fix(deferred): close backend correctness/efficiency tails from the hygiene sweep

Verified each deferred per-subsystem item against current source, then fixed the
real ones (tradeoffs left as-is, see siftlode-ops/CODE-HYGIENE.md closeout):

- search BUG-3: don't finalise shorts_probed on un-enriched stubs (enrichment
  failure/omitted rows) — restores the scheduler's enriched_at guard so a real
  Short can't leak into the feed and never get reclassified.
- downloads GC: 4th pass reaps orphaned errored, fileless, unreferenced assets
  (they carry no TTL, so the expiry passes never cleared them).
- downloads B6: quota/edit errors now return a structured {code,reason,limit}
  the trilingual client localises, instead of hardcoded English + dot-decimal GB.
- channels BB1: reset-backfill re-arms deep sync on every subscriber (bulk update)
  instead of 404ing when the admin isn't personally subscribed.
- channels BB2: enrich the stub on BOTH the normal and "already exists" desync
  path (nest the insert try inside the client `with`).
- channels CB3: drop the redundant second _discovery_rows read (identity-mapped
  rows are already enriched; re-sort in Python for the title tie-break).
- playlists PC1: read the live playlist once in push() and share it with plan_push
  + push_playlist (halves read-quota, closes the second TOCTOU window).
- playlists PC2/PC5: batch the cover thumbnails in one window query (was N+1);
  rename combines count+duration into one aggregate + a single cover lookup.
- messages MB2: get_thread only resolves a messageable partner OR one we already
  share a thread with (closes the user-enumeration oracle).
- messages MB3: push a live unread-count to the user's other tabs after mark-read.
- messages MC4: list_conversations uses DISTINCT ON + grouped COUNT instead of
  loading the whole message history into memory.
- config AB3: per-spec allow_empty so smtp_user/youtube_api_proxy can be blanked
  to disable them rather than snapping back to the env default.
This commit is contained in:
npeter83 2026-07-12 05:59:03 +02:00
parent 182dddf5ed
commit 4e80e2b39b
8 changed files with 205 additions and 102 deletions

View file

@ -92,19 +92,12 @@ def _remove_item(db: Session, pl: Playlist, video_id: str, *, mark_dirty: bool)
def _summary(
db: Session,
pl: Playlist,
count: int,
total_duration: int = 0,
has_video: bool | None = None,
cover: str | None = None,
) -> dict:
cover = db.scalar(
select(Video.thumbnail_url)
.join(PlaylistItem, PlaylistItem.video_id == Video.id)
.where(PlaylistItem.playlist_id == pl.id)
.order_by(PlaylistItem.position)
.limit(1)
)
out = {
"id": pl.id,
"name": pl.name,
@ -121,18 +114,6 @@ def _summary(
return out
def _total_duration(db: Session, playlist_id: int) -> int:
return (
db.scalar(
select(func.coalesce(func.sum(Video.duration_seconds), 0))
.select_from(PlaylistItem)
.join(Video, Video.id == PlaylistItem.video_id)
.where(PlaylistItem.playlist_id == playlist_id)
)
or 0
)
@router.get("")
def list_playlists(
contains: str | None = None,
@ -183,13 +164,34 @@ def list_playlists(
.scalars()
.all()
)
# Batch the cover thumbnails (first item per playlist by position) in ONE window query
# instead of a per-playlist SELECT inside _summary (the old N+1).
rn = func.row_number().over(
partition_by=PlaylistItem.playlist_id,
order_by=PlaylistItem.position,
).label("rn")
first_items = (
select(
PlaylistItem.playlist_id.label("pid"),
Video.thumbnail_url.label("thumb"),
rn,
)
.join(Video, Video.id == PlaylistItem.video_id)
.where(PlaylistItem.playlist_id.in_(ids))
.subquery()
)
covers = dict(
db.execute(
select(first_items.c.pid, first_items.c.thumb).where(first_items.c.rn == 1)
).all()
)
return [
_summary(
db,
p,
counts.get(p.id, 0),
durations.get(p.id, 0),
(p.id in member) if contains else None,
covers.get(p.id),
)
for p in pls
]
@ -207,7 +209,7 @@ def create_playlist(
pl = Playlist(user_id=user.id, name=name, position=_next_playlist_position(db, user.id))
db.add(pl)
db.commit()
return _summary(db, pl, 0)
return _summary(pl, 0)
def _watch_later(db: Session, user: User) -> Playlist:
@ -350,13 +352,23 @@ def push(
)
try:
with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PUSH):
plan = plan_push(db, user, pl)
# Read the live playlist ONCE (linked playlists only) and share it with both the
# plan and the push, halving read-quota and closing the second read→write TOCTOU
# window. A fresh export (no yt_playlist_id) reads nothing.
live = None
if pl.yt_playlist_id:
with YouTubeClient(db, user) as yt:
live = (
list(yt.iter_playlist_items_with_ids(pl.yt_playlist_id)),
yt.get_playlist_snippet(pl.yt_playlist_id),
)
plan = plan_push(db, user, pl, live=live)
if plan["units_estimate"] > quota.remaining_today(db):
raise HTTPException(
status_code=429,
detail="Not enough YouTube quota left today for this sync.",
)
return push_playlist(db, user, pl)
return push_playlist(db, user, pl, live=live)
except YouTubeError:
db.rollback()
raise HTTPException(status_code=422, detail="YouTube playlist sync failed.")
@ -405,10 +417,25 @@ def rename_playlist(
pl.name = name
recompute_dirty(db, pl)
db.commit()
count = db.scalar(
select(func.count()).where(PlaylistItem.playlist_id == pl.id)
# One aggregate for count + duration (outer join so an empty playlist still returns 0),
# plus a single cover lookup — was 3 separate round-trips.
count, total = db.execute(
select(
func.count(PlaylistItem.id),
func.coalesce(func.sum(Video.duration_seconds), 0),
)
.select_from(PlaylistItem)
.outerjoin(Video, Video.id == PlaylistItem.video_id)
.where(PlaylistItem.playlist_id == pl.id)
).one()
cover = db.scalar(
select(Video.thumbnail_url)
.join(PlaylistItem, PlaylistItem.video_id == Video.id)
.where(PlaylistItem.playlist_id == pl.id)
.order_by(PlaylistItem.position)
.limit(1)
)
return _summary(db, pl, count or 0, _total_duration(db, pl.id))
return _summary(pl, count or 0, total or 0, cover=cover)
@router.delete("/{playlist_id}")