feat(gallery): composable scroll filter (multi-tag AND, media, sort)

Phase 1 backend for the gallery filter bar. Extends scroll/timeline/jump
from a single mutually-exclusive filter to a composable one:

- tag_ids: image must carry ALL of them (one correlated EXISTS per tag —
  AND, no row multiplication), replacing the single-tag JOIN.
- artist_id composes with tags; media_type ('image'|'video') narrows by
  mime; post_id stays the exclusive post-detail path.
- sort ('newest'|'oldest') flips the effective_date/id cursor comparison
  and ordering; the cursor value is unchanged (direction comes from the
  request). jump_cursor honors sort too.
- Shared _apply_scope helper applied across scroll/timeline/jump so the
  timeline sidebar reflects the filtered set. API _parse_filters parses
  tag_id (comma list), artist_id, media, sort.

Tests: multi-tag AND, media filter, sort reversal (service + API);
post_id-excludes-others; single tag_id back-compat.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.claude/scheduled_tasks.lock

@@ -0,0 +1 @@
+{"sessionId":"168e9de3-9f44-4fca-8fa6-09c87523c11e","pid":1470750,"procStart":"11499472","acquiredAt":1780543996001}

backend/app/api/gallery.py

@@ -8,26 +8,42 @@ from ..services.gallery_service import GalleryService
 gallery_bp = Blueprint("gallery", __name__, url_prefix="/api/gallery")
 
 
+def _parse_filters():
+    """Parse the composable gallery filters from query args. Raises
+    ValueError (→ 400) on malformed ids. `tag_id` accepts a single id or a
+    comma-separated list (AND); `media` is image|video; `sort` is
+    newest|oldest."""
+    tag_raw = request.args.get("tag_id")
+    tag_ids = (
+        [int(x) for x in tag_raw.split(",") if x.strip()] if tag_raw else None
+    ) or None
+    post_id_raw = request.args.get("post_id")
+    post_id = int(post_id_raw) if post_id_raw else None
+    artist_id_raw = request.args.get("artist_id")
+    artist_id = int(artist_id_raw) if artist_id_raw else None
+    media = request.args.get("media")
+    media_type = media if media in ("image", "video") else None
+    sort = request.args.get("sort")
+    sort = sort if sort in ("newest", "oldest") else "newest"
+    return tag_ids, post_id, artist_id, media_type, sort
+
+
 @gallery_bp.route("/scroll", methods=["GET"])
 async def scroll():
     cursor = request.args.get("cursor") or None
     try:
         limit = int(request.args.get("limit", "50"))
+        tag_ids, post_id, artist_id, media_type, sort = _parse_filters()
     except ValueError:
-        return jsonify({"error": "limit must be an integer"}), 400
-    tag_id_raw = request.args.get("tag_id")
-    tag_id = int(tag_id_raw) if tag_id_raw else None
-    post_id_raw = request.args.get("post_id")
-    post_id = int(post_id_raw) if post_id_raw else None
-    artist_id_raw = request.args.get("artist_id")
-    artist_id = int(artist_id_raw) if artist_id_raw else None
+        return jsonify({"error": "invalid filter or limit parameter"}), 400
 
     async with get_session() as session:
         svc = GalleryService(session)
         try:
             page = await svc.scroll(
-                cursor=cursor, limit=limit, tag_id=tag_id,
+                cursor=cursor, limit=limit, tag_ids=tag_ids,
                 post_id=post_id, artist_id=artist_id,
+                media_type=media_type, sort=sort,
             )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400
@@ -58,17 +74,16 @@ async def scroll():
 
 @gallery_bp.route("/timeline", methods=["GET"])
 async def timeline():
-    tag_id_raw = request.args.get("tag_id")
-    tag_id = int(tag_id_raw) if tag_id_raw else None
-    post_id_raw = request.args.get("post_id")
-    post_id = int(post_id_raw) if post_id_raw else None
-    artist_id_raw = request.args.get("artist_id")
-    artist_id = int(artist_id_raw) if artist_id_raw else None
+    try:
+        tag_ids, post_id, artist_id, media_type, _sort = _parse_filters()
+    except ValueError:
+        return jsonify({"error": "invalid filter parameter"}), 400
     async with get_session() as session:
         svc = GalleryService(session)
         try:
             buckets = await svc.timeline(
-                tag_id=tag_id, post_id=post_id, artist_id=artist_id
+                tag_ids=tag_ids, post_id=post_id, artist_id=artist_id,
+                media_type=media_type,
             )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400
@@ -82,20 +97,16 @@ async def jump():
     try:
         year = int(request.args["year"])
         month = int(request.args["month"])
+        tag_ids, post_id, artist_id, media_type, sort = _parse_filters()
     except (KeyError, ValueError):
         return jsonify({"error": "year and month query params required"}), 400
-    tag_id_raw = request.args.get("tag_id")
-    tag_id = int(tag_id_raw) if tag_id_raw else None
-    post_id_raw = request.args.get("post_id")
-    post_id = int(post_id_raw) if post_id_raw else None
-    artist_id_raw = request.args.get("artist_id")
-    artist_id = int(artist_id_raw) if artist_id_raw else None
     async with get_session() as session:
         svc = GalleryService(session)
         try:
             cursor = await svc.jump_cursor(
-                year=year, month=month, tag_id=tag_id,
+                year=year, month=month, tag_ids=tag_ids,
                 post_id=post_id, artist_id=artist_id,
+                media_type=media_type, sort=sort,
             )
         except ValueError as exc:
             return jsonify({"error": str(exc)}), 400

