refactor(reader): the HTTP layer reads through queries and writes through the service

Feed, playlists, saved views, tags and the Home pins do no database work in their routes any more:
reads go through reader/queries (and feedquery for a feed page, its counts and facets), writes
through reader/service and discover/pins, which flush; the handlers commit. Reader is fenced below
its HTTP layer too: its owner filters go through userscope, and the catalog's jobs ask Reader
instead of joining its tables (the auto-tagger's system tags, the cleanup jobs' keep rule, the
maintenance notice). A playlist sync's catalog ingest moves to sync/videos.

backend/app/feedquery.py

@@ -1,10 +1,11 @@
-"""Feed read-model: the pure query-building and row-serialization layer behind the feed.
+"""Feed read-model: Reader's query-building, paging and row serialization behind the feed.
 
-Extracted from `routes/feed.py` so the read-model has one home instead of living inside the
-router module — the feed route handlers and the playlist-detail query share these helpers (the
-projection, the filter builder, and keyset paging). Nothing here defines a route or reaches for
-request state; it's all `(db, user, params) -> query`, and a malformed cursor raises a plain
-`ValueError` for the route handler to translate (the tsquery sanitizer lives in `app.utils`).
+One home for the read-model rather than the router module: the feed routes, the playlist-detail
+query and Home share these helpers (the projection, the filter builder, and keyset paging), and the
+feed's routes only validate and answer — a page, its counts and its facets are built here. Nothing
+here defines a route or reaches for request state; it's all `(db, user, params) -> query`, and a
+malformed cursor raises `BadCursor` for the route handler to translate (the tsquery sanitizer lives
+in `app.utils`).
 """
 
 import base64
@@ -28,6 +29,7 @@ from app.models import (
 )
 from app.reader.models import ChannelTag, Playlist, PlaylistItem, Tag, VideoState
 from app.utils import iso, like_escape, to_tsquery_str
+from app.userscope import owned_by
 
 
 def _channel_url(channel_id: str, handle: str | None) -> str:
@@ -44,7 +46,7 @@ def _saved_expr(user: User):
         .select_from(PlaylistItem)
         .join(Playlist, Playlist.id == PlaylistItem.playlist_id)
         .where(
-            Playlist.user_id == user.id,
+            owned_by(Playlist.user_id, user.id),
             Playlist.kind == "watch_later",
             PlaylistItem.video_id == Video.id,
         )
@@ -99,7 +101,7 @@ def serialize(row) -> dict:
 
 def _tag_visible(user: User):
     """A ChannelTag row this user may see: a shared system tag (user_id NULL) or their own."""
-    return or_(ChannelTag.user_id.is_(None), ChannelTag.user_id == user.id)
+    return or_(ChannelTag.user_id.is_(None), owned_by(ChannelTag.user_id, user.id))
 
 
 # The pseudo-category of a selected tag id no Tag row answers (a saved view or the feed state outlives
@@ -118,7 +120,7 @@ def tags_by_category(db: Session, user: User, tag_ids: list[int]) -> dict[str, l
     if not tag_ids:
         return {}  # skip the pointless `WHERE id IN ()` round-trip on the no-tag-filter hot path
     out: dict[str, list[int]] = {}
-    visible = or_(Tag.user_id.is_(None), Tag.user_id == user.id)
+    visible = or_(Tag.user_id.is_(None), owned_by(Tag.user_id, user.id))
     for tid, cat in db.execute(
         select(Tag.id, Tag.category).where(Tag.id.in_(tag_ids), visible)
     ).all():
@@ -138,7 +140,7 @@ def not_blocked_cond(user: User):
     position — and the one query that copied only PART of this predicate set is exactly how that
     video came back as the landing page's suggestion after the user had said "never again"."""
     return Video.channel_id.notin_(
-        select(BlockedChannel.channel_id).where(BlockedChannel.user_id == user.id)
+        select(BlockedChannel.channel_id).where(owned_by(BlockedChannel.user_id, user.id))
     )
 
 
@@ -183,7 +185,7 @@ def filtered_query(
             Subscription,
             and_(
                 Subscription.channel_id == Video.channel_id,
-                Subscription.user_id == user.id,
+                owned_by(Subscription.user_id, user.id),
             ),
         )
     else:
@@ -195,12 +197,12 @@ def filtered_query(
             Subscription,
             and_(
                 Subscription.channel_id == Video.channel_id,
-                Subscription.user_id == user.id,
+                owned_by(Subscription.user_id, user.id),
                 Subscription.hidden.is_(False),
             ),
         ).outerjoin(
             SearchFind,
-            and_(SearchFind.video_id == Video.id, SearchFind.user_id == user.id),
+            and_(SearchFind.video_id == Video.id, owned_by(SearchFind.user_id, user.id)),
         )
 
