Files
siftlode/backend/app/routes/plex/people.py
T
peter 0c746f5bcd fix(e5): deep-review survivors — TMDB key log leak, person-enrich rollback + timeout
Three verified deep-review findings (the 4th, the filter combobox a11y gap, is
deferred to a dedicated session on the combobox architecture):

- SEC (medium): TmdbClient sent the api_key as a URL query param, so an HTTP
  error's httpx exception string embedded the full URL incl. the key, which
  enrich_batch logged. _get now raises status+path only (never str(e)/the URL)
  and severs the secret-bearing cause with `from None`. Regression test asserts
  neither the status nor the network error path contains the key.
- STATE (low): person_detail's lazy-enrich except now db.rollback()s, so a
  failed enrich_person commit can't poison the session and 500 the subsequent
  SELECTs (SQLAlchemy 2.x deactivates the tx on a commit-time flush failure and
  does not auto-reset it). Test locks that the page renders despite a poisoned
  enrich.
- ABUSE (low): the request-path lazy person enrich now caps its TMDB client at
  an 8s timeout (was the 30s default) so a slow TMDB can't tie up a worker;
  TmdbClient gained a `timeout` param (batch keeps 30s). The fuller fix (move
  person enrichment off the request path) is logged for later.
2026-08-21 04:42:07 +02:00

