Files
siftlode/backend/app/routes/plex/playback.py
T
peter 3f8257059d feat(plex): Plex-authoritative watch-sync — resume write-back + faster pull (S2)
Make Plex the source of truth for watch state:

- Write-back during playback: item_progress now pushes the resume position to
  Plex on the periodic checkpoint too (not only the final flush), throttled to
  one push per item every ~10s (in-memory, single-process rate limiter). The FE
  now also fires an immediate (debounced) push on seek.
- Faster incremental pull: 30 → 15 min (plex_watch_sync_interval_min).
- Plex-authoritative pull: _pull_apply resolves a genuine divergence to Plex's
  state instead of last-write-wins; the _same_state + synced_to_plex short-circuit
  still prevents a freshly-pushed row from bouncing. Removed the now-unused
  _LWW_TOLERANCE_S / _sift_ts.

Tests: 5 new in test_plex_watch_sync.py (Plex-wins resume/watched, no-bounce,
throttle final vs periodic).
2026-08-27 02:07:45 +02:00

580 lines
24 KiB
Python

"""Plex playback: image/subtitle proxies, HLS streaming, and watch-state writes."""
import hashlib
import os
import tempfile
import threading
from datetime import datetime, timezone
import httpx
from fastapi import (
APIRouter,
BackgroundTasks,
Depends,
HTTPException,
Request,
Response,
)
from fastapi.responses import FileResponse
from pydantic import BaseModel
from sqlalchemy import select
from sqlalchemy.orm import Session
from app.auth import current_user, resolved_user_id
from app.db import SessionLocal, get_db
from app.models import (
PlexItem,
PlexSeason,
PlexShow,
PlexState,
User,
)
from app.plex import imgcache, subtitles
from app.plex import paths as plex_paths
from app.plex.lookups import by_rating_key
from app.plex import people as plex_people
from app.plex import stream as plex_stream
from app.plex import watch_sync as plex_watch
from app.plex.client import PlexClient, PlexError, PlexNotConfigured
from app.routes.plex._shared import item_or_404
router = APIRouter(prefix="/api/plex", tags=["plex"])
def _require_session(request: Request) -> int:
"""Lightweight auth for the high-fan-out image proxies: validate the signed session cookie WITHOUT
a DB user-load, so these endpoints never hold a pool connection for the auth. Poster images are
low-sensitivity; a valid session is enough."""
uid, _ = resolved_user_id(request)
if not uid:
raise HTTPException(status_code=401, detail="Not authenticated")
return uid
@router.get("/image/{rating_key}")
def image(rating_key: str, request: Request, variant: str = "thumb") -> Response:
"""Proxy a Plex poster/art image (keeps the admin token server-side; no image duplication). A
thin on-disk cache serves repeat views without re-hitting Plex.
⚠️ This endpoint is called in BURSTS (a collections page fires 100+ concurrent poster requests),
so it must NOT hold a DB connection during the slow Plex fetch — doing so exhausted the pool
(QueuePool timeout, broken images on prod). Warm path (cache hit) touches NO DB; cold path opens a
brief session only to resolve the image key + read the Plex config, then RELEASES it before the
fetch. Auth is the signed-session check (no DB user-load)."""
_require_session(request)
v = "art" if variant == "art" else "thumb"
w, h = imgcache.SIZES[v]
# Size is part of the cache key: Plex resizes server-side (see PlexClient.image_bytes), so we cache
# the small variant. The width tag also means changing a target size just re-caches, never serves a
# stale differently-sized file (old full-size files under the un-tagged key are simply orphaned).
cache_key = f"item_{rating_key}_{v}_{w}"
hit = imgcache.read(cache_key)
if hit:
return imgcache.response(*hit)
# Cold miss: short-lived session for the key + Plex client config, released before the slow fetch.
try:
with SessionLocal() as db:
key = imgcache.key_for(db, str(rating_key), v)
if not key:
raise HTTPException(status_code=404, detail="No image")
plex = PlexClient(db) # reads base URL + token now; the fetch below needs no DB
except PlexNotConfigured as e:
raise HTTPException(status_code=400, detail=str(e))
try:
with plex:
data, ct = plex.image_bytes(key, w, h)
except PlexError as e:
raise HTTPException(status_code=502, detail=f"Plex image fetch failed: {e}")
imgcache.write(cache_key, data, ct)
return imgcache.response(data, ct)
@router.get("/subtitle/{rating_key}/{sub_ord}")
def subtitle(rating_key: str, sub_ord: int, request: Request, offset: float = 0.0) -> Response:
"""Serve the ord-th subtitle track as WebVTT for the browser's <track> — so choosing a subtitle
overlays it directly (no HLS re-mux / session restart). Handles EXTERNAL sidecar subs (fetched
from Plex via the stream `key` — the old `-map 0:s` broke on these since they're not in the file)
AND embedded text subs (extracted from the local file). Image subs (PGS/VobSub) → 415. Disk-cached."""
