feat(downloads): clear multi-phase download progress + transient-error retries

The progress bar looked broken (95% -> 5% -> recount) because yt-dlp downloads the video and
audio streams separately (each 0->100%) then merges — with no indication of which step is
running. Now:
- worker labels the phase from the stream codecs (video / audio) and via a postprocessor hook
  (merging / processing), so the user sees what's happening
- DownloadCenter shows the phase as the status and renders an indeterminate pulse (no bogus %)
  during merge/processing; phase i18n en/hu/de
- yt-dlp retries (3) + fragment_retries (5) so transient network blips self-heal instead of
  failing the job (seen once as a DNS 'No address associated with hostname' error)

Verified: phase transitions queued -> video -> processing -> done.
This commit is contained in:
npeter83 2026-07-03 02:42:36 +02:00
parent c6ceaea899
commit b200f61642
6 changed files with 73 additions and 9 deletions

View file

@ -91,6 +91,10 @@ def build_ydl_opts(spec: dict, outtmpl: str, progress_hook) -> dict:
"writethumbnail": True, # kept for the poster.jpg sidecar (and embed, if requested)
"progress_hooks": [progress_hook],
"postprocessors": [],
# Self-heal transient network blips instead of failing the whole job.
"retries": 3,
"fragment_retries": 5,
"retry_sleep": {"http": 2, "fragment": 2},
}
if s["mode"] == "a":

View file

@ -219,6 +219,18 @@ def _make_progress_hook(job_id: int, asset_id: int):
if now - state["last_db"] < 1.0:
return
state["last_db"] = now
# yt-dlp downloads the video and audio streams SEPARATELY (each 0→100%), then merges.
# Label the phase so the user understands the bar resetting between streams instead of
# seeing a mysterious 95%→5% jump.
info = d.get("info_dict") or {}
vcodec = info.get("vcodec") or "none"
acodec = info.get("acodec") or "none"
if vcodec != "none" and acodec == "none":
phase = "video"
elif acodec != "none" and vcodec == "none":
phase = "audio"
else:
phase = "media"
total = d.get("total_bytes") or d.get("total_bytes_estimate") or 0
done = d.get("downloaded_bytes") or 0
pct = int(done * 100 / total) if total else 0
@ -227,12 +239,25 @@ def _make_progress_hook(job_id: int, asset_id: int):
progress=min(pct, 99),
speed_bps=int(d["speed"]) if d.get("speed") else None,
eta_s=int(d["eta"]) if d.get("eta") else None,
phase="downloading",
phase=phase,
)
return hook
def _make_pp_hook(job_id: int):
"""Postprocessor hook: surface the ffmpeg merge/convert/extract step so the bar shows a
'Merging/Processing' label instead of freezing at 100% after the streams finish."""
def hook(d: dict) -> None:
if d.get("status") in ("started", "processing"):
pp = d.get("postprocessor") or ""
phase = "merging" if "Merg" in pp else "processing"
_set_job(job_id, phase=phase, speed_bps=None, eta_s=None)
return hook
def _staging_dir(asset_id: int) -> Path:
return Path(settings.download_root) / ".staging" / f"asset-{asset_id}"
@ -253,6 +278,7 @@ def _download(job_id: int, asset_id: int, source_kind: str, source_ref: str, spe
outtmpl = str(staging / "%(id)s.%(ext)s")
opts = formats.build_ydl_opts(spec, outtmpl, _make_progress_hook(job_id, asset_id))
opts["postprocessor_hooks"] = [_make_pp_hook(job_id)]
url = service.source_url(source_kind, source_ref)
_set_job(job_id, phase="downloading", progress=0)