Compare commits
92
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
64ca858574 | ||
|
|
91be9df671 | ||
|
|
412edec028 | ||
|
|
937421485d | ||
|
|
9d0c0b7da8 | ||
|
|
43b778aa04 | ||
|
|
9cbdb70e13 | ||
|
|
8e4d252ae4 | ||
|
|
bd06794647 | ||
|
|
fdd3e01f56 | ||
|
|
f575cfb93b | ||
|
|
c82fb308b6 | ||
|
|
717b601c81 | ||
|
|
cfa4fb4084 | ||
|
|
2aa2002f22 | ||
|
|
66ff671f09 | ||
|
|
19aece1fc4 | ||
|
|
c9089b1d03 | ||
|
|
644d538bab | ||
|
|
ff35da4743 | ||
|
|
2f66de2928 | ||
|
|
8cf8d2ca4d | ||
|
|
94e7d20792 | ||
|
|
fb605af959 | ||
|
|
4c56cf121f | ||
|
|
b1d58bc3b8 | ||
|
|
9564d073b9 | ||
|
|
65386f02a0 | ||
|
|
f87a06a6bd | ||
|
|
5d284aae9f | ||
|
|
af7b5c95e9 | ||
|
|
667b05f14e | ||
|
|
8de7ccd07d | ||
|
|
d65f0b2091 | ||
|
|
856e9104b4 | ||
|
|
66f19d67f5 | ||
|
|
6fc8ae3106 | ||
|
|
0397642b21 | ||
|
|
a5101494b6 | ||
|
|
e3a7aff7a3 | ||
|
|
9cd6d09e60 | ||
|
|
237575447d | ||
|
|
810baf63ac | ||
|
|
44bb12a93d | ||
|
|
1eefed9ab3 | ||
|
|
adeee64a2d | ||
|
|
ed358757dc | ||
|
|
99b66aa85f | ||
|
|
77f7a23410 | ||
|
|
d181f4afb8 | ||
|
|
ff9e96e0e2 | ||
|
|
61ce1ce13c | ||
|
|
d28db32012 | ||
|
|
77e9859da3 | ||
|
|
2886fa4997 | ||
|
|
36f8ec80fd | ||
|
|
f256f587ee | ||
|
|
e35fb1edf7 | ||
|
|
08420cd619 | ||
|
|
8649a13118 | ||
|
|
8979e0e377 | ||
|
|
00e2608ba1 | ||
|
|
9ab5d709c8 | ||
|
|
44410db492 | ||
|
|
e76aa36a29 | ||
|
|
c95b760294 | ||
|
|
35fe420701 | ||
|
|
9e74c80e2f | ||
|
|
c87e8e0932 | ||
|
|
8c3900b998 | ||
|
|
972d9014ce | ||
|
|
75b6b8056e | ||
|
|
42ddac9996 | ||
|
|
384d8d5e50 | ||
|
|
1322056b22 | ||
|
|
32bdde049f | ||
|
|
9d18dacbe8 | ||
|
|
171c486939 | ||
|
|
21c1b0a81c | ||
|
|
597c6d48d3 | ||
|
|
a37dad33c7 | ||
|
|
cabd73287a | ||
|
|
def967a1a8 | ||
|
|
eebc8e2413 | ||
|
|
2358cedf3e | ||
|
|
215a8993a1 | ||
|
|
a459d21a65 | ||
|
|
73520b7cc3 | ||
|
|
56970fb66d | ||
|
|
bf8eb4468f | ||
|
|
e1fc65bd1b | ||
|
|
104cac5dca |
@@ -242,20 +242,32 @@ jobs:
|
||||
id: tag
|
||||
run: |
|
||||
# Three trigger shapes:
|
||||
# refs/tags/v… → tag-push: publish ONLY the immutable version
|
||||
# tag (e.g. :v26.05.26.5). Don't touch :latest;
|
||||
# that already got published by the main-push
|
||||
# build for the merge commit.
|
||||
# refs/heads/main → push to main (incl. PR merge commits):
|
||||
# publish :main + :latest (floating).
|
||||
# refs/tags/v… → tag-push: opt-in milestone label (vYY.MM.DD,
|
||||
# no `.N` per family release-posture rule).
|
||||
# Publish ONLY the immutable version tag;
|
||||
# don't touch :latest (the main-push build
|
||||
# for the merge commit already did that).
|
||||
# refs/heads/main → push to main: publish :main + :latest
|
||||
# (floating) AND :c-<short_sha> (immutable
|
||||
# per-commit rollback substrate, per family
|
||||
# release-posture rule "Tags are milestones,
|
||||
# not gates — commit-SHA images are the
|
||||
# rollback unit"). Rollback to any commit
|
||||
# becomes `docker pull …:c-<sha>` without a
|
||||
# release ceremony.
|
||||
# anything else → safety net; shouldn't fire given the `on:`
|
||||
# config above (dev was dropped). Tag :dev to
|
||||
# surface the unexpected run in the registry.
|
||||
# config above. Tag :dev to surface the
|
||||
# unexpected run in the registry.
|
||||
# POSIX-safe substring (the runner shell is dash/BusyBox sh, not
|
||||
# bash — `${var:0:7}` errors with "Bad substitution"; cut works
|
||||
# everywhere). Operator-flagged 2026-06-01 after first :c-<sha>
|
||||
# main-push build failed at this step.
|
||||
SHORT_SHA=$(printf '%s' "$GITHUB_SHA" | cut -c1-7)
|
||||
if [ "${GITHUB_REF#refs/tags/}" != "${GITHUB_REF}" ]; then
|
||||
TAG_NAME="${GITHUB_REF#refs/tags/}"
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:${TAG_NAME}" >> "$GITHUB_OUTPUT"
|
||||
elif [ "${GITHUB_REF##*/}" = "main" ]; then
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:main,git.fabledsword.com/bvandeusen/fabledcurator:latest" >> "$GITHUB_OUTPUT"
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:main,git.fabledsword.com/bvandeusen/fabledcurator:latest,git.fabledsword.com/bvandeusen/fabledcurator:c-${SHORT_SHA}" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator:dev" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
@@ -286,13 +298,19 @@ jobs:
|
||||
id: tag
|
||||
run: |
|
||||
# Mirrors build-web's three-shape logic (tag-push / main-push /
|
||||
# safety-net dev). The -ml image follows the same release cadence
|
||||
# as the web image.
|
||||
# safety-net dev) including the per-commit :c-<short_sha> tag
|
||||
# on main-push per the family release-posture rule. The -ml
|
||||
# image follows the same release cadence as the web image.
|
||||
# POSIX-safe substring (the runner shell is dash/BusyBox sh, not
|
||||
# bash — `${var:0:7}` errors with "Bad substitution"; cut works
|
||||
# everywhere). Operator-flagged 2026-06-01 after first :c-<sha>
|
||||
# main-push build failed at this step.
|
||||
SHORT_SHA=$(printf '%s' "$GITHUB_SHA" | cut -c1-7)
|
||||
if [ "${GITHUB_REF#refs/tags/}" != "${GITHUB_REF}" ]; then
|
||||
TAG_NAME="${GITHUB_REF#refs/tags/}"
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:${TAG_NAME}" >> "$GITHUB_OUTPUT"
|
||||
elif [ "${GITHUB_REF##*/}" = "main" ]; then
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:main,git.fabledsword.com/bvandeusen/fabledcurator-ml:latest" >> "$GITHUB_OUTPUT"
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:main,git.fabledsword.com/bvandeusen/fabledcurator-ml:latest,git.fabledsword.com/bvandeusen/fabledcurator-ml:c-${SHORT_SHA}" >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo "tags=git.fabledsword.com/bvandeusen/fabledcurator-ml:dev" >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
name: CI
|
||||
|
||||
# CI lanes per FabledRulebook/forgejo.md "CI philosophy":
|
||||
# - backend-lint-and-test: ruff + `pytest -m "not integration"`, no service containers.
|
||||
# - lint: ruff only, no dep install — fast-fail for the common lint bounce.
|
||||
# - backend-lint-and-test: `pytest -m "not integration"`, no service containers.
|
||||
# - frontend-build: vitest unit + vite build.
|
||||
# - integration: pgvector + redis service containers; alembic + `pytest -m integration`.
|
||||
|
||||
@@ -14,6 +15,20 @@ on:
|
||||
# (single-operator Forgejo repo) so push coverage is complete.
|
||||
|
||||
jobs:
|
||||
# Fast-fail lint lane. ruff is pre-installed in the ci-python image, so
|
||||
# this runs with NO dependency install and surfaces the most common bounce
|
||||
# class (lint: I001 / UP037 / ASYNC109 / W293 …) in seconds — instead of
|
||||
# after the backend job's ~30-60s wheel install. ruff is static analysis,
|
||||
# so no DB/secret env is needed.
|
||||
lint:
|
||||
runs-on: python-ci
|
||||
container:
|
||||
image: git.fabledsword.com/bvandeusen/ci-python:3.14
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Ruff lint
|
||||
run: ruff check backend/ tests/ alembic/
|
||||
|
||||
backend-lint-and-test:
|
||||
runs-on: python-ci
|
||||
container:
|
||||
@@ -51,9 +66,8 @@ jobs:
|
||||
pip install -r requirements.txt pytest pytest-asyncio
|
||||
fi
|
||||
|
||||
- name: Ruff lint
|
||||
run: ruff check backend/ tests/ alembic/
|
||||
|
||||
# Ruff moved to the dedicated fast `lint` job above (fails in seconds,
|
||||
# no dep install). This job is now unit tests only.
|
||||
- name: Pytest (unit only — integration runs in the integration job)
|
||||
run: pytest tests/ -v -m "not integration"
|
||||
|
||||
|
||||
@@ -0,0 +1,50 @@
|
||||
"""drop migration_run — one-and-done GS/IR migration tooling removed
|
||||
|
||||
Revision ID: 0027
|
||||
Revises: 0026
|
||||
Create Date: 2026-05-29
|
||||
|
||||
The GS/IR migration tooling (services/migrators, /api/migrate, the
|
||||
run_migration task, LegacyMigrationCard, and the MigrationRun model) was
|
||||
removed after the migration cutover completed. This drops its now-orphaned
|
||||
run-log table. Downgrade recreates the table (mirrors the old model) so the
|
||||
migration is reversible.
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy.dialects.postgresql import JSONB
|
||||
|
||||
revision: str = "0027"
|
||||
down_revision: Union[str, None] = "0026"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
op.drop_table("migration_run")
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.create_table(
|
||||
"migration_run",
|
||||
sa.Column("id", sa.Integer(), primary_key=True),
|
||||
sa.Column("kind", sa.String(length=32), nullable=False),
|
||||
sa.Column("status", sa.String(length=32), nullable=False),
|
||||
sa.Column("dry_run", sa.Boolean(), nullable=False, server_default=sa.false()),
|
||||
sa.Column(
|
||||
"started_at", sa.DateTime(timezone=True), nullable=False,
|
||||
server_default=sa.func.now(),
|
||||
),
|
||||
sa.Column("finished_at", sa.DateTime(timezone=True), nullable=True),
|
||||
sa.Column(
|
||||
"counts", JSONB(), nullable=False, server_default=sa.text("'{}'::jsonb"),
|
||||
),
|
||||
sa.Column("error", sa.Text(), nullable=True),
|
||||
sa.Column(
|
||||
"metadata", JSONB(), nullable=False, server_default=sa.text("'{}'::jsonb"),
|
||||
),
|
||||
)
|
||||
op.create_index("ix_migration_run_kind", "migration_run", ["kind"])
|
||||
op.create_index("ix_migration_run_status", "migration_run", ["status"])
|
||||
@@ -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
|
||||
@@ -0,0 +1,71 @@
|
||||
"""drop artist + copyright ml thresholds; lower general default to 0.50
|
||||
|
||||
Revision ID: 0029
|
||||
Revises: 0028
|
||||
Create Date: 2026-06-01
|
||||
|
||||
Operator-flagged 2026-06-01: the view modal's Suggestions panel hides
|
||||
most general-category predictions because the default threshold is
|
||||
0.95. Lowering the default to 0.50 (matches character) so general
|
||||
suggestions surface more aggressively; the value remains tunable in
|
||||
Settings → ML.
|
||||
|
||||
Same change retires two ML suggestion categories whose Tag.kind
|
||||
surfaces are unused:
|
||||
|
||||
- `artist`: retired in FC-2d-vii-c — artist identity is acquisition-
|
||||
derived (image_record.artist_id), never ML-inferred. The threshold
|
||||
column was a leftover from before that retirement.
|
||||
- `copyright`: retired 2026-06-01 — the app uses `fandom` for the
|
||||
franchise/copyright concept (per TagsView.vue's doc comment); no
|
||||
Tag rows of kind=copyright exist, and the threshold column never
|
||||
fed anything user-visible.
|
||||
|
||||
Both columns are dropped from ml_settings; the existing row's
|
||||
suggestion_threshold_general value is bumped from 0.95 to 0.50 iff
|
||||
it's still at the old default, so deployed installs pick up the new
|
||||
UX without overriding any operator tuning.
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
|
||||
from alembic import op
|
||||
from sqlalchemy import text
|
||||
|
||||
revision: str = "0029"
|
||||
down_revision: Union[str, None] = "0028"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
# Bump the general threshold for installs still at the old default.
|
||||
op.execute(text(
|
||||
"UPDATE ml_settings "
|
||||
"SET suggestion_threshold_general = 0.50 "
|
||||
"WHERE id = 1 AND suggestion_threshold_general = 0.95"
|
||||
))
|
||||
op.drop_column("ml_settings", "suggestion_threshold_artist")
|
||||
op.drop_column("ml_settings", "suggestion_threshold_copyright")
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# Restore the columns with their prior defaults. The bump from
|
||||
# 0.95 → 0.50 isn't reversible without remembering whether the
|
||||
# operator had explicitly set 0.95 (unlikely — that was just the
|
||||
# default) so we leave the current general value as-is.
|
||||
from sqlalchemy import Column, Float
|
||||
|
||||
op.add_column(
|
||||
"ml_settings",
|
||||
Column(
|
||||
"suggestion_threshold_artist",
|
||||
Float, nullable=False, server_default="0.30",
|
||||
),
|
||||
)
|
||||
op.add_column(
|
||||
"ml_settings",
|
||||
Column(
|
||||
"suggestion_threshold_copyright",
|
||||
Float, nullable=False, server_default="0.50",
|
||||
),
|
||||
)
|
||||
@@ -0,0 +1,145 @@
|
||||
"""nullable post.source_id + denormalized post.artist_id; retire sidecar synthetics
|
||||
|
||||
Revision ID: 0030
|
||||
Revises: 0029
|
||||
Create Date: 2026-06-01
|
||||
|
||||
Operator-asked 2026-06-01 after the Dymkens orphan investigation: the
|
||||
sidecar synthetic Source pattern (`sidecar:<platform>:<slug>` rows
|
||||
with enabled=false) was technically correct but misled the operator
|
||||
into thinking they had phantom subscriptions. The synthetics existed
|
||||
solely to satisfy `Post.source_id NOT NULL` for filesystem-imported
|
||||
content with no real subscription.
|
||||
|
||||
This migration makes the data model honest:
|
||||
|
||||
1. **Post gets a denormalized `artist_id` column** so artist filters
|
||||
work without traversing `Post → Source.artist_id`. Backfilled from
|
||||
the existing Source linkage, then NOT NULL'd.
|
||||
2. **`Post.source_id` becomes nullable**, FK ondelete `CASCADE` → `SET
|
||||
NULL`. Deleting a Source detaches its Posts instead of destroying
|
||||
imported content (semantically: subscription ends, archive stays).
|
||||
3. **`ImageProvenance.source_id` becomes nullable** with the same FK
|
||||
semantic change.
|
||||
4. **Sidecar synthetic Sources are deleted** — first NULL out the
|
||||
FKs from Post + ImageProvenance pointing at them (so the implicit
|
||||
CASCADE doesn't fire), then delete. DownloadEvent FK is unchanged
|
||||
(still CASCADE'd, NOT NULL'd) — synthetics have `enabled=false`
|
||||
so no events exist for them.
|
||||
|
||||
Uniqueness handling: the existing `uq_post_source_external_id`
|
||||
(source_id, external_post_id) keeps working for source-bound Posts
|
||||
(Postgres treats NULL != NULL so NULL-source rows aren't deduped by
|
||||
it). A second partial unique index covers the NULL-source case on
|
||||
(artist_id, external_post_id) so filesystem-imported posts still
|
||||
dedupe within an artist.
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
from sqlalchemy import text
|
||||
|
||||
revision: str = "0030"
|
||||
down_revision: Union[str, None] = "0029"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
conn = op.get_bind()
|
||||
|
||||
# Step 1: add Post.artist_id, initially nullable for backfill.
|
||||
# FK naming follows the Base.metadata naming_convention
|
||||
# (fk_<table>_<column>_<referred_table>) — alembic 0001 set this up.
|
||||
op.add_column(
|
||||
"post",
|
||||
sa.Column("artist_id", sa.Integer, nullable=True),
|
||||
)
|
||||
op.create_foreign_key(
|
||||
"fk_post_artist_id_artist", "post", "artist",
|
||||
["artist_id"], ["id"], ondelete="CASCADE",
|
||||
)
|
||||
|
||||
# Step 2: backfill from Source.artist_id (every existing Post has a
|
||||
# Source today, so every row gets populated).
|
||||
conn.execute(text("""
|
||||
UPDATE post p
|
||||
SET artist_id = s.artist_id
|
||||
FROM source s
|
||||
WHERE p.source_id = s.id AND p.artist_id IS NULL
|
||||
"""))
|
||||
|
||||
# Sanity: count any remaining NULLs. Should be zero pre-this-migration.
|
||||
remaining = conn.execute(text(
|
||||
"SELECT COUNT(*) FROM post WHERE artist_id IS NULL"
|
||||
)).scalar_one()
|
||||
if remaining:
|
||||
raise RuntimeError(
|
||||
f"alembic 0030: {remaining} post rows have no resolvable "
|
||||
f"artist_id after backfill. Investigate before continuing."
|
||||
)
|
||||
|
||||
# Step 3: enforce NOT NULL + add index for artist-filter queries.
|
||||
op.alter_column("post", "artist_id", nullable=False)
|
||||
op.create_index("ix_post_artist_id", "post", ["artist_id"])
|
||||
|
||||
# Step 4: relax post.source_id + flip FK to SET NULL. The original FK
|
||||
# name from alembic 0001 is `fk_post_source_id_source` per the
|
||||
# NAMING_CONVENTION in models/base.py.
|
||||
op.alter_column("post", "source_id", nullable=True)
|
||||
op.drop_constraint("fk_post_source_id_source", "post", type_="foreignkey")
|
||||
op.create_foreign_key(
|
||||
"fk_post_source_id_source", "post", "source",
|
||||
["source_id"], ["id"], ondelete="SET NULL",
|
||||
)
|
||||
|
||||
# Step 5: relax image_provenance.source_id + flip FK to SET NULL.
|
||||
op.alter_column("image_provenance", "source_id", nullable=True)
|
||||
op.drop_constraint(
|
||||
"fk_image_provenance_source_id_source", "image_provenance",
|
||||
type_="foreignkey",
|
||||
)
|
||||
op.create_foreign_key(
|
||||
"fk_image_provenance_source_id_source", "image_provenance", "source",
|
||||
["source_id"], ["id"], ondelete="SET NULL",
|
||||
)
|
||||
|
||||
# Step 6: partial unique index on (artist_id, external_post_id) for
|
||||
# NULL-source Posts. The existing uq_post_source_external_id keeps
|
||||
# guarding source-bound rows; NULL-source rows now dedupe within
|
||||
# an artist.
|
||||
op.execute(
|
||||
"CREATE UNIQUE INDEX uq_post_artist_external_id_null_source "
|
||||
"ON post (artist_id, external_post_id) "
|
||||
"WHERE source_id IS NULL"
|
||||
)
|
||||
|
||||
# Step 7: retire sidecar synthetic Sources. NULL out the references
|
||||
# FIRST (the new FK is SET NULL so CASCADE wouldn't fire anyway, but
|
||||
# being explicit makes the intent clear). Then delete the synthetic
|
||||
# source rows. Any DownloadEvent rows under synthetics CASCADE-die
|
||||
# with the source — synthetics have enabled=false so there shouldn't
|
||||
# be any in practice.
|
||||
conn.execute(text("""
|
||||
UPDATE post
|
||||
SET source_id = NULL
|
||||
WHERE source_id IN (SELECT id FROM source WHERE url LIKE 'sidecar:%')
|
||||
"""))
|
||||
conn.execute(text("""
|
||||
UPDATE image_provenance
|
||||
SET source_id = NULL
|
||||
WHERE source_id IN (SELECT id FROM source WHERE url LIKE 'sidecar:%')
|
||||
"""))
|
||||
deleted = conn.execute(text(
|
||||
"DELETE FROM source WHERE url LIKE 'sidecar:%' RETURNING id"
|
||||
)).rowcount
|
||||
print(f"alembic 0030: deleted {deleted} sidecar synthetic source rows")
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
# Lossy migration — the deleted sidecar synthetics can't be
|
||||
# restored from the orphan post.source_id / image_provenance.source_id
|
||||
# values, and the partial unique index encodes a constraint that
|
||||
# NULL-source Posts may now exist. No safe downgrade.
|
||||
pass
|
||||
@@ -0,0 +1,45 @@
|
||||
"""source.backfill_runs_remaining: sticky deep-scan mode
|
||||
|
||||
Revision ID: 0031
|
||||
Revises: 0030
|
||||
Create Date: 2026-06-01
|
||||
|
||||
Tick vs backfill mode for subscription downloads. When
|
||||
`backfill_runs_remaining > 0`, the next N download runs use
|
||||
`skip: True` + 30-min timeout (walk full history). When 0, runs use
|
||||
`skip: "exit:20"` + 14.5-min timeout (catch-up mode, exits early once
|
||||
20 contiguous archived items are seen).