backend/app/services/gallery_service.py

@@ -118,13 +118,43 @@ def thumbnail_url(thumbnail_path: str | None, sha256_hex: str, mime: str) -> str
     return f"/images/thumbs/{bucket}/{sha256_hex}{ext}"
 
 
-def _require_single_filter(tag_id, post_id, artist_id) -> None:
-    if sum(x is not None for x in (tag_id, post_id, artist_id)) > 1:
+def _require_single_filter(tag_ids, post_id, artist_id) -> None:
+    """post_id is the post-detail view — it can't combine with the
+    composable filters. tag_ids + artist_id (+ media_type) compose freely
+    (AND)."""
+    if post_id is not None and (tag_ids or artist_id is not None):
         raise ValueError(
-            "tag_id, post_id, artist_id are mutually exclusive"
+            "post_id cannot be combined with tag or artist filters"
         )
 
 
+def _apply_scope(stmt, *, tag_ids, post_id, artist_id, media_type):
+    """Apply the composable gallery filters to a statement already joined
+    to Post via _outer_join_primary_post.
+
+    - tag_ids: image must carry ALL of them — one correlated EXISTS per tag
+      (AND), which avoids the row-multiplication a multi-join would cause.
+    - post_id / artist_id: provenance EXISTS (post_id is exclusive, guarded
+      by _require_single_filter).
+    - media_type: 'image' | 'video' narrows by mime prefix.
+    """
+    for tid in tag_ids or []:
+        stmt = stmt.where(
+            exists().where(
+                image_tag.c.image_record_id == ImageRecord.id,
+                image_tag.c.tag_id == tid,
+            )
+        )
+    prov = _provenance_clause(post_id, artist_id)
+    if prov is not None:
+        stmt = stmt.where(prov)
+    if media_type == "image":
+        stmt = stmt.where(ImageRecord.mime.like("image/%"))
+    elif media_type == "video":
+        stmt = stmt.where(ImageRecord.mime.like("video/%"))
+    return stmt
+
+
 def _provenance_clause(post_id, artist_id):
     """Correlated EXISTS clause (NOT a join) so an image with multiple
     matching provenance rows is returned exactly once and the
@@ -180,35 +210,43 @@ class GalleryService:
         self,
         cursor: str | None,
         limit: int = 50,
-        tag_id: int | None = None,
+        tag_ids: list[int] | None = None,
         post_id: int | None = None,
         artist_id: int | None = None,
+        media_type: str | None = None,
+        sort: str = "newest",
     ) -> GalleryPage:
         if limit < 1 or limit > 200:
             raise ValueError("limit must be between 1 and 200")
-        _require_single_filter(tag_id, post_id, artist_id)
+        _require_single_filter(tag_ids, post_id, artist_id)
 
         eff = _effective_date_col()
         stmt = select(ImageRecord, Post.post_date, eff.label("eff"))
         stmt = _outer_join_primary_post(stmt)
-        if tag_id is not None:
-            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
-                image_tag.c.tag_id == tag_id
-            )
-        prov = _provenance_clause(post_id, artist_id)
-        if prov is not None:
-            stmt = stmt.where(prov)
+        stmt = _apply_scope(
+            stmt, tag_ids=tag_ids, post_id=post_id,
+            artist_id=artist_id, media_type=media_type,
+        )
 
+        descending = sort != "oldest"
         if cursor:
             cur_ts, cur_id = decode_cursor(cursor)
-            stmt = stmt.where(
-                or_(
-                    eff < cur_ts,
-                    and_(eff == cur_ts, ImageRecord.id < cur_id),
+            # The cursor is just (last eff, last id); the request's sort
+            # decides which side of it the next page lies on.
+            if descending:
+                stmt = stmt.where(
+                    or_(eff < cur_ts, and_(eff == cur_ts, ImageRecord.id < cur_id))
+                )
+            else:
+                stmt = stmt.where(
+                    or_(eff > cur_ts, and_(eff == cur_ts, ImageRecord.id > cur_id))
                 )
-            )
 
