Files
siftlode/backend/tests/test_hls_reaper.py
T
peter 47af4d5c05 fix(plex): an HLS artifact names the session it belongs to, and a paused viewer says so
Deep-review round 5, over round 4's own fixes.

- Sessions are keyed by rating_key alone while a session's DIRECTORY is per (key, offset, tag), and
  the artifact URL carried no session identity — so once a seek-restart or a second viewer of the
  same item took the registry slot, the old viewer's request for `seg_12.ts` was answered 200 with
  the new session's twelfth segment: bytes from a different `-ss` offset under `-copyts`, on a
  timeline the client is not on. Wrong content with a success status is the one failure a player
  cannot notice, and round 4's reclaim-on-404 could never fire on it. The id is in the path now (so
  the playlist's relative names resolve back into the same session), a mismatch is a 404, and the
  player reclaims at the playhead. The entry playlist's auto-start is gone with it: it could only
  ever begin at 0, silently discarding the viewer's position.

- Round 4 exempted paused viewers from the reaper by keeping EVERY finished session for the full
  ten-minute idle window — one whole segmented copy of a film per item, on the volume the download
  center shares. The signal it needed already existed: an open player checkpoints its position every
  10 s whether or not it is playing, so that route now touches the session and the periodic pass is
  back on the short rule.

- POST /session's opportunistic reap was never scoped to the key being started: it walked the whole
  registry with the 30 s finished rule, so pressing play on ANY item — even a direct-play one, the
  call ran before that early return — killed another viewer's paused session. It is gone; the
  periodic pass owns reaping.

- A segment that can never arrive no longer polls out the full 20 s: the producer's handle is passed
  to `wait_for`, so a finished ffmpeg answers at once. This is a sync route, so each such wait parked
  a threadpool worker AND a pooled DB connection, and an ordinary seek past the produced region was
  enough to do it.

- The DataError handler's re-raise branch — the half that keeps a genuine DataError a 500 — is
  pinned, so simplifying it to an unconditional 422 cannot pass in silence.

Six regression tests (two route-level, in the DB lane), each mutation-checked red on the assertion
it is named after. pytest 1124, vitest 999.
2026-09-12 03:57:52 +02:00