|
||||
|
||||
Operator-flagged 2026-06-01 (Knuxy run #38887): a creator with ~550
|
||||
archived posts saturates the 870s catch-up timeout even when there is
|
||||
no new content, because gallery-dl's default `skip: True` keeps walking.
|
||||
Tick mode short-circuits that; backfill mode is the explicit opt-in for
|
||||
deep history scans.
|
||||
|
||||
Default 0 (all existing subscriptions start in tick mode).
|
||||
"""
|
||||
from typing import Sequence, Union
|
||||
|
||||
import sqlalchemy as sa
|
||||
from alembic import op
|
||||
|
||||
revision: str = "0031"
|
||||
down_revision: Union[str, None] = "0030"
|
||||
branch_labels: Union[str, Sequence[str], None] = None
|
||||
depends_on: Union[str, Sequence[str], None] = None
|
||||
|
||||
|
||||
def upgrade() -> None:
|
||||
op.add_column(
|
||||
"source",
|
||||
sa.Column(
|
||||
"backfill_runs_remaining",
|
||||
sa.Integer,
|
||||
nullable=False,
|
||||
server_default="0",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def downgrade() -> None:
|
||||
op.drop_column("source", "backfill_runs_remaining")
|
||||
@@ -33,12 +33,6 @@ def create_app() -> Quart:
|
||||
|
||||
app = Quart(__name__)
|
||||
app.secret_key = cfg.secret_key
|
||||
# FC-5: legacy IR ingest JSON can run to tens of MB (hundreds of
|
||||
# thousands of image_tag_associations). Werkzeug's default form
|
||||
# memory cap is 500KB; raise both ceilings so the multipart upload
|
||||
# for /api/migrate/ir_ingest doesn't 413.
|
||||
app.config["MAX_CONTENT_LENGTH"] = 1024 * 1024 * 1024 # 1 GB
|
||||
app.config["MAX_FORM_MEMORY_SIZE"] = 1024 * 1024 * 1024 # 1 GB
|
||||
|
||||
for bp in all_blueprints():
|
||||
app.register_blueprint(bp)
|
||||
|
||||
@@ -26,7 +26,6 @@ def all_blueprints() -> list[Blueprint]:
|
||||
from .extension import extension_bp
|
||||
from .gallery import gallery_bp
|
||||
from .import_admin import import_admin_bp
|
||||
from .migrate import migrate_bp
|
||||
from .ml_admin import ml_admin_bp
|
||||
from .platforms import platforms_bp
|
||||
from .posts import posts_bp
|
||||
@@ -54,7 +53,6 @@ def all_blueprints() -> list[Blueprint]:
|
||||
admin_bp,
|
||||
cleanup_bp,
|
||||
import_admin_bp,
|
||||
migrate_bp,
|
||||
suggestions_bp,
|
||||
allowlist_bp,
|
||||
aliases_bp,
|
||||
|
||||
@@ -0,0 +1,16 @@
|
||||
"""Shared API response helpers."""
|
||||
|
||||
from quart import jsonify
|
||||
|
||||
|
||||
def error_response(
|
||||
error: str, *, status: int = 400, detail: str | None = None, **extra,
|
||||
):
|
||||
"""JSON error body + HTTP status. `detail` is included only when given;
|
||||
`extra` keys are merged into the body. Returns the (response, status)
|
||||
tuple Quart expects. Imported as `_bad` by the blueprints."""
|
||||
body = {"error": error}
|
||||
if detail is not None:
|
||||
body["detail"] = detail
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
@@ -6,6 +6,7 @@ Five action surfaces:
|
||||
DELETE /api/admin/tags/<int:tag_id> (Tier B)
|
||||
POST /api/admin/tags/<int:dest_id>/merge (Tier B)
|
||||
POST /api/admin/tags/prune-unused (Tier A)
|
||||
POST /api/admin/tags/purge-legacy (Tier A)
|
||||
GET /api/admin/tags/<int:tag_id>/usage-count (helper)
|
||||
|
||||
Tier-C ops take a dry_run body flag (returns projection inline,
|
||||
@@ -23,16 +24,11 @@ from sqlalchemy import select
|
||||
from ..extensions import get_session
|
||||
from ..models import Artist
|
||||
from ..services.cleanup_service import project_artist_cascade, project_bulk_image_delete
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
admin_bp = Blueprint("admin", __name__, url_prefix="/api/admin")
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, **extra):
|
||||
body = {"error": error}
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
def _bulk_image_confirm_token(image_ids: list[int]) -> str:
|
||||
"""Stable 8-hex token derived from the sorted id list. Mutates
|
||||
when the selection changes; stays the same across modal opens of
|
||||
@@ -206,3 +202,23 @@ async def tags_prune_unused():
|
||||
)
|
||||
)
|
||||
return jsonify(result)
|
||||
|
||||
|
||||
@admin_bp.route("/tags/purge-legacy", methods=["POST"])
|
||||
async def tags_purge_legacy():
|
||||
"""Tier-A: delete legacy IR-migration tags — archive/post/artist
|
||||
kinds (e.g. `BlenderKnight:Hannah_BJ_Loops`) PLUS general tags with
|
||||
a legacy name prefix (`source:*`, from IR's source kind that fell
|
||||
back to general). dry-run preview returns per-kind + per-prefix
|
||||
counts + a sample so the UI shows exactly what'll go before the
|
||||
operator confirms with dry_run=false."""
|
||||
from ..services.cleanup_service import purge_legacy_tags
|
||||
|
||||
body = await request.get_json(silent=True) or {}
|
||||
dry_run = bool(body.get("dry_run", False))
|
||||
|
||||
async with get_session() as session:
|
||||
result = await session.run_sync(
|
||||
lambda sync_sess: purge_legacy_tags(sync_sess, dry_run=dry_run)
|
||||
)
|
||||
return jsonify(result)
|
||||
|
||||
@@ -31,18 +31,13 @@ from sqlalchemy import select
|
||||
from ..extensions import get_session
|
||||
from ..models import LibraryAuditRun
|
||||
from ..services import cleanup_service
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
cleanup_bp = Blueprint("cleanup", __name__, url_prefix="/api/cleanup")
|
||||
|
||||
IMAGES_ROOT = Path("/images")
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, **extra):
|
||||
body = {"error": error}
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
def _min_dim_token(min_w: int, min_h: int) -> str:
|
||||
# SHA-256 (not MD5) — Web Crypto's subtle.digest rejects MD5; both
|
||||
# sides use SHA-256 truncated to 8 hex chars.
|
||||
|
||||
@@ -20,6 +20,7 @@ from ..services.credential_service import (
|
||||
UnknownPlatformError,
|
||||
WrongAuthTypeError,
|
||||
)
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
credentials_bp = Blueprint("credentials", __name__, url_prefix="/api/credentials")
|
||||
|
||||
@@ -38,14 +39,6 @@ def _get_crypto() -> CredentialCrypto:
|
||||
return _crypto
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
|
||||
body = {"error": error}
|
||||
if detail is not None:
|
||||
body["detail"] = detail
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
async def _ext_key_ok(session) -> bool:
|
||||
"""If X-Extension-Key is supplied, it must match the stored value.
|
||||
Missing header → True (browser path; accepted per homelab posture).
|
||||
@@ -124,3 +117,56 @@ async def delete_credential(platform: str):
|
||||
except LookupError:
|
||||
return _bad("not_found", status=404)
|
||||
return "", 204
|
||||
|
||||
|
||||
@credentials_bp.route("/<platform>/verify", methods=["POST"])
|
||||
async def verify_credential(platform: str):
|
||||
"""Test the stored credential by running gallery-dl --simulate
|
||||
against one of the platform's enabled sources. On success stamps
|
||||
last_verified. Returns {valid: bool|null, reason, last_verified?}.
|
||||
valid=null means "couldn't test" (no credential, or no enabled
|
||||
source to point at)."""
|
||||
from ..models import Artist, Source
|
||||
from ..services.gallery_dl import GalleryDLService, SourceConfig
|
||||
|
||||
async with get_session() as session:
|
||||
if not await _ext_key_ok(session):
|
||||
return _bad("unauthorized", status=401)
|
||||
svc = CredentialService(session, _get_crypto())
|
||||
record = await svc.get(platform)
|
||||
if record is None:
|
||||
return jsonify({"valid": None, "reason": "No credential stored for this platform."})
|
||||
|
||||
# Pick an enabled source for this platform to point the probe at.
|
||||
row = (await session.execute(
|
||||
select(Source, Artist)
|
||||
.join(Artist, Artist.id == Source.artist_id)
|
||||
.where(Source.platform == platform, Source.enabled.is_(True))
|
||||
.order_by(Source.id.asc())
|
||||
)).first()
|
||||
if row is None:
|
||||
return jsonify({
|
||||
"valid": None,
|
||||
"reason": "No enabled source for this platform to verify against — add a subscription first.",
|
||||
})
|
||||
source, artist = row
|
||||
|
||||
cookies_path = await svc.get_cookies_path(platform)
|
||||
auth_token = await svc.get_token(platform)
|
||||
|
||||
gdl = GalleryDLService(images_root=Path("/images"))
|
||||
ok, message = await gdl.verify(
|
||||
url=source.url,
|
||||
artist_slug=artist.slug,
|
||||
platform=platform,
|
||||
source_config=SourceConfig.from_dict(source.config_overrides or {}),
|
||||
cookies_path=str(cookies_path) if cookies_path else None,
|
||||
auth_token=auth_token,
|
||||
)
|
||||
|
||||
last_verified = None
|
||||
if ok:
|
||||
async with get_session() as session:
|
||||
ts = await CredentialService(session, _get_crypto()).mark_verified(platform)
|
||||
last_verified = ts.isoformat() if ts else None
|
||||
return jsonify({"valid": ok, "reason": message, "last_verified": last_verified})
|
||||
|
||||
@@ -126,6 +126,54 @@ async def downloads_stats():
|
||||
return jsonify(out)
|
||||
|
||||
|
||||
@downloads_bp.route("/activity", methods=["GET"])
|
||||
async def downloads_activity():
|
||||
"""Hourly download-event counts over the last `?hours=` (default 24).
|
||||
|
||||
Returns a fixed-length, oldest-first bucket array so the UI can render
|
||||
a sparkline directly. Bucketing is done in Python against UTC to dodge
|
||||
session-timezone ambiguity in SQL date_trunc.
|
||||
"""
|
||||
try:
|
||||
hours = int(request.args.get("hours", "24"))
|
||||
except ValueError:
|
||||
return jsonify({"error": "invalid_hours"}), 400
|
||||
hours = max(1, min(168, hours))
|
||||
|
||||
now = datetime.now(UTC)
|
||||
end = now.replace(minute=0, second=0, microsecond=0)
|
||||
start = end - timedelta(hours=hours - 1)
|
||||
buckets = [
|
||||
{"hour": (start + timedelta(hours=i)).isoformat(),
|
||||
"ok": 0, "error": 0, "other": 0, "total": 0}
|
||||
for i in range(hours)
|
||||
]
|
||||
|
||||
async with get_session() as session:
|
||||
rows = (await session.execute(
|
||||
select(DownloadEvent.started_at, DownloadEvent.status)
|
||||
.where(DownloadEvent.started_at >= start)
|
||||
)).all()
|
||||
|
||||
for started_at, status in rows:
|
||||
if started_at is None:
|
||||
continue
|
||||
sa = started_at if started_at.tzinfo else started_at.replace(tzinfo=UTC)
|
||||
idx = int((sa - start).total_seconds() // 3600)
|
||||
if not (0 <= idx < hours):
|
||||
continue
|
||||
b = buckets[idx]
|
||||
if status == "ok":
|
||||
b["ok"] += 1
|
||||
elif status == "error":
|
||||
b["error"] += 1
|
||||
else:
|
||||
b["other"] += 1
|
||||
b["total"] += 1
|
||||
|
||||
return jsonify({"hours": hours, "buckets": buckets})
|
||||
|
||||
|
||||
@downloads_bp.route("/<int:event_id>", methods=["GET"])
|
||||
async def get_download(event_id: int):
|
||||
async with get_session() as session:
|
||||
@@ -139,3 +187,20 @@ async def get_download(event_id: int):
|
||||
return jsonify({"error": "not_found"}), 404
|
||||
event, source, artist = row
|
||||
return jsonify(_detail_record(event, source, artist))
|
||||
|
||||
|
||||
@downloads_bp.route("/recover-stalled", methods=["POST"])
|
||||
async def recover_stalled():
|
||||
"""Trigger the recover_stalled_download_events sweep on demand.
|
||||
|
||||
The same sweep runs every 5 min via Beat (see celery_app.beat_schedule);
|
||||
this endpoint exists so the operator can force-clear stuck pending/
|
||||
running download_events from the Subscriptions → Downloads maintenance
|
||||
menu without waiting for the next scheduled tick.
|
||||
"""
|
||||
# Local import: avoids registering maintenance tasks during blueprint
|
||||
# import (Celery task discovery races with the API import otherwise).
|
||||
from ..tasks.maintenance import recover_stalled_download_events
|
||||
|
||||
recover_stalled_download_events.delay()
|
||||
return jsonify({"queued": True}), 202
|
||||
|
||||
@@ -20,6 +20,7 @@ from ..services.extension_service import (
|
||||
UnknownPlatformError,
|
||||
)
|
||||
from ..services.source_service import KNOWN_PLATFORMS
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
extension_bp = Blueprint("extension", __name__, url_prefix="/api/extension")
|
||||
|
||||
@@ -30,12 +31,6 @@ XPI_DIR = Path("/app/frontend/dist/extension")
|
||||
_XPI_VERSION_RE = re.compile(r"fabledcurator-(?P<version>[\w.-]+)\.xpi$")
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, **extra):
|
||||
body = {"error": error}
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
async def _ext_key_required(session) -> bool:
|
||||
"""Unlike /api/credentials (which accepts the browser path with no
|
||||
header), quick-add-source writes server state and must be explicitly
|
||||
@@ -62,6 +57,24 @@ def _sha256(path: Path) -> str:
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
@extension_bp.route("/probe", methods=["GET"])
|
||||
async def probe_source():
|
||||
"""Read-only resolution of a creator-page URL: tells the extension
|
||||
whether this URL is already a Source, is for an Artist that exists
|
||||
but with a different URL, is brand new, or doesn't match any known
|
||||
platform pattern. Drives the content-script chip's color/copy
|
||||
BEFORE the operator clicks, so the button can show 'already added'
|
||||
without requiring an add-attempt."""
|
||||
url = (request.args.get("url") or "").strip()
|
||||
if not url:
|
||||
return _bad("invalid_body", detail="url query parameter is required")
|
||||
async with get_session() as session:
|
||||
if not await _ext_key_required(session):
|
||||
return _bad("unauthorized", status=401)
|
||||
result = await ExtensionService(session).probe(url)
|
||||
return jsonify(result)
|
||||
|
||||
|
||||
@extension_bp.route("/quick-add-source", methods=["POST"])
|
||||
async def quick_add_source():
|
||||
body = await request.get_json(silent=True)
|
||||
|
||||
@@ -159,9 +159,7 @@ def _refetch_task_sync(session, task_id: int) -> dict:
|
||||
return {"status": "not_found"}
|
||||
if task.status != "failed":
|
||||
return {"status": "not_failed"}
|
||||
settings = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
settings = ImportSettings.load_sync(session)
|
||||
return attempt_refetch(session, task, Path(settings.import_scan_path))
|
||||
|
||||
|
||||
|
||||
@@ -1,112 +0,0 @@
|
||||
"""FC-5: /api/migrate — trigger and poll migration runs.
|
||||
|
||||
Ingest kinds (gs_ingest, ir_ingest) accept multipart/form-data with an
|
||||
`export_file` field. All other kinds accept JSON. Backup + rollback
|
||||
were retired in FC-3h (2026-05-24); use /api/system/backup/* instead.
|
||||
"""
|
||||
|
||||
import json
|
||||
|
||||
from quart import Blueprint, jsonify, request
|
||||
from sqlalchemy import select
|
||||
|
||||
from ..extensions import get_session
|
||||
from ..models import MigrationRun
|
||||
from ..tasks.migration import run_migration
|
||||
|
||||
migrate_bp = Blueprint("migrate", __name__, url_prefix="/api/migrate")
|
||||
|
||||
# 'backup' + 'rollback' retired 2026-05-24 (FC-3h); see /api/system/backup/*.
|
||||
_VALID_KINDS = frozenset({
|
||||
"gs_ingest", "ir_ingest", "tag_apply",
|
||||
"ml_queue", "verify", "cleanup",
|
||||
})
|
||||
_INGEST_KINDS = frozenset({"gs_ingest", "ir_ingest"})
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, **extra):
|
||||
body = {"error": error}
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
def _run_to_dict(run: MigrationRun) -> dict:
|
||||
return {
|
||||
"id": run.id,
|
||||
"kind": run.kind,
|
||||
"status": run.status,
|
||||
"dry_run": run.dry_run,
|
||||
"started_at": run.started_at.isoformat(),
|
||||
"finished_at": run.finished_at.isoformat() if run.finished_at else None,
|
||||
"counts": run.counts or {},
|
||||
"error": run.error,
|
||||
"metadata": run.metadata_ or {},
|
||||
}
|
||||
|
||||
|
||||
@migrate_bp.route("/<kind>", methods=["POST"])
|
||||
async def create_run(kind: str):
|
||||
if kind not in _VALID_KINDS:
|
||||
return _bad("unknown_kind", detail=f"kind must be one of {sorted(_VALID_KINDS)}")
|
||||
|
||||
# Ingest kinds accept multipart/form-data; everything else takes JSON.
|
||||
if kind in _INGEST_KINDS:
|
||||
form = await request.form
|
||||
files = await request.files
|
||||
if "export_file" not in files:
|
||||
return _bad("missing_export_file", detail="multipart export_file required")
|
||||
export_file = files["export_file"]
|
||||
try:
|
||||
raw = export_file.read()
|
||||
data = json.loads(raw.decode("utf-8"))
|
||||
except (UnicodeDecodeError, json.JSONDecodeError) as exc:
|
||||
return _bad("invalid_export_file", detail=str(exc))
|
||||
dry_run = str(form.get("dry_run", "false")).lower() in ("true", "1", "yes")
|
||||
params: dict = {"data": data, "dry_run": dry_run}
|
||||
else:
|
||||
body = await request.get_json()
|
||||
if body is None:
|
||||
body = {}
|
||||
if not isinstance(body, dict):
|
||||
return _bad("invalid_body")
|
||||
dry_run = bool(body.get("dry_run", False))
|
||||
params = dict(body)
|
||||
|
||||
async with get_session() as session:
|
||||
run = MigrationRun(kind=kind, status="pending", dry_run=dry_run)
|
||||
session.add(run)
|
||||
await session.commit()
|
||||
await session.refresh(run)
|
||||
run_id = run.id
|
||||
|
||||
run_migration.delay(run_id, kind, params)
|
||||
return jsonify({"run_id": run_id, "status": "pending"}), 202
|
||||
|
||||
|
||||
@migrate_bp.route("/runs/<int:run_id>", methods=["GET"])
|
||||
async def get_run(run_id: int):
|
||||
async with get_session() as session:
|
||||
run = (await session.execute(
|
||||
select(MigrationRun).where(MigrationRun.id == run_id)
|
||||
)).scalar_one_or_none()
|
||||
if run is None:
|
||||
return _bad("not_found", status=404)
|
||||
return jsonify(_run_to_dict(run))
|
||||
|
||||
|
||||
@migrate_bp.route("/runs", methods=["GET"])
|
||||
async def list_runs():
|
||||
try:
|
||||
limit = int(request.args.get("limit", "10"))
|
||||
except ValueError:
|
||||
return _bad("invalid_limit")
|
||||
if limit < 1 or limit > 100:
|
||||
return _bad("invalid_limit")
|
||||
|
||||
async with get_session() as session:
|
||||
rows = (await session.execute(
|
||||
select(MigrationRun)
|
||||
.order_by(MigrationRun.id.desc())
|
||||
.limit(limit)
|
||||
)).scalars().all()
|
||||
return jsonify([_run_to_dict(r) for r in rows])
|
||||
@@ -9,9 +9,7 @@ ml_admin_bp = Blueprint("ml_admin", __name__, url_prefix="/api/ml")
|
||||
|
||||
|
||||
_EDITABLE = (
|
||||
"suggestion_threshold_artist",
|
||||
"suggestion_threshold_character",
|
||||
"suggestion_threshold_copyright",
|
||||
"suggestion_threshold_general",
|
||||
"centroid_similarity_threshold",
|
||||
"min_reference_images",
|
||||
@@ -28,9 +26,7 @@ async def get_settings():
|
||||
).scalar_one()
|
||||
return jsonify(
|
||||
{
|
||||
"suggestion_threshold_artist": s.suggestion_threshold_artist,
|
||||
"suggestion_threshold_character": s.suggestion_threshold_character,
|
||||
"suggestion_threshold_copyright": s.suggestion_threshold_copyright,
|
||||
"suggestion_threshold_general": s.suggestion_threshold_general,
|
||||
"centroid_similarity_threshold": s.centroid_similarity_threshold,
|
||||
"min_reference_images": s.min_reference_images,
|
||||
|
||||
+25
-11
@@ -5,18 +5,11 @@ from quart import Blueprint, jsonify, request
|
||||
from ..extensions import get_session
|
||||
from ..services.post_feed_service import PostFeedService
|
||||
from ..services.source_service import KNOWN_PLATFORMS
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
posts_bp = Blueprint("posts", __name__, url_prefix="/api/posts")
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
|
||||
body = {"error": error}
|
||||
if detail is not None:
|
||||
body["detail"] = detail
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
@posts_bp.route("", methods=["GET"])
|
||||
async def list_posts():
|
||||
args = request.args
|
||||
@@ -25,6 +18,8 @@ async def list_posts():
|
||||
artist_id_raw = args.get("artist_id")
|
||||
platform = args.get("platform") or None
|
||||
limit_raw = args.get("limit", "24")
|
||||
direction = args.get("direction", "older")
|
||||
around_raw = args.get("around")
|
||||
|
||||
try:
|
||||
limit = int(limit_raw)
|
||||
@@ -33,6 +28,16 @@ async def list_posts():
|
||||
if limit < 1 or limit > 100:
|
||||
return _bad("invalid_limit", detail="limit must be between 1 and 100")
|
||||
|
||||
if direction not in ("older", "newer"):
|
||||
return _bad("invalid_direction", detail="direction must be 'older' or 'newer'")
|
||||
|
||||
around_id = None
|
||||
if around_raw is not None:
|
||||
try:
|
||||
around_id = int(around_raw)
|
||||
except ValueError:
|
||||
return _bad("invalid_around", detail="around must be an integer post id")
|
||||
|
||||
artist_id = None
|
||||
if artist_id_raw is not None:
|
||||
try:
|
||||
@@ -47,11 +52,20 @@ async def list_posts():
|
||||
)
|
||||
|
||||
async with get_session() as session:
|
||||
try:
|
||||
page = await PostFeedService(session).scroll(
|
||||
cursor=cursor, artist_id=artist_id,
|
||||
svc = PostFeedService(session)
|
||||
if around_id is not None:
|
||||
result = await svc.around(
|
||||
post_id=around_id, artist_id=artist_id,
|
||||
platform=platform, limit=limit,
|
||||
)
|
||||
if result is None:
|
||||
return _bad("not_found", status=404, detail=f"post id={around_id}")
|
||||
return jsonify(result)
|
||||
try:
|
||||
page = await svc.scroll(
|
||||
cursor=cursor, artist_id=artist_id,
|
||||
platform=platform, limit=limit, direction=direction,
|
||||
)
|
||||
except ValueError as exc:
