counting)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/api/schemas/storage.py

@@ -0,0 +1,45 @@
+"""Storage / library statistics response schemas (§A6)."""
+
+import datetime as dt
+
+from pydantic import BaseModel
+
+
+class DiskUsageOut(BaseModel):
+    total: int
+    used: int
+    free: int
+
+
+class FormatBreakdownOut(BaseModel):
+    file_format: str
+    track_count: int
+    total_size: int
+
+
+class GenreCountOut(BaseModel):
+    genre: str
+    track_count: int
+
+
+class StorageStatsOut(BaseModel):
+    """Everything the Storage screen needs in a single call."""
+
+    # library catalogue
+    total_tracks: int
+    total_artists: int
+    total_albums: int
+    total_size: int
+    total_duration_seconds: int
+    largest_track_size: int
+    earliest_added: dt.datetime | None
+    latest_added: dt.datetime | None
+
+    # breakdowns
+    by_format: list[FormatBreakdownOut]
+    by_metadata_status: dict[str, int]
+    by_source: dict[str, int]
+    top_genres: list[GenreCountOut]
+
+    # backing volume (``None`` for object-store backends)
+    disk: DiskUsageOut | None

app/api/v1/storage.py

@@ -4,11 +4,70 @@ from typing import Any
 
 from fastapi import APIRouter
 
+from app.api.deps import (
+    AlbumRepoDep,
+    ArtistRepoDep,
+    CurrentUser,
+    FileStorageDep,
+    TrackRepoDep,
+)
+from app.api.schemas.storage import (
+    DiskUsageOut,
+    FormatBreakdownOut,
+    GenreCountOut,
+    StorageStatsOut,
+)
+
 router = APIRouter(prefix="/storage", tags=["storage"])
 
+# How many of the most common genres the dashboard surfaces.
+_TOP_GENRES = 8
+
 
 @router.get("")
-async def get_storage_stats() -> Any: ...
+async def get_storage_stats(
+    track_repo: TrackRepoDep,
+    artist_repo: ArtistRepoDep,
+    album_repo: AlbumRepoDep,
+    storage: FileStorageDep,
+    _: CurrentUser,
+) -> StorageStatsOut:
+    """Library + disk statistics for the Storage dashboard (§A6).
+
+    Aggregates come from the catalogue (cheap GROUP BYs); ``disk`` reflects the
+    real backing volume and is ``None`` for backends without a fixed-capacity
+    disk (e.g. object stores)."""
+    stats = await track_repo.library_stats()
+    total_artists = await artist_repo.count(q=None)
+    total_albums = await album_repo.count(artist_id=None, q=None)
+    genres = await track_repo.genres()
+    disk = await storage.disk_usage()
+
+    return StorageStatsOut(
+        total_tracks=stats.total_tracks,
+        total_artists=total_artists,
+        total_albums=total_albums,
+        total_size=stats.total_size,
+        total_duration_seconds=stats.total_duration_seconds,
+        largest_track_size=stats.largest_track_size,
+        earliest_added=stats.earliest_added,
+        latest_added=stats.latest_added,
+        by_format=[
+            FormatBreakdownOut(
+                file_format=f.file_format,
+                track_count=f.track_count,
+                total_size=f.total_size,
+            )
+            for f in stats.by_format
+        ],
+        by_metadata_status=stats.by_metadata_status,
+        by_source=stats.by_source,
+        top_genres=[
+            GenreCountOut(genre=genre, track_count=count)
+            for genre, count in genres[:_TOP_GENRES]
+        ],
+        disk=DiskUsageOut(total=disk.total, used=disk.used, free=disk.free) if disk else None,
+    )
 
 
 @router.get("/duplicates")

app/domain/entities/__init__.py

@@ -6,7 +6,12 @@ from app.domain.entities.history import PlayHistoryEntry
 from app.domain.entities.like import Like
 from app.domain.entities.metadata import AudioTags, Fingerprint, RecordingMatch
 from app.domain.entities.playlist import Playlist
-from app.domain.entities.storage import ObjectStat
+from app.domain.entities.storage import (
+    DiskUsage,
+    FormatBreakdown,
+    LibraryStats,
+    ObjectStat,
+)
 from app.domain.entities.track import Artist, Track
 from app.domain.entities.user import Credentials, SubsonicCredentials, User
 
@@ -16,7 +21,10 @@ __all__ = [
     "AudioTags",
     "CoverArt",
     "Credentials",
+    "DiskUsage",
     "Fingerprint",
+    "FormatBreakdown",
+    "LibraryStats",
     "Like",
     "ObjectStat",
     "PlayHistoryEntry",

app/domain/entities/storage.py

@@ -1,5 +1,6 @@
 """Value objects for file storage."""
 
