fix(logs): deep-review round 3 — a failure nobody could record is one scrubbed line

- The download and edit failure lines go back after their DB write: a job the
  write could not fail is not a failed job, and the worker's child_exit line
  already says it failed.
- The download child's runner is the last stop before Python's hook: an
  escaping exception is one download.child.failed line with its chain scrubbed,
  then exit 1, instead of a raw stderr traceback carrying the URL.
- A crash the database will not record carries its stack once, and the
  fail-write line has an event code.
- The job's own generic-extractor name is taken out as a literal (formats.hiding),
  so brackets and colons in a direct link's file name no longer leak; the
  pattern stays as the fallback. `Downloading just the video <id>` is covered.
- Tests: scrubbed_stack's cause, suppress, unprintable and text-format paths,
  the image steps' failure kinds, the watchdog error through the real
  _fail_running, exact poster/storyboard messages, ffmpeg skip marker.
This commit is contained in:
2026-09-18 23:44:42 +02:00
parent 0b672ed6e7
commit 89c77ae6b5
9 changed files with 407 additions and 81 deletions
+52 -56
View File
@@ -654,30 +654,28 @@ def _download(
diagnosis = dlerrors.diagnose(msg, url=url, cookie_attached=cookiefile is not None)
# SEC-12: redact a transport-level readout for user-supplied URLs (see user_error_text).
msg = dlerrors.user_error_text(source_kind, msg, diagnosis.code)
# The line goes out whether or not the write below succeeds: when the database is what
# failed, that write fails too, and the failure would otherwise leave no line at all.
try:
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "error"
asset.error = msg
# Atomic fail: only while still running, so a route-set cancel/pause is never
# overwritten with `error` (error also holds the asset → would re-open the
# double-release class).
service.finalize_if_running(
db,
job_id,
status=JobStatus.ERROR,
error=msg,
error_code=diagnosis.code,
error_detail=diagnosis.detail,
phase=None,
)
db.commit()
finally:
# silent-ok: not silent — `_log_download_failed` is the report.
_log_download_failed(job_id, msg, diagnosis.code, exc)
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "error"
asset.error = msg
# Atomic fail: only while still running, so a route-set cancel/pause is never
# overwritten with `error` (error also holds the asset → would re-open the
# double-release class).
service.finalize_if_running(
db,
job_id,
status=JobStatus.ERROR,
error=msg,
error_code=diagnosis.code,
error_detail=diagnosis.detail,
phase=None,
)
db.commit()
# After the write: a job the write could not fail is not a failed job. When it raises,
# the runner reports this failure with it (`runner._run`) and the worker fails the job.
# silent-ok: not silent — `_log_download_failed` is the report.
_log_download_failed(job_id, msg, diagnosis.code, exc)
finally:
# Unlink the decrypted cookie file explicitly (the rmtree below removes the whole staging
# tree too, but never leave a plaintext session cookie on disk a moment longer than needed).
@@ -729,40 +727,38 @@ def _fail_edit(job_id: int, asset_id: int, msg: str, exc: BaseException | None =
where its line and its event code live. `exc` is the exception when there was one.
Its traceback goes with the line unless the message already tells it all (`_failure_stack`).
The line goes out whether or not the write succeeds (see the download error path)."""
try:
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "error"
asset.error = msg
# Atomic fail: only while still running (see the download error path).
service.finalize_if_running(
db,
job_id,
status=JobStatus.ERROR,
error=msg,
error_code=dlerrors.classify(msg),
phase=None,
)
db.commit()
finally:
# `msg` is the user's copy; ffmpeg's stderr tail in it can name the source file, whose
# path is built from the channel and the title.
log.warning(
"edit job %s failed: %s",
Logged after the write, as on the download error path."""
with SessionLocal() as db:
asset = db.get(MediaAsset, asset_id)
if asset:
asset.status = "error"
asset.error = msg
# Atomic fail: only while still running (see the download error path).
service.finalize_if_running(
db,
job_id,
formats.log_safe(msg),
extra={
**logs.event(
"edit.job.failed",
job_id=job_id,
asset_id=asset_id,
**({"error_type": type(exc).__name__} if exc is not None else {}),
),
**(_failure_stack(exc) if exc is not None else {}),
},
status=JobStatus.ERROR,
error=msg,
error_code=dlerrors.classify(msg),
phase=None,
)
db.commit()
# `msg` is the user's copy; ffmpeg's stderr tail in it can name the source file, whose path is
# built from the channel and the title.
log.warning(
"edit job %s failed: %s",
job_id,
formats.log_safe(msg),
extra={
**logs.event(
"edit.job.failed",
job_id=job_id,
asset_id=asset_id,
**({"error_type": type(exc).__name__} if exc is not None else {}),
),
**(_failure_stack(exc) if exc is not None else {}),
},
)
def _process_edit(job_id: int, asset_id: int) -> None: