Merge pull request 'Sidecar synthetic anchor cleanup + tier-gated classifier fix' (#39) from dev into main
CI / lint (push) Successful in 5s
CI / frontend-build (push) Successful in 22s
CI / backend-lint-and-test (push) Successful in 28s
CI / intimp (push) Successful in 3m54s
Build images / sign-extension (push) Has been skipped
Build images / build-web (push) Successful in 1m1s
Build images / build-ml (push) Successful in 1m21s
CI / intapi (push) Successful in 7m31s
CI / intcore (push) Successful in 8m0s

This commit was merged in pull request #39.
This commit is contained in:
2026-06-01 00:16:58 -04:00
8 changed files with 380 additions and 23 deletions
@@ -0,0 +1,190 @@
"""collapse-sidecar-synthetic: repoint Posts/ImageProvenance/DownloadEvents
from `sidecar:<platform>:<slug>` synthetic Source anchors onto the real
Source for the same (artist, platform) when one exists, then delete the
synthetic.
Revision ID: 0028
Revises: 0027
Create Date: 2026-05-31
Background: alembic 0022 (2026-05-26) consolidated the old per-post-URL
Source rows into one canonical Source per (artist, platform). When NO
real campaign URL was salvageable among the candidates, it rewrote the
canonical row to url='sidecar:<platform>:<slug>' enabled=false as a
disabled anchor for any Posts already attached.
That was fine while it was the only Source for that artist+platform.
But: the unique constraint on Source is (artist_id, platform, url), not
(artist_id, platform). When the operator later added the real
subscription via the UI / extension / etc., a SECOND row landed —
the real one — with id > the synthetic. Both coexisted.
Two follow-on problems surfaced 2026-05-31:
1. The Subscriptions UI listed both rows. The synthetic was disabled
so the scheduler never polled it, but it looked like a phantom
subscription. (Fixed in same commit by SourceService.list filter.)
2. importer._source_for_sidecar picked Source by `ORDER BY id ASC
LIMIT 1`, so EVERY gallery-dl download since the real Source was
added attached its Post to the SYNTHETIC anchor, not the real
Source. (Fixed in same commit by preferring non-sidecar URLs.)
This migration is the data half of the cleanup: for every (artist,
platform) with both a synthetic AND a real Source, repoint the
synthetic's children (Posts, ImageProvenance, DownloadEvents) onto the
real Source and delete the synthetic. Reuses the same epid/provenance
collision dance from alembic 0022 because the same uniqueness
constraints fire row-by-row during bulk UPDATEs.
Lone synthetic anchors — those where no real Source for the same
(artist, platform) exists (e.g., filesystem-imported artist with no
subscription added) — are LEFT INTACT. They anchor real imported
content; deleting them would CASCADE-delete the Posts the operator
imported. The SourceService.list filter hides them from the UI; the
operator can delete them by hand if they want the underlying imports
gone.
"""
from typing import Sequence, Union
from alembic import op
from sqlalchemy import text
revision: str = "0028"
down_revision: Union[str, None] = "0027"
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
conn = op.get_bind()
# Find (artist_id, platform) groups where BOTH a sidecar synthetic
# and at least one real Source exist.
groups = conn.execute(text("""
SELECT artist_id, platform
FROM source
GROUP BY artist_id, platform
HAVING bool_or(url LIKE 'sidecar:%')
AND bool_or(url NOT LIKE 'sidecar:%')
""")).fetchall()
for artist_id, platform in groups:
rows = conn.execute(
text("""
SELECT id, url FROM source
WHERE artist_id = :a AND platform = :p
ORDER BY id ASC
"""),
{"a": artist_id, "p": platform},
).fetchall()
synthetic_ids = [sid for sid, url in rows if url.startswith("sidecar:")]
real_rows = [(sid, url) for sid, url in rows if not url.startswith("sidecar:")]
if not synthetic_ids or not real_rows:
continue # belt+suspenders; the GROUP BY already filtered
# Canonical real: lowest-id non-sidecar Source.
canonical_id = real_rows[0][0]