+import datetime as dt
 from dataclasses import dataclass
 
 
@@ -7,3 +8,39 @@ from dataclasses import dataclass
 class ObjectStat:
     size: int
     content_type: str | None
+
+
+@dataclass(frozen=True, slots=True)
+class DiskUsage:
+    """Capacity of the volume backing the media store. ``None`` for backends
+    (e.g. object stores) that expose no notion of total disk capacity."""
+
+    total: int
+    used: int
+    free: int
+
+
+@dataclass(frozen=True, slots=True)
+class FormatBreakdown:
+    """Per-container-format slice of the library (e.g. ``flac`` → 312 tracks)."""
+
+    file_format: str
+    track_count: int
+    total_size: int
+
+
+@dataclass(frozen=True, slots=True)
+class LibraryStats:
+    """Aggregate facts about everything the instance has stored. Computed from
+    the catalogue (DB), not the filesystem — ``total_size`` is the sum of the
+    recorded ``file_size`` of every track."""
+
+    total_tracks: int
+    total_size: int
+    total_duration_seconds: int
+    by_format: list[FormatBreakdown]
+    by_metadata_status: dict[str, int]
+    by_source: dict[str, int]
+    largest_track_size: int
+    earliest_added: dt.datetime | None
+    latest_added: dt.datetime | None

app/domain/ports.py

@@ -17,7 +17,9 @@ from app.domain.entities import (
     AudioTags,
     CoverArt,
     Credentials,
+    DiskUsage,
     Fingerprint,
+    LibraryStats,
     Like,
     ObjectStat,
     PlayHistoryEntry,
@@ -98,6 +100,10 @@ class FileStorage(Protocol):
     async def exists(self, key: str) -> bool: ...
     async def delete(self, key: str) -> None: ...
     def as_local_path(self, key: str) -> AbstractAsyncContextManager[Path]: ...
+    async def disk_usage(self) -> DiskUsage | None:
+        """Capacity of the volume backing the store, or ``None`` when the
+        backend has no addressable disk (e.g. an object store)."""
+        ...
 
 
 class ArtistRepository(Protocol):
@@ -128,9 +134,11 @@ class TrackRepository(Protocol):
         added_by: uuid.UUID | None,
     ) -> Track: ...
     async def delete(self, track_id: uuid.UUID) -> None: ...
-    # genres must come before ``list`` — the method named ``list`` shadows the
+    # genres / library_stats must come before ``list`` — the method named
-    # builtin in later annotations (same pattern as AlbumRepository below).
+    # ``list`` shadows the builtin in later annotations (same pattern as
+    # AlbumRepository below).
     async def genres(self) -> list[tuple[str, int]]: ...
+    async def library_stats(self) -> LibraryStats: ...
     async def list(
         self,
         *,

app/infrastructure/db/repositories/track_repository.py

@@ -6,6 +6,7 @@ import uuid
 from sqlalchemy import func, select
 from sqlalchemy.ext.asyncio import AsyncSession
 
+from app.domain.entities.storage import FormatBreakdown, LibraryStats
 from app.domain.entities.track import Track
 from app.domain.errors import NotFoundError
 from app.infrastructure.db.models.artist import ArtistModel
@@ -106,6 +107,63 @@ class SqlAlchemyTrackRepository:
         ).all()
         return [(row.genre, row.cnt) for row in rows]
 
