fix(logs): keep polling reads and a channel-less account out of the warnings

The reads the frontend polls (unread counts, /api/me, the download index,
sync status, subtitle progress) are logged at DEBUG: at INFO they were ~95%
of the stored log on prod. A scheduler job failure and a playlist sync
failure carry event codes, and a Google account without a YouTube channel
has an empty playlist list instead of a warning every six hours.
This commit is contained in:
2026-09-19 04:51:31 +02:00
parent 29094f5f51
commit 3ee00fb051
6 changed files with 136 additions and 10 deletions
+24 -1
View File
@@ -644,6 +644,27 @@ _REQUEST_ID_RE = re.compile(r"^[A-Za-z0-9._-]{8,64}$")
# — this lowers the floor, it does not hide.
_QUIET_PREFIXES = ("/healthz", "/assets/", "/static/", "/api/admin/logs")
# The reads the frontend POLLS (a `useLiveQuery`, the `me` heartbeat, the sync status, the subtitle
# progress), by route template, GET only — logged at DEBUG like the prefixes above. One open tab asked
# for the two unread counts, `/api/me` and the download index every 30 s, and at INFO those were ~95%
# of the stored log (measured on prod 2026-09-19): 11k lines a day per tab burying every line someone
# caused. The same route answered with a failure still logs at WARNING/ERROR.
_POLLED_ROUTES = frozenset(
{
"/api/me",
"/api/me/notifications/unread_count",
"/api/messages/unread_count",
"/api/downloads",
"/api/downloads/index",
"/api/downloads/usage",
"/api/sync/my-status",
"/api/admin/scheduler",
"/api/admin/downloads",
"/api/admin/downloads/storage",
"/api/plex/subtitle/{rating_key}/{sub_ord}/status",
}
)
# Not `siftlode.logs`: this is the replacement for uvicorn's ACCESS log, and `siftlode.http` is
# what an operator pins a level on when they want request lines and nothing else. The module it
# happens to live in is not what the name is about.
@@ -689,7 +710,9 @@ async def log_requests(request, call_next):
raise
duration_ms = round((time.perf_counter() - started) * 1000, 1)
status = response.status_code
quiet = request.url.path.startswith(_QUIET_PREFIXES)
quiet = request.url.path.startswith(_QUIET_PREFIXES) or (
request.method == "GET" and _route_template(request) in _POLLED_ROUTES
)
if status >= 500:
level = logging.ERROR
elif status >= 400:
+1 -1
View File
@@ -208,7 +208,7 @@ def _job(name: str, fn) -> None:
_audit_run(db, actor_id, name, "ok", summary, result)
except Exception as exc:
db.rollback()
log.exception("job %s failed", name)
log.exception("job %s failed", name, extra=logs.event("scheduler.job.failed", job=name))
err = str(exc) or exc.__class__.__name__
_record(name, status="error", last_finished=_now_iso(), last_error=err, progress=None)
if actor_id is not None:
+11 -3
View File
@@ -670,11 +670,19 @@ def sync_all_playlists(db: Session) -> dict:
try:
with quota.attribute(user.id, quota.QuotaAction.PLAYLISTS_PULL):
total += sync_user_playlists(db, user).get("synced", 0)
except YouTubeError:
except YouTubeError as exc:
db.rollback()
log.warning("Playlist sync failed for user %s", user.id)
log.warning(
"Playlist sync failed for user %s",
user.id,
extra=logs.event("sync.playlists.failed", user_id=user.id, reason=exc.reason),
)
except Exception:
db.rollback()
log.exception("Playlist sync crashed for user %s", user.id)
log.exception(
"Playlist sync crashed for user %s",
user.id,
extra=logs.event("sync.playlists.crashed", user_id=user.id),
)
progress.report(i, len(users), "playlist_sync")
return {"users": len(users), "playlists_synced": total}
+30 -5
View File
@@ -6,6 +6,7 @@ so they don't depend on a specific user's token; subscriptions.list?mine=true al
uses OAuth.
"""
import logging
from collections.abc import Iterator
from datetime import datetime, timedelta, timezone
@@ -50,7 +51,9 @@ def _error_reason(resp: httpx.Response) -> str:
return reasons or "<none>"
def _upstream_failure(method: str, path: str, resp: httpx.Response) -> YouTubeError:
def _upstream_failure(
method: str, path: str, resp: httpx.Response, expected: frozenset[str] = frozenset()
) -> YouTubeError:
"""Report one upstream failure and build the error to raise. Every YouTube response that is
not a success goes through here — the Data API's reads, writes and deletes and the OAuth
token refresh — so what may appear in a log line cannot drift apart between them, and the
@@ -59,7 +62,11 @@ def _upstream_failure(method: str, path: str, resp: httpx.Response) -> YouTubeEr
response at all is `_send`'s, with the reason `transport`.) The body is logged only under
the requesting user's own Teljes consent: it is the request quoted back."""