# STEP A: PRE-merge Post collisions on (canonical, external_post_id).
# Mirror alembic 0022's pre-merge logic — when synth has Post X
# epid=N and real has Post Y epid=N, the bulk UPDATE below would
# trip uq_post_source_external_id row-by-row. Group all Posts
# under (canonical + synthetics) by epid; for any group >1,
# pick a keep (prefer one already under canonical, else lowest
# id) and merge the rest into it.
all_posts = conn.execute(
text("""
SELECT external_post_id, id, source_id
FROM post
WHERE source_id = :canonical OR source_id = ANY(:synths)
ORDER BY external_post_id, id
"""),
{"canonical": canonical_id, "synths": synthetic_ids},
).fetchall()
by_epid: dict = {}
for epid, post_id, src_id in all_posts:
by_epid.setdefault(epid, []).append((post_id, src_id))
for _epid, posts in by_epid.items():
if len(posts) <= 1:
continue
canonical_side = [p for p in posts if p[1] == canonical_id]
keep_id = canonical_side[0][0] if canonical_side else posts[0][0]
drop_ids = [p[0] for p in posts if p[0] != keep_id]
for drop_id in drop_ids:
# Pre-delete image_provenance rows under drop_ whose
# image_record_id already has provenance under keep —
# avoids tripping uq_image_provenance_image_post (0021)
# row-by-row during the repoint UPDATE.
conn.execute(
text("""
DELETE FROM image_provenance
WHERE post_id = :drop_
AND image_record_id IN (
SELECT image_record_id FROM image_provenance
WHERE post_id = :keep
)
"""),
{"keep": keep_id, "drop_": drop_id},
)
conn.execute(
text("""
UPDATE image_provenance SET post_id = :keep
WHERE post_id = :drop_
"""),
{"keep": keep_id, "drop_": drop_id},
)
conn.execute(
text("""
UPDATE image_record SET primary_post_id = :keep
WHERE primary_post_id = :drop_
"""),
{"keep": keep_id, "drop_": drop_id},
)
conn.execute(
text("DELETE FROM post WHERE id = :drop_"),
{"drop_": drop_id},
)
# STEP B: Bulk reparent the remaining Posts off the synthetics.
conn.execute(
text("""
UPDATE post SET source_id = :canonical
WHERE source_id = ANY(:synths)
"""),
{"canonical": canonical_id, "synths": synthetic_ids},
)
# STEP C: Reparent ImageProvenance.source_id (denormalized FK;
# no UNIQUE on source_id, safe bulk).
conn.execute(
text("""
UPDATE image_provenance SET source_id = :canonical
WHERE source_id = ANY(:synths)
"""),
{"canonical": canonical_id, "synths": synthetic_ids},
)
# STEP D: Reparent any DownloadEvent.source_id. Synthetics are
# enabled=false so the scheduler never created events for them;
# this is belt+suspenders for any rows planted by manual force
# or older code paths.
conn.execute(
text("""
UPDATE download_event SET source_id = :canonical
WHERE source_id = ANY(:synths)
"""),
{"canonical": canonical_id, "synths": synthetic_ids},
)
# STEP E: Drop the now-empty synthetics.
conn.execute(
text("DELETE FROM source WHERE id = ANY(:synths)"),
{"synths": synthetic_ids},
)
def downgrade() -> None:
# Lossy migration — synthetic Sources deleted, Posts repointed and
# potentially merged. No safe downgrade.
pass
+21 -8
View File
@@ -42,13 +42,16 @@ class ErrorType(StrEnum):
UNKNOWN_ERROR = "unknown_error"