205 lines
7.3 KiB
Python

"""Idle HLS sessions are reaped on a timer, and a viewer who is merely PAUSED keeps theirs.
plex/stream.py promises "a periodic reaper kills idle ones", but `reap_idle` ran only inside
POST /session: after the last playback, an abandoned session (its ffmpeg still working through the
film, its directory a whole segmented copy of it) lived until somebody pressed play again
(deep-review round 4).
And it must not take a PAUSED viewer's session: a remux finishes long before the film does, and a
paused player with a full buffer fetches nothing, so "finished and unfetched for 30 s" does not mean
"abandoned". Round 4 bought that safety by keeping EVERY finished session for the full ten-minute
idle window — one segmented copy of a film per item, on the volume the download center shares. Round
5 replaced the blanket retention with the signal that already existed: an open player checkpoints its
position every 10 s whether or not it is playing, and that route says "still here".
Both call sites are pinned here, because the bug each time was that only one of them moved: the
periodic pass, and the fact that starting a session no longer sweeps OTHER viewers' sessions at all.
"""
import asyncio
import time
from types import SimpleNamespace
import pytest
from fastapi.testclient import TestClient
import app.main as app_main
import app.state as state
from app.auth import current_user
from app.db import get_db
from app.main import app
from app.models import PlexItem, PlexLibrary, User
from app.plex import paths as plex_paths
from app.plex import stream
class _Configured:
def __enter__(self):
return None
def __exit__(self, *exc):
return False
def test_the_periodic_pass_is_the_one_that_runs_and_it_uses_the_short_rule(monkeypatch):
async def _no_sweep():
return None
reaped: list[int] = []
monkeypatch.setattr(app_main, "SessionLocal", _Configured)
monkeypatch.setattr(app_main.state, "is_configured", lambda db: True)
monkeypatch.setattr(app_main, "_sweep_hls_orphans", _no_sweep)
monkeypatch.setattr(app_main, "start_scheduler", lambda: None)
monkeypatch.setattr(app_main, "shutdown_scheduler", lambda: None)
monkeypatch.setattr(app_main.plex_subtitles, "shutdown", lambda: None)
monkeypatch.setattr(app_main, "_HLS_REAP_EVERY_S", 0.01)
# `reap_idle`, i.e. the SHORT finished rule: a finished session nobody has said they still want
# is a whole copy of a film sitting on the download volume.
monkeypatch.setattr(app_main.plex_stream, "reap_idle", lambda: reaped.append(1) or 0)
async def _cycle():
async with app_main.lifespan(app):
await asyncio.sleep(0.2)
asyncio.run(_cycle())
assert len(reaped) >= 2, "no periodic reap ran while the app was up"
class _Proc:
def __init__(self, finished: bool):
self.finished = finished
self.killed = False
def poll(self):
return 0 if self.finished else None
def terminate(self):
self.killed = True
def wait(self, timeout=None):
return 0
class _Session:
def __init__(self, tmp_path, name: str, finished: bool, idle_s: float):
self.dir = tmp_path / name
self.dir.mkdir()
self.proc = _Proc(finished)
self.last_access = time.time() - idle_s
@pytest.fixture
def sessions(monkeypatch):
live: dict = {}
monkeypatch.setattr(stream, "_sessions", live)
return live
def test_the_periodic_pass_reaps_a_finished_session_nobody_has_claimed(tmp_path, sessions):
sessions["12345"] = _Session(tmp_path, "done", finished=True, idle_s=45)
assert stream.reap_idle() == 1
assert sessions == {}
def test_the_periodic_pass_still_reaps_what_nobody_has_touched_for_the_idle_limit(
tmp_path, sessions
):
sessions["1"] = _Session(
tmp_path, "gone_done", finished=True, idle_s=stream._SESSION_IDLE_S + 5
)
sessions["2"] = _Session(
tmp_path, "gone_live", finished=False, idle_s=stream._SESSION_IDLE_S + 5
)
assert stream.reap_idle() == 2
assert sessions == {}
def test_touching_a_session_keeps_it_through_the_short_rule(tmp_path, sessions):
s = _Session(tmp_path, "paused", finished=True, idle_s=90)
sessions["12345"] = s
stream.touch_session("12345")
assert stream.reap_idle() == 0
assert "12345" in sessions and s.dir.exists() and not s.proc.killed
# --- the two call sites, driven through the real routes (DB lane) -------------------------------
def _library_item(db, rating_key: str, *, playable: str = "remux"):
lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
db.add(lib)
db.flush()
it = PlexItem(
rating_key=rating_key,
library_id=lib.id,
kind="movie",
title="A Movie",
file_path="/media/a.mkv",
playable=playable,
)
db.add(it)
db.commit()
return it
def _client(db, user):
app.dependency_overrides[get_db] = lambda: db
app.dependency_overrides[current_user] = lambda: user
return TestClient(app)
def test_a_paused_viewers_checkpoint_keeps_their_session_alive(db, monkeypatch, tmp_path, sessions):
"""The whole reason the short rule is safe again: a paused player fetches nothing, so
`last_access` never moved on its own — but it does keep checkpointing its position."""
monkeypatch.setattr(state, "_configured_cache", True)
it = _library_item(db, "paused1")
user = User(email="paused@example.com")
db.add(user)
db.commit()
s = _Session(tmp_path, "paused", finished=True, idle_s=90)
sessions["paused1"] = s
try:
resp = _client(db, user).post(
f"/api/plex/item/{it.rating_key}/progress",
json={"position_seconds": 600, "duration_seconds": 3000, "final": False},
)
finally:
app.dependency_overrides.clear()
assert resp.status_code == 200, resp.text
assert stream.reap_idle() == 0, "the checkpoint did not say the viewer is still there"
assert "paused1" in sessions and not s.proc.killed
def test_starting_a_session_leaves_another_viewers_paused_one_alone(
db, monkeypatch, tmp_path, sessions
):
"""The opportunistic sweep this route used to run was not scoped to the key being started: it
walked the WHOLE registry with the 30 s finished rule, so pressing play on any item killed a
paused viewer's session — the very case round 4 set out to protect (found in round 5)."""
monkeypatch.setattr(state, "_configured_cache", True)
monkeypatch.setattr(plex_paths, "local_media_path", lambda db_, fp: "/local/a.mkv")
started = _library_item(db, "starting")
user = User(email="starter@example.com")
db.add(user)
db.commit()
paused = _Session(tmp_path, "paused", finished=True, idle_s=90)
sessions["someone-else"] = paused
def fake_start(db_, item, start, audio=None, aoff=0.0, multi=False, transcode=False):
return SimpleNamespace(
id="sid",
media_start_s=start,
entry="index.m3u8",
transcode=transcode,
hw=False,
tonemap=False,
)
monkeypatch.setattr(stream, "start_session", fake_start)
try:
resp = _client(db, user).post(f"/api/plex/stream/{started.rating_key}/session")
finally:
app.dependency_overrides.clear()
assert resp.status_code == 200, resp.text
assert "someone-else" in sessions and not paused.proc.killed