|
||||
# Service raises ValueError for malformed cursors only;
|
||||
# limit bounds are validated above.
|
||||
|
||||
@@ -31,9 +31,7 @@ _EDITABLE_FIELDS = (
|
||||
@settings_bp.route("/settings/import", methods=["GET"])
|
||||
async def get_import_settings():
|
||||
async with get_session() as session:
|
||||
row = (
|
||||
await session.execute(select(ImportSettings).where(ImportSettings.id == 1))
|
||||
).scalar_one()
|
||||
row = await ImportSettings.load(session)
|
||||
return jsonify({
|
||||
"min_width": row.min_width,
|
||||
"min_height": row.min_height,
|
||||
@@ -99,9 +97,7 @@ async def update_import_settings():
|
||||
return _bad_int("download_failure_warning_threshold", 1, 100)
|
||||
|
||||
async with get_session() as session:
|
||||
row = (
|
||||
await session.execute(select(ImportSettings).where(ImportSettings.id == 1))
|
||||
).scalar_one()
|
||||
row = await ImportSettings.load(session)
|
||||
for field in _EDITABLE_FIELDS:
|
||||
if field in body:
|
||||
setattr(row, field, body[field])
|
||||
|
||||
+59
-10
@@ -5,6 +5,7 @@ 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,
|
||||
@@ -14,18 +15,11 @@ from ..services.source_service import (
|
||||
SourceService,
|
||||
UnknownPlatformError,
|
||||
)
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
sources_bp = Blueprint("sources", __name__, url_prefix="/api/sources")
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, detail: str | None = None, **extra):
|
||||
body = {"error": error}
|
||||
if detail is not None:
|
||||
body["detail"] = detail
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
@sources_bp.route("", methods=["GET"])
|
||||
async def list_sources():
|
||||
artist_id_raw = request.args.get("artist_id")
|
||||
@@ -35,11 +29,19 @@ async def list_sources():
|
||||
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)
|
||||
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:
|
||||
@@ -118,12 +120,46 @@ async def delete_source(source_id: int):
|
||||
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."""
|
||||
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)
|
||||
@@ -133,6 +169,19 @@ async def check_source(source_id: int):
|
||||
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,
|
||||
|
||||
@@ -20,6 +20,7 @@ from sqlalchemy import desc, func, select
|
||||
from ..config import get_config
|
||||
from ..extensions import get_session
|
||||
from ..models import TaskRun
|
||||
from ..services.scheduler_service import scheduler_status
|
||||
|
||||
system_activity_bp = Blueprint(
|
||||
"system_activity", __name__, url_prefix="/api/system/activity",
|
||||
@@ -81,17 +82,22 @@ def _read_workers_sync() -> dict:
|
||||
}
|
||||
|
||||
|
||||
async def _queues_cached() -> dict:
|
||||
"""Per-queue Redis LLEN, cached 2s. Shared by /queues and /summary."""
|
||||
now = time.time()
|
||||
if _QUEUE_CACHE["data"] is None or (now - _QUEUE_CACHE["ts"]) > _QUEUE_CACHE_TTL:
|
||||
_QUEUE_CACHE["data"] = await asyncio.to_thread(_read_queues_sync)
|
||||
_QUEUE_CACHE["ts"] = now
|
||||
return _QUEUE_CACHE["data"]
|
||||
|
||||
|
||||
@system_activity_bp.route("/queues", methods=["GET"])
|
||||
async def get_queues():
|
||||
"""Per-queue Redis LLEN. Cached 2s.
|
||||
|
||||
Response: {queues: {name: depth_or_null}, fetched_at: iso8601}
|
||||
"""
|
||||
now = time.time()
|
||||
if _QUEUE_CACHE["data"] is None or (now - _QUEUE_CACHE["ts"]) > _QUEUE_CACHE_TTL:
|
||||
_QUEUE_CACHE["data"] = await asyncio.to_thread(_read_queues_sync)
|
||||
_QUEUE_CACHE["ts"] = now
|
||||
return jsonify(_QUEUE_CACHE["data"])
|
||||
return jsonify(await _queues_cached())
|
||||
|
||||
|
||||
@system_activity_bp.route("/workers", methods=["GET"])
|
||||
@@ -107,6 +113,35 @@ async def get_workers():
|
||||
return jsonify(_WORKER_CACHE["data"])
|
||||
|
||||
|
||||
@system_activity_bp.route("/summary", methods=["GET"])
|
||||
async def get_summary():
|
||||
"""One-call rollup for the always-on TopNav pipeline indicator:
|
||||
scheduler health, per-queue pending depths, currently-running count, and
|
||||
recent (24h) failure count. Cheap — cached queue LLENs + two TaskRun
|
||||
counts — so it's safe to poll app-wide."""
|
||||
queues_data = await _queues_cached()
|
||||
depths = queues_data.get("queues", {})
|
||||
queued_total = sum(v for v in depths.values() if isinstance(v, int))
|
||||
since = datetime.now(UTC) - timedelta(hours=24)
|
||||
async with get_session() as session:
|
||||
scheduler = await scheduler_status(session)
|
||||
running = (await session.execute(
|
||||
select(func.count(TaskRun.id)).where(TaskRun.status == "running")
|
||||
)).scalar_one()
|
||||
failing = (await session.execute(
|
||||
select(func.count(TaskRun.id))
|
||||
.where(TaskRun.status.in_(["error", "timeout"]))
|
||||
.where(TaskRun.finished_at >= since)
|
||||
)).scalar_one()
|
||||
return jsonify({
|
||||
"scheduler": scheduler,
|
||||
"queues": depths,
|
||||
"queued_total": queued_total,
|
||||
"running": int(running),
|
||||
"failing": int(failing),
|
||||
})
|
||||
|
||||
|
||||
@system_activity_bp.route("/runs", methods=["GET"])
|
||||
async def list_runs():
|
||||
"""Paginated task_run history. Query params:
|
||||
|
||||
@@ -14,6 +14,7 @@ from sqlalchemy import desc, select
|
||||
|
||||
from ..extensions import get_session
|
||||
from ..models import BackupRun, ImportSettings
|
||||
from ._responses import error_response as _bad
|
||||
|
||||
system_backup_bp = Blueprint(
|
||||
"system_backup", __name__, url_prefix="/api/system/backup",
|
||||
@@ -29,12 +30,6 @@ _BACKUP_SETTINGS_FIELDS = (
|
||||
)
|
||||
|
||||
|
||||
def _bad(error: str, *, status: int = 400, **extra):
|
||||
body = {"error": error}
|
||||
body.update(extra)
|
||||
return jsonify(body), status
|
||||
|
||||
|
||||
def _row_to_dict(r: BackupRun) -> dict:
|
||||
return {
|
||||
"id": r.id,
|
||||
@@ -232,9 +227,7 @@ async def delete_run(run_id: int):
|
||||
@system_backup_bp.route("/settings", methods=["GET"])
|
||||
async def get_settings():
|
||||
async with get_session() as session:
|
||||
row = (await session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
)).scalar_one()
|
||||
row = await ImportSettings.load(session)
|
||||
return jsonify({
|
||||
"backup_db_nightly_enabled": row.backup_db_nightly_enabled,
|
||||
"backup_db_nightly_hour_utc": row.backup_db_nightly_hour_utc,
|
||||
@@ -254,9 +247,7 @@ async def patch_settings():
|
||||
return err
|
||||
|
||||
async with get_session() as session:
|
||||
row = (await session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
)).scalar_one()
|
||||
row = await ImportSettings.load(session)
|
||||
for field in _BACKUP_SETTINGS_FIELDS:
|
||||
if field in body:
|
||||
setattr(row, field, body[field])
|
||||
|
||||
@@ -1,5 +1,7 @@
|
||||
"""Thumbnail admin API: backfill trigger."""
|
||||
|
||||
import asyncio
|
||||
|
||||
from quart import Blueprint, jsonify
|
||||
|
||||
thumbnails_bp = Blueprint("thumbnails", __name__, url_prefix="/api/thumbnails")
|
||||
@@ -7,7 +9,20 @@ thumbnails_bp = Blueprint("thumbnails", __name__, url_prefix="/api/thumbnails")
|
||||
|
||||
@thumbnails_bp.route("/backfill", methods=["POST"])
|
||||
async def trigger_backfill():
|
||||
from ..tasks.thumbnail import backfill_thumbnails
|
||||
"""Run the backfill scan synchronously, return the counts. The actual
|
||||
thumbnail generation work is still off-loaded to the thumbnail Celery
|
||||
queue via `generate_thumbnail.delay()` per missing row — so this
|
||||
handler is fast even on a 100k-image library (a scan is just SELECT
|
||||
id, thumbnail_path + a file.stat() per row, no heavy work).
|
||||
|
||||
r = backfill_thumbnails.delay()
|
||||
return jsonify({"celery_task_id": r.id}), 202
|
||||
Operator-flagged 2026-06-01: the previous fire-and-forget shape
|
||||
returned `{celery_task_id}` only, so the admin UI had no idea whether
|
||||
backfill found 0 or 5000 candidates — \"found nothing\" was
|
||||
indistinguishable from \"the worker isn't picking up the task.\""""
|
||||
from ..tasks.thumbnail import _run_backfill_scan
|
||||
|
||||
# Sync scan inside an executor so we don't block the event loop.
|
||||
counts = await asyncio.get_running_loop().run_in_executor(
|
||||
None, _run_backfill_scan,
|
||||
)
|
||||
return jsonify(counts), 200
|
||||
|
||||
@@ -28,7 +28,6 @@ def make_celery() -> Celery:
|
||||
"backend.app.tasks.import_file",
|
||||
"backend.app.tasks.thumbnail",
|
||||
"backend.app.tasks.maintenance",
|
||||
"backend.app.tasks.migration",
|
||||
"backend.app.tasks.ml",
|
||||
"backend.app.tasks.download",
|
||||
"backend.app.tasks.backup",
|
||||
@@ -45,7 +44,6 @@ def make_celery() -> Celery:
|
||||
"backend.app.tasks.download.*": {"queue": "download"},
|
||||
"backend.app.tasks.scan.*": {"queue": "scan"},
|
||||
"backend.app.tasks.maintenance.*": {"queue": "maintenance"},
|
||||
"backend.app.tasks.migration.*": {"queue": "maintenance"},
|
||||
"backend.app.tasks.backup.*": {"queue": "maintenance"},
|
||||
"backend.app.tasks.admin.*": {"queue": "maintenance"},
|
||||
"backend.app.tasks.library_audit.*": {"queue": "maintenance"},
|
||||
@@ -87,6 +85,10 @@ def make_celery() -> Celery:
|
||||
"task": "backend.app.tasks.maintenance.cleanup_old_download_events",
|
||||
"schedule": 86400.0, # daily
|
||||
},
|
||||
"recover-stalled-download-events": {
|
||||
"task": "backend.app.tasks.maintenance.recover_stalled_download_events",
|
||||
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
|
||||
},
|
||||
"recover-stalled-task-runs": {
|
||||
"task": "backend.app.tasks.maintenance.recover_stalled_task_runs",
|
||||
"schedule": 300.0, # every 5 min, matches recover-interrupted-tasks
|
||||
|
||||
@@ -66,10 +66,7 @@ def _queue_for(task) -> str:
|
||||
return "download"
|
||||
if name.startswith("backend.app.tasks.scan."):
|
||||
return "scan"
|
||||
if name.startswith((
|
||||
"backend.app.tasks.maintenance.",
|
||||
"backend.app.tasks.migration.",
|
||||
)):
|
||||
if name.startswith("backend.app.tasks.maintenance."):
|
||||
return "maintenance"
|
||||
return "default"
|
||||
|
||||
|
||||
@@ -12,7 +12,6 @@ from .import_batch import ImportBatch
|
||||
from .import_settings import ImportSettings
|
||||
from .import_task import ImportTask
|
||||
from .library_audit_run import LibraryAuditRun
|
||||
from .migration_run import MigrationRun
|
||||
from .ml_settings import MLSettings
|
||||
from .post import Post
|
||||
from .post_attachment import PostAttachment
|
||||
@@ -46,7 +45,6 @@ __all__ = [
|
||||
"ImportSettings",
|
||||
"LibraryAuditRun",
|
||||
"MLSettings",
|
||||
"MigrationRun",
|
||||
"TagAlias",
|
||||
"TagAllowlist",
|
||||
"TagReferenceEmbedding",
|
||||
|
||||
@@ -34,8 +34,12 @@ class ImageProvenance(Base):
|
||||
post_id: Mapped[int] = mapped_column(
|
||||
ForeignKey("post.id", ondelete="CASCADE"), nullable=False, index=True
|
||||
)
|
||||
source_id: Mapped[int] = mapped_column(
|
||||
ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
|
||||
# Nullable since alembic 0030 — provenance rows for filesystem-imported
|
||||
# content with no subscription have NULL source_id. FK ondelete SET
|
||||
# NULL so deleting a Source detaches its provenance rows instead of
|
||||
# destroying the linkage between image and post.
|
||||
source_id: Mapped[int | None] = mapped_column(
|
||||
ForeignKey("source.id", ondelete="SET NULL"), nullable=True, index=True
|
||||
)
|
||||
captured_metadata: Mapped[dict | None] = mapped_column(JSON, nullable=True)
|
||||
captured_at: Mapped[datetime] = mapped_column(
|
||||
|
||||
@@ -4,7 +4,7 @@ Enforced as a single row via a CHECK (id = 1) constraint. The application
|
||||
always SELECTs id=1 and never inserts/deletes after the initial migration.
|
||||
"""
|
||||
|
||||
from sqlalchemy import Boolean, CheckConstraint, Float, Integer, Text
|
||||
from sqlalchemy import Boolean, CheckConstraint, Float, Integer, Text, select
|
||||
from sqlalchemy.orm import Mapped, mapped_column
|
||||
|
||||
from .base import Base
|
||||
@@ -63,3 +63,13 @@ class ImportSettings(Base):
|
||||
backup_images_keep_last_n: Mapped[int] = mapped_column(
|
||||
Integer, nullable=False, default=3,
|
||||
)
|
||||
|
||||
@classmethod
|
||||
async def load(cls, session) -> ImportSettings:
|
||||
"""The singleton settings row (id=1), via an async session."""
|
||||
return (await session.execute(select(cls).where(cls.id == 1))).scalar_one()
|
||||
|
||||
@classmethod
|
||||
def load_sync(cls, session) -> ImportSettings:
|
||||
"""The singleton settings row (id=1), via a sync session."""
|
||||
return session.execute(select(cls).where(cls.id == 1)).scalar_one()
|
||||
|
||||
@@ -1,37 +0,0 @@
|
||||
"""MigrationRun — tracks each FC-5 migration invocation (backup/gs/ir/etc).
|
||||
|
||||
kind/status are String(32) not Postgres ENUM so adding kinds later
|
||||
doesn't need a schema migration. The API layer validates values.
|
||||
"""
|
||||
|
||||
from datetime import datetime
|
||||
|
||||
import sqlalchemy as sa
|
||||
from sqlalchemy import Boolean, DateTime, Integer, String, Text, func
|
||||
from sqlalchemy.dialects.postgresql import JSONB
|
||||
from sqlalchemy.orm import Mapped, mapped_column
|
||||
|
||||
from .base import Base
|
||||
|
||||
|
||||
class MigrationRun(Base):
|
||||
__tablename__ = "migration_run"
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
||||
kind: Mapped[str] = mapped_column(String(32), nullable=False, index=True)
|
||||
status: Mapped[str] = mapped_column(String(32), nullable=False, index=True)
|
||||
dry_run: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
|
||||
started_at: Mapped[datetime] = mapped_column(
|
||||
DateTime(timezone=True), nullable=False, server_default=func.now(),
|
||||
)
|
||||
finished_at: Mapped[datetime | None] = mapped_column(
|
||||
DateTime(timezone=True), nullable=True,
|
||||
)
|
||||
counts: Mapped[dict] = mapped_column(
|
||||
JSONB, nullable=False, default=dict, server_default=sa.text("'{}'::jsonb"),
|
||||
)
|
||||
error: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
metadata_: Mapped[dict] = mapped_column(
|
||||
"metadata", JSONB, nullable=False, default=dict,
|
||||
server_default=sa.text("'{}'::jsonb"),
|
||||
)
|
||||
@@ -15,17 +15,14 @@ class MLSettings(Base):
|
||||
__table_args__ = (CheckConstraint("id = 1", name="singleton"),)
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
||||
suggestion_threshold_artist: Mapped[float] = mapped_column(
|
||||
Float, nullable=False, default=0.30
|
||||
)
|
||||
suggestion_threshold_character: Mapped[float] = mapped_column(
|
||||
Float, nullable=False, default=0.50
|
||||
)
|
||||
suggestion_threshold_copyright: Mapped[float] = mapped_column(
|
||||
Float, nullable=False, default=0.50
|
||||
)
|
||||
# Default lowered 0.95 → 0.50 on 2026-06-01 — operator-flagged that
|
||||
# 0.95 hid most general suggestions. Operator-tunable via Settings →
|
||||
# ML if too noisy.
|
||||
suggestion_threshold_general: Mapped[float] = mapped_column(
|
||||
Float, nullable=False, default=0.95
|
||||
Float, nullable=False, default=0.50
|
||||
)
|
||||
centroid_similarity_threshold: Mapped[float] = mapped_column(
|
||||
Float, nullable=False, default=0.55
|
||||
|
||||
@@ -1,6 +1,9 @@
|
||||
"""Post — provenance anchor for content downloaded from a Source.
|
||||
"""Post — provenance anchor for one creator post (may contain many images).
|
||||
|
||||
A Post is one creator post; it may contain many images/videos.
|
||||
`source_id` is nullable since alembic 0030 — filesystem-imported posts
|
||||
with no live subscription have NULL source_id. `artist_id` is the
|
||||
denormalized always-present link to the creator (added in 0030 so
|
||||
artist-filter queries don't depend on the Source detour).
|
||||
"""
|
||||
|
||||
from datetime import datetime
|
||||
@@ -14,12 +17,25 @@ from .base import Base
|
||||
class Post(Base):
|
||||
__tablename__ = "post"
|
||||
__table_args__ = (
|
||||
# Source-bound dedup. Postgres treats NULL != NULL so rows
|
||||
# with source_id IS NULL aren't deduped by this constraint;
|
||||
# the partial unique index `uq_post_artist_external_id_null_source`
|
||||
# (created in alembic 0030) covers that case via
|
||||
# (artist_id, external_post_id).
|
||||
UniqueConstraint("source_id", "external_post_id", name="uq_post_source_external_id"),
|
||||
)
|
||||
|
||||
id: Mapped[int] = mapped_column(Integer, primary_key=True)
|
||||
source_id: Mapped[int] = mapped_column(
|
||||
ForeignKey("source.id", ondelete="CASCADE"), nullable=False, index=True
|
||||
source_id: Mapped[int | None] = mapped_column(
|
||||
ForeignKey("source.id", ondelete="SET NULL"), nullable=True, index=True
|
||||
)
|
||||
# Denormalized; always equals source.artist_id when source_id is set
|
||||
# (the importer is responsible for keeping them consistent on insert).
|
||||
# Filter queries (artist detail, artist-scoped posts feed) use this
|
||||
# directly instead of joining through Source.
|
||||
artist_id: Mapped[int] = mapped_column(
|
||||
ForeignKey("artist.id", ondelete="CASCADE"),
|
||||
nullable=False, index=True,
|
||||
)
|
||||
external_post_id: Mapped[str] = mapped_column(String(128), nullable=False)
|
||||
post_url: Mapped[str | None] = mapped_column(Text, nullable=True)
|
||||
|
||||
@@ -29,4 +29,13 @@ class Source(Base):
|
||||
check_interval_override: Mapped[int | None] = mapped_column(Integer, nullable=True)
|
||||
consecutive_failures: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
|
||||
|
||||
# alembic 0031: sticky deep-scan budget. When > 0, the next N download
|
||||
# runs use gallery-dl's full-walk config (skip: True + 1800s timeout);
|
||||
# when 0, runs use tick mode (skip: "exit:20" + 870s, exits early once
|
||||
# 20 contiguous archived items are seen). Auto-decrements per run, with
|
||||
# an auto-reset to 0 on clean exit + zero downloads (queue drained).
|
||||
backfill_runs_remaining: Mapped[int] = mapped_column(
|
||||
Integer, nullable=False, default=0, server_default="0",
|
||||
)
|
||||
|
||||
artist = relationship("Artist", back_populates="sources")
|
||||
|
||||
@@ -127,17 +127,20 @@ class ArtistDirectoryService:
|
||||
ImageRecord.artist_id.label("artist_id"),
|
||||
ImageRecord.sha256.label("sha256"),
|
||||
ImageRecord.mime.label("mime"),
|
||||
ImageRecord.thumbnail_path.label("thumbnail_path"),
|
||||
rn,
|
||||
)
|
||||
.where(ImageRecord.artist_id.in_(artist_ids))
|
||||
.subquery()
|
||||
)
|
||||
stmt = (
|
||||
select(sub.c.artist_id, sub.c.sha256, sub.c.mime)
|
||||
select(
|
||||
sub.c.artist_id, sub.c.sha256, sub.c.mime, sub.c.thumbnail_path,
|
||||
)
|
||||
.where(sub.c.rn <= _PREVIEW_COUNT)
|
||||
.order_by(sub.c.artist_id, sub.c.rn)
|
||||
)
|
||||
out: dict[int, list[str]] = {}
|
||||
for aid, sha, mime in (await self.session.execute(stmt)).all():
|
||||
out.setdefault(aid, []).append(thumbnail_url(sha, mime))
|
||||
for aid, sha, mime, tp in (await self.session.execute(stmt)).all():
|
||||
out.setdefault(aid, []).append(thumbnail_url(tp, sha, mime))
|
||||
return out
|
||||
|
||||
@@ -58,13 +58,17 @@ class ArtistService:
|
||||
)
|
||||
).scalar_one()
|
||||
|
||||
# Posts under this artist that have at least one image attached.
|
||||
# Use Post.artist_id (alembic 0030) for the artist filter; keep
|
||||
# the ImageProvenance JOIN so date bounds reflect only image-
|
||||
# bearing posts (matches the original semantic). NULL-source
|
||||
# posts now surface too.
|
||||
date_row = (
|
||||
await self.session.execute(
|
||||
select(func.min(Post.post_date), func.max(Post.post_date))
|
||||
.select_from(Post)
|
||||
.join(ImageProvenance, ImageProvenance.post_id == Post.id)
|
||||
.join(Source, Source.id == ImageProvenance.source_id)
|
||||
.where(Source.artist_id == aid)
|
||||
.where(Post.artist_id == aid)
|
||||
)
|
||||
).first()
|
||||
dmin, dmax = date_row if date_row else (None, None)
|
||||
@@ -98,14 +102,14 @@ class ArtistService:
|
||||
)
|
||||
).all()
|
||||
|
||||
# Same Post.artist_id direct filter — counts NULL-source posts too.
|
||||
month = func.date_trunc("month", Post.post_date).label("m")
|
||||
activity = (
|
||||
await self.session.execute(
|
||||
select(month, func.count(func.distinct(ImageProvenance.image_record_id)))
|
||||
.select_from(Post)
|
||||
.join(ImageProvenance, ImageProvenance.post_id == Post.id)
|
||||
.join(Source, Source.id == ImageProvenance.source_id)
|
||||
.where(and_(Source.artist_id == aid, Post.post_date.isnot(None)))
|
||||
.where(and_(Post.artist_id == aid, Post.post_date.isnot(None)))
|
||||
.group_by(month)
|
||||
.order_by(month)
|
||||
)
|
||||
@@ -114,9 +118,7 @@ class ArtistService:
|
||||
post_count = (
|
||||
await self.session.execute(
|
||||
select(func.count(func.distinct(Post.id)))
|
||||
.select_from(Post)
|
||||
.join(Source, Source.id == Post.source_id)
|
||||
.where(Source.artist_id == aid)
|
||||
.where(Post.artist_id == aid)
|
||||
)
|
||||
).scalar_one()
|
||||
|
||||
@@ -198,7 +200,7 @@ class ArtistService:
|
||||
"mime": r.mime,
|
||||
"width": r.width,
|
||||
"height": r.height,
|
||||
"thumbnail_url": thumbnail_url(r.sha256, r.mime),
|
||||
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
|
||||
}
|
||||
for r in rows
|
||||
],
|
||||
|
||||
@@ -6,9 +6,8 @@ HTTP handlers (small ops) and from Celery tasks in
|
||||
backend.app.tasks.admin (long ops).
|
||||
|
||||
This module is the PERMANENT home of artist-cascade + image-unlink
|
||||
logic. The legacy copy at backend/app/services/migrators/cleanup.py
|
||||
stays in place until FC-3j; FC-3j will replace its body with thin
|
||||
re-exports from this module and then delete the wrapper.
|
||||
logic. (The legacy migrators/cleanup.py copy was removed with the rest of
|
||||
the one-and-done GS/IR migration tooling.)
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
@@ -16,7 +15,7 @@ from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
from sqlalchemy import func, select, update
|
||||
from sqlalchemy import func, or_, select, update
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from ..models import Artist, ImageRecord, LibraryAuditRun, Tag
|
||||
@@ -369,6 +368,72 @@ def prune_unused_tags(session: Session, *, dry_run: bool = False) -> dict:
|
||||
return {"deleted": len(ids), "sample_names": sample}
|
||||
|
||||
|
||||
# Legacy tags FC no longer uses, in two shapes:
|
||||
# (1) kinds the tag input never produces — archive/post/artist.
|
||||
# provenance (post grouping) + archive membership are their own
|
||||
# systems now, and artists are first-class Artist/Source rows.
|
||||
# meta/rating were already hard-deleted by alembic 0023.
|
||||
# (2) name prefixes from IR kinds FC never adopted — `source:*`.
|
||||
# ImageRepo had a `source` kind; FC's enum doesn't, so ir_ingest
|
||||
# fell those back to `general` (kind=general, name="source:patreon"
|
||||
# etc.). They can't be caught by kind, so we match the name prefix.
|
||||
PURGEABLE_TAG_KINDS = ("archive", "post", "artist")
|
||||
LEGACY_NAME_PREFIXES = ("source:",)
|
||||
|
||||
|
||||
def _legacy_tag_predicate():
|
||||
name_clauses = [Tag.name.like(f"{p}%") for p in LEGACY_NAME_PREFIXES]
|
||||
return or_(Tag.kind.in_(PURGEABLE_TAG_KINDS), *name_clauses)
|
||||
|
||||
|
||||
def purge_legacy_tags(session: Session, *, dry_run: bool = False) -> dict:
|
||||
"""Count (dry_run) or delete legacy IR-migration tags: archive/post/
|
||||
artist-kind tags PLUS general tags whose name matches a legacy
|
||||
prefix (source:*).
|
||||
|
||||
CASCADE on image_tag / tag_alias / tag_allowlist /
|
||||
tag_reference_embedding / tag_suggestion_rejection / series_page
|
||||
clears the related rows on the parent DELETE.
|
||||
|
||||
Returns:
|
||||
{"by_kind": {kind: count, ...}, # kind-matched rows
|
||||
"by_prefix": {"source:*": count}, # name-prefix-matched rows
|
||||
"count": total, "sample_names": [first 50],
|
||||
and on live runs "deleted": total}
|
||||
"""
|
||||
predicate = _legacy_tag_predicate()
|
||||
rows = session.execute(
|
||||
select(Tag.id, Tag.name, Tag.kind).where(predicate)
|
||||
).all()
|
||||
by_kind: dict[str, int] = {}
|
||||
by_prefix: dict[str, int] = {}
|
||||
for _id, name, kind in rows:
|
||||
# Classify by name-prefix first so a source:* row counts once,
|
||||
# under the prefix bucket, regardless of its (general) kind.
|
||||
matched_prefix = next(
|
||||
(p for p in LEGACY_NAME_PREFIXES if name.startswith(p)), None,
|
||||
)
|
||||
if matched_prefix is not None:
|
||||
label = f"{matched_prefix}*"
|
||||
by_prefix[label] = by_prefix.get(label, 0) + 1
|
||||
else:
|
||||
key = kind.value if hasattr(kind, "value") else str(kind)
|
||||
by_kind[key] = by_kind.get(key, 0) + 1
|
||||
sample = [name for _id, name, _kind in rows[:50]]
|
||||
total = len(rows)
|
||||
result = {
|
||||
"by_kind": by_kind, "by_prefix": by_prefix,
|
||||
"count": total, "sample_names": sample,
|
||||
}
|
||||
if dry_run:
|
||||
return result
|
||||
if total:
|
||||
session.execute(Tag.__table__.delete().where(predicate))
|
||||
session.commit()
|
||||
result["deleted"] = total
|
||||
return result
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# FC-Cleanup additions (2026-05-26): retroactive audit of import-filter rules.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@@ -7,7 +7,7 @@ from __future__ import annotations
|
||||
import json
|
||||
import os
|
||||
from dataclasses import dataclass
|
||||
from datetime import datetime
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
@@ -163,6 +163,19 @@ class CredentialService:
|
||||
return None
|
||||
return self.crypto.decrypt(row.encrypted_blob)
|
||||
|
||||
async def mark_verified(self, platform: str) -> datetime | None:
|
||||
"""Stamp last_verified=now after a successful verify. Returns the
|
||||
timestamp, or None if the credential is gone."""
|
||||
row = (await self.session.execute(
|
||||
select(Credential).where(Credential.platform == platform)
|
||||
)).scalar_one_or_none()
|
||||
if row is None:
|
||||
return None
|
||||
ts = datetime.now(UTC)
|
||||
row.last_verified = ts
|
||||
await self.session.commit()
|
||||
return ts
|
||||
|
||||
|
||||
def _augment_cookies(platform: str, netscape: str) -> str:
|
||||
"""Delegate to the platform's `augment_cookies` hook if one is
|
||||
|
||||
@@ -25,9 +25,17 @@ from sqlalchemy.orm import joinedload
|
||||
|
||||
from ..models import Artist, DownloadEvent, Source
|
||||
from .credential_service import CredentialService
|
||||
from .gallery_dl import GalleryDLService, SourceConfig
|
||||
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 .scheduler_service import set_platform_cooldown
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
@@ -83,6 +91,18 @@ class DownloadService:
|
||||
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 {}
|
||||
)
|
||||
@@ -94,6 +114,7 @@ class DownloadService:
|
||||
source_config=source_config,
|
||||
cookies_path=ctx["cookies_path"],
|
||||
auth_token=ctx["auth_token"],
|
||||
skip_value=skip_value,
|
||||
)
|
||||
|
||||
resolved_campaign_id: str | None = None
|
||||
@@ -120,6 +141,7 @@ class DownloadService:
|
||||
source_config=source_config,
|
||||
cookies_path=ctx["cookies_path"],
|
||||
auth_token=ctx["auth_token"],
|
||||
skip_value=skip_value,
|
||||
)
|
||||
|
||||
return await self._phase3_persist(
|
||||
@@ -184,6 +206,7 @@ class DownloadService:
|
||||
"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(
|
||||
@@ -237,6 +260,40 @@ class DownloadService:
|
||||
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",
|
||||
):
|
||||
@@ -245,6 +302,12 @@ class DownloadService:
|
||||
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
|
||||
else:
|
||||
import_summary["errors"] += 1
|
||||
|
||||
@@ -258,12 +321,21 @@ class DownloadService:
|
||||
run_stats["quarantined_count"] = dl_result.files_quarantined
|
||||
stderr_summary = self.gdl._extract_errors_warnings(dl_result.stderr)
|
||||
|
||||
status = "ok" if (dl_result.success and import_summary["errors"] == 0) else "error"
|
||||
# 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 not dl_result.success else None
|
||||
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,
|
||||
@@ -276,18 +348,40 @@ class DownloadService:
|
||||
}
|
||||
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.
|
||||
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()
|
||||
if dl_result.return_code == 0 and dl_result.files_downloaded == 0:
|
||||
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)
|
||||
@@ -299,6 +393,8 @@ class DownloadService:
|
||||
elif status == "error":
|
||||
source.consecutive_failures = (source.consecutive_failures or 0) + 1
|
||||
source.last_error = error_message
|
||||
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
|
||||
|
||||
@@ -86,6 +86,67 @@ class ExtensionService:
|
||||
"created_artist": created_artist,
|
||||
}
|
||||
|
||||
async def probe(self, url: str) -> dict:
|
||||
"""Read-only resolution of a creator-page URL against the FC DB.
|
||||
Returns one of:
|
||||
- {state: 'unknown_platform'} — URL didn't match any
|
||||
platform's strict artist-page pattern
|
||||
- {state: 'new', platform, slug} — would create both
|
||||
artist and source on quick-add
|
||||
- {state: 'artist_match', platform, slug, artist}
|
||||
— artist exists, this
|
||||
exact URL isn't a Source yet (collapses the sidecar-synthetic
|
||||
case too — the synthetic anchor counts as an existing artist
|
||||
row but not as a pollable Source for this URL)
|
||||
- {state: 'source_match', platform, slug, artist, source}
|
||||
— exact (artist, platform,
|
||||
url) Source already exists
|
||||
|
||||
Side-effect-free: two SELECTs at most.
|
||||
"""
|
||||
try:
|
||||
platform, raw_slug = self._derive(url)
|
||||
except (UnknownPlatformError, InvalidUrlError):
|
||||
return {"state": "unknown_platform"}
|
||||
|
||||
slug = slugify(raw_slug)
|
||||
artist = (await self.session.execute(
|
||||
select(Artist).where(Artist.slug == slug)
|
||||
)).scalar_one_or_none()
|
||||
if artist is None:
|
||||
return {"state": "new", "platform": platform, "slug": slug}
|
||||
|
||||
artist_payload = {"id": artist.id, "name": artist.name, "slug": artist.slug}
|
||||
|
||||
source = (await self.session.execute(
|
||||
select(Source).where(
|
||||
Source.artist_id == artist.id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
)).scalar_one_or_none()
|
||||
if source is None:
|
||||
return {
|
||||
"state": "artist_match",
|
||||
"platform": platform,
|
||||
"slug": slug,
|
||||
"artist": artist_payload,
|
||||
}
|
||||
|
||||
return {
|
||||
"state": "source_match",
|
||||
"platform": platform,
|
||||
"slug": slug,
|
||||
"artist": artist_payload,
|
||||
"source": {
|
||||
"id": source.id,
|
||||
"artist_id": source.artist_id,
|
||||
"platform": source.platform,
|
||||
"url": source.url,
|
||||
"enabled": source.enabled,
|
||||
},
|
||||
}
|
||||
|
||||
def _derive(self, url: str) -> tuple[str, str]:
|
||||
if not isinstance(url, str) or not url.strip():
|
||||
raise InvalidUrlError("url is empty")
|
||||
|
||||
@@ -39,19 +39,58 @@ class ErrorType(StrEnum):
|
||||
HTTP_ERROR = "http_error"
|
||||
UNSUPPORTED_URL = "unsupported_url"
|
||||
VALIDATION_FAILED = "validation_failed"
|
||||
# Run made real progress (downloaded ≥1 file) but did not finish in the
|
||||
# subprocess budget. Distinct from UNKNOWN_ERROR — the downstream status
|
||||
# mapping classifies this as "ok" because the next tick continues.
|
||||
PARTIAL = "partial"
|
||||
UNKNOWN_ERROR = "unknown_error"
|
||||
|
||||
|
||||
# Tick mode (routine cron polls): skip ≤20 contiguous already-archived
|
||||
# items, then exit gallery-dl. Established subscription with zero new
|
||||
# content exits in ~30s of HEAD requests instead of walking to the bottom
|
||||
# of the post history (which can be hours for prolific creators). 20 (not
|
||||
# 5) is operator-set headroom against any edge case where paywalled or
|
||||
# otherwise-non-downloadable items might interleave with archived ones —
|
||||
# 20 contiguous HEADs is still negligible.
|
||||
TICK_SKIP_VALUE = "exit:20"
|
||||
|
||||
# Backfill mode (operator-triggered deep scan): walk the full history.
|
||||
# Source.backfill_runs_remaining > 0 selects this mode; the longer
|
||||
# timeout below absorbs creators with thousands of posts.
|
||||
BACKFILL_SKIP_VALUE = True
|
||||
BACKFILL_TIMEOUT_SECONDS = 1800
|
||||
|
||||
|
||||
# 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
|
||||
class SourceConfig:
|
||||
"""Per-source overrides loaded from Source.config_overrides JSON.
|
||||
|
||||
Note: the gallery-dl `skip` value (tick vs backfill, see TICK_SKIP_VALUE /
|
||||
BACKFILL_SKIP_VALUE) is NOT carried here — it derives from the
|
||||
Source.backfill_runs_remaining column at the download_service layer
|
||||
and is passed to _build_config_for_source as `skip_value`. Same for
|
||||
the per-run subprocess timeout.
|
||||
"""
|
||||
content_types: list[str] = field(default_factory=lambda: ["all"])
|
||||
sleep: float | None = None
|
||||
sleep_request: float | None = None
|
||||
directory_pattern: str | None = None
|
||||
filename_pattern: str | None = None
|
||||
skip_existing: bool = True
|
||||
save_metadata: bool = True
|
||||
timeout: int = 3600
|
||||
timeout: int = _DEFAULT_GDL_TIMEOUT_SECONDS
|
||||
|
||||
@classmethod
|
||||
def from_dict(cls, data: dict) -> SourceConfig:
|
||||
@@ -61,9 +100,8 @@ class SourceConfig:
|
||||
sleep_request=data.get("sleep_request"),
|
||||
directory_pattern=data.get("directory_pattern"),
|
||||
filename_pattern=data.get("filename_pattern"),
|
||||
skip_existing=data.get("skip_existing", True),
|
||||
save_metadata=data.get("save_metadata", True),
|
||||
timeout=data.get("timeout", 3600),
|
||||
timeout=data.get("timeout", _DEFAULT_GDL_TIMEOUT_SECONDS),
|
||||
)
|
||||
|
||||
|
||||
@@ -219,6 +257,25 @@ class GalleryDLService:
|
||||
"part-directory": str(self._config_dir / "temp"),
|
||||
"retries": 3,
|
||||
"timeout": 120.0,
|
||||
# Forward Patreon as Referer/Origin to yt-dlp when it
|
||||
# fetches video manifests. Operator-flagged 2026-06-01
|
||||
# (DaferQ patreon): video posts hosted on Mux carry a JWT
|
||||
# playback restriction that checks Referer/Origin on every
|
||||
# request — not just the token signature. gallery-dl's
|
||||
# HEAD probe to stream.mux.com returns 200 (the token is
|
||||
# valid), but yt-dlp's actual GET-with-Range to fetch the
|
||||
# m3u8 manifest 403s because yt-dlp sends its own default
|
||||
# Referer, which Mux's policy rejects. Forcing the right
|
||||
# headers fixes the headers-only case; Mux IP-range
|
||||
# restrictions are unfixable from here.
|
||||
"ytdl": {
|
||||
"raw-options": {
|
||||
"http_headers": {
|
||||
"Referer": "https://www.patreon.com/",
|
||||
"Origin": "https://www.patreon.com",
|
||||
},
|
||||
},
|
||||
},
|
||||
},
|
||||
"output": {"progress": True},
|
||||
}
|
||||
@@ -233,7 +290,18 @@ class GalleryDLService:
|
||||
platform: str,
|
||||
source_config: SourceConfig,
|
||||
artist_slug: str,
|
||||
skip_value: bool | str = BACKFILL_SKIP_VALUE,
|
||||
) -> dict:
|
||||
"""`skip_value` controls gallery-dl's archive-walk behavior:
|
||||
- True (BACKFILL_SKIP_VALUE): walk full post history, skipping
|
||||
archived items but continuing past them. Used in backfill mode.
|
||||
- "exit:20" (TICK_SKIP_VALUE): exit gallery-dl after 20
|
||||
contiguous archived items. Used in tick (routine catch-up)
|
||||
mode for fast no-op syncs on creators with deep history.
|
||||
- False: don't skip — redownload everything (not used in FC).
|
||||
The caller (download_service) chooses based on
|
||||
Source.backfill_runs_remaining.
|
||||
"""
|
||||
config = json.loads(json.dumps(self._get_default_config())) # deep copy
|
||||
|
||||
destination = str(self.images_root / artist_slug / platform)
|
||||
@@ -243,7 +311,7 @@ class GalleryDLService:
|
||||
config["extractor"]["sleep"] = source_config.sleep
|
||||
if source_config.sleep_request is not None:
|
||||
config["extractor"]["sleep-request"] = source_config.sleep_request
|
||||
config["extractor"]["skip"] = source_config.skip_existing
|
||||
config["extractor"]["skip"] = skip_value
|
||||
|
||||
if source_config.save_metadata:
|
||||
config["extractor"]["postprocessors"] = [
|
||||
@@ -360,7 +428,17 @@ 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
|
||||
@@ -372,6 +450,22 @@ class GalleryDLService:
|
||||
f"Subscription tier does not grant access to {count} post{'s' if count != 1 else ''}",
|
||||
)
|
||||
|
||||
# Partial-success: the subprocess exited non-zero (typically because
|
||||
# the wall-clock timeout fired mid-walk), but it had downloaded ≥1
|
||||
# file by then and no source-level error category fired. The work
|
||||
# the run DID do is real; gallery-dl's archive will pick up where
|
||||
# it left off on the next tick. Mapped to status="ok" downstream
|
||||
# (download_service.py) so this doesn't flag the source as
|
||||
# "needs attention." Operator-flagged 2026-06-01 after a Knuxy
|
||||
# patreon run downloaded hundreds of files then ran red on timeout.
|
||||
files_downloaded = self._count_downloaded_files(stdout)
|
||||
if not has_actual_error and files_downloaded > 0:
|
||||
return (
|
||||
ErrorType.PARTIAL,
|
||||
f"Downloaded {files_downloaded} file{'s' if files_downloaded != 1 else ''}; "
|
||||
"run did not complete in budget — next tick will continue",
|
||||
)
|
||||
|
||||
return ErrorType.UNKNOWN_ERROR, f"Unknown error (return code: {return_code})"
|
||||
|
||||
def _count_downloaded_files(self, stdout: str) -> int:
|
||||
@@ -523,6 +617,7 @@ class GalleryDLService:
|
||||
source_config: SourceConfig | None = None,
|
||||
cookies_path: str | None = None,
|
||||
auth_token: str | None = None,
|
||||
skip_value: bool | str = BACKFILL_SKIP_VALUE,
|
||||
) -> DownloadResult:
|
||||
start_time = time.time()
|
||||
started_at = datetime.now(UTC).isoformat()
|
||||
@@ -530,7 +625,9 @@ class GalleryDLService:
|
||||
if source_config is None:
|
||||
source_config = SourceConfig()
|
||||
|
||||
config = self._build_config_for_source(platform, source_config, artist_slug)
|
||||
config = self._build_config_for_source(
|
||||
platform, source_config, artist_slug, skip_value=skip_value,
|
||||
)
|
||||
|
||||
if cookies_path:
|
||||
config["extractor"]["cookies"] = cookies_path
|
||||
@@ -632,13 +729,57 @@ class GalleryDLService:
|
||||
started_at=started_at, completed_at=completed_at,
|
||||
)
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
except subprocess.TimeoutExpired as e:
|
||||
duration = time.time() - start_time
|
||||
log.error("Download timeout for %s/%s after %.1fs", artist_slug, platform, duration)
|
||||
# subprocess.run(text=True) makes these str if non-None, but the
|
||||
# caller may have raised TimeoutExpired manually with None or
|
||||
# bytes (tests do); coerce both cases to str.
|
||||
partial_stdout = e.stdout or ""
|
||||
partial_stderr = e.stderr or ""
|
||||
if isinstance(partial_stdout, bytes):
|
||||
partial_stdout = partial_stdout.decode("utf-8", "replace")
|
||||
if isinstance(partial_stderr, bytes):
|
||||
partial_stderr = partial_stderr.decode("utf-8", "replace")
|
||||
|
||||
files_so_far = self._count_downloaded_files(partial_stdout)
|
||||
written_so_far = [str(p) for p in self._written_paths(partial_stdout)]
|
||||
stderr_lines = partial_stderr.strip().splitlines()
|
||||
tail_hint = stderr_lines[-1] if stderr_lines else "no stderr output"
|
||||
|
||||
# If the partial output already shows a rate-limit pattern, the
|
||||
# timeout was almost certainly gallery-dl spinning on retries —
|
||||
# promote to RATE_LIMITED so _update_source_health stamps the
|
||||
# platform cooldown (same code path as a clean-exit rate limit).
|
||||
# Otherwise stay TIMEOUT and let the captured stdout/stderr +
|
||||
# files_so_far tell the operator whether it was "lots of
|
||||
# content" vs "stuck retrying" vs "hung silent".
|
||||
combined = (partial_stdout + "\n" + partial_stderr).lower()
|
||||
if any(p in combined for p in self.RATE_LIMIT_PATTERNS):
|
||||
error_type = ErrorType.RATE_LIMITED
|
||||
error_message = (
|
||||
f"Rate-limited and never completed within "
|
||||
f"{source_config.timeout}s ({files_so_far} files written)"
|
||||
)
|
||||
else:
|
||||
error_type = ErrorType.TIMEOUT
|
||||
error_message = (
|
||||
f"Download timed out after {source_config.timeout}s — "
|
||||
f"{files_so_far} file(s) written; last stderr: {tail_hint}"
|
||||
)
|
||||
|
||||
log.error(
|
||||
"Download timeout for %s/%s after %.1fs (%d files written, "
|
||||
"last stderr: %s)",
|
||||
artist_slug, platform, duration, files_so_far, tail_hint,
|
||||
)
|
||||
|
||||
return DownloadResult(
|
||||
success=False, url=url, artist_slug=artist_slug, platform=platform,
|
||||
error_type=ErrorType.TIMEOUT,
|
||||
error_message=f"Download timed out after {source_config.timeout} seconds",
|
||||
files_downloaded=files_so_far,
|
||||
written_paths=written_so_far,
|
||||
stdout=partial_stdout, stderr=partial_stderr,
|
||||
return_code=-1, # killed by timeout, no real exit code
|
||||
error_type=error_type, error_message=error_message,
|
||||
duration_seconds=duration,
|
||||
started_at=started_at,
|
||||
completed_at=datetime.now(UTC).isoformat(),
|
||||
@@ -658,3 +799,64 @@ class GalleryDLService:
|
||||
Path(temp_config_path).unlink() # noqa: ASYNC240
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
async def verify(
|
||||
self,
|
||||
url: str,
|
||||
artist_slug: str,
|
||||
platform: str,
|
||||
source_config: SourceConfig | None = None,
|
||||
cookies_path: str | None = None,
|
||||
auth_token: str | None = None,
|
||||
timeout: float = 45.0, # noqa: ASYNC109 — subprocess.run timeout, not a coroutine deadline
|
||||
) -> tuple[bool, str]:
|
||||
"""Test that credentials authenticate against `url` WITHOUT
|
||||
downloading anything. Runs gallery-dl in --simulate mode limited
|
||||
to the first item; if auth is bad the extractor errors before it
|
||||
can list, which _categorize_error flags as AUTH_ERROR. Returns
|
||||
(ok, message). Used by the credential Verify button."""
|
||||
if source_config is None:
|
||||
source_config = SourceConfig()
|
||||
config = self._build_config_for_source(platform, source_config, artist_slug)
|
||||
if cookies_path:
|
||||
config["extractor"]["cookies"] = cookies_path
|
||||
if auth_token and platform == "discord":
|
||||
config["extractor"].setdefault("discord", {})["token"] = auth_token
|
||||
if auth_token and platform == "pixiv":
|
||||
config["extractor"].setdefault("pixiv", {})["refresh-token"] = auth_token
|
||||
|
||||
with tempfile.NamedTemporaryFile(
|
||||
mode="w", suffix=".json", delete=False, dir=str(self._config_dir),
|
||||
) as fh:
|
||||
json.dump(config, fh, indent=2)
|
||||
temp_config_path = fh.name
|
||||
try:
|
||||
cmd = [
|
||||
sys.executable, "-m", "gallery_dl",
|
||||
"--config", temp_config_path,
|
||||
"--simulate", "--range", "1-1", "--verbose", url,
|
||||
]
|
||||
loop = asyncio.get_running_loop()
|
||||
proc = await loop.run_in_executor(
|
||||
None,
|
||||
lambda: subprocess.run(
|
||||
cmd, capture_output=True, text=True, timeout=timeout,
|
||||
),
|
||||
)
|
||||
etype, msg = self._categorize_error(proc.returncode, proc.stdout, proc.stderr)
|
||||
if proc.returncode == 0 or etype == ErrorType.NO_NEW_CONTENT:
|
||||
return True, "Credentials valid — the feed authenticated."
|
||||
if etype == ErrorType.AUTH_ERROR:
|
||||
return False, msg
|
||||
# Network / not-found / rate-limit / unknown: inconclusive,
|
||||
# not a definitive credential failure. Surface the reason.
|
||||
return False, f"Could not confirm ({etype.value}): {msg}"
|
||||
except subprocess.TimeoutExpired:
|
||||
return False, f"Verification timed out after {timeout:.0f}s"
|
||||
except Exception as exc: # noqa: BLE001
|
||||
return False, f"Verification error: {exc}"
|
||||
finally:
|
||||
try:
|
||||
Path(temp_config_path).unlink() # noqa: ASYNC240
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
@@ -20,8 +20,9 @@ from datetime import datetime
|
||||
|
||||
from sqlalchemy import Select, and_, exists, func, or_, select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.orm import aliased
|
||||
|
||||
from ..models import Artist, ImageProvenance, ImageRecord, Post, Source, Tag
|
||||
from ..models import Artist, ImageProvenance, ImageRecord, Post, Tag
|
||||
from ..models.tag import image_tag
|
||||
|
||||
CURSOR_SEPARATOR = "|"
|
||||
@@ -90,9 +91,27 @@ class TimelineBucket:
|
||||
count: int
|
||||
|
||||
|
||||
def thumbnail_url(sha256_hex: str, mime: str) -> str:
|
||||
# Quart serves /images/* via the frontend blueprint (FC-1); thumbnails go
|
||||
# under /images/thumbs/. The MIME determines the extension.
|
||||
def thumbnail_url(thumbnail_path: str | None, sha256_hex: str, mime: str) -> str:
|
||||
"""Return the URL to fetch a thumbnail.
|
||||
|
||||
Prefers the stored thumbnail_path verbatim — Quart serves /images/*
|
||||
1:1 from the volume (frontend.py:20-36), so the URL IS the disk
|
||||
path. Falls back to deriving from (sha256, mime) only when the
|
||||
record's thumbnail_path is NULL (thumbnailer hasn't run yet); that
|
||||
URL will 404 until backfill catches it, same as before the path
|
||||
was tracked.
|
||||
|
||||
Pre-2026-05-30 this was derived only from (sha256, mime), which
|
||||
disagreed with the actual on-disk extension when the thumbnailer
|
||||
chose its format from transparency rather than MIME — every PNG
|
||||
source without alpha (extension was .jpg on disk) and every WebP
|
||||
source with alpha (extension was .png on disk) silently 404'd
|
||||
despite the thumbnail file existing.
|
||||
"""
|
||||
if thumbnail_path:
|
||||
return thumbnail_path
|
||||
# Fallback for records with no thumbnail recorded yet — preserves
|
||||
# prior behavior (URL exists but 404s until backfill regenerates).
|
||||
ext = ".png" if mime in ("image/png", "image/gif") else ".jpg"
|
||||
bucket = sha256_hex[:3]
|
||||
return f"/images/thumbs/{bucket}/{sha256_hex}{ext}"
|
||||
@@ -115,10 +134,23 @@ def _provenance_clause(post_id, artist_id):
|
||||
ImageProvenance.post_id == post_id,
|
||||
)
|
||||
if artist_id is not None:
|
||||
# Use Post.artist_id (alembic 0030 denormalized column) instead
|
||||
# of joining through ImageProvenance.source_id → Source.artist_id.
|
||||
# The denormalization is the always-present linkage; the source
|
||||
# path now drops NULL-source provenance rows (filesystem-imported
|
||||
# content) which would otherwise vanish from artist-filtered
|
||||
# gallery views.
|
||||
# ALIAS Post: the gallery query outer-joins Post on
|
||||
# ImageRecord.primary_post_id (`_outer_join_primary_post`).
|
||||
# SQLAlchemy would otherwise correlate a bare `Post` reference
|
||||
# in this EXISTS subquery to that outer Post (which is NULL for
|
||||
# images with no primary post), and the filter would silently
|
||||
# match nothing.
|
||||
post_inner = aliased(Post)
|
||||
return exists().where(
|
||||
ImageProvenance.image_record_id == ImageRecord.id,
|
||||
ImageProvenance.source_id == Source.id,
|
||||
Source.artist_id == artist_id,
|
||||
ImageProvenance.post_id == post_inner.id,
|
||||
post_inner.artist_id == artist_id,
|
||||
)
|
||||
return None
|
||||
|
||||
@@ -198,7 +230,7 @@ class GalleryService:
|
||||
created_at=record.created_at,
|
||||
effective_date=eff_date,
|
||||
posted_at=posted_at,
|
||||
thumbnail_url=thumbnail_url(record.sha256, record.mime),
|
||||
thumbnail_url=thumbnail_url(record.thumbnail_path, record.sha256, record.mime),
|
||||
artist=artists.get(record.id),
|
||||
)
|
||||
for record, posted_at, eff_date in rows
|
||||
@@ -306,7 +338,7 @@ class GalleryService:
|
||||
"integrity_status": record.integrity_status,
|
||||
"created_at": record.created_at.isoformat(),
|
||||
"posted_at": posted_at.isoformat() if posted_at else None,
|
||||
"thumbnail_url": thumbnail_url(record.sha256, record.mime),
|
||||
"thumbnail_url": thumbnail_url(record.thumbnail_path, record.sha256, record.mime),
|
||||
"image_url": f"/images/{record.path.split('/images/', 1)[-1]}",
|
||||
"artist": (
|
||||
{"id": artist.id, "name": artist.name, "slug": artist.slug}
|
||||
|
||||
+109
-104
@@ -204,6 +204,32 @@ class Importer:
|
||||
(phash, width or 0, height or 0, image_id)
|
||||
)
|
||||
|
||||
def _get_or_create(self, stmt, factory):
|
||||
"""Race-safe find-or-create. Run `stmt` (scalar_one_or_none); if a
|
||||
row exists, return it. Otherwise open a savepoint and INSERT
|
||||
``factory()``; on IntegrityError (a concurrent worker inserted the
|
||||
same row first) roll the savepoint back — NOT the outer transaction,
|
||||
which would lose the surrounding scan's progress — and re-run `stmt`
|
||||
(scalar_one) to return the row the other worker created.
|
||||
|
||||
Centralizes the pattern shared by _find_or_create_source and
|
||||
_find_or_create_post. The plain SELECT-then-INSERT version lost
|
||||
races under the 5-min recovery sweep (operator-flagged
|
||||
2026-05-26)."""
|
||||
existing = self.session.execute(stmt).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
sp = self.session.begin_nested()
|
||||
try:
|
||||
row = factory()
|
||||
self.session.add(row)
|
||||
self.session.flush()
|
||||
sp.commit()
|
||||
return row
|
||||
except IntegrityError:
|
||||
sp.rollback()
|
||||
return self.session.execute(stmt).scalar_one()
|
||||
|
||||
def _find_or_create_source(
|
||||
self, *, artist_id: int, platform: str, url: str,
|
||||
) -> Source:
|
||||
@@ -222,53 +248,35 @@ class Importer:
|
||||
and re-select — the concurrent op just created the row we
|
||||
wanted, so the second select will find it.
|
||||
"""
|
||||
existing = self.session.execute(
|
||||
select(Source).where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
sp = self.session.begin_nested()
|
||||
try:
|
||||
row = Source(artist_id=artist_id, platform=platform, url=url)
|
||||
self.session.add(row)
|
||||
self.session.flush()
|
||||
sp.commit()
|
||||
return row
|
||||
except IntegrityError:
|
||||
sp.rollback()
|
||||
return self.session.execute(
|
||||
select(Source).where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
).scalar_one()
|
||||
stmt = select(Source).where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
return self._get_or_create(
|
||||
stmt,
|
||||
lambda: Source(artist_id=artist_id, platform=platform, url=url),
|
||||
)
|
||||
|
||||
def _source_for_sidecar(
|
||||
self, *, artist_id: int, platform: str, artist_slug: str,
|
||||
) -> Source:
|
||||
"""Filesystem-import sidecar Source resolver.
|
||||
def _lookup_source_for_sidecar(
|
||||
self, *, artist_id: int, platform: str,
|
||||
) -> Source | None:
|
||||
"""Find the real subscription Source for (artist, platform), or
|
||||
None if no subscription exists.
|
||||
|
||||
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
|
||||
subscription checker into trying to poll patreon post URLs as feeds.
|
||||
Operator-flagged 2026-05-26.
|
||||
|
||||
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).
|
||||
Pre-alembic-0030 this method would CREATE a synthetic
|
||||
`sidecar:<platform>:<slug>` Source when no real one existed —
|
||||
because `Post.source_id` was NOT NULL and the importer needed
|
||||
something to attach Posts to. Alembic 0030 relaxed both
|
||||
`Post.source_id` and `ImageProvenance.source_id` to nullable, so
|
||||
synthetic anchors are obsolete; the importer now leaves
|
||||
source_id as None when no subscription exists for the (artist,
|
||||
platform). Operator-asked 2026-06-01: synthetic Sources had
|
||||
leaked into the Subscriptions UI as phantom subscriptions and
|
||||
the operator wanted the data model to truthfully say "this
|
||||
content has no live subscription."
|
||||
"""
|
||||
existing = self.session.execute(
|
||||
stmt = (
|
||||
select(Source)
|
||||
.where(
|
||||
Source.artist_id == artist_id,
|
||||
@@ -276,63 +284,39 @@ class Importer:
|
||||
)
|
||||
.order_by(Source.id.asc())
|
||||
.limit(1)
|
||||
).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
synthetic_url = f"sidecar:{platform}:{artist_slug}"
|
||||
sp = self.session.begin_nested()
|
||||
try:
|
||||
row = Source(
|
||||
artist_id=artist_id,
|
||||
platform=platform,
|
||||
url=synthetic_url,
|
||||
enabled=False,
|
||||
)
|
||||
self.session.add(row)
|
||||
self.session.flush()
|
||||
sp.commit()
|
||||
return row
|
||||
except IntegrityError:
|
||||
sp.rollback()
|
||||
return self.session.execute(
|
||||
select(Source)
|
||||
.where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
)
|
||||
.order_by(Source.id.asc())
|
||||
.limit(1)
|
||||
).scalar_one()
|
||||
)
|
||||
return self.session.execute(stmt).scalar_one_or_none()
|
||||
|
||||
def _find_or_create_post(
|
||||
self, *, source_id: int, external_post_id: str,
|
||||
self, *, source_id: int | None, external_post_id: str,
|
||||
artist_id: int,
|
||||
) -> Post:
|
||||
"""Race-safe find-or-create on `post` keyed by
|
||||
(source_id, external_post_id). Mirrors `_find_or_create_source`
|
||||
— same savepoint + IntegrityError-recovery pattern."""
|
||||
existing = self.session.execute(
|
||||
select(Post).where(
|
||||
"""Race-safe find-or-create on `post`. Keyed by
|
||||
(source_id, external_post_id) when source_id is set — the
|
||||
`uq_post_source_external_id` constraint guards. For NULL-source
|
||||
posts the existence check matches on (artist_id, external_post_id),
|
||||
which the partial unique index `uq_post_artist_external_id_null_source`
|
||||
(alembic 0030) guards. Same savepoint + IntegrityError-recovery
|
||||
pattern as the rest of the helpers."""
|
||||
if source_id is not None:
|
||||
stmt = select(Post).where(
|
||||
Post.source_id == source_id,
|
||||
Post.external_post_id == external_post_id,
|
||||
)
|
||||
).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
sp = self.session.begin_nested()
|
||||
try:
|
||||
row = Post(source_id=source_id, external_post_id=external_post_id)
|
||||
self.session.add(row)
|
||||
self.session.flush()
|
||||
sp.commit()
|
||||
return row
|
||||
except IntegrityError:
|
||||
sp.rollback()
|
||||
return self.session.execute(
|
||||
select(Post).where(
|
||||
Post.source_id == source_id,
|
||||
Post.external_post_id == external_post_id,
|
||||
)
|
||||
).scalar_one()
|
||||
else:
|
||||
stmt = select(Post).where(
|
||||
Post.source_id.is_(None),
|
||||
Post.artist_id == artist_id,
|
||||
Post.external_post_id == external_post_id,
|
||||
)
|
||||
return self._get_or_create(
|
||||
stmt,
|
||||
lambda: Post(
|
||||
source_id=source_id,
|
||||
artist_id=artist_id,
|
||||
external_post_id=external_post_id,
|
||||
),
|
||||
)
|
||||
|
||||
def import_one(self, source: Path) -> ImportResult:
|
||||
"""Dispatch by kind. Media → normal pipeline. Archive → extract
|
||||
@@ -372,12 +356,14 @@ class Importer:
|
||||
return None
|
||||
sd = parse_sidecar(data)
|
||||
platform = sd.platform or "unknown"
|
||||
src = self._source_for_sidecar(
|
||||
artist_id=artist.id, platform=platform, artist_slug=artist.slug,
|
||||
src = self._lookup_source_for_sidecar(
|
||||
artist_id=artist.id, platform=platform,
|
||||
)
|
||||
epid = sd.external_post_id or sc.stem
|
||||
return self._find_or_create_post(
|
||||
source_id=src.id, external_post_id=epid,
|
||||
source_id=src.id if src else None,
|
||||
external_post_id=epid,
|
||||
artist_id=artist.id,
|
||||
)
|
||||
|
||||
def _capture_attachment(
|
||||
@@ -664,16 +650,34 @@ class Importer:
|
||||
them through. The sidecar JSON gallery-dl emits next to each
|
||||
downloaded file is read by `_apply_sidecar` via `find_sidecar`.