# Pinned to download_source's Celery soft_time_limit (900s, see
# tasks/download.py:32). Anything larger and Celery kills the task before
# subprocess.run can raise TimeoutExpired — leaving the DownloadEvent
# stranded for the recovery sweep instead of capturing a clean timeout
# error. Per-source bumps live in source.config_overrides for legitimately
# long syncs. Operator-confirmed 2026-05-30 (~40-min hang investigation).
_DEFAULT_GDL_TIMEOUT_SECONDS = 900
# 30 seconds shy of download_source's Celery soft_time_limit (900s, see
# tasks/download.py:32). subprocess.run MUST raise TimeoutExpired before
# Celery raises SoftTimeLimitExceeded — otherwise Celery wins the race,
# SIGKILLs the worker, in-memory stdout/stderr is lost, and the
# DownloadEvent ends up empty-logged with "stranded by recovery sweep"
# 18 minutes later (operator-flagged 2026-05-31, Knuxy event #38275).
# The 30s buffer absorbs scheduler jitter / GC pauses without making
# legitimately-long-running syncs timeout-friendlier. Per-source bumps
# still live in source.config_overrides for legitimately long syncs.
_DEFAULT_GDL_TIMEOUT_SECONDS = 870
@dataclass
@@ -369,7 +372,17 @@ class GalleryDLService:
if return_code in (1, 4) and (skip_line_count > 0 or has_skip_text) and not has_actual_error:
return ErrorType.NO_NEW_CONTENT, "No new content to download"
if return_code in (1, 4) and not has_actual_error:
# Tier-gated classification used to require `return_code in (1, 4)`,
# which silently fell through to UNKNOWN_ERROR when gallery-dl
# returned a different exit code for mixed-failure runs (e.g.
# paywall warnings + a missing yt-dlp dep flipping the exit bits).
# The artist then surfaced as "needs attention" purely because a
# paywall blocked posts the operator wasn't paying to see —
# operator-flagged 2026-05-31. Now: if no source-level error
# category fired AND tier-gated warnings are present, classify
# as TIER_LIMITED regardless of return code. Same priority order
# as before (auth/rate/access/not_found/network/http still win).
if not has_actual_error:
tier_gated_lines = [
line for line in combined.split("\n")
if "][warning]" in line and "not allowed to view post" in line
+34 -14
View File
@@ -261,24 +261,44 @@ class Importer:
def _source_for_sidecar(
self, *, artist_id: int, platform: str, artist_slug: str,
) -> Source:
"""Filesystem-import sidecar Source resolver.
"""Sidecar-import Source resolver. Used by both filesystem imports
and gallery-dl downloads (both write sidecar JSON, both flow through
_apply_sidecar / _capture_attachment).
Source represents a subscription feed (one per artist+platform — the
gallery-dl URL polled by the FC-3 downloader). The filesystem importer
used to call _find_or_create_source(url=sd.post_url), which created
one Source row per post URL — 100s of junk Sources per artist, all
with enabled=True, polluting the artist detail page and tricking the
URL polled by the FC-3 downloader). The filesystem importer used to
call _find_or_create_source(url=sd.post_url), creating one Source
row per post URL — 100s of junk Sources per artist, all with
enabled=True, polluting the artist detail page and tricking the
subscription checker into trying to poll patreon post URLs as feeds.
Operator-flagged 2026-05-26.
Operator-flagged 2026-05-26; consolidated via alembic 0022.
New behaviour: if any Source row exists for (artist_id, platform),
reuse it regardless of its URL — the artist's real subscription Source
(created by the downloader / extension / UI) is the canonical
attachment point for filesystem-imported posts. If none exists, create
ONE synthetic anchor with url='sidecar:<platform>:<artist_slug>' and
enabled=False (so the subscription checker doesn't poll it).
Resolution order: prefer a real (non-sidecar) Source over a
synthetic anchor. When alembic 0022 ran, it may have rewritten
per-post Sources into `sidecar:<platform>:<slug>` synthetic
anchors. If the operator later added the real subscription, both
rows now coexist. A naive `ORDER BY id ASC LIMIT 1` lookup would
pick the older synthetic and silently attach every gallery-dl
download to the wrong Source — operator-flagged 2026-05-31 after
the Subscriptions UI surfaced the phantom anchors. Pick the real
one when one exists; fall back to the synthetic; only create a
new synthetic when nothing exists for (artist, platform).
