fix(worker): cancel abandoned slskd transfers + cap download fall-through

Two compounding causes of 'many downloads of one album from different sources' in
slskd: (1) the slskd client raised on timeout/error WITHOUT cancelling the transfer
it enqueued, so as the pipeline fell through to other peers each left a transfer
running; (2) the incomplete-download fall-through was uncapped, grinding through
every candidate of a popular album (~200 Soulseek peers), amplified now that Qobuz
pacing pushes most jobs to Soulseek.

- SlskdClient.download now cancels its enqueued transfers (DELETE) on any abandon.
- The download loop caps at _MAX_DOWNLOAD_ATTEMPTS (6) candidates.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Jonathan
2026-07-15 19:03:05 +02:00
parent 67f374c470
commit 1fc61a0f5a
4 changed files with 140 additions and 0 deletions
@@ -89,3 +89,37 @@ def test_all_sources_incomplete_still_needs_attention(conn, tmp_path):
run_pipeline(conn, job_id, [_Qobuz(deliver=2), _Soulseek(deliver=1)], dest_root=str(tmp_path))
assert _state_error(conn, job_id) == ("needs_attention", "incomplete download")
assert not (tmp_path / "Radiohead" / "In Rainbows").exists() # nothing imported
class _CountingIncompleteQobuz:
"""Offers `n` candidates that all download but come back incomplete; counts download calls."""
name = "qobuz"
tier = 0
def __init__(self, n):
self.n = n
self.calls = 0
def health(self):
return True
def search(self, target):
q = _HIRES
return [Candidate(source="qobuz", source_ref=f"r{i}", matched_artist=target.artist,
matched_album=target.album, quality=q, track_count=3, source_tier=0)
for i in range(self.n)]
def download(self, candidate, dest, on_progress):
self.calls += 1
_stage(dest, 1) # 1 of 3 → always incomplete
return DownloadResult(ok=True, path=dest, track_count=1)
def test_fall_through_is_capped(conn):
from lyra_worker.pipeline import _MAX_DOWNLOAD_ATTEMPTS
a = _CountingIncompleteQobuz(n=20)
job_id = insert_request(conn, artist="Radiohead", album="In Rainbows")
claim_next(conn)
run_pipeline(conn, job_id, [a], dest_root="/tmp/lib-cap")
assert _state_error(conn, job_id) == ("needs_attention", "incomplete download")
assert a.calls == _MAX_DOWNLOAD_ATTEMPTS # capped, not all 20 peers tried