|
||||
|
||||
File-type dispatch parity with `import_one` (FC-2d-iii): zips,
|
||||
PDFs, audio etc. become PostAttachments; archives are extracted.
|
||||
Without this dispatch, gallery-dl-downloaded non-media bounced
|
||||
back as `skipped+invalid_image`, which DownloadService counted
|
||||
as an ingest error and flipped otherwise-successful runs to
|
||||
status="error". Operator-flagged 2026-06-02 after a Lustria
|
||||
patreon run with a 94MB OST zip went red despite 21 successful
|
||||
image attaches.
|
||||
|
||||
Caller's responsibilities after this returns:
|
||||
- duplicate_hash / duplicate_phash skip → delete the on-disk file
|
||||
- superseded → file stays where it is (now canonical)
|
||||
- imported → file stays where it is
|
||||
- attached → the file's been copied into the attachments store;
|
||||
caller may delete the on-disk original (mirrors duplicate_hash)
|
||||
- failed → file untouched; caller decides
|
||||
"""
|
||||
if not is_supported(path):
|
||||
if path.suffix.lower() == ".json":
|
||||
return ImportResult(
|
||||
status="skipped", skip_reason=SkipReason.invalid_image,
|
||||
error=f"unsupported extension {path.suffix}",
|
||||
error="sidecar json is metadata, not content",
|
||||
)
|
||||
if is_archive(path):
|
||||
return self._import_archive(path)
|
||||
if not is_supported(path):
|
||||
post = self._post_for_sidecar(path, artist) if artist else None
|
||||
return self._capture_attachment(
|
||||
path, post=post, artist=artist, resolved=True,
|
||||
)
|
||||
|
||||
# Format / dimension / transparency filters (mirror _import_media).
|
||||
@@ -860,14 +864,15 @@ class Importer:
|
||||
src = explicit_source
|
||||
else:
|
||||
platform = sd.platform or "unknown"
|
||||
src = self._source_for_sidecar(
|
||||
src = self._lookup_source_for_sidecar(
|
||||
artist_id=artist.id, platform=platform,
|
||||
artist_slug=artist.slug,
|
||||
)
|
||||
|
||||
epid = sd.external_post_id or sc.stem
|
||||
post = self._find_or_create_post(
|
||||
source_id=src.id, external_post_id=epid,
|
||||
source_id=src.id if src else None,
|
||||
external_post_id=epid,
|
||||
artist_id=artist.id,
|
||||
)
|
||||
if sd.post_url is not None:
|
||||
post.post_url = sd.post_url
|
||||
@@ -903,7 +908,7 @@ class Importer:
|
||||
ImageProvenance(
|
||||
image_record_id=record.id,
|
||||
post_id=post.id,
|
||||
source_id=src.id,
|
||||
source_id=src.id if src else None,
|
||||
captured_metadata=sd.raw,
|
||||
)
|
||||
)
|
||||
|
||||
@@ -1,10 +0,0 @@
|
||||
"""FC-5 migration tooling.
|
||||
|
||||
One module per concern (gs/ir/overlap/ml_queue/verify/cleanup).
|
||||
Each migrator returns a counts dict; the run_migration task wires
|
||||
that dict into MigrationRun.counts so the UI polling shows progress.
|
||||
|
||||
backup + rollback were retired in FC-3h (2026-05-24); first-class
|
||||
backup lives at backend/app/services/backup_service.py and exposes
|
||||
its own /api/system/backup/* surface.
|
||||
"""
|
||||
@@ -1,182 +0,0 @@
|
||||
"""Targeted cleanup migrator: delete every image attributed to one Artist.
|
||||
|
||||
Built for the IR-migration rescue case where the filesystem scan derived
|
||||
a bogus 'imagerepo' artist from a mismatched bind-mount layout. Every
|
||||
image attributed to that artist (40k+ rows) needs to be removed — DB
|
||||
rows, original files under `/images/<bucket>/...`, and thumbnails under
|
||||
`/images/thumbs/...` — before the operator remounts and re-scans.
|
||||
|
||||
CASCADE handles image_tag, image_provenance, series_page, and
|
||||
tag_suggestion_rejection child rows; import_task.result_image_id is
|
||||
SET NULL by FK. We also delete ImportTask rows whose source_path starts
|
||||
with the (still-existing) IR scan prefix so the next scan isn't fooled
|
||||
by them.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import delete, func, select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import Artist, ImageRecord, ImportBatch, ImportTask
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
_BATCH_SIZE = 500
|
||||
|
||||
|
||||
def _zero_counts() -> dict:
|
||||
return {
|
||||
"rows_processed": 0, "rows_inserted": 0, "rows_skipped": 0,
|
||||
"files_copied": 0, "bytes_copied": 0, "conflicts": 0,
|
||||
}
|
||||
|
||||
|
||||
def _thumb_path(images_root: Path, sha256_hex: str) -> tuple[Path, Path]:
|
||||
"""Return both possible thumbnail paths (.jpg and .png). We try both
|
||||
because the extension is chosen at generate-time based on the source
|
||||
image's mode (alpha → .png, otherwise → .jpg)."""
|
||||
bucket = sha256_hex[:3]
|
||||
base = images_root / "thumbs" / bucket / sha256_hex
|
||||
return base.with_suffix(".jpg"), base.with_suffix(".png")
|
||||
|
||||
|
||||
def _delete_file(path: Path) -> bool:
|
||||
"""Best-effort unlink; True if the file was actually removed."""
|
||||
try:
|
||||
path.unlink(missing_ok=True)
|
||||
return True
|
||||
except OSError as exc:
|
||||
log.warning("cleanup: failed to unlink %s: %s", path, exc)
|
||||
return False
|
||||
|
||||
|
||||
async def cleanup_artist_async(
|
||||
db: AsyncSession,
|
||||
*,
|
||||
slug: str,
|
||||
images_root: Path | None = None,
|
||||
dry_run: bool = False,
|
||||
source_path_prefix: str | None = None,
|
||||
) -> dict:
|
||||
"""Delete every image attributed to the Artist with this slug,
|
||||
along with the artist row itself and any associated import tasks.
|
||||
|
||||
Args:
|
||||
slug: artist.slug to target (e.g. 'imagerepo').
|
||||
images_root: defaults to /images.
|
||||
dry_run: skip filesystem + DB writes; still walk rows for counts.
|
||||
source_path_prefix: if set, ImportTask rows whose source_path
|
||||
starts with this string are deleted too (use the IR scan
|
||||
mount prefix, e.g. '/import/imagerepo').
|
||||
"""
|
||||
root = images_root if images_root is not None else Path("/images")
|
||||
|
||||
artist = (await db.execute(
|
||||
select(Artist).where(Artist.slug == slug)
|
||||
)).scalar_one_or_none()
|
||||
if artist is None:
|
||||
raise ValueError(f"no Artist with slug={slug!r}")
|
||||
|
||||
artist_id = artist.id
|
||||
artist_name = artist.name
|
||||
|
||||
total_images = (await db.execute(
|
||||
select(func.count(ImageRecord.id)).where(ImageRecord.artist_id == artist_id)
|
||||
)).scalar_one()
|
||||
|
||||
counts = _zero_counts()
|
||||
files_deleted = 0
|
||||
thumbs_deleted = 0
|
||||
images_deleted = 0
|
||||
|
||||
# Batched delete loop. CASCADE handles image_tag, image_provenance,
|
||||
# series_page, tag_suggestion_rejection. import_task.result_image_id
|
||||
# is SET NULL by FK.
|
||||
while True:
|
||||
rows = (await db.execute(
|
||||
select(ImageRecord.id, ImageRecord.path, ImageRecord.sha256)
|
||||
.where(ImageRecord.artist_id == artist_id)
|
||||
.limit(_BATCH_SIZE)
|
||||
)).all()
|
||||
if not rows:
|
||||
break
|
||||
|
||||
ids = [r.id for r in rows]
|
||||
counts["rows_processed"] += len(ids)
|
||||
|
||||
if not dry_run:
|
||||
for r in rows:
|
||||
if r.path:
|
||||
if _delete_file(Path(r.path)):
|
||||
files_deleted += 1
|
||||
if r.sha256:
|
||||
jpg, png = _thumb_path(root, r.sha256)
|
||||
if _delete_file(jpg):
|
||||
thumbs_deleted += 1
|
||||
if _delete_file(png):
|
||||
thumbs_deleted += 1
|
||||
|
||||
await db.execute(
|
||||
delete(ImageRecord).where(ImageRecord.id.in_(ids))
|
||||
)
|
||||
await db.commit()
|
||||
|
||||
images_deleted += len(ids)
|
||||
|
||||
if dry_run:
|
||||
# Nothing was actually deleted from the DB; bail after one
|
||||
# pass so we don't loop forever.
|
||||
break
|
||||
|
||||
import_tasks_deleted = 0
|
||||
if source_path_prefix and not dry_run:
|
||||
# Delete ImportTask rows whose source_path is under the bad mount
|
||||
# prefix. These are mostly orphaned now (result_image_id was set
|
||||
# NULL by CASCADE) but their presence still blocks the
|
||||
# idempotency check in scan_directory if the operator remounts
|
||||
# the same prefix.
|
||||
like_pattern = source_path_prefix.rstrip("/") + "/%"
|
||||
result = await db.execute(
|
||||
delete(ImportTask).where(ImportTask.source_path.like(like_pattern))
|
||||
)
|
||||
import_tasks_deleted = result.rowcount or 0
|
||||
await db.commit()
|
||||
|
||||
# Sweep ImportBatch rows that are now empty.
|
||||
empty_batches_deleted = 0
|
||||
if not dry_run:
|
||||
empty_batch_ids = (await db.execute(
|
||||
select(ImportBatch.id).where(
|
||||
~select(ImportTask.id)
|
||||
.where(ImportTask.batch_id == ImportBatch.id)
|
||||
.exists()
|
||||
)
|
||||
)).scalars().all()
|
||||
if empty_batch_ids:
|
||||
result = await db.execute(
|
||||
delete(ImportBatch).where(ImportBatch.id.in_(empty_batch_ids))
|
||||
)
|
||||
empty_batches_deleted = result.rowcount or 0
|
||||
await db.commit()
|
||||
|
||||
# Finally, the artist row.
|
||||
if not dry_run:
|
||||
await db.execute(delete(Artist).where(Artist.id == artist_id))
|
||||
await db.commit()
|
||||
|
||||
return {
|
||||
"counts": counts,
|
||||
"artist": {"id": artist_id, "name": artist_name, "slug": slug},
|
||||
"summary": {
|
||||
"images_targeted": total_images,
|
||||
"images_deleted": images_deleted,
|
||||
"files_deleted": files_deleted,
|
||||
"thumbs_deleted": thumbs_deleted,
|
||||
"import_tasks_deleted": import_tasks_deleted,
|
||||
"empty_batches_deleted": empty_batches_deleted,
|
||||
"dry_run": dry_run,
|
||||
},
|
||||
}
|
||||
@@ -1,126 +0,0 @@
|
||||
"""GallerySubscriber export → FabledCurator ingest.
|
||||
|
||||
Reads a parsed gallerysubscriber-export-v1.json dict (no DB connection
|
||||
to GS). Creates Artist (from subscriptions) + Source (nested under each
|
||||
subscription) + Credential (re-encrypted with FC's key). Idempotent on
|
||||
natural keys: Artist.slug, (artist_id, platform, url), Credential.platform.
|
||||
|
||||
Credentials arrive plaintext in the export — GS's export script
|
||||
decrypts using GS's Fernet key in GS's own process. FC re-encrypts
|
||||
with FC's CredentialCrypto.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import Artist, Credential, Source
|
||||
from ...utils.slug import slugify
|
||||
from ..credential_crypto import CredentialCrypto
|
||||
|
||||
|
||||
def _zero_counts() -> dict:
|
||||
return {
|
||||
"rows_processed": 0, "rows_inserted": 0, "rows_skipped": 0,
|
||||
"files_copied": 0, "bytes_copied": 0, "conflicts": 0,
|
||||
}
|
||||
|
||||
|
||||
async def migrate_async(
|
||||
db: AsyncSession,
|
||||
*,
|
||||
data: dict,
|
||||
fc_crypto: CredentialCrypto | None = None,
|
||||
dry_run: bool = False,
|
||||
) -> dict:
|
||||
"""Ingest a parsed gallerysubscriber-export-v1.json dict."""
|
||||
if data.get("source_app") != "gallerysubscriber":
|
||||
raise ValueError("export source_app must be 'gallerysubscriber'")
|
||||
if data.get("schema_version") != 1:
|
||||
raise ValueError(f"unsupported schema_version: {data.get('schema_version')}")
|
||||
|
||||
counts = _zero_counts()
|
||||
|
||||
# Phase 1: subscriptions → Artist; nested sources within each.
|
||||
for sub in data.get("subscriptions", []):
|
||||
counts["rows_processed"] += 1
|
||||
slug = slugify(sub["name"])
|
||||
artist = (await db.execute(
|
||||
select(Artist).where(Artist.slug == slug)
|
||||
)).scalar_one_or_none()
|
||||
if artist is None:
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
# Continue to nested sources, but they can't link without an artist row.
|
||||
continue
|
||||
notes = json.dumps(sub.get("metadata"), indent=2) if sub.get("metadata") else None
|
||||
artist = Artist(
|
||||
name=sub["name"], slug=slug,
|
||||
is_subscription=True,
|
||||
auto_check=bool(sub.get("enabled", True)),
|
||||
notes=notes,
|
||||
)
|
||||
db.add(artist)
|
||||
await db.flush()
|
||||
counts["rows_inserted"] += 1
|
||||
else:
|
||||
counts["rows_skipped"] += 1
|
||||
|
||||
# Nested sources under this subscription.
|
||||
for src in sub.get("sources", []):
|
||||
counts["rows_processed"] += 1
|
||||
existing = (await db.execute(
|
||||
select(Source).where(
|
||||
Source.artist_id == artist.id,
|
||||
Source.platform == src["platform"],
|
||||
Source.url == src["url"],
|
||||
)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
db.add(Source(
|
||||
artist_id=artist.id,
|
||||
platform=src["platform"],
|
||||
url=src["url"],
|
||||
enabled=bool(src.get("enabled", True)),
|
||||
check_interval_override=src.get("check_interval"),
|
||||
config_overrides=src.get("metadata") or {},
|
||||
))
|
||||
counts["rows_inserted"] += 1
|
||||
|
||||
# Phase 2: credentials.
|
||||
for cred in data.get("credentials", []):
|
||||
counts["rows_processed"] += 1
|
||||
existing = (await db.execute(
|
||||
select(Credential).where(Credential.platform == cred["platform"])
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
if fc_crypto is None:
|
||||
# Without a crypto helper we can't encrypt — skip rather than
|
||||
# store plaintext.
|
||||
counts["rows_skipped"] += 1
|
||||
counts["conflicts"] += 1
|
||||
continue
|
||||
encrypted = fc_crypto.encrypt(cred["plaintext"])
|
||||
db.add(Credential(
|
||||
platform=cred["platform"],
|
||||
credential_type=cred.get("credential_type") or "cookies",
|
||||
encrypted_blob=encrypted,
|
||||
expires_at=cred.get("expires_at"),
|
||||
))
|
||||
counts["rows_inserted"] += 1
|
||||
|
||||
if not dry_run:
|
||||
await db.commit()
|
||||
return counts
|
||||
@@ -1,146 +0,0 @@
|
||||
"""ImageRepo export → FabledCurator ingest.
|
||||
|
||||
Reads a parsed imagerepo-export-v1.json dict (no DB connection to IR).
|
||||
Creates Tag rows (skipping artist/post kinds, resolving fandom_name to
|
||||
FK). Writes the per-image-sha256 artist assignments + tag associations
|
||||
+ series page assignments to /images/_migration_state/ir_tag_manifest.json
|
||||
so tag_apply.py can join them to ImageRecord rows AFTER the operator
|
||||
runs FC's filesystem scan.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import Tag, TagKind
|
||||
|
||||
_SKIP_KINDS = frozenset({"artist", "post"})
|
||||
_MIGRATION_STATE_DIRNAME = "_migration_state"
|
||||
_IR_MANIFEST_FILENAME = "ir_tag_manifest.json"
|
||||
|
||||
|
||||
def _zero_counts() -> dict:
|
||||
return {
|
||||
"rows_processed": 0, "rows_inserted": 0, "rows_skipped": 0,
|
||||
"files_copied": 0, "bytes_copied": 0, "conflicts": 0,
|
||||
}
|
||||
|
||||
|
||||
def manifest_path(images_root: Path | None = None) -> Path:
|
||||
root = images_root if images_root is not None else Path("/images")
|
||||
p = root / _MIGRATION_STATE_DIRNAME
|
||||
p.mkdir(parents=True, exist_ok=True)
|
||||
return p / _IR_MANIFEST_FILENAME
|
||||
|
||||
|
||||
async def _resolve_fandom_id(
|
||||
db: AsyncSession, fandom_name: str | None, dry_run: bool,
|
||||
) -> int | None:
|
||||
"""Find-or-create a fandom-kind Tag by name."""
|
||||
if not fandom_name:
|
||||
return None
|
||||
existing = (await db.execute(
|
||||
select(Tag).where(Tag.name == fandom_name, Tag.kind == "fandom")
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing.id
|
||||
if dry_run:
|
||||
return None
|
||||
t = Tag(name=fandom_name, kind=TagKind.fandom)
|
||||
db.add(t)
|
||||
await db.flush()
|
||||
return t.id
|
||||
|
||||
|
||||
async def migrate_async(
|
||||
db: AsyncSession,
|
||||
*,
|
||||
data: dict,
|
||||
images_root: Path | None = None,
|
||||
dry_run: bool = False,
|
||||
) -> dict:
|
||||
"""Ingest a parsed imagerepo-export-v1.json dict.
|
||||
|
||||
Creates Tag rows + writes the IR tag manifest file. Tag-to-image
|
||||
binding happens later in tag_apply.py (after FC's filesystem scan
|
||||
populates image_record.sha256 → id).
|
||||
"""
|
||||
if data.get("source_app") != "imagerepo":
|
||||
raise ValueError("export source_app must be 'imagerepo'")
|
||||
if data.get("schema_version") not in (1, 2):
|
||||
raise ValueError(f"unsupported schema_version: {data.get('schema_version')}")
|
||||
|
||||
counts = _zero_counts()
|
||||
|
||||
# Phase 1: tags (skip artist + post kinds; resolve fandom_name → fandom_id).
|
||||
# First pass: create all fandom-kind tags so they're available for FK resolution.
|
||||
for tag in data.get("tags", []):
|
||||
kind = tag.get("kind") or "general"
|
||||
if kind != "fandom":
|
||||
continue
|
||||
counts["rows_processed"] += 1
|
||||
existing = (await db.execute(
|
||||
select(Tag).where(Tag.name == tag["name"], Tag.kind == "fandom")
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
db.add(Tag(name=tag["name"], kind=TagKind.fandom))
|
||||
counts["rows_inserted"] += 1
|
||||
if not dry_run:
|
||||
await db.flush()
|
||||
|
||||
# Second pass: every other kind.
|
||||
for tag in data.get("tags", []):
|
||||
kind_str = tag.get("kind") or "general"
|
||||
if kind_str in _SKIP_KINDS:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if kind_str == "fandom":
|
||||
continue # handled above
|
||||
counts["rows_processed"] += 1
|
||||
try:
|
||||
kind = TagKind(kind_str)
|
||||
except ValueError:
|
||||
kind = TagKind.general
|
||||
fandom_id = await _resolve_fandom_id(db, tag.get("fandom_name"), dry_run)
|
||||
existing = (await db.execute(
|
||||
select(Tag).where(Tag.name == tag["name"], Tag.kind == kind)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
db.add(Tag(name=tag["name"], kind=kind, fandom_id=fandom_id))
|
||||
counts["rows_inserted"] += 1
|
||||
|
||||
if not dry_run:
|
||||
await db.commit()
|
||||
|
||||
# Phase 2: write the per-image manifest for tag_apply.py to consume later.
|
||||
# schema_version 2 (added 2026-05-24) carries `image_posts` for
|
||||
# Post + Source + ImageProvenance restore; schema 1 manifests
|
||||
# without it stay valid (tag_apply treats the missing field as []).
|
||||
manifest = {
|
||||
"schema_version": data.get("schema_version", 1),
|
||||
"image_artist_assignments": data.get("image_artist_assignments", []),
|
||||
"image_tag_associations": data.get("image_tag_associations", []),
|
||||
"series_pages": data.get("series_pages", []),
|
||||
"image_posts": data.get("image_posts", []),
|
||||
}
|
||||
counts["rows_processed"] += len(manifest["image_artist_assignments"])
|
||||
counts["rows_processed"] += len(manifest["image_tag_associations"])
|
||||
counts["rows_processed"] += len(manifest["series_pages"])
|
||||
counts["rows_processed"] += len(manifest["image_posts"])
|
||||
if not dry_run:
|
||||
manifest_path(images_root).write_text(json.dumps(manifest, indent=2))
|
||||
|
||||
return counts
|
||||
@@ -1,21 +0,0 @@
|
||||
"""Queue every migrated image_record with no embedding for ML re-processing."""