reason = _error_reason(resp)
log.warning(
# A reason the caller named as an answer rather than a failure (`channelNotFound` on a `mine`
# read: the account simply has no channel) is still raised, but it is not a warning — it came
# back every six hours for an account that will never have one.
log.log(
logging.DEBUG if reason in expected else logging.WARNING,
"YouTube %s %s -> %s (%s)",
method,
path,
@@ -83,6 +90,10 @@ def _upstream_failure(method: str, path: str, resp: httpx.Response) -> YouTubeEr
return YouTubeError(f"{method} {path} -> {resp.status_code}: {reason}", reason=reason)
# The `mine` reads' answer for a Google account that has no YouTube channel.
_NO_CHANNEL = frozenset({"channelNotFound"})
def _chunks(items: list, size: int) -> Iterator[list]:
for i in range(0, len(items), size):
yield items[i : i + size]
@@ -167,7 +178,14 @@ class YouTubeClient:
return access
# --- core request ---
def _get(self, path: str, params: dict, cost: int = 1, allow_key: bool = True) -> dict:
def _get(
self,
path: str,
params: dict,
cost: int = 1,
allow_key: bool = True,
expected: frozenset[str] = frozenset(),
) -> dict:
p = dict(params)
headers = {}
api_key = sysconfig.get_str(self.db, "youtube_api_key")
@@ -178,7 +196,7 @@ class YouTubeClient:
resp = self._send("GET", f"{API_BASE}/{path}", params=p, headers=headers)
quota.record_usage(cost)
if resp.status_code != 200:
raise _upstream_failure("GET", path, resp)
raise _upstream_failure("GET", path, resp, expected)
return resp.json()
# --- endpoints ---
@@ -218,7 +236,14 @@ class YouTubeClient:
params = {"part": "snippet,contentDetails", "mine": "true", "maxResults": 50}
if page_token:
params["pageToken"] = page_token
data = self._get("playlists", params, cost=1, allow_key=False)
try:
data = self._get("playlists", params, cost=1, allow_key=False, expected=_NO_CHANNEL)
except YouTubeError as exc:
# A Google account without a YouTube channel has no playlists, and YouTube says
# so as a 404. That is an empty list, not a failed sync.
if exc.reason in _NO_CHANNEL:
return
raise
for item in data.get("items", []):
sn = item.get("snippet", {})
yield {
+32
View File
@@ -219,6 +219,14 @@ def _client() -> TestClient:
raise HTTPException(status_code=400, detail={"code": "bad_cursor"})
return {"ok": True}
@app.get("/api/messages/unread_count")
def _unread():
return {"count": 0}
@app.post("/api/messages/unread_count")
def _unread_write():
return {"ok": True}
@app.get("/boom")
def _boom():
raise RuntimeError("kaboom")
@@ -323,6 +331,30 @@ def test_the_log_consoles_own_reads_are_debug_but_its_failures_are_not(sink):
assert sink.objects()[-1]["level"] == "WARNING"
def test_a_polled_read_is_debug_a_write_to_the_same_route_is_not(sink):
# One open tab polled the unread counts, /api/me and the download index every 30 s: at INFO
# that was ~95% of the stored log on prod.
http = logging.getLogger("siftlode.http")
http.setLevel(logs.TRACE)
client = _client()
client.get("/api/messages/unread_count")
assert sink.objects()[-1]["level"] == "DEBUG"
client.post("/api/messages/unread_count")
assert sink.objects()[-1]["level"] == "INFO"
client.get("/api/videos/abc")
assert sink.objects()[-1]["level"] == "INFO"
def test_every_polled_route_is_a_route_the_app_has():
# The list names route TEMPLATES; one renamed on the router side would silently fall back to
# INFO, so the list is held to the app's own routes.
from app.main import app
# The schema, not `app.routes`: FastAPI 0.141 keeps an included router behind a wrapper there.
gets = {path for path, ops in app.openapi()["paths"].items() if "get" in ops}
assert logs._POLLED_ROUTES - gets == set()
def test_a_failing_request_is_logged_by_status_and_an_unhandled_error_is_logged_at_all(sink):
client = _client()
client.get("/api/videos/missing/deeper") # 404 from the router
+38
View File
@@ -0,0 +1,38 @@
"""A Google account without a YouTube channel: its `mine` playlists read answers 404
`channelNotFound`. That is an empty list, not a failed sync — it came back as a warning every six
hours on prod for an account that will never have a channel."""
import logging
import httpx
import pytest
from app.youtube import client as yt
def _client(monkeypatch, status: int, reason: str) -> yt.YouTubeClient:
resp = httpx.Response(
status,
json={"error": {"code": status, "errors": [{"reason": reason, "message": "prose"}]}},
request=httpx.Request("GET", f"{yt.API_BASE}/playlists"),
)
c = yt.YouTubeClient.__new__(yt.YouTubeClient) # no HTTP client: `_send` is the stub
c.db = None
monkeypatch.setattr(yt.sysconfig, "get_str", lambda db, key: "")
monkeypatch.setattr(yt.quota, "record_usage", lambda cost: None)
monkeypatch.setattr(c, "_access_token", lambda: "t")
monkeypatch.setattr(c, "_send", lambda *a, **k: resp)
return c
def test_no_channel_is_an_empty_playlist_list_and_no_warning(monkeypatch, caplog):
caplog.set_level(logging.DEBUG, logger="siftlode")
assert list(_client(monkeypatch, 404, "channelNotFound").iter_my_playlists()) == []
assert not [r for r in caplog.records if r.levelno >= logging.WARNING]
def test_any_other_failure_still_raises_and_warns(monkeypatch, caplog):
caplog.set_level(logging.DEBUG, logger="siftlode")
with pytest.raises(yt.YouTubeError):
list(_client(monkeypatch, 403, "quotaExceeded").iter_my_playlists())
assert [r for r in caplog.records if r.levelno == logging.WARNING]