peter/siftlode
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix(clip): a clip is held to its owner's storage cap, and its limits and failures say the server's truth

Browse Source 
- The cut file is measured against what its owner has left, for a YouTube range (whose fetch never
  reads yt-dlp's size ceiling) and for a Plex clip (which fetches nothing), before the fetch and
  again before it is placed; a refusal leaves the asset pending for a Retry.
- A silent Plex file is cut silent; a file the probe cannot read says so.
- A second job on a failed or renamed clip gets the same YouTube diagnosis and the fetched title.
- The "too long" refusal names the server's cap; a contract test holds the client's copies of the
  clip limits to clip.py; the shipped player clients are pinned against the installed yt-dlp.
- One HDR transfer set and one rating_key lookup; job status words from JobStatus; the display-name
  guard sees subscript writes and the clip route; stale comments and types follow the clip job.
This commit is contained in:
peter
2026-10-10 15:35:12 +02:00
parent 72df11f2c0
commit b4bf71ea64
25 changed files with 385 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/worker.py
+29 -10
View File
@@ -29,6 +29,7 @@ from datetime import datetime, timezone
from functools import partial
from sqlalchemy import text
from sqlalchemy.orm import Session
from app import logs
from app import logsink
@@ -44,7 +45,7 @@ from app.downloads.jobdb import (
_reset_asset_pending,
_staging_dir,
)
from app.downloads.status import STOPPED_BY_ROUTE, JobStatus
from app.downloads.status import STOPPED_BY_ROUTE, JobKind, JobStatus
from app.models import DISPLAY_TEXT_MAX, DownloadJob, MediaAsset
log = logs.get_logger(__name__)
@@ -437,7 +438,7 @@ def _run_supervised(job_id: int, asset_id: int) -> None:
if status is None or status in STOPPED_BY_ROUTE:
reason = "cancelled" # a route stopped it (or the row vanished)
break
if status == "running":
if status == JobStatus.RUNNING:
if stale is not None and stale > stall_s:
reason = "stalled"
break
@@ -448,7 +449,7 @@ def _run_supervised(job_id: int, asset_id: int) -> None:
# teardown. A still-running job over the cap is failed ("timeout"); a terminal one (already
# done/error) just gets its lingering child killed, its DB status left intact ("abandon").
if time.monotonic() - started > wall_s:
reason = "timeout" if status == "running" else "abandon"
reason = "timeout" if status == JobStatus.RUNNING else "abandon"
break
# else: a terminal status under the cap (done/error, or a re-queued contended asset) means
# the child is exiting on its own — keep polling; NEVER kill a finishing child (that could
@@ -479,7 +480,7 @@ def _run_supervised(job_id: int, asset_id: int) -> None:
_reset_asset_pending(asset_id)
if proc.returncode != _CHILD_OK:
status, _ = _job_liveness(job_id)
if status == "running":
if status == JobStatus.RUNNING:
_cleanup_staging(asset_id)
_fail_running(
job_id,
@@ -560,15 +561,12 @@ def _process_job(job_id: int) -> None:
asset_id = asset.id if asset else None
asset_status = asset.status if asset else None
asset_error = asset.error if asset else None
if asset_status == "error":
if asset is not None and asset_status == "error":
# A job that meets an already-failed asset gets that failure's explanation — not a bare
# "Download failed". Only the text is on the asset, so it is diagnosed again, for this
# link, with whether a cookie goes with it asked of the same gate the download child
# used (`credentials.usable_cookie`) — as it stands now, so the advice fits this job's Retry.
url = service.source_url(job.source_kind, job.source_ref)
cookie = credentials.usable_cookie(
db, job.user_id, url, asset, formats.normalize(job.profile_snapshot)
)
url, cookie = _failed_link_and_cookie(db, job, asset)
diagnosis = dlerrors.diagnose(asset_error, url=url, cookie_attached=cookie is not None)
del cookie # only whether there is one matters here
@@ -605,13 +603,34 @@ def _process_job(job_id: int) -> None:
_run_supervised(job_id, asset_id)
def _failed_link_and_cookie(
db: Session, job: DownloadJob, asset: MediaAsset
) -> tuple[str | None, str | None]:
"""The link a job's failed asset was fetched from, and the cookie that fetch would go with now.
A clip's link is its source's (a `clip` ref names the user's range, no page), asked of the
clip's own cookie gate, as its fetch was (`_clip_source`); a Plex clip fetches nothing."""
if job.job_kind == JobKind.CLIP:
spec = dict(job.edit_spec or {})
if spec.get("source") != "youtube":
return None, None
url = service.source_url("youtube", spec["ref"])
return url, credentials.usable_clip_cookie(db, job.user_id, url, asset, spec)
url = service.source_url(job.source_kind, job.source_ref)
spec = formats.normalize(job.profile_snapshot)
return url, credentials.usable_cookie(db, job.user_id, url, asset, spec)
def _finish_from_cache(job_id: int, asset_id: int) -> None:
with SessionLocal() as db:
job = db.get(DownloadJob, job_id)
asset = db.get(MediaAsset, asset_id)
if job and asset:
fields = {"status": JobStatus.DONE, "progress": 100, "phase": None}
if not job.display_name and asset.title:
# A clip queued under the placeholder takes the title its sibling's fetch found.
unnamed = not job.display_name or (
job.job_kind == JobKind.CLIP and job.display_name == service.clip_title(None, None)
)
if unnamed and asset.title:
# display_name is VARCHAR(255); a title can be longer (e.g. a recipe in the title).
fields["display_name"] = asset.title[:DISPLAY_TEXT_MAX]
asset.last_access_at = datetime.now(timezone.utc)