+    async def library_stats(self) -> LibraryStats:
+        """One-shot aggregate over the whole catalogue (no pagination). Defined
+        before ``list`` for the same shadowing reason as ``genres``."""
+        totals = (
+            await self._session.execute(
+                select(
+                    func.count(TrackModel.id),
+                    func.coalesce(func.sum(TrackModel.file_size), 0),
+                    func.coalesce(func.sum(TrackModel.duration_seconds), 0),
+                    func.coalesce(func.max(TrackModel.file_size), 0),
+                    func.min(TrackModel.created_at),
+                    func.max(TrackModel.created_at),
+                )
+            )
+        ).one()
+
+        fmt_rows = (
+            await self._session.execute(
+                select(
+                    TrackModel.file_format,
+                    func.count(TrackModel.id),
+                    func.coalesce(func.sum(TrackModel.file_size), 0),
+                )
+                .group_by(TrackModel.file_format)
+                .order_by(func.sum(TrackModel.file_size).desc())
+            )
+        ).all()
+
+        status_rows = (
+            await self._session.execute(
+                select(TrackModel.metadata_status, func.count(TrackModel.id)).group_by(
+                    TrackModel.metadata_status
+                )
+            )
+        ).all()
+
+        source_rows = (
+            await self._session.execute(
+                select(TrackModel.source, func.count(TrackModel.id)).group_by(TrackModel.source)
+            )
+        ).all()
+
+        return LibraryStats(
+            total_tracks=totals[0],
+            total_size=totals[1],
+            total_duration_seconds=totals[2],
+            largest_track_size=totals[3],
+            earliest_added=totals[4],
+            latest_added=totals[5],
+            by_format=[
+                FormatBreakdown(file_format=fmt, track_count=cnt, total_size=size)
+                for fmt, cnt, size in fmt_rows
+            ],
+            by_metadata_status={status: cnt for status, cnt in status_rows},
+            by_source={source: cnt for source, cnt in source_rows},
+        )
+
     async def list(
         self,
         *,

app/infrastructure/storage/local.py

@@ -8,7 +8,7 @@ from pathlib import Path
 
 import anyio
 
-from app.domain.entities.storage import ObjectStat
+from app.domain.entities.storage import DiskUsage, ObjectStat
 from app.domain.errors import StorageError
 
 _EXT_CONTENT_TYPE: dict[str, str] = {
@@ -78,6 +78,15 @@ class LocalFileStorage:
     async def delete(self, key: str) -> None:
         (self._media_path / key).unlink(missing_ok=True)
 
+    async def disk_usage(self) -> DiskUsage | None:
+        # The media root may not exist yet on a fresh instance — walk up to the
+        # nearest existing ancestor so we still report the underlying volume.
+        path = self._media_path
+        while not path.exists() and path != path.parent:
+            path = path.parent
+        usage = await anyio.to_thread.run_sync(shutil.disk_usage, str(path))
+        return DiskUsage(total=usage.total, used=usage.used, free=usage.free)
+
     def as_local_path(self, key: str) -> AbstractAsyncContextManager[Path]:
         return self._as_local_path_cm(key)
 

app/infrastructure/storage/s3.py

@@ -127,6 +127,10 @@ class S3FileStorage:
             except ClientError as exc:
                 raise StorageError(str(exc)) from exc
 
+    async def disk_usage(self) -> None:
+        # Object stores have no fixed-capacity volume to report.
+        return None
+
     def as_local_path(self, key: str) -> AbstractAsyncContextManager[Path]:
         return self._as_local_path_cm(key)
 

tests/test_storage_stats_api.py

@@ -0,0 +1,138 @@
+"""Integration tests for the storage statistics endpoint (§A6).
+
+Requires a reachable Postgres; skips otherwise.
+"""
+
+import asyncio
+import os
+from collections.abc import AsyncIterator
+from pathlib import Path
+
+import pytest
+from app.core.config import get_settings
+from app.infrastructure.db import Base, dispose_engine, get_engine, session_scope
+from app.infrastructure.db.repositories import (
+    SqlAlchemyRefreshTokenRepository,
+    SqlAlchemyUserRepository,
+)
+from asgi_lifespan import LifespanManager
+from httpx import ASGITransport, AsyncClient
+
+pytestmark = pytest.mark.asyncio
+
+_db_reachable_cache: bool | None = None
+
+
+async def _db_reachable() -> bool:
+    global _db_reachable_cache
+    if _db_reachable_cache is not None:
+        return _db_reachable_cache
+
+    from sqlalchemy import text
+
+    try:
+        async with asyncio.timeout(3):
+            async with get_engine().connect() as conn:
+                await conn.execute(text("SELECT 1"))
+        _db_reachable_cache = True
+    except Exception:
+        _db_reachable_cache = False
+    return _db_reachable_cache
+
+
+@pytest.fixture
+async def api(tmp_path: Path) -> AsyncIterator[AsyncClient]:
+    if not await _db_reachable():
+        pytest.skip("Postgres not reachable — integration test skipped.")
+
+    os.environ["MEDIA_PATH"] = str(tmp_path)
+    get_settings.cache_clear()
+
+    import app.infrastructure.storage.provider as _storage_provider
+
+    _storage_provider._storage = None
+
+    try:
+        async with get_engine().begin() as conn:
+            await conn.run_sync(Base.metadata.drop_all)
+            await conn.run_sync(Base.metadata.create_all)
+
+        from app.application.user_service import UserService
+        from app.core.security import Argon2PasswordHasher
+
+        async with session_scope() as session:
+            await UserService(
+                users=SqlAlchemyUserRepository(session),
+                refresh_tokens=SqlAlchemyRefreshTokenRepository(session),
+                hasher=Argon2PasswordHasher(),
+            ).create_user(username="testuser", password="testpass1", is_superuser=False)
+
+        from app.main import create_app
+
+        app = create_app()
+        async with LifespanManager(app):
+            transport = ASGITransport(app=app)
+            async with AsyncClient(transport=transport, base_url="http://test") as client:
+                yield client
+
+        async with get_engine().begin() as conn:
+            await conn.run_sync(Base.metadata.drop_all)
+        await dispose_engine()
+    finally:
+        _storage_provider._storage = None
+        os.environ.pop("MEDIA_PATH", None)
+        get_settings.cache_clear()
+
+
+async def _login(api: AsyncClient) -> str:
+    resp = await api.post(
+        "/api/v1/auth/login", json={"username": "testuser", "password": "testpass1"}
+    )
+    assert resp.status_code == 200
+    return str(resp.json()["access_token"])
+
+
+async def _upload(api: AsyncClient, token: str, *, name: str) -> None:
+    # Vary the bytes per file so dedup (by content) keeps them distinct.
+    audio = (f"fake audio bytes for storage stats test {name}".encode()) * 10
+    resp = await api.post(
+        "/api/v1/upload",
+        files={"file": (name, audio, "audio/mpeg")},
+        headers={"Authorization": f"Bearer {token}"},
+    )
+    assert resp.status_code == 200, resp.text
+
+
+async def test_storage_stats_requires_auth(api: AsyncClient) -> None:
+    resp = await api.get("/api/v1/storage")
+    assert resp.status_code == 401
+
+
+async def test_storage_stats_empty_library(api: AsyncClient) -> None:
+    token = await _login(api)
+    resp = await api.get("/api/v1/storage", headers={"Authorization": f"Bearer {token}"})
+    assert resp.status_code == 200, resp.text
+    body = resp.json()
+    assert body["total_tracks"] == 0
+    assert body["total_size"] == 0
+    assert body["by_format"] == []
+    # Local backend reports a real disk in the test environment.
+    assert body["disk"] is not None
+    assert body["disk"]["total"] > 0
+
+
+async def test_storage_stats_counts_uploads(api: AsyncClient) -> None:
+    token = await _login(api)
+    await _upload(api, token, name="one.mp3")
+    await _upload(api, token, name="two.mp3")
+
+    resp = await api.get("/api/v1/storage", headers={"Authorization": f"Bearer {token}"})
+    assert resp.status_code == 200, resp.text
+    body = resp.json()
+    assert body["total_tracks"] == 2
+    assert body["total_size"] > 0
+    assert body["total_artists"] >= 1
+    fmt = {f["file_format"]: f for f in body["by_format"]}
+    assert "mp3" in fmt
+    assert fmt["mp3"]["track_count"] == 2
+    assert sum(body["by_source"].values()) == 2