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

Channels, search and sync do no database work in their routes any more: reads go through
catalog/queries, writes through catalog/service, and a live search's ingest is catalog/search.
What a catalog route needs from Reader (a playlist's channels, a user's tag links, the feed
projection of results) it asks reader/queries and reader/service. The scheduler and the runs page
read channel titles and the work queue through catalog/queries. Catalog is fenced below its HTTP
layer: its owner filters go through userscope, it reads no other unit's tables, and its ingest
jobs commit only where they are named.

backend/app/routes/scheduler.py

@@ -4,7 +4,6 @@ and the shared quota picture."""
 
 from fastapi import APIRouter, Depends
 from pydantic import BaseModel
-from sqlalchemy import and_, func, or_, select
 from sqlalchemy.orm import Session
 
 from app import audit, quota, state, sysconfig
@@ -13,7 +12,7 @@ from app.auth import admin_user
 from app.config import settings
 from app.db import get_db
 from app.models import User
-from app.catalog.models import Channel, Subscription, Video
+from app.catalog import queries as catalog_queries
 from app.scheduler import (
     JOB_INTERVALS,
     MAX_INTERVAL,
@@ -24,7 +23,6 @@ from app.scheduler import (
     trigger_all,
     trigger_job,
 )
-from app.sync.explore import followed_channel
 from app.sync.runner import estimate_deep_backfill
 from app.routes._common import not_found
 from app.refusal import refused
@@ -123,58 +121,14 @@ def get_scheduler(_: User = Depends(admin_user), db: Session = Depends(get_db))
     snap = scheduler_snapshot(db)
 
     # Work still queued (shared catalog, so these are instance-wide, not per-user).
-    deep_requested = (
-        select(Subscription.id)
-        .where(
-            Subscription.channel_id == Channel.id,
-            Subscription.deep_requested.is_(True),
-        )
-        .exists()
-    )
-    deep_channels = (
-        db.execute(select(Channel).where(Channel.backfill_done.is_(False), deep_requested))
-        .scalars()
-        .all()
-    )
-    deep_eta = estimate_deep_backfill(db, deep_channels)
-
-    queue = {
-        "channels_recent_pending": db.scalar(
-            # The same selection run_recent_backfill works through, or the card counts channels
-            # the job will never touch and never reaches zero.
-            select(func.count())
-            .select_from(Channel)
-            .where(Channel.recent_synced_at.is_(None), followed_channel())
-        )
-        or 0,
-        # The whole opted-in BACKLOG, deliberately not `run_deep_backfill`'s next-pass selection
-        # (which also wants `recent_synced_at`): the same figure /api/sync/my-status shows the user,
-        # and a channel missing its recent pull is one the same job tick fetches first, not one the
-        # job will never touch. Narrowing it here would under-report work that is genuinely queued.
-        "channels_deep_pending": deep_eta["channels_pending"],
-        "deep_eta_seconds": deep_eta["eta_seconds"],
-        "videos_pending_enrich": db.scalar(
-            select(func.count()).select_from(Video).where(Video.enriched_at.is_(None))
-        )
-        or 0,
-        "videos_pending_shorts": db.scalar(
-            select(func.count())
-            .select_from(Video)
-            .where(Video.shorts_probed.is_(False), Video.enriched_at.is_not(None))
-        )
-        or 0,
-        "videos_live_refresh": db.scalar(
-            select(func.count())
-            .select_from(Video)
-            .where(
-                or_(
-                    Video.live_status.in_(("live", "upcoming")),
-                    and_(Video.live_status == "was_live", Video.duration_seconds.is_(None)),
-                )
-            )
-        )
-        or 0,
-    }
+    deep_eta = estimate_deep_backfill(db, catalog_queries.deep_backlog(db))
+    queue = catalog_queries.work_queue(db)
+    # The whole opted-in BACKLOG, deliberately not `run_deep_backfill`'s next-pass selection
+    # (which also wants `recent_synced_at`): the same figure /api/sync/my-status shows the user,
+    # and a channel missing its recent pull is one the same job tick fetches first, not one the
+    # job will never touch. Narrowing it here would under-report work that is genuinely queued.
+    queue["channels_deep_pending"] = deep_eta["channels_pending"]
+    queue["deep_eta_seconds"] = deep_eta["eta_seconds"]
 
     used = quota.units_used_today(db)
     quota_info = {