|
||||
from __future__ import annotations
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import ImageRecord
|
||||
|
||||
|
||||
async def queue_all_unprocessed_async(db: AsyncSession) -> int:
|
||||
"""Find every ImageRecord with siglip_embedding IS NULL, fire
|
||||
tag_and_embed.delay(id) for each. Returns count queued.
|
||||
"""
|
||||
from ...tasks.ml import tag_and_embed
|
||||
|
||||
rows = (await db.execute(
|
||||
select(ImageRecord.id).where(ImageRecord.siglip_embedding.is_(None))
|
||||
)).scalars().all()
|
||||
for image_id in rows:
|
||||
tag_and_embed.delay(image_id)
|
||||
return len(rows)
|
||||
@@ -1,368 +0,0 @@
|
||||
"""Apply the IR tag manifest after FC's filesystem scan.
|
||||
|
||||
Reads /images/_migration_state/ir_tag_manifest.json and joins each entry
|
||||
to an ImageRecord row by sha256 (which exists after the operator runs
|
||||
FC's filesystem scan over the mounted IR images dir).
|
||||
|
||||
- image_artist_assignments → ImageRecord.artist_id (find_or_create Artist by slug).
|
||||
- image_tag_associations → image_tag insert (idempotent).
|
||||
- series_pages → series_page insert (idempotent on image_id unique).
|
||||
- image_posts (schema v2) → Source + Post + ImageProvenance restore.
|
||||
|
||||
Unmatched sha256s are logged into the result's `unmatched` list so the
|
||||
Celery task can drop them into MigrationRun.metadata for the operator
|
||||
to inspect.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import (
|
||||
Artist,
|
||||
ImageProvenance,
|
||||
ImageRecord,
|
||||
Post,
|
||||
SeriesPage,
|
||||
Source,
|
||||
Tag,
|
||||
TagKind,
|
||||
image_tag,
|
||||
)
|
||||
from ...utils.slug import slugify
|
||||
from .ir_ingest import manifest_path
|
||||
|
||||
# Per-platform artist-profile URL — used as Source.url when restoring
|
||||
# IR PostMetadata into FC. Must cover every platform that
|
||||
# backend/app/services/extension_service.py:_PLATFORM_PATTERNS
|
||||
# recognizes; an entry missing here silently drops ALL PostMetadata for
|
||||
# that platform during phase 4 (operator hit this 2026-05-25:
|
||||
# DeviantArt + Pixiv posts in the IR migration produced empty
|
||||
# ImageProvenance because they fell through this table).
|
||||
#
|
||||
# Pixiv caveat: the real profile URL takes a numeric user_id
|
||||
# (https://www.pixiv.net/users/12345), but IR's PostMetadata.artist
|
||||
# stores the display name not the id. We use the slugified name here
|
||||
# so we preserve the artist→post→image linkage; the resulting Source.url
|
||||
# won't resolve in a browser and the operator may want to manually fix
|
||||
# it via Settings → Subscriptions once the migration lands.
|
||||
_PLATFORM_PROFILE_URL = {
|
||||
"patreon": "https://www.patreon.com/{slug}",
|
||||
"subscribestar": "https://www.subscribestar.com/{slug}",
|
||||
"hentaifoundry": "https://www.hentai-foundry.com/user/{slug}",
|
||||
"deviantart": "https://www.deviantart.com/{slug}",
|
||||
"pixiv": "https://www.pixiv.net/users/{slug}",
|
||||
}
|
||||
|
||||
|
||||
def _profile_url(platform: str, artist_slug: str) -> str | None:
|
||||
fmt = _PLATFORM_PROFILE_URL.get(platform)
|
||||
return fmt.format(slug=artist_slug) if fmt else None
|
||||
|
||||
|
||||
async def _find_or_create_source(
|
||||
db: AsyncSession, *, artist_id: int, platform: str, url: str, dry_run: bool,
|
||||
) -> int | None:
|
||||
existing = (await db.execute(
|
||||
select(Source.id).where(
|
||||
Source.artist_id == artist_id,
|
||||
Source.platform == platform,
|
||||
Source.url == url,
|
||||
)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
if dry_run:
|
||||
return None
|
||||
s = Source(artist_id=artist_id, platform=platform, url=url, enabled=False)
|
||||
db.add(s)
|
||||
await db.flush()
|
||||
return s.id
|
||||
|
||||
|
||||
async def _find_or_create_post(
|
||||
db: AsyncSession, *,
|
||||
source_id: int, external_post_id: str,
|
||||
title: str | None, description: str | None, post_url: str | None,
|
||||
post_date_iso: str | None, attachment_count: int, dry_run: bool,
|
||||
) -> int | None:
|
||||
existing = (await db.execute(
|
||||
select(Post.id).where(
|
||||
Post.source_id == source_id,
|
||||
Post.external_post_id == external_post_id,
|
||||
)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing
|
||||
if dry_run:
|
||||
return None
|
||||
post_date = None
|
||||
if post_date_iso:
|
||||
post_date = datetime.fromisoformat(post_date_iso)
|
||||
p = Post(
|
||||
source_id=source_id,
|
||||
external_post_id=external_post_id,
|
||||
post_title=title,
|
||||
description=description,
|
||||
post_url=post_url,
|
||||
post_date=post_date,
|
||||
attachment_count=attachment_count,
|
||||
raw_metadata={"migrated_from": "imagerepo"},
|
||||
)
|
||||
db.add(p)
|
||||
await db.flush()
|
||||
return p.id
|
||||
|
||||
|
||||
async def _ensure_provenance(
|
||||
db: AsyncSession, *,
|
||||
image_id: int, post_id: int, source_id: int, dry_run: bool,
|
||||
) -> bool:
|
||||
"""Returns True if a new ImageProvenance row was inserted.
|
||||
|
||||
Also sets ImageRecord.primary_post_id to this post if the image
|
||||
doesn't already have one — preserves any primary_post_id already
|
||||
assigned at download time by the importer (don't clobber). This is
|
||||
the linkage gallery_service.py uses to surface Post.post_date as
|
||||
the image's effective date for sort/group/jump/neighbor nav.
|
||||
"""
|
||||
existing = (await db.execute(
|
||||
select(ImageProvenance.id).where(
|
||||
ImageProvenance.image_record_id == image_id,
|
||||
ImageProvenance.post_id == post_id,
|
||||
ImageProvenance.source_id == source_id,
|
||||
)
|
||||
)).scalar_one_or_none()
|
||||
|
||||
# Whether-or-not the provenance row already exists, ensure the
|
||||
# image's primary_post_id is set so the gallery date-coalesce works.
|
||||
# Idempotent: only writes when currently NULL.
|
||||
if not dry_run:
|
||||
await db.execute(
|
||||
ImageRecord.__table__.update()
|
||||
.where(ImageRecord.id == image_id)
|
||||
.where(ImageRecord.primary_post_id.is_(None))
|
||||
.values(primary_post_id=post_id)
|
||||
)
|
||||
|
||||
if existing is not None:
|
||||
return False
|
||||
if dry_run:
|
||||
return True
|
||||
db.add(ImageProvenance(
|
||||
image_record_id=image_id, post_id=post_id, source_id=source_id,
|
||||
))
|
||||
await db.flush()
|
||||
return True
|
||||
|
||||
|
||||
def _zero_counts() -> dict:
|
||||
return {
|
||||
"rows_processed": 0, "rows_inserted": 0, "rows_skipped": 0,
|
||||
"files_copied": 0, "bytes_copied": 0, "conflicts": 0,
|
||||
}
|
||||
|
||||
|
||||
async def _ensure_artist_id(
|
||||
db: AsyncSession, artist_name: str, dry_run: bool,
|
||||
) -> int | None:
|
||||
if not artist_name or not artist_name.strip():
|
||||
return None
|
||||
slug = slugify(artist_name)
|
||||
existing = (await db.execute(
|
||||
select(Artist).where(Artist.slug == slug)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
return existing.id
|
||||
if dry_run:
|
||||
return None
|
||||
a = Artist(name=artist_name, slug=slug, is_subscription=False)
|
||||
db.add(a)
|
||||
await db.flush()
|
||||
return a.id
|
||||
|
||||
|
||||
async def _resolve_tag_id(
|
||||
db: AsyncSession, tag_name: str, tag_kind: str,
|
||||
) -> int | None:
|
||||
try:
|
||||
kind = TagKind(tag_kind)
|
||||
except ValueError:
|
||||
kind = TagKind.general
|
||||
row = (await db.execute(
|
||||
select(Tag.id).where(Tag.name == tag_name, Tag.kind == kind)
|
||||
)).scalar_one_or_none()
|
||||
return row
|
||||
|
||||
|
||||
async def _sha_to_image_id(db: AsyncSession, sha: str) -> int | None:
|
||||
return (await db.execute(
|
||||
select(ImageRecord.id).where(ImageRecord.sha256 == sha)
|
||||
)).scalar_one_or_none()
|
||||
|
||||
|
||||
async def apply_async(
|
||||
db: AsyncSession,
|
||||
*,
|
||||
images_root: Path | None = None,
|
||||
dry_run: bool = False,
|
||||
) -> dict:
|
||||
"""Apply the manifest. Returns counts + an `unmatched` list of sha256s."""
|
||||
mf_path = manifest_path(images_root)
|
||||
if not mf_path.exists():
|
||||
raise FileNotFoundError(f"no IR tag manifest at {mf_path}")
|
||||
|
||||
manifest = json.loads(mf_path.read_text())
|
||||
counts = _zero_counts()
|
||||
unmatched: list[dict] = []
|
||||
|
||||
# 1. Artist assignments.
|
||||
for entry in manifest.get("image_artist_assignments", []):
|
||||
counts["rows_processed"] += 1
|
||||
img_id = await _sha_to_image_id(db, entry["sha256"])
|
||||
if img_id is None:
|
||||
unmatched.append({"kind": "artist", **entry})
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
aid = await _ensure_artist_id(db, entry["artist_name"], dry_run)
|
||||
if aid is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
img = await db.get(ImageRecord, img_id)
|
||||
if img is not None and img.artist_id != aid:
|
||||
img.artist_id = aid
|
||||
counts["rows_inserted"] += 1
|
||||
else:
|
||||
counts["rows_skipped"] += 1
|
||||
|
||||
# 2. Tag associations.
|
||||
for entry in manifest.get("image_tag_associations", []):
|
||||
counts["rows_processed"] += 1
|
||||
img_id = await _sha_to_image_id(db, entry["sha256"])
|
||||
if img_id is None:
|
||||
unmatched.append({"kind": "tag", **entry})
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
tag_id = await _resolve_tag_id(
|
||||
db, entry["tag_name"], entry.get("tag_kind") or "general",
|
||||
)
|
||||
if tag_id is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
# Skip if association already exists.
|
||||
already = (await db.execute(
|
||||
select(image_tag.c.image_record_id).where(
|
||||
image_tag.c.image_record_id == img_id,
|
||||
image_tag.c.tag_id == tag_id,
|
||||
)
|
||||
)).first()
|
||||
if already is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
await db.execute(image_tag.insert().values(
|
||||
image_record_id=img_id, tag_id=tag_id, source="manual",
|
||||
))
|
||||
counts["rows_inserted"] += 1
|
||||
|
||||
# 3. Series pages.
|
||||
for entry in manifest.get("series_pages", []):
|
||||
counts["rows_processed"] += 1
|
||||
img_id = await _sha_to_image_id(db, entry["sha256"])
|
||||
if img_id is None:
|
||||
unmatched.append({"kind": "series", **entry})
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
series_tag_id = await _resolve_tag_id(db, entry["series_tag_name"], "series")
|
||||
if series_tag_id is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
existing = (await db.execute(
|
||||
select(SeriesPage).where(SeriesPage.image_id == img_id)
|
||||
)).scalar_one_or_none()
|
||||
if existing is not None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
if dry_run:
|
||||
counts["rows_inserted"] += 1
|
||||
continue
|
||||
db.add(SeriesPage(
|
||||
series_tag_id=series_tag_id,
|
||||
image_id=img_id,
|
||||
page_number=entry["page_number"],
|
||||
))
|
||||
counts["rows_inserted"] += 1
|
||||
|
||||
# 4. Image posts (schema v2) → Source + Post + ImageProvenance.
|
||||
# Restores IR PostMetadata as FC's downloader-track provenance,
|
||||
# so the modal's ProvenancePanel surfaces title/description/
|
||||
# source URL/publish date the same way it does for live
|
||||
# gallery-dl downloads.
|
||||
for entry in manifest.get("image_posts", []):
|
||||
counts["rows_processed"] += 1
|
||||
platform = entry.get("platform")
|
||||
artist_name = entry.get("artist")
|
||||
if not platform or not artist_name:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
|
||||
aid = await _ensure_artist_id(db, artist_name, dry_run)
|
||||
if aid is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
|
||||
url = _profile_url(platform, slugify(artist_name))
|
||||
if url is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
|
||||
source_id = await _find_or_create_source(
|
||||
db, artist_id=aid, platform=platform, url=url, dry_run=dry_run,
|
||||
)
|
||||
if source_id is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
|
||||
post_id = await _find_or_create_post(
|
||||
db, source_id=source_id,
|
||||
external_post_id=entry.get("post_id") or "",
|
||||
title=entry.get("title"),
|
||||
description=entry.get("description"),
|
||||
post_url=entry.get("source_url"),
|
||||
post_date_iso=entry.get("published_at"),
|
||||
attachment_count=entry.get("attachment_count") or 0,
|
||||
dry_run=dry_run,
|
||||
)
|
||||
if post_id is None:
|
||||
counts["rows_skipped"] += 1
|
||||
continue
|
||||
|
||||
for sha in entry.get("image_sha256s", []):
|
||||
img_id = await _sha_to_image_id(db, sha)
|
||||
if img_id is None:
|
||||
unmatched.append({
|
||||
"kind": "post", "sha256": sha,
|
||||
"post_id": entry.get("post_id"),
|
||||
})
|
||||
continue
|
||||
inserted = await _ensure_provenance(
|
||||
db, image_id=img_id, post_id=post_id,
|
||||
source_id=source_id, dry_run=dry_run,
|
||||
)
|
||||
if inserted:
|
||||
counts["rows_inserted"] += 1
|
||||
else:
|
||||
counts["rows_skipped"] += 1
|
||||
|
||||
if not dry_run:
|
||||
await db.commit()
|
||||
return {"counts": counts, "unmatched": unmatched}
|
||||
@@ -1,80 +0,0 @@
|
||||
"""Post-migration verification: row counts + sha256 sampling."""
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import func, select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from ...models import Artist, Credential, ImageRecord, Source, Tag
|
||||
|
||||
|
||||
async def verify_async(db: AsyncSession, *, expected: dict | None = None) -> dict:
|
||||
"""Return per-check status dicts. `expected` is optional row-count
|
||||
assertions; checks default to status='ok' when no expected provided."""
|
||||
expected = expected or {}
|
||||
results: dict[str, dict] = {}
|
||||
|
||||
checks = {
|
||||
"artist_subscriptions": (
|
||||
select(func.count(Artist.id)).where(Artist.is_subscription.is_(True))
|
||||
),
|
||||
"source_count": select(func.count(Source.id)),
|
||||
"credential_count": select(func.count(Credential.id)),
|
||||
"tag_count": select(func.count(Tag.id)),
|
||||
"image_record_imported_or_downloaded": (
|
||||
select(func.count(ImageRecord.id))
|
||||
.where(ImageRecord.origin.in_(["imported_filesystem", "downloaded"]))
|
||||
),
|
||||
}
|
||||
for name, stmt in checks.items():
|
||||
actual = (await db.execute(stmt)).scalar_one()
|
||||
exp = expected.get(name)
|
||||
status = "ok" if exp is None or exp == actual else "mismatch"
|
||||
results[name] = {"status": status, "actual": int(actual), "expected": exp}
|
||||
return results
|
||||
|
||||
|
||||
async def verify_sha256_sample(
|
||||
db: AsyncSession, *, sample_size: int = 20,
|
||||
) -> dict:
|
||||
"""Sample N image_records; verify file exists + sha256 matches."""
|
||||
rows = (await db.execute(
|
||||
select(ImageRecord.id, ImageRecord.path, ImageRecord.sha256)
|
||||
.order_by(func.random()).limit(sample_size)
|
||||
)).all()
|
||||
|
||||
matched = 0
|
||||
mismatched = 0
|
||||
missing = 0
|
||||
samples: list[dict] = []
|
||||
for img_id, path, expected_sha in rows:
|
||||
p = Path(path)
|
||||
# Sync stdlib filesystem ops are intentional: this verify pass runs
|
||||
# inside a Celery task under asyncio.run; no other awaitables compete
|
||||
# for the loop. Same pattern as download_service.py.
|
||||
if not p.exists(): # noqa: ASYNC240
|
||||
missing += 1
|
||||
samples.append({"id": img_id, "path": path, "result": "missing"})
|
||||
continue
|
||||
h = hashlib.sha256()
|
||||
with p.open("rb") as f: # noqa: ASYNC230
|
||||
for chunk in iter(lambda: f.read(65536), b""):
|
||||
h.update(chunk)
|
||||
if h.hexdigest() == expected_sha:
|
||||
matched += 1
|
||||
samples.append({"id": img_id, "result": "ok"})
|
||||
else:
|
||||
mismatched += 1
|
||||
samples.append({
|
||||
"id": img_id, "path": path, "result": "mismatch",
|
||||
"expected_sha": expected_sha, "actual_sha": h.hexdigest(),
|
||||
})
|
||||
return {
|
||||
"sample_size": len(rows),
|
||||
"matched": matched,
|
||||
"mismatched": mismatched,
|
||||
"missing": missing,
|
||||
"samples": samples,
|
||||
}
|
||||
@@ -48,11 +48,11 @@ class SuggestionService:
|
||||
).scalar_one()
|
||||
|
||||
def _threshold_for(self, s: MLSettings, category: str) -> float:
|
||||
# 'artist' intentionally absent (FC-2d-vii-c) — falls through to
|
||||
# the 1.01 "never surfaces" default like any unsurfaced category.
|
||||
# 'artist' (FC-2d-vii-c) and 'copyright' (2026-06-01) retired;
|
||||
# both fall through to the 1.01 "never surfaces" default like any
|
||||
# unsurfaced category.
|
||||
return {
|
||||
"character": s.suggestion_threshold_character,
|
||||
"copyright": s.suggestion_threshold_copyright,
|
||||
"general": s.suggestion_threshold_general,
|
||||
}.get(category, 1.01)
|
||||
|
||||
|
||||
@@ -38,10 +38,13 @@ STORE_FLOOR = float(os.environ.get("TAGGER_STORE_FLOOR", "0.05"))
|
||||
|
||||
# The categories FC-2b surfaces in the UI. Others (meta/rating/year) are
|
||||
# still stored but the suggestion service filters them out.
|
||||
# FC-2d-vii-c: 'artist' retired — artist identity is acquisition-derived
|
||||
# (image_record.artist_id), never ML-inferred. Raw predictions are still
|
||||
# stored at STORE_FLOOR but artist never surfaces.
|
||||
SURFACED_CATEGORIES = {"character", "copyright", "general"}
|
||||
# 'artist' retired in FC-2d-vii-c — artist identity is acquisition-derived
|
||||
# (image_record.artist_id), never ML-inferred. 'copyright' retired
|
||||
# 2026-06-01 — operator doesn't use the copyright tag-kind; fandom is
|
||||
# this app's franchise/series concept (per TagsView.vue's doc comment).
|
||||
# Raw predictions for both categories still get stored at STORE_FLOOR but
|
||||
# don't surface in suggestions.
|
||||
SURFACED_CATEGORIES = {"character", "general"}
|
||||
|
||||
# ImageNet preprocessing constants (per Camie v2 onnx_inference.py).
|
||||
_IMAGENET_MEAN = np.array([0.485, 0.456, 0.406], dtype=np.float32)
|
||||
|
||||
@@ -96,10 +96,12 @@ def str_field(v) -> str | None:
|
||||
# Shared gallery-dl invocation defaults. Embedded in each platform's
|
||||
# default_config (with platform-specific overrides) so per-platform
|
||||
# choices stay explicit.
|
||||
# Note: the gallery-dl `skip` value (tick "exit:20" vs backfill True) is
|
||||
# NOT here — it's derived from Source.backfill_runs_remaining at download
|
||||
# time. See plan #544 / gallery_dl.TICK_SKIP_VALUE,BACKFILL_SKIP_VALUE.
|
||||
GD_DEFAULTS = {
|
||||
"sleep": 3.0,
|
||||
"sleep_request": 1.5,
|
||||
"skip_existing": True,
|
||||
"save_metadata": True,
|
||||
"timeout": 3600,
|
||||
}
|
||||
|
||||
@@ -56,38 +56,67 @@ class PostFeedService:
|
||||
artist_id: int | None = None,
|
||||
platform: str | None = None,
|
||||
limit: int = 24,
|
||||
direction: str = "older",
|
||||
) -> dict:
|
||||
"""Paginate the feed from `cursor`. direction='older' walks back in
|
||||
time (default, infinite-scroll down); direction='newer' walks forward
|
||||
(scroll up in an anchored view). Items are always returned in feed
|
||||
(descending) order; `next_cursor` points to the far edge in the
|
||||
requested direction (null when exhausted)."""
