Files
FabledCurator/backend/app/services/download_service.py
T
bvandeusen f05aaa707b
CI / lint (push) Successful in 3s
CI / frontend-build (push) Successful in 19s
CI / backend-lint-and-test (push) Failing after 26s
CI / intimp (push) Successful in 3m46s
CI / intapi (push) Failing after 8m10s
CI / intcore (push) Failing after 9m42s
fix(audit-g5d): surface ErrorType taxonomy on FailingSourcesCard
Alembic 0032 adds Source.error_type (varchar(32), indexed).
_update_source_health stamps it alongside last_error on status='error'
and clears it on 'ok'. SourceRecord/to_dict exposes it.

FailingSourcesCard renders a colored chip next to the consecutive-
failures count, with a tooltip explaining the suggested operator
action. Color reflects intent:
  - warning (yellow) — operator action needed (auth_error)
  - info (blue)      — backend-paced (rate_limited / timeout /
                       network_error / partial / tier_limited)
  - error (red)      — likely terminal without intervention
                       (not_found / access_denied / validation_failed /
                        unsupported_url / http_error / unknown_error)

Audit 2026-06-02: the backend computed 13 ErrorType categories but
only the free-text last_error reached the operator. Bulk-triage by
class ("all auth_error → rotate cookies", "12 rate_limited → just
wait") required opening Logs per row.
2026-06-02 17:54:44 -04:00

470 lines
20 KiB
Python

"""FC-3c download orchestrator.
Three-phase pipeline:
Phase 1 — DB setup (brief session): load source, mark event running,
fetch credentials + settings.
Phase 2 — Execute (no DB connection): call GalleryDLService; on
Patreon campaign-ID failure, resolve vanity and retry once.
Phase 3 — Import + persist (fresh session): attach_in_place each
written file; clean up duplicates; persist rich metadata.
"""
from __future__ import annotations
import asyncio
import logging
import re
from datetime import UTC, datetime
from pathlib import Path
from typing import Any
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from sqlalchemy.orm import Session as SyncSession
from sqlalchemy.orm import joinedload
from ..models import Artist, DownloadEvent, Source
from .credential_service import CredentialService
from .gallery_dl import (
BACKFILL_SKIP_VALUE,
BACKFILL_TIMEOUT_SECONDS,
TICK_SKIP_VALUE,
ErrorType,
GalleryDLService,
SourceConfig,
)
from .importer import Importer
from .patreon_resolver import resolve_campaign_id
from .platforms import auth_type_for
from .scheduler_service import set_platform_cooldown
log = logging.getLogger(__name__)
_PATREON_VANITY_RE = re.compile(
r"^https?://(?:www\.)?patreon\.com/(?:c/)?(?!id:)([^/?#]+)",
re.IGNORECASE,
)
_CAMPAIGN_ID_FAILURE_PATTERN = "failed to extract campaign id"
def _extract_patreon_vanity(url: str) -> str | None:
m = _PATREON_VANITY_RE.match(url)
return m.group(1) if m else None
def _looks_like_campaign_id_failure(stdout: str, stderr: str) -> bool:
return _CAMPAIGN_ID_FAILURE_PATTERN in f"{stdout}\n{stderr}".lower()
def _effective_url(platform: str, source_url: str, overrides: dict) -> str:
if platform == "patreon" and overrides.get("patreon_campaign_id"):
return f"https://www.patreon.com/id:{overrides['patreon_campaign_id']}"
return source_url
class DownloadService:
"""Async orchestrator. The Celery task runs `asyncio.run(svc.download_source(N))`.
The Importer is sync (existing FC convention); calls to attach_in_place
happen via run_in_executor.
"""
def __init__(
self,
async_session: AsyncSession,
sync_session: SyncSession,
gdl: GalleryDLService,
importer: Importer,
cred_service: CredentialService,
):
self.async_session = async_session
self.sync_session = sync_session
self.gdl = gdl
self.importer = importer
self.cred_service = cred_service
async def download_source(self, source_id: int) -> int:
"""Returns DownloadEvent.id. Idempotent: in-flight events are returned as-is."""
