Files
FabledCurator/backend/app/api/sources.py
T
bvandeusen 19aece1fc4
CI / lint (push) Successful in 3s
CI / backend-lint-and-test (push) Successful in 16s
CI / frontend-build (push) Successful in 27s
CI / intimp (push) Successful in 3m42s
CI / intapi (push) Successful in 7m38s
CI / intcore (push) Successful in 8m20s
feat(download): tick/backfill modes + partial-success classifier (plan #544)
Routine subscription polls walked the entire post history every tick
even when nothing had changed, because gallery-dl's default `skip: True`
continues iterating archived posts. A creator with ~550 archived posts
(Knuxy patreon) saturates the 870s wall-clock cap before completing,
even with zero downloads needed. Plus, a tier-limited run that
downloaded hundreds of files but ran out the clock should be a
warning, not an error.

Two coupled changes, both operator-flagged 2026-06-01:

* **Tick mode (default, cron polls).** New `TICK_SKIP_VALUE = "exit:20"`
  asks gallery-dl to exit after 20 contiguous archived items. Fresh
  subscriptions + new-content cases still walk normally; established
  subscription with zero new content exits in ~30s of HEAD requests
  instead of pegging the timeout. 20 (not 5) gives headroom against
  paywall warnings interleaving with archived items.
* **Backfill mode (explicit, operator-triggered).** Sticky for N runs
  via new `Source.backfill_runs_remaining` (alembic 0031). While > 0,
  downloads use `skip: True` + 1800s timeout. Auto-decrements per run
  with early-reset to 0 when a clean run finds zero files (queue
  drained). N defaults to 3 — multiple runs give the system enough
  budget to finish a deep walk across timeout boundaries. New
  `POST /api/sources/{id}/backfill` arms the source; "Deep scan"
  button on each SourceRow (chip shows remaining count) wires it.

Plus partial-success classifier: non-zero gallery-dl exit + ≥1 file
downloaded + no source-level error fires `ErrorType.PARTIAL`, which
download_service maps to `status=\"ok\"`. The run did real work; the
next tick continues via gallery-dl's archive. No more red events for
"timed out mid-walk after downloading 300 files."

Retires `SourceConfig.skip_existing` — skip value is now derived from
the source state and passed as a separate `skip_value` parameter
through download() / _build_config_for_source(). `GD_DEFAULTS` drops
the now-dead key (was inert data after this refactor).

Tests cover:
* tick + backfill skip-value emission in _build_config_for_source
* PARTIAL classifier branch + TIER_LIMITED-wins-over-PARTIAL ordering
* SourceService.set_backfill_runs validation + persistence
* /api/sources/{id}/backfill 200/400/404 paths
* download_service auto-decrement / auto-reset / tick-mode-no-touch
* PARTIAL → status=ok in the orchestrator (no consecutive_failures bump)
2026-06-01 18:23:28 -04:00