"""
stmt = (
real_stmt = (
select(Source)
.where(
Source.artist_id == artist_id,
Source.platform == platform,
~Source.url.like("sidecar:%"),
)
.order_by(Source.id.asc())
.limit(1)
)
real = self.session.execute(real_stmt).scalar_one_or_none()
if real is not None:
return real
any_stmt = (
select(Source)
.where(
Source.artist_id == artist_id,
@@ -288,7 +308,7 @@ class Importer:
.limit(1)
)
return self._get_or_create(
stmt,
any_stmt,
lambda: Source(
artist_id=artist_id,
platform=platform,
+8
View File
@@ -151,10 +151,18 @@ class SourceService:
async def list(
self, artist_id: int | None = None, failing: bool = False,
include_synthetic: bool = False,
) -> list[SourceRecord]:
stmt = select(Source, Artist).join(Artist, Artist.id == Source.artist_id)
if artist_id is not None:
stmt = stmt.where(Source.artist_id == artist_id)
if not include_synthetic:
# Filesystem-import sidecar anchors (importer._source_for_sidecar)
# have url='sidecar:<platform>:<slug>' and exist only to give
# imported Posts a NOT-NULL Source FK. They aren't pollable
# feeds; the Subscriptions UI used to render them as phantom
# subscriptions. Hide by default.
stmt = stmt.where(~Source.url.like("sidecar:%"))
if failing:
# Worst-first so the rollup card surfaces the loudest failures.
stmt = stmt.where(Source.consecutive_failures > 0).order_by(
+5
View File
@@ -22,6 +22,11 @@ imagehash>=4.3,<4.4
# Gallery-dl wrapper (lands in FC-3)
gallery-dl>=1.32,<1.33
# Video extractor backend for gallery-dl. Without it, every video post
# attachment fails with `[downloader.ytdl][error] Cannot import yt-dlp`
# → `[download][error] Failed to download NN_video.mp4`. Operator-flagged
# 2026-05-31 after Patreon video posts produced empty downloads.
yt-dlp>=2025.1
# Utilities
python-dotenv>=1.2,<2.0
+52
View File
@@ -164,6 +164,58 @@ async def test_validation_quarantines_truncated_files(tmp_path, monkeypatch):
assert result.error_type == ErrorType.VALIDATION_FAILED
@pytest.mark.asyncio
async def test_download_tier_limited_classified_as_success(gdl, monkeypatch):
"""Pure tier-gated stderr (paywall warnings only, no source-level
errors). Should be TIER_LIMITED with success=True so the
DownloadEvent doesn't surface as 'needs attention' for an operator
who's just not paying the top tier. Pre-fix: this fell through to
UNKNOWN_ERROR when the return code wasn't 1 or 4."""
stderr = (
"[patreon][warning] Not allowed to view post 159421258\n"
"[patreon][warning] Not allowed to view post 159247879\n"
"[patreon][warning] Not allowed to view post 158111214\n"
)
# Use a non-(1,4) return code to prove the gate widened.
monkeypatch.setattr(
"backend.app.services.gallery_dl.subprocess.run",
lambda *a, **k: _proc(stdout="", stderr=stderr, returncode=128),
)
result = await gdl.download(
url="https://patreon.com/alice", artist_slug="alice", platform="patreon",
source_config=SourceConfig(),
)
assert result.error_type == ErrorType.TIER_LIMITED
assert result.success is True
assert "3 posts" in (result.error_message or "")
@pytest.mark.asyncio
async def test_download_tier_limited_with_per_item_video_failures(gdl, monkeypatch):
"""Real operator log shape (2026-05-31): hundreds of paywall warnings
+ a handful of per-item video errors caused by missing yt-dlp. The
video errors are classified as per-item (not source-level), so the
classifier should still pick TIER_LIMITED. Once yt-dlp is installed
the video errors stop firing; until then, the source-health doesn't
flap to 'needs attention' over paywalled content."""