_require_session(request)
# Cache the ABSOLUTE-time VTT once (per rk+ord); the per-session cue-shift is applied on the way
# out, so a resume/seek to any offset reuses the same cached track (no cache-per-offset explosion).
cache_key = f"sub_{rating_key}_{sub_ord}"
hit = subtitles.cache_read(cache_key)
if hit is not None:
return Response(subtitles.shift_vtt(hit, offset), media_type="text/vtt")
try:
with SessionLocal() as db:
it = item_or_404(db, rating_key)
with PlexClient(db) as plex:
part = ((plex.metadata(it.rating_key) or {}).get("Media") or [{}])[0].get(
"Part"
) or [{}]
subs = [s for s in (part[0].get("Stream") or []) if s.get("streamType") == 3]
if sub_ord < 0 or sub_ord >= len(subs):
raise HTTPException(status_code=404, detail="No such subtitle")
s = subs[sub_ord]
codec = (s.get("codec") or s.get("format") or "").lower()
if codec in subtitles.BITMAP_SUBS:
raise HTTPException(
status_code=415,
detail="Image-based subtitle can't be shown as text",
)
if s.get("key"): # external sidecar → fetch from Plex, convert to VTT
raw = plex.raw_get(s["key"])
if codec in ("srt", "subrip", ""):
vtt = subtitles.srt_to_vtt(raw.decode("utf-8", "replace"))
else:
fd, tmp = tempfile.mkstemp(suffix="." + (codec or "sub"))
try:
os.write(fd, raw)
os.close(fd)
vtt = subtitles.ffmpeg_to_vtt(tmp, None)
finally:
os.unlink(tmp)
elif s.get("index") is not None: # embedded → extract from the local file
src = plex_paths.local_media_path(db, it.file_path)
if src is None:
raise HTTPException(status_code=404, detail="Media file not found on disk")
emb_ord = sum(1 for x in subs[:sub_ord] if x.get("index") is not None)
vtt = subtitles.ffmpeg_to_vtt(str(src), emb_ord)
else:
raise HTTPException(status_code=404, detail="Subtitle not fetchable")
except PlexNotConfigured as e:
raise HTTPException(status_code=400, detail=str(e))
except PlexError as e:
raise HTTPException(status_code=502, detail=f"Subtitle fetch failed: {e}")
subtitles.cache_write(cache_key, vtt)
return Response(subtitles.shift_vtt(vtt, offset), media_type="text/vtt")
# Resume/watched thresholds. _PROGRESS_MIN_S matches the feed's PROGRESS_MIN_SECONDS (5), but
# _FINISH_MARGIN_S is DELIBERATELY larger than the feed's FINISH_MARGIN_SECONDS (30 vs 10): this is
# long-form content (movies/episodes with credits) and crossing it MARKS THE ITEM WATCHED, whereas
# the feed's margin only clears a short video's resume bar — different domains, intentional divergence,
# not drift. Keep them separate on purpose (see routes/feed.py).
_PROGRESS_MIN_S = 5
_FINISH_MARGIN_S = 30
# S2 write-back throttle: the resume position is now pushed to Plex on the periodic (non-final)
# checkpoint too — not only on the final pause/unmount flush — so Plex (the source of truth) stays
# current in near-real-time. To keep a single watch from spraying `/:/timeline` calls, a push is
# rate-limited to at most one per item per user every _PUSH_THROTTLE_S seconds; a `final` checkpoint
# (pause / seek / stop) always pushes immediately and resets the window. This is an in-memory, single-
# process rate-limiter (the deployment is one FastAPI process): after a restart the map is empty, so at
# most one extra push happens on the first checkpoint — harmless. It is NOT durable domain state.
_PUSH_THROTTLE_S = 10
_last_push_at: dict[tuple[int, int], datetime] = {}
_push_throttle_lock = threading.Lock()
def _should_push_resume(user_id: int, item_id: int, now: datetime, final: bool) -> bool:
"""Whether to mirror this resume checkpoint to Plex now. `final` always pushes; a periodic tick
pushes only when ≥_PUSH_THROTTLE_S has elapsed since the last push for this (user, item). Records
`now` as the last-push time whenever it returns True so the window is measured from the real push."""
with _push_throttle_lock:
last = _last_push_at.get((user_id, item_id))
if final or last is None or (now - last).total_seconds() >= _PUSH_THROTTLE_S:
_last_push_at[(user_id, item_id)] = now
return True
return False
@router.get("/person-image")
def person_image(u: str, request: Request) -> Response:
"""Proxy a cast/crew photo from Plex's public metadata CDN (host-whitelisted; no token needed).
