danvics/soulsync
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

diag: log every cancel_download caller with a trigger label

Browse source 
Diagnostic-only change for issue Technodude reported: Tidal sync-playlist
downloads getting mass-cancelled mid-flight with no clear cause in the
logs. App.log shows ~91 second gaps between Tidal download start and
cancel — matches the monitor's 90s queue-timeout exactly — but none of
the monitor's WARNING log lines fire, so the trigger is ambiguous
between five `_should_retry_task` paths, three web_server cancel paths,
and the API endpoints.

Added a single `[CancelTrigger:<label>]` INFO log line immediately
before every `download_orchestrator.cancel_download(...)` call so the
next log dump pins down which path is firing.

Labels (grep-able, prefix tells the file, suffix tells the trigger):

  monitor.not_in_live_transfers_90s
  monitor.errored_state_retry
  monitor.queued_state_timeout
  monitor.stuck_at_0pct_timeout
  monitor.unknown_state_no_progress_timeout
  candidates.worker_cancelled_during_download
  web.orphan_cleanup
  web.cancel_download_task
  web.atomic_cancel_v2
  api.manual_cancel_single
  api.public_cancel

The monitor's `deferred_ops` tuple grew from 3 elements to 4 (added
trigger label as last element). The dispatch loop unpacks both legacy
and new shapes so the change is backward-compatible for any in-flight
ops mid-deploy.

Zero behavior change. 367 download tests still green. WHATS_NEW left
untouched — diagnostic only, not user-facing.

After ship: ask Technodude to re-run the same sync playlist scenario,
attach the new app.log, grep `[CancelTrigger:` lines for the trigger
context, then write the actual fix.
This commit is contained in:
Broque Thomas 2026-05-19 22:31:29 -07:00
parent 716ec66cf5
commit a685f9ca4a
5 changed files with 47 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
api/downloads.py
View file

@ -125,6 +125,9 @@ def register_routes(bp):
if not soulseek:
return api_error("NOT_AVAILABLE", "Soulseek client not configured.", 503)
current_app.logger.info(
f"[CancelTrigger:api.public_cancel] download_id={download_id} username={username}"
)
ok = run_async(soulseek.cancel_download(download_id, username, remove=True))
if ok:
return api_success({"message": "Download cancelled."})

3
core/downloads/cancel.py
View file

@ -45,6 +45,9 @@ _TERMINAL_STATUSES = {
def cancel_single_download(download_orchestrator, run_async: Callable,
download_id: str, username: str) -> bool:
"""Cancel one specific slskd download (with `remove=True`)."""
logger.info(
f"[CancelTrigger:api.manual_cancel_single] download_id={download_id} username={username}"
)
return run_async(download_orchestrator.cancel_download(download_id, username, remove=True))

4
core/downloads/candidates.py
View file

@ -343,6 +343,10 @@ def attempt_download_with_candidates(task_id, candidates, track, batch_id=None,
logger.warning(f"[Modal Worker] Task {task_id} cancelled after download {download_id} started - attempting to cancel download")
# Try to cancel the download immediately
try:
logger.info(
f"[CancelTrigger:candidates.worker_cancelled_during_download] "
f"download_id={download_id} username={username} task_id={task_id}"
)
deps.run_async(deps.download_orchestrator.cancel_download(download_id, username, remove=True))
logger.warning(f"Successfully cancelled active download {download_id}")
except Exception as cancel_error:

30
core/downloads/monitor.py
View file

@ -197,8 +197,21 @@ class WebUIDownloadMonitor:
for op in deferred_ops:
try:
if op[0] == 'cancel_download':
# Issue #648 diagnostic — `op` now carries a trigger
# label (4-tuple, was 3-tuple) so the next log dump
# tells us WHICH path in `_should_retry_task` is
# firing for users seeing "Tidal downloads failed to
# start" mass-cancels. Label format pinned in commit
# message for grep-ability.
if len(op) >= 4:
_, download_id, username, trigger = op[0], op[1], op[2], op[3]
else:
_, download_id, username = op
logger.debug(f"[Deferred] Cancelling download: {download_id} from {username}")
trigger = 'unlabeled'
logger.info(
f"[CancelTrigger:monitor.{trigger}] download_id={download_id} "
f"username={username}"
)
run_async(download_orchestrator.cancel_download(download_id, username, remove=True))
logger.debug(f"[Deferred] Successfully cancelled download {download_id}")
elif op[0] == 'cleanup_orphan':
@ -353,7 +366,8 @@ class WebUIDownloadMonitor:
# Defer slskd cancel to outside the lock
if task_username and download_id:
deferred_ops.append(('cancel_download', download_id, task_username))
deferred_ops.append(('cancel_download', download_id, task_username,
'not_in_live_transfers_90s'))
# Mark current source as used (full filename to match worker format)
if task_username and task_filename:
@ -424,7 +438,8 @@ class WebUIDownloadMonitor:
# Defer slskd cancel to outside the lock
if username and download_id:
deferred_ops.append(('cancel_download', download_id, username))
deferred_ops.append(('cancel_download', download_id, username,
'errored_state_retry'))
# Mark current source as used to prevent retry loops
# CRITICAL: Use full filename (not basename) to match worker's source_key format
@ -527,7 +542,8 @@ class WebUIDownloadMonitor:
# Defer slskd cancel to outside the lock
if username and download_id:
deferred_ops.append(('cancel_download', download_id, username))
deferred_ops.append(('cancel_download', download_id, username,
'queued_state_timeout'))
# UNIFIED RETRY LOGIC: Handle timeout retry exactly like error retry
# Mark current source as used to prevent retry loops
@ -615,7 +631,8 @@ class WebUIDownloadMonitor:
# Defer slskd cancel to outside the lock
if username and download_id:
deferred_ops.append(('cancel_download', download_id, username))
deferred_ops.append(('cancel_download', download_id, username,
'stuck_at_0pct_timeout'))
# UNIFIED RETRY LOGIC: Handle 0% timeout retry exactly like error retry
# Mark current source as used to prevent retry loops
@ -704,7 +721,8 @@ class WebUIDownloadMonitor:
download_id = task.get('download_id')
if username and download_id:
deferred_ops.append(('cancel_download', download_id, username))
deferred_ops.append(('cancel_download', download_id, username,
'unknown_state_no_progress_timeout'))
if username and filename:
used_sources = task.get('used_sources', set())

12
web_server.py
View file

@ -6068,6 +6068,10 @@ def get_download_status():
transfer_id = file_info.get('id')
if transfer_id:
try:
logger.info(
f"[CancelTrigger:web.orphan_cleanup] "
f"download_id={transfer_id} username={username}"
)
run_async(download_orchestrator.cancel_download(str(transfer_id), username, remove=True))
except Exception as e:
logger.debug("orphan transfer cancel failed: %s", e)
@ -16980,6 +16984,10 @@ def cancel_download_task():
# Optionally try to cancel the Soulseek download (don't block worker progression)
if download_id and username:
try:
logger.info(
f"[CancelTrigger:web.cancel_download_task] "
f"download_id={download_id} username={username} task_id={task_id}"
)
# This is an async call, so we run it and wait
run_async(download_orchestrator.cancel_download(download_id, username, remove=True))
logger.warning(f"Successfully cancelled Soulseek download {download_id} for task {task_id}")
@ -17232,6 +17240,10 @@ def cancel_task_v2():
# and silently left streaming downloads running in background.
try:
logger.info(f"[Atomic Cancel] Dispatching cancel to orchestrator: username={username} download_id={download_id}")
logger.info(
f"[CancelTrigger:web.atomic_cancel_v2] "
f"download_id={download_id} username={username}"
)
cancel_success = run_async(
download_orchestrator.cancel_download(download_id, username, remove=True)
)