setup = await self._phase1_setup(source_id)
if setup["status"] in ("skipped", "in_flight"):
return setup["event_id"]
ctx = setup
source_config = SourceConfig.from_dict(ctx["config_overrides"] or {})
# alembic 0031 / plan #544: derive skip_value + timeout from the
# source's backfill_runs_remaining counter. When > 0, walk the full
# post history (skip: True + 1800s); when 0, exit gallery-dl after
# 20 contiguous archived items (skip: "exit:20" + the default
# 870s). Operator sets backfill via POST /api/sources/{id}/backfill.
backfill_remaining = ctx.get("backfill_runs_remaining", 0) or 0
if backfill_remaining > 0:
skip_value: bool | str = BACKFILL_SKIP_VALUE
source_config.timeout = BACKFILL_TIMEOUT_SECONDS
else:
skip_value = TICK_SKIP_VALUE
effective_url = _effective_url(
ctx["platform"], ctx["url"], ctx["config_overrides"] or {}
)
dl_result = await self.gdl.download(
url=effective_url,
artist_slug=ctx["artist_slug"],
platform=ctx["platform"],
source_config=source_config,
cookies_path=ctx["cookies_path"],
auth_token=ctx["auth_token"],
skip_value=skip_value,
)
resolved_campaign_id: str | None = None
if (
ctx["platform"] == "patreon"
and not dl_result.success
and "patreon_campaign_id" not in (ctx["config_overrides"] or {})
and _looks_like_campaign_id_failure(dl_result.stdout, dl_result.stderr)
):
vanity = _extract_patreon_vanity(ctx["url"])
if vanity:
log.info(
"Attempting campaign-ID resolution for %s (%s)",
ctx["artist_slug"], vanity,
)
resolved_campaign_id = await resolve_campaign_id(
vanity, ctx["cookies_path"]
)
if resolved_campaign_id:
dl_result = await self.gdl.download(
url=f"https://www.patreon.com/id:{resolved_campaign_id}",
artist_slug=ctx["artist_slug"],
platform=ctx["platform"],
source_config=source_config,
cookies_path=ctx["cookies_path"],
auth_token=ctx["auth_token"],
skip_value=skip_value,
)
return await self._phase3_persist(
ctx["event_id"], ctx, dl_result, resolved_campaign_id,
)
async def _phase1_setup(self, source_id: int) -> dict[str, Any]:
source = (await self.async_session.execute(
select(Source).options(joinedload(Source.artist)).where(Source.id == source_id)
)).scalar_one_or_none()
if source is None:
raise LookupError(f"source {source_id} not found")
if not source.enabled:
ev = DownloadEvent(source_id=source_id, status="pending")
self.async_session.add(ev)
await self.async_session.commit()
await self.async_session.refresh(ev)
await self._finalize_event_and_source(
event_id=ev.id, source_id=source_id, status="skipped",
error_message="source disabled",
)
return {"status": "skipped", "event_id": ev.id}
existing = (await self.async_session.execute(
select(DownloadEvent).where(
DownloadEvent.source_id == source_id,
DownloadEvent.status.in_(["pending", "running"]),
).order_by(DownloadEvent.id.desc()).limit(1)
)).scalar_one_or_none()
if existing and existing.status == "running":
return {"status": "in_flight", "event_id": existing.id}
if existing and existing.status == "pending":
existing.status = "running"
# Reset started_at on the pending→running transition so the
# recovery sweep (DOWNLOAD_STALL_THRESHOLD_MINUTES, 30 min)
# measures from real start, not from enqueue. On heavy-queue
# days a freshly-promoted event whose original started_at
# predated the cutoff would otherwise get swept mid-flight,
# racing phase3's commit. Audit 2026-06-02.
existing.started_at = datetime.now(UTC)
await self.async_session.commit()
event_id = existing.id
else:
ev = DownloadEvent(source_id=source_id, status="running")
self.async_session.add(ev)
await self.async_session.commit()
await self.async_session.refresh(ev)
event_id = ev.id
artist = source.artist
# Drive cookies-vs-token selection from the platform registry's
# auth_type so a new 7th token-platform automatically picks the
# right credential path. The hardcoded tuple here used to drift
# out of sync with credential_service's auth_type_for(). Audit
# 2026-06-02.
if auth_type_for(source.platform) == "token":
cookies_path = None
auth_token = await self.cred_service.get_token(source.platform)
else:
cookies_path_obj = await self.cred_service.get_cookies_path(source.platform)
cookies_path = str(cookies_path_obj) if cookies_path_obj else None
auth_token = None
return {
"status": "ok",
"event_id": event_id,
"source_id": source_id,
"url": source.url,
"platform": source.platform,
"artist_slug": artist.slug if artist else "_unknown",
"artist_id": artist.id if artist else None,
"config_overrides": dict(source.config_overrides or {}),
"cookies_path": cookies_path,
"auth_token": auth_token,
"backfill_runs_remaining": source.backfill_runs_remaining or 0,
}
async def _phase3_persist(
self,
event_id: int,
ctx: dict,
dl_result,
resolved_campaign_id: str | None,
) -> int:
# Cache Patreon campaign id on the source.
if resolved_campaign_id:
src = self.sync_session.get(Source, ctx["source_id"])
if src is not None:
src.config_overrides = {
**(src.config_overrides or {}),
"patreon_campaign_id": resolved_campaign_id,
}
self.sync_session.commit()
artist = None
source_row = None
if ctx.get("artist_id"):
artist = self.sync_session.get(Artist, ctx["artist_id"])
source_row = self.sync_session.get(Source, ctx["source_id"])
import_summary = {"attached": 0, "skipped": 0, "errors": 0}
bytes_downloaded = 0
loop = asyncio.get_running_loop()
for path_str in dl_result.written_paths or []:
if path_str in (dl_result.quarantined_paths or []):
continue
path = Path(path_str)
# Sync stdlib filesystem ops are intentional here: this orchestrator
# runs under `asyncio.run` inside a Celery task — no other awaitables
# compete for the loop. ASYNC240 suppressed below.
if not path.exists(): # noqa: ASYNC240
continue
def _attach(p=path):
return self.importer.attach_in_place(
p, artist=artist, source=source_row,
)
result = await loop.run_in_executor(None, _attach)
if result.status in ("imported", "superseded"):
import_summary["attached"] += 1
try:
bytes_downloaded += path.stat().st_size # noqa: ASYNC240
except OSError:
pass
# Enqueue thumbnail + ML for newly-attached images, matching
# the filesystem-import path (tasks/import_file.py:228-239).
# Importer.attach_in_place deliberately skips inline thumb
# generation to keep the import queue moving; the calling
# task is responsible for the enqueue. Operator-flagged
# 2026-06-01: without this, every downloaded image stayed
# at thumbnail_path=NULL until a periodic backfill swept
# it up, surfacing as broken-thumbnail tiles in the gallery
# for hours after a download landed. Lazy import to avoid
# circular-import risk between this service and the
# tasks/* modules that import it.
from ..tasks.ml import tag_and_embed
from ..tasks.thumbnail import generate_thumbnail
ids = list(result.member_image_ids)
if result.image_id is not None and result.image_id not in ids:
ids.append(result.image_id)
for img_id in ids:
generate_thumbnail.delay(img_id)
tag_and_embed.delay(img_id)
elif result.status == "attached":
# Non-media or extracted archive captured as PostAttachment
# (FC-2d-iii). The canonical copy lives in the attachments
# store; the original download path is now redundant —
# mirror duplicate_hash cleanup so we don't keep two copies.
# Operator-flagged 2026-06-02 (Lustria OST zip).
import_summary["attached"] += 1
try:
bytes_downloaded += path.stat().st_size # noqa: ASYNC240
except OSError:
pass
try:
path.unlink(missing_ok=True) # noqa: ASYNC240
except OSError:
pass
elif result.status == "skipped" and result.skip_reason and result.skip_reason.value in (
"duplicate_hash", "duplicate_phash",
):
import_summary["skipped"] += 1
try:
path.unlink(missing_ok=True) # noqa: ASYNC240
except OSError:
pass
elif result.status == "skipped":
# Soft skip (too_small, too_transparent, invalid_image) —
# the file just didn't qualify, not a download/ingest
# failure. Don't flag the run as error; the file stays
# on disk for operator inspection.
import_summary["skipped"] += 1
elif result.status == "failed":
# Hard failure (today only: archive probe crash/timeout).
# The original archive sits in /images/ as an orphan; the
# filesystem scanner would re-import and re-crash on the
# same file, so delete the source file and surface the
# error in import_summary. Audit 2026-06-02.
import_summary["errors"] += 1
try:
path.unlink(missing_ok=True) # noqa: ASYNC240
except OSError:
pass
elif result.status == "refreshed":
# Currently unreachable from attach_in_place (the download
# path never runs in deep=True mode), but the importer's
# ImportResult contract enumerates it. Treat the same as
# 'attached' — work happened, no error. Audit 2026-06-02.
import_summary["attached"] += 1
else:
import_summary["errors"] += 1
ev = (await self.async_session.execute(
select(DownloadEvent).where(DownloadEvent.id == event_id)
)).scalar_one()
run_stats = self.gdl._compute_run_stats(
dl_result.return_code, dl_result.stdout, dl_result.stderr
)
run_stats["quarantined_count"] = dl_result.files_quarantined
stderr_summary = self.gdl._extract_errors_warnings(dl_result.stderr)