Signed-session auth (no DB) so it, like /image, never holds a pool connection during the fetch."""
_require_session(request)
if not u.startswith(plex_people.PERSON_IMG_HOST):
raise HTTPException(status_code=400, detail="Unsupported image host")
cache_key = "person_" + hashlib.sha1(u.encode()).hexdigest()
hit = imgcache.read(cache_key)
if hit:
return imgcache.response(*hit)
try:
with httpx.Client(timeout=10.0, follow_redirects=True) as c:
r = c.get(u)
r.raise_for_status()
except httpx.HTTPError:
raise HTTPException(status_code=502, detail="Image fetch failed")
ct = r.headers.get("content-type", "image/jpeg")
imgcache.write(cache_key, r.content, ct)
return imgcache.response(r.content, ct)
def _push_watch(
background: BackgroundTasks,
db: Session,
user_id: int,
item_id: int,
rating_key: str,
action: str,
time_ms: int = 0,
duration_ms: int = 0,
) -> None:
"""Schedule a best-effort Siftlode→Plex watch push, but only for a user whose owner link has
push enabled — non-owner users never touch Plex. Guarding here (with the request session) avoids
spinning up a throwaway background session on every state change for the common no-link case."""
if plex_watch.link_for_push(db, user_id) is None:
return
# Capture the row's freshest timestamp NOW so the background push can tell if a newer local edit
# lands before it settles synced_to_plex (which would otherwise strand that newer value).
st = (
db.execute(
select(PlexState).where(PlexState.user_id == user_id, PlexState.item_id == item_id)
)
.scalars()
.first()
)
background.add_task(
plex_watch.push_state_to_plex,
user_id,
item_id,
rating_key,
action,
time_ms,
duration_ms,
plex_watch._state_marker(st),
)
class ItemProgressIn(BaseModel):
# float, truncated in the handler — the player may post a raw currentTime (a float); a plain
# `int` field would 422 it on the periodic progress checkpoint (the old `int(...)` truncated).
position_seconds: float = 0
duration_seconds: float = 0
final: bool = False
@router.post("/item/{rating_key}/progress")
def item_progress(
rating_key: str,
body: ItemProgressIn,
background: BackgroundTasks,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Checkpoint the resume position while playing (near the end → mark watched + clear it).
S2 write-back: the resume position is mirrored to Plex (the source of truth) on the periodic
checkpoint too, not only on the final flush — throttled to ≥_PUSH_THROTTLE_S per item (see
`_should_push_resume`). `final` (sent on pause / seek / pagehide / unmount) pushes immediately and
resets the throttle window, so Plex sees a settled position the instant the user pauses or seeks."""
it = item_or_404(db, rating_key)
position = max(0, int(body.position_seconds))
duration = int(body.duration_seconds)
final = body.final
now = datetime.now(timezone.utc)
st = (
db.execute(
select(PlexState).where(PlexState.user_id == user.id, PlexState.item_id == it.id)
)
.scalars()
.first()
)
was_watched = st is not None and st.status == "watched"
near_end = duration > 0 and position > duration - _FINISH_MARGIN_S
if near_end:
if st is None:
st = PlexState(user_id=user.id, item_id=it.id)
db.add(st)
st.status = "watched"
st.watched_at = now
st.position_seconds = 0
st.progress_updated_at = now
st.synced_to_plex = False
db.commit()
# Immediate on the watched transition; skip a repeat scrobble if it was already watched
# (a later checkpoint of the same finished item would otherwise bump Plex's viewCount again).
if not was_watched:
_push_watch(background, db, user.id, it.id, rating_key, "watched")
return {"status": "watched", "position_seconds": 0}
if position < _PROGRESS_MIN_S:
if st is not None and st.status == "new":
db.delete(st)
elif st is not None:
st.position_seconds = 0
st.progress_updated_at = now
db.commit()
return {"position_seconds": 0}
if st is None:
st = PlexState(user_id=user.id, item_id=it.id)
db.add(st)
st.position_seconds = position
st.progress_updated_at = now
push_now = _should_push_resume(user.id, it.id, now, final)
if push_now:
# Mark dirty before the (background) push so the reconcile knows to re-push if it fails, and so
# `push_state_to_plex` can settle synced_to_plex once Plex confirms.
st.synced_to_plex = False
db.commit()
if push_now:
_push_watch(
background,
db,
user.id,
it.id,
rating_key,
"resume",
position * 1000,
duration * 1000,
)
return {"position_seconds": position}
class ItemStateIn(BaseModel):
status: str = ""
@router.post("/item/{rating_key}/state")
def item_state(
rating_key: str,
body: ItemStateIn,
background: BackgroundTasks,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Set the per-user watch status (new|watched|hidden). watched→scrobble / →new→unscrobble push
to a linked Plex account immediately; `hidden` is a Siftlode-only concept with no Plex analogue,
so it never touches Plex."""
it = item_or_404(db, rating_key)
status = body.status
if status not in ("new", "watched", "hidden"):
raise HTTPException(status_code=400, detail="Invalid status")
st = (
db.execute(
select(PlexState).where(PlexState.user_id == user.id, PlexState.item_id == it.id)
)
.scalars()
.first()
)
prev_status = st.status if st is not None else "new"
if status == "new":
if st is not None:
db.delete(st)
db.commit()
if prev_status != "new": # something → unwatched: mirror the un-mark to Plex
_push_watch(background, db, user.id, it.id, rating_key, "unwatched")
return {"status": "new"}
if st is None:
st = PlexState(user_id=user.id, item_id=it.id)
db.add(st)
st.status = status
if status == "watched":
st.watched_at = datetime.now(timezone.utc)
st.position_seconds = 0
st.synced_to_plex = False
db.commit()
if status == "watched" and prev_status != "watched":
_push_watch(background, db, user.id, it.id, rating_key, "watched")
return {"status": status}
def _bulk_state(
background: BackgroundTasks,
db: Session,
user_id: int,
eps: list[PlexItem],
watched: bool,
) -> int:
"""Mark every episode in `eps` watched (or unwatched) for a user, mirroring each change to a
linked Plex account in the background (best-effort). Returns how many rows actually changed."""
now = datetime.now(timezone.utc)
existing = {
s.item_id: s
for s in db.execute(
select(PlexState).where(
PlexState.user_id == user_id,
PlexState.item_id.in_([e.id for e in eps] or [0]),
)
).scalars()
}
pushable = plex_watch.link_for_push(db, user_id) is not None
to_push: list[tuple[int, str, str]] = []
for e in eps:
st = existing.get(e.id)
prev = st.status if st is not None else "new"
if watched:
if st is None:
st = PlexState(user_id=user_id, item_id=e.id)
db.add(st)
st.status = "watched"
st.watched_at = now
st.position_seconds = 0
st.synced_to_plex = False
if prev != "watched":
to_push.append((e.id, e.rating_key, "watched"))
else: # → new: drop any state (but keep the user's private "hidden" marks)
if st is not None and prev != "hidden":
db.delete(st)
if prev != "new":
to_push.append((e.id, e.rating_key, "unwatched"))
db.commit()
if pushable and to_push:
# One coalesced background task for the whole batch (reuses a single session + Plex client),
# not one task per episode — a 200-ep show mark is 1 task, not 200.
background.add_task(plex_watch.push_bulk_state_to_plex, user_id, to_push)
return len(to_push)
class WatchedIn(BaseModel):
watched: bool = False
@router.post("/show/{rating_key}/state")
def show_state(
rating_key: str,
body: WatchedIn,
background: BackgroundTasks,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Mark a whole show watched/unwatched (all its episodes) for the current user + push to Plex."""
sh = by_rating_key(db, PlexShow, rating_key)
if sh is None:
raise HTTPException(status_code=404, detail="Unknown Plex show")
watched = body.watched
eps = (
db.execute(select(PlexItem).where(PlexItem.show_id == sh.id, PlexItem.kind == "episode"))
.scalars()
.all()
)
changed = _bulk_state(background, db, user.id, eps, watched)
return {"changed": changed, "watched": watched}
@router.post("/season/{rating_key}/state")
def season_state(
rating_key: str,
body: WatchedIn,
background: BackgroundTasks,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Mark a whole season watched/unwatched (all its episodes) for the current user + push to Plex."""
se = by_rating_key(db, PlexSeason, rating_key)
if se is None:
raise HTTPException(status_code=404, detail="Unknown Plex season")
watched = body.watched
eps = (
db.execute(select(PlexItem).where(PlexItem.season_id == se.id, PlexItem.kind == "episode"))
.scalars()
.all()
)
changed = _bulk_state(background, db, user.id, eps, watched)
return {"changed": changed, "watched": watched}
@router.post("/stream/{rating_key}/session")
def stream_session(
rating_key: str,
start: float = 0.0,
audio: int | None = None,
aoff: float = 0.0,
multi: bool = False,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> dict:
"""Prepare playback from `start` seconds. Direct-playable files are served raw; remux files
(re)start an HLS session at the offset (seek-restart); transcode (HEVC/VP9) is P3. Selecting a
non-default audio track (`audio` = stream ordinal) forces the HLS path so the chosen audio can be
muxed in. Subtitles are independent WebVTT tracks (GET /subtitle) — no session restart."""
plex_stream.reap_idle() # opportunistic cleanup of idle sessions on each new playback
it = item_or_404(db, rating_key)
if it.playable == "transcode":
raise HTTPException(
status_code=501, detail="This format needs transcoding (a later phase)."
)
# `multi` (item has ≥2 audio tracks) forces the HLS path so ALL audio tracks ship as renditions and
# the client can switch audio without a restart — even for otherwise direct-playable files.
if it.playable == "direct" and audio is None and not aoff and not multi:
return {
"mode": "direct",
"url": f"/api/plex/stream/{it.rating_key}/file",
"start_s": 0.0,
}
if plex_paths.local_media_path(db, it.file_path) is None:
raise HTTPException(status_code=404, detail="Media file not found on disk")
s = plex_stream.start_session(db, it, start, audio, aoff, multi)
if s is None:
raise HTTPException(status_code=404, detail="Media file not found on disk")
# Report the REAL media start (the keyframe ffmpeg landed on, which hls.js zero-bases to), not the
# requested offset — the client's absolute clock and the subtitle cue-shift both key off this.
return {
"mode": "hls",
"start_s": s.media_start_s,
"url": f"/api/plex/stream/{it.rating_key}/hls/{s.entry}",
}
@router.get("/stream/{rating_key}/file")
def stream_file(
rating_key: str,
download: bool = False,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> FileResponse:
"""Serve the raw local media file with HTTP range support. Used both for direct-play (inline)
and for the player's "download original" button (`?download=1` → attachment). The download is
the untouched physical file — no re-encode/repackage."""
it = item_or_404(db, rating_key)
src = plex_paths.local_media_path(db, it.file_path)
if src is None:
raise HTTPException(status_code=404, detail="Media file not found on disk")
if download:
# A clean, safe download name from the title + the real file extension.
ext = src.suffix or (f".{it.container}" if it.container else "")
base = (
"".join(c for c in (it.title or "video") if c.isalnum() or c in " -_.").strip()
or "video"
)
return FileResponse(str(src), filename=f"{base}{ext}")
return FileResponse(str(src)) # Starlette honours the Range header (206)
_HLS_CT = {
".m3u8": "application/vnd.apple.mpegurl",
".ts": "video/mp2t",
".vtt": "text/vtt",
}
@router.get("/stream/{rating_key}/hls/{filename}")
def stream_hls_file(
rating_key: str,
filename: str,
user: User = Depends(current_user),
db: Session = Depends(get_db),
) -> Response:
"""Serve a file (playlist / segment / subtitle) from the current HLS session directory. The
playlist references its segments/subtitles by relative name, all resolving back here."""
# Filename must be a plain hls artifact — no path separators, only the expected extensions.
ext = "." + filename.rsplit(".", 1)[-1] if "." in filename else ""
if ext not in _HLS_CT or "/" in filename or "\\" in filename or ".." in filename:
raise HTTPException(status_code=404, detail="Not found")
s = plex_stream.current_session(str(rating_key))
if s is None:
# No session yet (e.g. reaped): the ENTRY playlist may auto-start one at 0 — master.m3u8 for a
# multi-audio item, index.m3u8 for a single-audio remux item.
it = item_or_404(db, rating_key)
if filename == "master.m3u8":
s = plex_stream.start_session(db, it, 0.0, multi=True)
elif filename == "index.m3u8" and it.playable == "remux":
s = plex_stream.start_session(db, it, 0.0)
else:
raise HTTPException(status_code=404, detail="No active playback session")
if s is None:
raise HTTPException(status_code=404, detail="Media file not found on disk")
path = s.dir / filename
timeout = 30 if ext == ".m3u8" else 20
if not plex_stream.wait_for(path, timeout):
raise HTTPException(status_code=404, detail="Not available yet")
return Response(
content=path.read_bytes(),
media_type=_HLS_CT[ext],
headers={"Cache-Control": "no-store"},
)