-        stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc()).limit(limit + 1)
+        if descending:
+            stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc())
+        else:
+            stmt = stmt.order_by(eff.asc(), ImageRecord.id.asc())
+        stmt = stmt.limit(limit + 1)
         rows = (await self.session.execute(stmt)).all()
 
         next_cursor = None
@@ -244,9 +282,10 @@ class GalleryService:
 
     async def timeline(
         self,
-        tag_id: int | None = None,
+        tag_ids: list[int] | None = None,
         post_id: int | None = None,
         artist_id: int | None = None,
+        media_type: str | None = None,
     ) -> list[TimelineBucket]:
         eff = _effective_date_col()
         year_col = func.date_part("year", eff).label("yr")
@@ -255,25 +294,23 @@ class GalleryService:
             year_col, month_col, func.count(ImageRecord.id).label("cnt")
         )
         stmt = _outer_join_primary_post(stmt)
-        _require_single_filter(tag_id, post_id, artist_id)
-        if tag_id is not None:
-            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
-                image_tag.c.tag_id == tag_id
-            )
-        prov = _provenance_clause(post_id, artist_id)
-        if prov is not None:
-            stmt = stmt.where(prov)
+        _require_single_filter(tag_ids, post_id, artist_id)
+        stmt = _apply_scope(
+            stmt, tag_ids=tag_ids, post_id=post_id,
+            artist_id=artist_id, media_type=media_type,
+        )
         stmt = stmt.group_by(year_col, month_col).order_by(year_col.desc(), month_col.desc())
         rows = (await self.session.execute(stmt)).all()
         return [TimelineBucket(year=int(r.yr), month=int(r.mo), count=int(r.cnt)) for r in rows]
 
     async def jump_cursor(
-        self, year: int, month: int, tag_id: int | None = None,
+        self, year: int, month: int, tag_ids: list[int] | None = None,
         post_id: int | None = None, artist_id: int | None = None,
+        media_type: str | None = None, sort: str = "newest",
     ) -> str | None:
-        """Returns a cursor that, when passed to scroll(), positions at the
-        first image of the given year-month (by effective_date, not
-        created_at). None if the bucket is empty.
+        """Returns a cursor that, when passed to scroll() with the same sort,
+        positions at the first image of the given year-month. None if the
+        bucket is empty.
         """
         from sqlalchemy import extract
 
@@ -283,22 +320,24 @@ class GalleryService:
             extract("month", eff) == month,
         )
         stmt = _outer_join_primary_post(stmt)
-        _require_single_filter(tag_id, post_id, artist_id)
-        if tag_id is not None:
-            stmt = stmt.join(image_tag, image_tag.c.image_record_id == ImageRecord.id).where(
-                image_tag.c.tag_id == tag_id
-            )
-        prov = _provenance_clause(post_id, artist_id)
-        if prov is not None:
-            stmt = stmt.where(prov)
-        stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc()).limit(1)
-        first = (await self.session.execute(stmt)).first()
+        _require_single_filter(tag_ids, post_id, artist_id)
+        stmt = _apply_scope(
+            stmt, tag_ids=tag_ids, post_id=post_id,
+            artist_id=artist_id, media_type=media_type,
+        )
+        descending = sort != "oldest"
+        if descending:
+            stmt = stmt.order_by(eff.desc(), ImageRecord.id.desc())
+        else:
+            stmt = stmt.order_by(eff.asc(), ImageRecord.id.asc())
+        first = (await self.session.execute(stmt.limit(1))).first()
         if first is None:
             return None
         record, eff_date = first
-        # Cursor is exclusive; we encode a cursor with id+1 so the row itself
-        # is the first result in the next scroll().
-        return encode_cursor(eff_date, record.id + 1)
+        # Cursor is exclusive; nudge the id one past the boundary row (in the
+        # scan direction) so the row itself is the first result of scroll().
+        boundary = record.id + 1 if descending else record.id - 1
+        return encode_cursor(eff_date, boundary)
 
     async def get_image_with_tags(self, image_id: int) -> dict | None:
         record = await self.session.get(ImageRecord, image_id)