# Plan #544: PARTIAL means the run downloaded ≥1 file but the
# subprocess didn't finish in budget (typically wall-clock timeout
# mid-walk). Real work happened; the next tick continues via
# gallery-dl's archive. NOT a failure for status purposes.
if dl_result.success and import_summary["errors"] == 0:
status = "ok"
elif dl_result.error_type == ErrorType.PARTIAL and import_summary["errors"] == 0:
status = "ok"
else:
status = "error"
ev.status = status
ev.finished_at = datetime.now(UTC)
ev.files_count = import_summary["attached"]
ev.bytes_downloaded = bytes_downloaded
ev.error = dl_result.error_message if status == "error" else None
ev.metadata_ = {
"run_stats": run_stats,
"error_type": dl_result.error_type.value if dl_result.error_type else None,
"stdout": self.gdl._truncate_log(dl_result.stdout) or None,
"stderr": self.gdl._truncate_log(dl_result.stderr) or None,
"stderr_errors_warnings": stderr_summary or None,
"duration_seconds": dl_result.duration_seconds,
"quarantined_paths": dl_result.quarantined_paths or None,
"import_summary": import_summary,
}
await self._update_source_health(
source_id=ctx["source_id"], status=status, error_message=ev.error,
error_type=dl_result.error_type.value if dl_result.error_type else None,
)
# Plan #544: backfill lifecycle — auto-complete when a clean
# backfill run drained the queue (gallery-dl exited 0 + zero files
# downloaded means there was nothing to fetch); otherwise decrement
# the counter. Next tick falls back to tick mode once it hits 0.
#
# Audit 2026-06-02 gating: VALIDATION_FAILED also exits the
# subprocess with return_code=0 and files_downloaded=0 (every
# file was quarantined), which used to match the auto-complete
# predicate exactly — zeroing the operator's armed budget on
# the FIRST quarantine run instead of decrementing. Require
# dl_result.success + no error_type so only genuinely-empty
# successful runs drain the counter.
backfill_remaining = ctx.get("backfill_runs_remaining", 0) or 0
if backfill_remaining > 0:
src = (await self.async_session.execute(
select(Source).where(Source.id == ctx["source_id"])
)).scalar_one()
queue_drained = (
dl_result.success
and dl_result.error_type is None
and dl_result.return_code == 0
and dl_result.files_downloaded == 0
)
if queue_drained:
src.backfill_runs_remaining = 0
else:
src.backfill_runs_remaining = max(0, backfill_remaining - 1)
await self.async_session.commit()
return event_id
async def _update_source_health(
self, *, source_id: int, status: str, error_message: str | None,
error_type: str | None = None,
) -> None:
"""FC-3d: update Source.{consecutive_failures, last_error, last_checked_at}.
ok -> failures = 0, error = None, checked_at = now
error -> failures += 1, error = error_message, checked_at = now
skipped -> failures unchanged, error = None, checked_at = now
When error_type == 'rate_limited', also stamps a platform-wide
cooldown via scheduler_service.set_platform_cooldown so the next
scan tick skips every source on this platform until the cooldown
expires. Preventive half of the burst-prevention pair —
consecutive_failures still backs the offending source off across
ticks.
"""
source = (await self.async_session.execute(
select(Source).where(Source.id == source_id)
)).scalar_one()
now = datetime.now(UTC)
if status == "ok":
source.consecutive_failures = 0
source.last_error = None
# alembic 0032 — clear the failure-class chip on success.
source.error_type = None
elif status == "error":
source.consecutive_failures = (source.consecutive_failures or 0) + 1
source.last_error = error_message
# alembic 0032 — stamp the failure-class so FailingSourcesCard
# can render a colored chip and operators can bulk-triage
# by error class without opening Logs per row.
source.error_type = error_type
if error_type == "rate_limited":
await set_platform_cooldown(self.async_session, source.platform)
elif status == "skipped":
source.last_error = None
source.last_checked_at = now
async def _finalize_event_and_source(
self, *, event_id: int, source_id: int, status: str,
error_message: str | None,
) -> None:
"""Finalize the event AND the source-health columns in one
transactional step. Used by the skipped early-out path and by
unit tests that exercise the source-health writes directly.
"""
ev = (await self.async_session.execute(
select(DownloadEvent).where(DownloadEvent.id == event_id)
)).scalar_one()
ev.status = status
ev.finished_at = datetime.now(UTC)
ev.error = error_message
await self._update_source_health(
source_id=source_id, status=status, error_message=error_message,
)
await self.async_session.commit()