stderr = (
"[patreon][warning] Not allowed to view post 159421258\n"
"[patreon][warning] Not allowed to view post 159247879\n"
"[downloader.ytdl][error] Cannot import yt-dlp or youtube-dl\n"
"[download][error] Failed to download 02_video.mp4\n"
)
monkeypatch.setattr(
"backend.app.services.gallery_dl.subprocess.run",
lambda *a, **k: _proc(stdout="", stderr=stderr, returncode=1),
)
result = await gdl.download(
url="https://patreon.com/alice", artist_slug="alice", platform="patreon",
source_config=SourceConfig(),
)
assert result.error_type == ErrorType.TIER_LIMITED
assert result.success is True
def test_compute_run_stats(gdl):
stats = gdl._compute_run_stats(
return_code=0,
+33
View File
@@ -210,3 +210,36 @@ def test_source_for_sidecar_distinct_platforms_distinct_anchors(
assert p.id != x.id
assert p.platform == "patreon"
assert x.platform == "pixiv"
def test_source_for_sidecar_prefers_real_over_synthetic_when_both_exist(
importer, artist_row, db_sync,
):
"""When BOTH a synthetic anchor AND a real Source exist for the same
(artist, platform), the resolver must return the REAL one. This is the
fix for the 2026-05-31 phantom-subscription bug: alembic 0022 had
rewritten an older per-post Source row into a sidecar synthetic, and
the operator later added the real subscription. The old `ORDER BY
id ASC LIMIT 1` lookup picked the older synthetic (lower id),
silently attaching every gallery-dl download to the wrong Source.
"""
synthetic = Source(
artist_id=artist_row.id, platform="patreon",
url=f"sidecar:patreon:{artist_row.slug}", enabled=False,
)
db_sync.add(synthetic)
db_sync.flush()
real = Source(
artist_id=artist_row.id, platform="patreon",
url="https://www.patreon.com/testartist", enabled=True,
)
db_sync.add(real)
db_sync.flush()
assert synthetic.id < real.id # ordering precondition
resolved = importer._source_for_sidecar(
artist_id=artist_row.id, platform="patreon",
artist_slug=artist_row.slug,
)
assert resolved.id == real.id
assert resolved.url == "https://www.patreon.com/testartist"
+37 -1
View File
@@ -1,7 +1,7 @@
import pytest
from sqlalchemy import select
from backend.app.models import Artist
from backend.app.models import Artist, Source
from backend.app.services.source_service import (
KNOWN_PLATFORMS,
ArtistNotFoundError,
@@ -133,3 +133,39 @@ async def test_update_changes_fields(db):
updated = await svc.update(rec.id, enabled=False, config_overrides={"videos": False})
assert updated.enabled is False
assert updated.config_overrides == {"videos": False}
@pytest.mark.asyncio
async def test_list_hides_sidecar_synthetic_anchors(db):
"""Filesystem-import synthetic Sources (url='sidecar:<platform>:<slug>',
enabled=False — see importer._source_for_sidecar) used to leak into the
Subscriptions UI as phantom subscriptions because list() didn't filter
them. They aren't pollable feeds; hide by default."""
artist = await _artist(db, "Alice")
real = Source(
artist_id=artist.id, platform="patreon",
url="https://patreon.com/alice", enabled=True, config_overrides={},
)
synthetic = Source(
artist_id=artist.id, platform="patreon",
url="sidecar:patreon:alice", enabled=False, config_overrides={},
)
db.add_all([real, synthetic])
await db.commit()
svc = SourceService(db)
visible = await svc.list()
visible_urls = {s.url for s in visible}
assert "https://patreon.com/alice" in visible_urls
assert "sidecar:patreon:alice" not in visible_urls
# Same filter applies to the artist-scoped list path (the artist detail
# page hits /api/sources?artist_id=N).
artist_scoped = await svc.list(artist_id=artist.id)
assert {s.url for s in artist_scoped} == {"https://patreon.com/alice"}
# include_synthetic=True opts back in for admin tooling.
everything = await svc.list(include_synthetic=True)
assert {s.url for s in everything} >= {
"https://patreon.com/alice", "sidecar:patreon:alice",
}