fix: the download boot hook imports a model-only module, keeping the membership roster off the fetch path (#4433)
CI and images / lint (push) Failing after 4s
CI and images / extension-version (push) Successful in 4s
CI and images / extension-test (push) Successful in 18s
CI and images / frontend-build (push) Successful in 21s
CI and images / backend-lint-and-test (push) Successful in 32s
CI and images / integration (push) Successful in 2m22s
CI and images / sign-extension (push) Skipped
CI and images / build-web (push) Skipped
CI and images / smoke-web (push) Skipped
CI and images / promote (push) Skipped
CI and images / build-agent (push) Skipped

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR
This commit is contained in:
2026-09-25 10:32:41 -04:00
co-authored by Claude Opus 5.5
parent 0fad744bfb
commit e704c70f32
5 changed files with 62 additions and 48 deletions
+1 -44
View File
@@ -7,8 +7,7 @@ from datetime import UTC, datetime, timedelta
from pathlib import Path
from PIL import Image
from sqlalchemy import Integer, and_, cast, delete, func, literal, or_, select, update
from sqlalchemy.dialects.postgresql import JSONB
from sqlalchemy import Integer, and_, cast, delete, func, or_, select, update
from ..celery_app import celery
from ..models import (
@@ -732,48 +731,6 @@ def recover_stalled_download_events() -> int:
return events_recovered
DOWNLOAD_INTERRUPTED_MESSAGE = (
"interrupted by a worker restart — the next check picks it up where it left off"
)
def interrupt_orphaned_download_events(session, *, booted_at: datetime) -> int:
"""Close the download events a restart orphaned, without blaming the source.
Called when the download lane comes up (#4433). Anything still
pending/running from before this boot belongs to the previous process:
a walk that outlived the 90s stop grace was SIGKILLed, and a queued or
serialize-deferred task is held unacked until Redis redelivers it about an
hour later. Left alone, the 30-min stall sweep would error each one and
bump `consecutive_failures`, backing the source off as if the platform had
failed.
Instead they end as `skipped` (terminal, not a failure) and the source is
not touched: `last_checked_at` keeps its old value, so the next tick finds
it due and the walk resumes from its checkpoint. A redelivered message
that arrives later finds no pending event and opens a fresh one.
An event promoted to running after the boot has `started_at` reset to its
real start (download_service), so it is never caught here. Does NOT commit.
"""
now = datetime.now(UTC)
result = session.execute(
update(DownloadEvent)
.where(DownloadEvent.status.in_(["pending", "running"]))
.where(DownloadEvent.started_at < booted_at)
.values(
status="skipped",
finished_at=now,
error=DOWNLOAD_INTERRUPTED_MESSAGE,
metadata_=DownloadEvent.metadata_.op("||")(
literal({"error_type": "interrupted"}, JSONB)
),
)
.returning(DownloadEvent.id)
)
return len(result.all())
@celery.task(name="backend.app.tasks.maintenance.recover_stalled_backup_runs")
def recover_stalled_backup_runs() -> int:
"""Flip BackupRun rows stuck in running/restoring past the hard limit