206 lines
8.0 KiB
Python

"""FC-3a: CRUD over Source rows. FC-3c adds POST /<id>/check."""
from quart import Blueprint, jsonify, request
from sqlalchemy import select
from ..extensions import get_session
from ..models import DownloadEvent, Source
from ..services.scheduler_service import active_platform_cooldowns, scheduler_status
from ..services.source_service import (
KNOWN_PLATFORMS,
ArtistNotFoundError,
DuplicateSourceError,
EmptyUrlError,
InvalidConfigError,
SourceService,
UnknownPlatformError,
)
from ._responses import error_response as _bad
sources_bp = Blueprint("sources", __name__, url_prefix="/api/sources")
@sources_bp.route("", methods=["GET"])
async def list_sources():
artist_id_raw = request.args.get("artist_id")
artist_id = None
if artist_id_raw is not None:
try:
artist_id = int(artist_id_raw)
except ValueError:
return _bad("invalid_artist_id", detail="artist_id must be an integer")
failing = request.args.get("failing", "").lower() in ("1", "true", "yes")
async with get_session() as session:
records = await SourceService(session).list(artist_id=artist_id, failing=failing)
return jsonify([r.to_dict() for r in records])
@sources_bp.route("/schedule-status", methods=["GET"])
async def schedule_status():
"""FC-dashboards: scheduler health for the Subscriptions hub."""
async with get_session() as session:
return jsonify(await scheduler_status(session))
@sources_bp.route("/<int:source_id>", methods=["GET"])
async def get_source(source_id: int):
async with get_session() as session:
record = await SourceService(session).get(source_id)
if record is None:
return _bad("not_found", status=404, detail=f"source id={source_id}")
return jsonify(record.to_dict())
@sources_bp.route("", methods=["POST"])
async def create_source():
body = await request.get_json()
if not isinstance(body, dict):
return _bad("invalid_body", detail="body must be a JSON object")
try:
artist_id = int(body["artist_id"])
platform = body["platform"]
url = body["url"]
except (KeyError, TypeError, ValueError):
return _bad("invalid_body", detail="artist_id, platform, url are required")
optional = {
k: body[k]
for k in ("enabled", "config_overrides", "check_interval_override")
if k in body
}
async with get_session() as session:
svc = SourceService(session)
try:
record = await svc.create(
artist_id=artist_id, platform=platform, url=url, **optional,
)
except ArtistNotFoundError:
return _bad("artist_not_found", status=404, detail=f"artist id={artist_id}")
except UnknownPlatformError as exc:
return _bad("unknown_platform", detail=str(exc), known=sorted(KNOWN_PLATFORMS))
except InvalidConfigError as exc:
return _bad("invalid_config", detail=str(exc))
except EmptyUrlError as exc:
return _bad("empty_url", detail=str(exc))
except DuplicateSourceError as exc:
return _bad("duplicate", status=409, existing_id=exc.existing_id)
return jsonify(record.to_dict()), 201
@sources_bp.route("/<int:source_id>", methods=["PATCH"])
async def patch_source(source_id: int):
body = await request.get_json()
if not isinstance(body, dict):
return _bad("invalid_body", detail="body must be a JSON object")
async with get_session() as session:
svc = SourceService(session)
try:
record = await svc.update(source_id, **body)
except LookupError:
return _bad("not_found", status=404)
except UnknownPlatformError as exc:
return _bad("unknown_platform", detail=str(exc), known=sorted(KNOWN_PLATFORMS))
except InvalidConfigError as exc:
return _bad("invalid_config", detail=str(exc))
except EmptyUrlError as exc:
return _bad("empty_url", detail=str(exc))
except DuplicateSourceError as exc:
return _bad("duplicate", status=409, existing_id=exc.existing_id)
return jsonify(record.to_dict())
@sources_bp.route("/<int:source_id>", methods=["DELETE"])
async def delete_source(source_id: int):
async with get_session() as session:
try:
await SourceService(session).delete(source_id)
except LookupError:
return _bad("not_found", status=404)
return "", 204
@sources_bp.route("/<int:source_id>/backfill", methods=["POST"])
async def set_backfill(source_id: int):
"""Plan #544: arm a source for backfill mode for the next N download
runs. Body: `{"runs": int}` (1..10, default 3). Returns the updated
source dict. While backfill_runs_remaining > 0, downloads use
gallery-dl's full-walk config (skip: True + 30-min timeout) instead
of the catch-up default (skip: "exit:20" + 14.5-min timeout)."""
payload = await request.get_json(silent=True) or {}
runs = payload.get("runs", 3)
try:
runs = int(runs)
except (TypeError, ValueError):
return _bad("invalid_runs", detail="runs must be an integer")
async with get_session() as session:
try:
record = await SourceService(session).set_backfill_runs(
source_id, runs,
)
except LookupError:
return _bad("not_found", status=404)
except ValueError as exc:
return _bad("invalid_runs", detail=str(exc))
return jsonify(record.to_dict())
@sources_bp.route("/<int:source_id>/check", methods=["POST"])
async def check_source(source_id: int):
"""FC-3c: enqueue a download for this source.
Returns 202 with the new DownloadEvent id. If a pending/running
event already exists for this source, returns 409 with that id. If
the source's platform is currently in a rate-limit cooldown, returns
**202 with `{status: "deferred", cooldown_until, platform}`** and
does NOT create an event or dispatch — the bulk retry path uses this
to avoid bowling N sources right back into the rate limit the
cooldown is preventing. Single-click "retry this one source" passes
`?force=true` to override the cooldown (operator-explicit, useful
for rapid auth-fix testing). The in-flight guard always applies.
"""
force = (request.args.get("force") or "").lower() in ("1", "true", "yes")
async with get_session() as session:
source = (await session.execute(
select(Source).where(Source.id == source_id)
)).scalar_one_or_none()
if source is None:
return _bad("not_found", status=404, detail=f"source id={source_id}")
if not source.enabled:
return _bad("source_disabled", detail="enable the source first")
# Cooldown gate (unless explicitly overridden). Checked before the
# in-flight guard because a deferred retry doesn't need to create
# or check for an event at all.
if not force:
cooldowns = await active_platform_cooldowns(session)
expires_at = cooldowns.get(source.platform)
if expires_at is not None:
return jsonify({
"status": "deferred",
"platform": source.platform,
"cooldown_until": expires_at.isoformat(),
}), 202
in_flight = (await session.execute(
select(DownloadEvent.id).where(
DownloadEvent.source_id == source_id,
DownloadEvent.status.in_(["pending", "running"]),
).order_by(DownloadEvent.id.desc()).limit(1)
)).scalar_one_or_none()
if in_flight is not None:
return jsonify(
{"download_event_id": in_flight, "status": "already_running"}
), 409
event = DownloadEvent(source_id=source_id, status="pending")
session.add(event)
await session.commit()
await session.refresh(event)
event_id = event.id
from ..tasks.download import download_source
download_source.delay(source_id)
return jsonify({"download_event_id": event_id, "status": "pending"}), 202