235 lines
9.1 KiB
Python

"""Plex people: cast/crew filter-chip cards + a single person's filmography page."""
import logging
from fastapi import APIRouter, Depends
from sqlalchemy import func, or_, select
from sqlalchemy.orm import Session
from app.auth import current_user
from app.db import get_db
from app.models import (
PlexItem,
PlexPerson,
PlexShow,
PlexState,
User,
)
from app.plex import rollup
from app.plex import tmdb as plex_tmdb
from app.plex.cards import movie_card, show_card
from app.plex.query import split_csv
from app.routes.plex._shared import _content_libs
router = APIRouter(prefix="/api/plex", tags=["plex"])
log = logging.getLogger("siftlode.plex")
def _resolve_known_for(
db: Session,
known_for: list | None,
uid: int,
movie_lib_ids: list[int],
show_lib_ids: list[int],
) -> list[dict]:
"""The person's TMDB "Known for" credits (top by popularity) that are IN our library, as cards, in
popularity order. Matched by the canonical guid `tmdb:<id>`; out-of-library credits are dropped."""
if not known_for:
return []
# Bucket by media_type: TMDB movie ids and tv ids collide numerically, so a movie credit must only
# match a library movie and a tv credit only a library show (mirrors tmdb.resolve_recs). Matching
# blind to media_type would render a tv credit as an unrelated movie whose tmdb id happens to match.
movie_guids = [
f"tmdb:{k['tmdb_id']}" for k in known_for if k.get("tmdb_id") and k.get("media_type") != "tv"
]
tv_guids = [
f"tmdb:{k['tmdb_id']}" for k in known_for if k.get("tmdb_id") and k.get("media_type") == "tv"
]
if not movie_guids and not tv_guids:
return []
movies: dict[str, PlexItem] = {}
if movie_lib_ids and movie_guids:
for m in db.execute(
select(PlexItem).where(
PlexItem.kind == "movie",
PlexItem.library_id.in_(movie_lib_ids),
PlexItem.guid.in_(movie_guids),
)
).scalars():
movies.setdefault(m.guid, m)
shows: dict[str, PlexShow] = {}
if show_lib_ids and tv_guids:
for s in db.execute(
select(PlexShow).where(
PlexShow.library_id.in_(show_lib_ids), PlexShow.guid.in_(tv_guids)
)
).scalars():
shows.setdefault(s.guid, s)
m_states = {
s.item_id: s
for s in db.execute(
select(PlexState).where(
PlexState.user_id == uid,
PlexState.item_id.in_([m.id for m in movies.values()] or [0]),
)
).scalars()
}
show_statuses = rollup.state_map(db, uid, [s.id for s in shows.values()])
out: list[dict] = []
for k in known_for:
g = f"tmdb:{k.get('tmdb_id')}"
# A credit resolves against its OWN media_type's bucket only.
if k.get("media_type") == "tv":
if g in shows:
out.append(show_card(shows[g], show_statuses.get(shows[g].id, "new")))
elif g in movies:
out.append(movie_card(movies[g], m_states.get(movies[g].id)))
return out
@router.get("/people/cards")
def people_cards(
names: str,
scope: str = "both",
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Cards for the actor filter-chips currently applied: each name + its cached headshot + how many
movies/shows (in the given scope) feature them. Photos come from the plex_people cache (populated
as items are rich-fetched — info-page view + the rich re-sync); counts are live against cast_names.
A name with no cached photo yet still returns a card (the UI shows a placeholder)."""
wanted = split_csv(names)[:16]
if not wanted:
return {"people": []}
movie_lib_ids, show_lib_ids = _content_libs(db)
want_movies = scope in ("movie", "both") and bool(movie_lib_ids)
want_shows = scope in ("show", "both") and bool(show_lib_ids)
photos = {
p.name: p.photo_thumb
for p in db.execute(
select(PlexPerson).where(PlexPerson.name.in_(wanted))
).scalars()
}
out = []
for nm in wanted:
count = 0
if want_movies:
count += (
db.scalar(
select(func.count(PlexItem.id)).where(
PlexItem.kind == "movie",
PlexItem.library_id.in_(movie_lib_ids),
PlexItem.cast_names.contains([nm]),
)
)
or 0
)
if want_shows:
count += (
db.scalar(
select(func.count(PlexShow.id)).where(
PlexShow.library_id.in_(show_lib_ids),
PlexShow.cast_names.contains([nm]),
)
)
or 0
)
out.append({"name": nm, "photo": photos.get(nm), "count": count})
return {"people": out}
# Cap each filmography section — a prolific person shouldn't return an unbounded list the client then
# mounts a card per row for (the grid paginates at PAGE; this page renders all at once). Ample for a
# personal library; the most-recent titles win via the year-desc order.
_PERSON_SECTION_MAX = 200
@router.get("/person/{name}")
def person_detail(
name: str,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""One cast/crew member's filmography: their cached headshot + the movies and shows (in the enabled
libraries) whose cast OR directors include this name — the inverse of the cast-name → library-filter
link. The name string is the identity key (Plex cast carries no stable per-person id), so distinct
people who share a name share a page. Each section is capped at _PERSON_SECTION_MAX. An unknown name
simply returns empty sections.
E5 S6: the first time a page is opened, the person's TMDB bio + "Known for" credits are lazily
fetched (from the S2-linked `tmdb_person_id`) and persisted, then served from the row on every open.
"""
person = db.execute(select(PlexPerson).where(PlexPerson.name == name)).scalars().first()
# Lazy one-time bio enrich — best-effort, never fail the page if TMDB is down / the id is stale.
if person is not None and person.tmdb_person_id and person.tmdb_enriched_at is None:
try:
plex_tmdb.enrich_person(db, person)
except Exception: # noqa: BLE001 — enrichment is optional; the filmography still renders
# A failed enrich_person commit leaves the session in a needs-rollback state; without this
# the following SELECTs would raise PendingRollbackError and 500 the page (SQLAlchemy 2.x
# deactivates the transaction on a commit-time flush failure and does NOT auto-reset it).
db.rollback()
log.warning("person bio enrich failed for %s", name, exc_info=True)
movie_lib_ids, show_lib_ids = _content_libs(db)
movies: list[dict] = []
if movie_lib_ids:
items = db.execute(
select(PlexItem)
.where(
PlexItem.kind == "movie",
PlexItem.library_id.in_(movie_lib_ids),
or_(
PlexItem.cast_names.contains([name]),
PlexItem.directors.contains([name]),
),
)
.order_by(PlexItem.year.desc().nullslast(), func.lower(PlexItem.title))
.limit(_PERSON_SECTION_MAX)
).scalars().all()
item_ids = [it.id for it in items]
states = {
s.item_id: s
for s in db.execute(
select(PlexState).where(
PlexState.user_id == user.id,
PlexState.item_id.in_(item_ids or [0]),
)
).scalars()
}
movies = [movie_card(it, states.get(it.id)) for it in items]
shows: list[dict] = []
if show_lib_ids:
show_rows = db.execute(
select(PlexShow)
.where(
PlexShow.library_id.in_(show_lib_ids),
or_(
PlexShow.cast_names.contains([name]),
PlexShow.directors.contains([name]),
),
)
.order_by(PlexShow.year.desc().nullslast(), func.lower(PlexShow.title))
.limit(_PERSON_SECTION_MAX)
).scalars().all()
statuses = rollup.state_map(db, user.id, [s.id for s in show_rows])
shows = [show_card(sh, statuses.get(sh.id, "new")) for sh in show_rows]
known_for = _resolve_known_for(
db, person.known_for if person else None, user.id, movie_lib_ids, show_lib_ids
)
return {
"name": name,
"photo": person.photo_thumb if person else None,
"biography": person.biography if person else None,
"birthday": person.birthday if person else None,
"deathday": person.deathday if person else None,
"place_of_birth": person.place_of_birth if person else None,
"known_for_department": person.known_for_department if person else None,
"also_known_as": (person.also_known_as if person else None) or [],
"known_for": known_for,
"movies": movies,
"shows": shows,
}