     # The state-gated views (watched/hidden/in_progress) only ever return videos that HAVE a
@@ -223,8 +225,8 @@ def filtered_query(
     # catalog. Applied in BOTH scopes; the channel page reaches its ephemeral videos by
     # asking for scope=all + channel_ids (the channel is in this accessible set).
     accessible_explore = (
-        select(Subscription.channel_id).where(Subscription.user_id == user.id)
-    ).union(select(ExploredChannel.channel_id).where(ExploredChannel.user_id == user.id))
+        select(Subscription.channel_id).where(owned_by(Subscription.user_id, user.id))
+    ).union(select(ExploredChannel.channel_id).where(owned_by(ExploredChannel.user_id, user.id)))
     query = query.where(
         or_(
             Video.via_explore.is_(False),
@@ -342,7 +344,7 @@ def filtered_query(
     if untagged:
         query = query.where(
             Video.channel_id.notin_(
-                select(ChannelTag.channel_id).where(ChannelTag.user_id == user.id)
+                select(ChannelTag.channel_id).where(owned_by(ChannelTag.user_id, user.id))
             )
         )
 
@@ -692,3 +694,98 @@ def decode_cursor(keys: list[dict], cursor: str) -> tuple[list, str, datetime |
         # Framework-free: the route handler translates this into an HTTP 400 so the
         # read-model stays web-layer-agnostic (see routes/feed.get_feed).
         raise ValueError("Invalid feed cursor") from exc
+
+
+class BadCursor(ValueError):
+    """A `cursor` this module did not write (or one from another sort): the caller's bad input."""
+
+
+def feed_page(
+    db: Session,
+    user: User,
+    params: dict,
+    *,
+    sort: str,
+    seed: int,
+    limit: int,
+    cursor: str | None,
+    lang: str,
+) -> dict:
+    """One page of the feed, and the cursor for the next. A malformed cursor raises `BadCursor`."""
+    query, rank_expr = filtered_query(db, user, **params)
+    keys = sort_keys(sort, seed, rank_expr, lang)
+
+    vals, cursor_id, window = None, None, None
+    if cursor:
+        try:
+            vals, cursor_id, window = decode_cursor(keys, cursor)
+        except ValueError as e:
+            raise BadCursor(str(e)) from e
+    ranked = sort == "relevance" and rank_expr is not None
+    if ranked and not cursor:
+        window = rank_window_start(db, query)
+    if ranked and window is not None:
+        keys = sort_keys(sort, seed, windowed_rank(rank_expr, window), lang)
+
+    # Expose each key column on the row so we can build the next cursor from the last item.
+    query = query.add_columns(*[k["expr"].label(f"_k{i}") for i, k in enumerate(keys)])
+    if vals is not None:
+        for k, v in zip(keys, vals, strict=True):
+            k["value"] = v
+    if ranked and window is not None:
+        rows = windowed_relevance_rows(db, query, keys, window, cursor_id, limit + 1)
+    else:
+        query = query.order_by(*order_by(keys))
+        if cursor_id is not None:
+            query = query.where(keyset_predicate(keys, cursor_id))
+        rows = db.execute(query.limit(limit + 1)).all()
+    has_more = len(rows) > limit
+    page = rows[:limit]
+    return {
+        "items": [serialize(r) for r in page],
+        "next_cursor": (
+            encode_cursor(keys, page[-1], window if ranked else None)
+            if (has_more and page)
+            else None
+        ),
+        "has_more": has_more,
+        "limit": limit,
+    }
+
+
+def feed_count(db: Session, user: User, **params) -> int:
+    """How many videos the filters match — the reference oracle `feed_summary`'s count is tested
+    against."""
+    query, _rank = filtered_query(db, user, **params)
+    return db.scalar(select(func.count()).select_from(query.subquery())) or 0
+
+
+def facet_counts(db: Session, user: User, **params) -> dict[int, int]:
+    """Per-tag channel counts for the current filter context, one pass per category — the reference
+    oracle `feed_summary`'s facets are tested against.
+
+    Each category is counted with every other filter applied but its own selections ignored
+    (drill-down faceting: selecting one topic doesn't zero out the rest). A conjunctive (AND)
+    category keeps them applied, so each remaining chip narrows to channels that ALSO have every
+    selected tag, and tags that can't co-occur drop to zero."""
+    visible = _tag_visible(user)
+    counts: dict[int, int] = {}
+    for category in ("language", "topic", "other"):
+        conjunctive = params.get("tag_modes", {}).get(category) == "and"
+        base, _rank = filtered_query(
+            db,
+            user,
+            **{**params, "exclude_tag_category": None if conjunctive else category},
+        )
+        channels = base.with_only_columns(Video.channel_id).distinct().subquery()
+        rows = db.execute(
+            select(ChannelTag.tag_id, func.count(func.distinct(ChannelTag.channel_id)))
+            .select_from(channels)
+            .join(ChannelTag, ChannelTag.channel_id == channels.c.channel_id)
+            .join(Tag, and_(Tag.id == ChannelTag.tag_id, Tag.category == category))
+            .where(visible)
+            .group_by(ChannelTag.tag_id)
+        ).all()
+        for tag_id, count in rows:
+            counts[tag_id] = count
+    return counts