tests/test_api_gallery.py

@@ -59,3 +59,21 @@ async def test_jump_requires_year_month(client):
 async def test_image_detail_404_when_missing(client):
     resp = await client.get("/api/gallery/image/99999")
     assert resp.status_code == 404
+
+
+@pytest.mark.asyncio
+async def test_scroll_sort_param_reverses(client, db):
+    await _seed(db, 3)
+    newest = await (await client.get("/api/gallery/scroll?limit=10&sort=newest")).get_json()
+    oldest = await (await client.get("/api/gallery/scroll?limit=10&sort=oldest")).get_json()
+    ids_new = [i["id"] for i in newest["images"]]
+    ids_old = [i["id"] for i in oldest["images"]]
+    assert ids_old == list(reversed(ids_new))
+
+
+@pytest.mark.asyncio
+async def test_scroll_media_param(client, db):
+    await _seed(db, 2)  # only image/jpeg seeded
+    resp = await client.get("/api/gallery/scroll?limit=10&media=video")
+    assert resp.status_code == 200
+    assert (await resp.get_json())["images"] == []

tests/test_gallery_provenance_filter.py

@@ -81,10 +81,10 @@ async def test_scroll_artist_id_filter(db):
 
 
 @pytest.mark.asyncio
-async def test_mutually_exclusive_filters_raise(db):
+async def test_post_id_excludes_other_filters(db):
     svc = GalleryService(db)
     with pytest.raises(ValueError):
-        await svc.scroll(cursor=None, limit=10, tag_id=1, post_id=2)
+        await svc.scroll(cursor=None, limit=10, tag_ids=[1], post_id=2)
 
 
 @pytest.mark.asyncio

tests/test_gallery_service.py

@@ -87,7 +87,7 @@ async def test_scroll_with_tag_filter(db):
     )
 
     svc = GalleryService(db)
-    page = await svc.scroll(cursor=None, limit=10, tag_id=tag.id)
+    page = await svc.scroll(cursor=None, limit=10, tag_ids=[tag.id])
     assert len(page.images) == 1
     assert page.images[0].id == images[0].id
 
@@ -272,3 +272,53 @@ async def test_get_image_with_tags_includes_posted_at_when_present(db):
     assert payload["posted_at"] is not None
     # Image's own created_at is still surfaced separately.
     assert payload["created_at"] != payload["posted_at"]
+
+
+@pytest.mark.asyncio
+async def test_scroll_multi_tag_and(db):
+    images = await _seed_images(db, 5)
+    a = Tag(name="aa", kind=TagKind.general)
+    b = Tag(name="bb", kind=TagKind.general)
+    db.add_all([a, b])
+    await db.flush()
+    # images[0] carries BOTH tags; images[1] carries only a.
+    await db.execute(image_tag.insert().values([
+        {"image_record_id": images[0].id, "tag_id": a.id, "source": "manual"},
+        {"image_record_id": images[0].id, "tag_id": b.id, "source": "manual"},
+        {"image_record_id": images[1].id, "tag_id": a.id, "source": "manual"},
+    ]))
+    svc = GalleryService(db)
+    both = await svc.scroll(cursor=None, limit=10, tag_ids=[a.id, b.id])
+    assert [i.id for i in both.images] == [images[0].id]  # AND: only the both-tagged
+    just_a = await svc.scroll(cursor=None, limit=10, tag_ids=[a.id])
+    assert {i.id for i in just_a.images} == {images[0].id, images[1].id}
+
+
+@pytest.mark.asyncio
+async def test_scroll_media_filter(db):
+    imgs = await _seed_images(db, 2)  # image/jpeg
+    vid = ImageRecord(
+        path="/images/test/v.mp4", sha256="v" * 64, size_bytes=1,
+        mime="video/mp4", width=1, height=1,
+        origin="imported_filesystem", integrity_status="unknown",
+    )
+    vid.created_at = _now()
+    vid.effective_date = vid.created_at
+    db.add(vid)
+    await db.flush()
+    svc = GalleryService(db)
+    vids = await svc.scroll(cursor=None, limit=10, media_type="video")
+    assert [i.id for i in vids.images] == [vid.id]
+    pics = await svc.scroll(cursor=None, limit=10, media_type="image")
+    assert {i.id for i in pics.images} == {i.id for i in imgs}
+
+
+@pytest.mark.asyncio
+async def test_scroll_sort_oldest_reverses_order(db):
+    images = await _seed_images(db, 4)  # images[0] newest ... images[3] oldest
+    svc = GalleryService(db)
+    newest = await svc.scroll(cursor=None, limit=10)
+    oldest = await svc.scroll(cursor=None, limit=10, sort="oldest")
+    newest_ids = [i.id for i in newest.images]
+    assert newest_ids[0] == images[0].id
+    assert [i.id for i in oldest.images] == list(reversed(newest_ids))