|
||||
if limit < 1 or limit > 100:
|
||||
raise ValueError("limit must be between 1 and 100")
|
||||
if direction not in ("older", "newer"):
|
||||
raise ValueError("direction must be 'older' or 'newer'")
|
||||
|
||||
sort_key = _sort_key()
|
||||
# Artist via the denormalized Post.artist_id (alembic 0030);
|
||||
# Source via LEFT JOIN since post.source_id can now be NULL for
|
||||
# filesystem-imported posts with no live subscription. A
|
||||
# platform= filter implicitly excludes NULL-source posts (they
|
||||
# have no platform); an artist_id= filter still surfaces them
|
||||
# because Post.artist_id is always set.
|
||||
stmt = (
|
||||
select(Post, Artist, Source)
|
||||
.join(Source, Post.source_id == Source.id)
|
||||
.join(Artist, Source.artist_id == Artist.id)
|
||||
.join(Artist, Post.artist_id == Artist.id)
|
||||
.outerjoin(Source, Post.source_id == Source.id)
|
||||
)
|
||||
if artist_id is not None:
|
||||
stmt = stmt.where(Source.artist_id == artist_id)
|
||||
stmt = stmt.where(Post.artist_id == artist_id)
|
||||
if platform is not None:
|
||||
stmt = stmt.where(Source.platform == platform)
|
||||
if cursor:
|
||||
cur_ts, cur_id = decode_cursor(cursor)
|
||||
stmt = stmt.where(
|
||||
or_(
|
||||
if direction == "older":
|
||||
stmt = stmt.where(or_(
|
||||
sort_key < cur_ts,
|
||||
and_(sort_key == cur_ts, Post.id < cur_id),
|
||||
)
|
||||
)
|
||||
))
|
||||
else:
|
||||
stmt = stmt.where(or_(
|
||||
sort_key > cur_ts,
|
||||
and_(sort_key == cur_ts, Post.id > cur_id),
|
||||
))
|
||||
|
||||
stmt = stmt.order_by(sort_key.desc(), Post.id.desc()).limit(limit + 1)
|
||||
if direction == "older":
|
||||
stmt = stmt.order_by(sort_key.desc(), Post.id.desc())
|
||||
else:
|
||||
stmt = stmt.order_by(sort_key.asc(), Post.id.asc())
|
||||
stmt = stmt.limit(limit + 1)
|
||||
rows = (await self.session.execute(stmt)).all()
|
||||
|
||||
has_more = len(rows) > limit
|
||||
rows = rows[:limit]
|
||||
if direction == "newer":
|
||||
# Fetched ascending (closest-newer first); flip to feed order.
|
||||
rows = list(reversed(rows))
|
||||
|
||||
next_cursor: str | None = None
|
||||
if len(rows) > limit:
|
||||
last_post, _, _ = rows[limit - 1]
|
||||
last_key = last_post.post_date or last_post.downloaded_at
|
||||
next_cursor = encode_cursor(last_key, last_post.id)
|
||||
rows = rows[:limit]
|
||||
if has_more and rows:
|
||||
# Far edge in the travel direction: oldest row going older,
|
||||
# newest row going newer (rows is descending for display).
|
||||
edge_post = rows[-1][0] if direction == "older" else rows[0][0]
|
||||
edge_key = edge_post.post_date or edge_post.downloaded_at
|
||||
next_cursor = encode_cursor(edge_key, edge_post.id)
|
||||
|
||||
post_ids = [p.id for p, _, _ in rows]
|
||||
thumbs_map = await self._thumbnails_for(post_ids)
|
||||
@@ -99,11 +128,54 @@ class PostFeedService:
|
||||
]
|
||||
return {"items": items, "next_cursor": next_cursor}
|
||||
|
||||
async def around(
|
||||
self,
|
||||
*,
|
||||
post_id: int,
|
||||
artist_id: int | None = None,
|
||||
platform: str | None = None,
|
||||
limit: int = 12,
|
||||
) -> dict | None:
|
||||
"""A window centered on `post_id`: up to `limit` newer posts + the
|
||||
post + up to `limit` older posts, in feed (descending) order, with a
|
||||
cursor for each end. Returns None if the post doesn't exist."""
|
||||
anchor = (await self.session.execute(
|
||||
select(Post, Artist, Source)
|
||||
.join(Artist, Post.artist_id == Artist.id)
|
||||
.outerjoin(Source, Post.source_id == Source.id)
|
||||
.where(Post.id == post_id)
|
||||
)).one_or_none()
|
||||
if anchor is None:
|
||||
return None
|
||||
anchor_post, anchor_artist, anchor_source = anchor
|
||||
anchor_key = anchor_post.post_date or anchor_post.downloaded_at
|
||||
anchor_cursor = encode_cursor(anchor_key, anchor_post.id)
|
||||
|
||||
older = await self.scroll(
|
||||
cursor=anchor_cursor, artist_id=artist_id, platform=platform,
|
||||
limit=limit, direction="older",
|
||||
)
|
||||
newer = await self.scroll(
|
||||
cursor=anchor_cursor, artist_id=artist_id, platform=platform,
|
||||
limit=limit, direction="newer",
|
||||
)
|
||||
thumbs_map = await self._thumbnails_for([anchor_post.id])
|
||||
atts_map = await self._attachments_for([anchor_post.id])
|
||||
anchor_item = self._to_dict(
|
||||
anchor_post, anchor_artist, anchor_source, thumbs_map, atts_map,
|
||||
)
|
||||
return {
|
||||
"items": newer["items"] + [anchor_item] + older["items"],
|
||||
"cursor_older": older["next_cursor"],
|
||||
"cursor_newer": newer["next_cursor"],
|
||||
"anchor_id": anchor_post.id,
|
||||
}
|
||||
|
||||
async def get_post(self, post_id: int) -> dict | None:
|
||||
row = (await self.session.execute(
|
||||
select(Post, Artist, Source)
|
||||
.join(Source, Post.source_id == Source.id)
|
||||
.join(Artist, Source.artist_id == Artist.id)
|
||||
.join(Artist, Post.artist_id == Artist.id)
|
||||
.outerjoin(Source, Post.source_id == Source.id)
|
||||
.where(Post.id == post_id)
|
||||
)).one_or_none()
|
||||
if row is None:
|
||||
@@ -141,6 +213,7 @@ class PostFeedService:
|
||||
ImageRecord.primary_post_id,
|
||||
ImageRecord.sha256,
|
||||
ImageRecord.mime,
|
||||
ImageRecord.thumbnail_path,
|
||||
func.row_number().over(
|
||||
partition_by=ImageRecord.primary_post_id,
|
||||
order_by=ImageRecord.id.asc(),
|
||||
@@ -154,18 +227,18 @@ class PostFeedService:
|
||||
)
|
||||
stmt = select(
|
||||
ranked.c.id, ranked.c.primary_post_id,
|
||||
ranked.c.sha256, ranked.c.mime, ranked.c.total,
|
||||
ranked.c.sha256, ranked.c.mime, ranked.c.thumbnail_path, ranked.c.total,
|
||||
)
|
||||
if limit is not None:
|
||||
stmt = stmt.where(ranked.c.rn <= limit)
|
||||
rows = (await self.session.execute(stmt)).all()
|
||||
|
||||
out: dict[int, dict] = {pid: {"thumbs": [], "more": 0} for pid in post_ids}
|
||||
for img_id, pid, sha, mime, total in rows:
|
||||
for img_id, pid, sha, mime, tp, total in rows:
|
||||
entry = out.setdefault(pid, {"thumbs": [], "more": 0})
|
||||
entry["thumbs"].append({
|
||||
"image_id": img_id,
|
||||
"thumbnail_url": thumbnail_url(sha, mime),
|
||||
"thumbnail_url": thumbnail_url(tp, sha, mime),
|
||||
"mime": mime,
|
||||
})
|
||||
# `total` is constant per partition; overflow = total - THUMBNAIL_LIMIT.
|
||||
@@ -193,7 +266,7 @@ class PostFeedService:
|
||||
return out
|
||||
|
||||
def _to_dict(
|
||||
self, post: Post, artist: Artist, source: Source,
|
||||
self, post: Post, artist: Artist, source: Source | None,
|
||||
thumbs_map: dict, atts_map: dict,
|
||||
) -> dict:
|
||||
plain_full = html_to_plain(post.description) if post.description else None
|
||||
@@ -202,6 +275,9 @@ class PostFeedService:
|
||||
else:
|
||||
description_plain, truncated = truncate_at_word(plain_full, DESCRIPTION_LIMIT)
|
||||
thumbs_entry = thumbs_map.get(post.id, {"thumbs": [], "more": 0})
|
||||
# `source` is null for filesystem-imported posts with no live
|
||||
# subscription (alembic 0030). Frontend renders that as a
|
||||
# "filesystem import" affordance instead of a platform chip.
|
||||
return {
|
||||
"id": post.id,
|
||||
"external_post_id": post.external_post_id,
|
||||
@@ -212,7 +288,10 @@ class PostFeedService:
|
||||
"description_plain": description_plain,
|
||||
"description_truncated": truncated,
|
||||
"artist": {"id": artist.id, "name": artist.name, "slug": artist.slug},
|
||||
"source": {"id": source.id, "platform": source.platform},
|
||||
"source": (
|
||||
{"id": source.id, "platform": source.platform}
|
||||
if source is not None else None
|
||||
),
|
||||
"thumbnails": thumbs_entry["thumbs"],
|
||||
"thumbnails_more": thumbs_entry["more"],
|
||||
"attachments": atts_map.get(post.id, []),
|
||||
|
||||
@@ -70,11 +70,15 @@ class ProvenanceService:
|
||||
rec = await self.session.get(ImageRecord, image_id)
|
||||
if rec is None:
|
||||
return None
|
||||
# Artist via Post.artist_id (alembic 0030); Source via LEFT JOIN
|
||||
# since both Post.source_id and ImageProvenance.source_id can be
|
||||
# NULL for filesystem-imported content. Frontend renders source=
|
||||
# null as "filesystem import."
|
||||
stmt = (
|
||||
select(ImageProvenance, Post, Source, Artist)
|
||||
.join(Post, Post.id == ImageProvenance.post_id)
|
||||
.join(Source, Source.id == ImageProvenance.source_id)
|
||||
.join(Artist, Artist.id == Source.artist_id)
|
||||
.join(Artist, Artist.id == Post.artist_id)
|
||||
.outerjoin(Source, Source.id == ImageProvenance.source_id)
|
||||
.where(ImageProvenance.image_record_id == image_id)
|
||||
.order_by(ImageProvenance.captured_at.asc(),
|
||||
ImageProvenance.id.asc())
|
||||
@@ -90,7 +94,7 @@ class ProvenanceService:
|
||||
"captured_at": ip.captured_at.isoformat()
|
||||
if ip.captured_at else None,
|
||||
"post": _post_dict(post),
|
||||
"source": _source_dict(src),
|
||||
"source": _source_dict(src) if src is not None else None,
|
||||
"artist": _artist_dict(art),
|
||||
}
|
||||
for ip, post, src, art in rows
|
||||
@@ -99,10 +103,12 @@ class ProvenanceService:
|
||||
}
|
||||
|
||||
async def for_post(self, post_id: int) -> dict | None:
|
||||
# Same LEFT JOIN to Source — get_post must succeed for a
|
||||
# NULL-source post.
|
||||
stmt = (
|
||||
select(Post, Source, Artist)
|
||||
.join(Source, Source.id == Post.source_id)
|
||||
.join(Artist, Artist.id == Source.artist_id)
|
||||
.join(Artist, Artist.id == Post.artist_id)
|
||||
.outerjoin(Source, Source.id == Post.source_id)
|
||||
.where(Post.id == post_id)
|
||||
)
|
||||
row = (await self.session.execute(stmt)).first()
|
||||
@@ -111,7 +117,7 @@ class ProvenanceService:
|
||||
post, src, art = row
|
||||
return {
|
||||
"post": _post_dict(post),
|
||||
"source": _source_dict(src),
|
||||
"source": _source_dict(src) if src is not None else None,
|
||||
"artist": _artist_dict(art),
|
||||
"attachments": await self._attachments_for_posts([post.id]),
|
||||
}
|
||||
|
||||
@@ -86,7 +86,7 @@ def attempt_refetch(
|
||||
if src is None:
|
||||
return {"status": "no_source"}
|
||||
|
||||
# Remove the bad copy so gallery-dl (skip_existing) re-fetches it on
|
||||
# Remove the bad copy so gallery-dl's archive-skip re-fetches it on
|
||||
# the source re-check instead of skipping the still-present corrupt
|
||||
# file.
|
||||
try:
|
||||
|
||||
@@ -9,15 +9,33 @@ from __future__ import annotations
|
||||
from datetime import UTC, datetime, timedelta
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.dialects.postgresql import insert as pg_insert
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
from sqlalchemy.orm import selectinload
|
||||
|
||||
from ..models import Artist, ImportSettings, Source
|
||||
from ..models import AppSetting, Artist, ImportSettings, Source
|
||||
|
||||
MIN_INTERVAL_SECONDS = 60
|
||||
MAX_INTERVAL_SECONDS = 86400
|
||||
MAX_BACKOFF_EXPONENT = 6
|
||||
|
||||
# AppSetting key stamped every time the Beat tick fires (see scan.py). The
|
||||
# tick runs every 60s; the UI flags the scheduler as stalled if the last
|
||||
# stamp is older than a few minutes.
|
||||
SCHEDULER_LAST_TICK_KEY = "scheduler_last_tick_at"
|
||||
|
||||
# AppSetting key prefix for per-platform rate-limit cooldowns. When a
|
||||
# download surfaces ErrorType.RATE_LIMITED, every other source on the same
|
||||
# platform is deferred for PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS so the next
|
||||
# scan tick doesn't fire a burst of due same-platform sources back into the
|
||||
# same limit. Per-source consecutive_failures backoff still applies on top
|
||||
# of this — but this is PREVENTIVE (kills the same-tick burst from N due
|
||||
# sources hammering the platform at once), while consecutive_failures is
|
||||
# REACTIVE (slows the offender down over many cycles). Operator-confirmed
|
||||
# 2026-05-30.
|
||||
PLATFORM_COOLDOWN_KEY_PREFIX = "platform_cooldown:"
|
||||
PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS = 900 # 15 min
|
||||
|
||||
|
||||
def compute_effective_interval(
|
||||
source: Source, artist: Artist, settings: ImportSettings,
|
||||
@@ -40,10 +58,76 @@ def compute_effective_interval(
|
||||
return max(MIN_INTERVAL_SECONDS, min(MAX_INTERVAL_SECONDS, raw))
|
||||
|
||||
|
||||
async def set_platform_cooldown(
|
||||
session: AsyncSession, platform: str,
|
||||
seconds: int = PLATFORM_RATE_LIMIT_COOLDOWN_SECONDS,
|
||||
) -> None:
|
||||
"""Stamp a cooldown expiry on the given platform so select_due_sources
|
||||
skips every source on that platform until it expires.
|
||||
|
||||
Called when a download surfaces ErrorType.RATE_LIMITED so the other
|
||||
sources on the same platform don't all retry into the same rate limit.
|
||||
Caller is responsible for committing the session.
|
||||
|
||||
Uses INSERT...ON CONFLICT DO UPDATE so two concurrent workers hitting
|
||||
the same platform's rate limit don't race: a SELECT-then-INSERT pattern
|
||||
would let the loser's whole transaction (including the source-health
|
||||
update + event finalize) roll back on a unique-violation, stranding
|
||||
that event. Atomic upsert avoids that.
|
||||
"""
|
||||
now = datetime.now(UTC)
|
||||
expires_at = (now + timedelta(seconds=seconds)).isoformat()
|
||||
key = f"{PLATFORM_COOLDOWN_KEY_PREFIX}{platform}"
|
||||
stmt = pg_insert(AppSetting.__table__).values(
|
||||
key=key, value=expires_at, updated_at=now,
|
||||
).on_conflict_do_update(
|
||||
index_elements=["key"],
|
||||
set_={"value": expires_at, "updated_at": now},
|
||||
)
|
||||
await session.execute(stmt)
|
||||
|
||||
|
||||
async def active_platform_cooldowns(session: AsyncSession) -> dict[str, datetime]:
|
||||
"""Return {platform: expires_at} for platforms whose cooldown is still
|
||||
in the future. Expired rows are ignored (a future maintenance sweep can
|
||||
delete them; they don't affect routing decisions on their own).
|
||||
|
||||
Exposed beyond scheduler_service so the manual check endpoint
|
||||
(`/api/sources/<id>/check`) can defer bulk retries that would bowl
|
||||
into the same rate limit the cooldown is preventing.
|
||||
"""
|
||||
rows = (await session.execute(
|
||||
select(AppSetting.key, AppSetting.value)
|
||||
.where(AppSetting.key.startswith(PLATFORM_COOLDOWN_KEY_PREFIX))
|
||||
)).all()
|
||||
if not rows:
|
||||
return {}
|
||||
now = datetime.now(UTC)
|
||||
active: dict[str, datetime] = {}
|
||||
for key, value in rows:
|
||||
try:
|
||||
expires_at = datetime.fromisoformat(value)
|
||||
except (ValueError, TypeError):
|
||||
continue
|
||||
if expires_at > now:
|
||||
active[key[len(PLATFORM_COOLDOWN_KEY_PREFIX):]] = expires_at
|
||||
return active
|
||||
|
||||
|
||||
async def select_due_sources(session: AsyncSession) -> list[Source]:
|
||||
"""Sources where (enabled, artist.auto_check) and now >= last_checked_at + effective_interval.
|
||||
|
||||
Never-checked sources (last_checked_at IS NULL) are always due.
|
||||
Never-checked sources (last_checked_at IS NULL) are always due. Sources
|
||||
whose platform is currently in a rate-limit cooldown are excluded — the
|
||||
cooldown is the preventive half of the burst-prevention pair (per-source
|
||||
consecutive_failures backoff handles the offending source itself).
|
||||
|
||||
Ordering: last_checked_at ASC NULLS FIRST, then id. Never-checked
|
||||
sources go first, then the longest-since-checked, so the most overdue
|
||||
sources hit Celery's FIFO download queue first. Anti-starvation: if
|
||||
queue throughput ever falls below the tick rate, a freshly-rerun source
|
||||
can't keep cutting in line ahead of one that hasn't been checked at all.
|
||||
Operator-confirmed 2026-05-30.
|
||||
"""
|
||||
rows = (await session.execute(
|
||||
select(Source)
|
||||
@@ -51,15 +135,17 @@ async def select_due_sources(session: AsyncSession) -> list[Source]:
|
||||
.join(Artist, Source.artist_id == Artist.id)
|
||||
.where(Source.enabled.is_(True))
|
||||
.where(Artist.auto_check.is_(True))
|
||||
.order_by(Source.last_checked_at.asc().nulls_first(), Source.id)
|
||||
)).scalars().all()
|
||||
|
||||
settings = (await session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
)).scalar_one()
|
||||
cooldowns = await active_platform_cooldowns(session)
|
||||
settings = await ImportSettings.load(session)
|
||||
|
||||
now = datetime.now(UTC)
|
||||
due: list[Source] = []
|
||||
for s in rows:
|
||||
if s.platform in cooldowns:
|
||||
continue
|
||||
interval = compute_effective_interval(s, s.artist, settings)
|
||||
if s.last_checked_at is None:
|
||||
due.append(s)
|
||||
@@ -78,3 +164,65 @@ def compute_next_check_at(
|
||||
return None
|
||||
interval = compute_effective_interval(source, artist, settings)
|
||||
return source.last_checked_at + timedelta(seconds=interval)
|
||||
|
||||
|
||||
async def record_tick(session: AsyncSession) -> None:
|
||||
"""Stamp the current time on the SCHEDULER_LAST_TICK_KEY AppSetting.
|
||||
|
||||
Called once per Beat tick so the UI can prove the scheduler is alive.
|
||||
Commits its own write so the stamp survives even if the rest of the
|
||||
tick errors out.
|
||||
"""
|
||||
now_iso = datetime.now(UTC).isoformat()
|
||||
row = (await session.execute(
|
||||
select(AppSetting).where(AppSetting.key == SCHEDULER_LAST_TICK_KEY)
|
||||
)).scalar_one_or_none()
|
||||
if row is None:
|
||||
session.add(AppSetting(key=SCHEDULER_LAST_TICK_KEY, value=now_iso))
|
||||
else:
|
||||
row.value = now_iso
|
||||
await session.commit()
|
||||
|
||||
|
||||
async def scheduler_status(session: AsyncSession) -> dict:
|
||||
"""Summarise scheduler health for the dashboard.
|
||||
|
||||
Returns last_tick_at (when Beat last fired), next_due_at (earliest
|
||||
upcoming scheduled check across enabled auto-check sources), due_now
|
||||
(how many are due right now), and auto_sources (total under schedule).
|
||||
"""
|
||||
last_tick_at = (await session.execute(
|
||||
select(AppSetting.value).where(AppSetting.key == SCHEDULER_LAST_TICK_KEY)
|
||||
)).scalar_one_or_none()
|
||||
|
||||
rows = (await session.execute(
|
||||
select(Source)
|
||||
.options(selectinload(Source.artist))
|
||||
.join(Artist, Source.artist_id == Artist.id)
|
||||
.where(Source.enabled.is_(True))
|
||||
.where(Artist.auto_check.is_(True))
|
||||
)).scalars().all()
|
||||
settings = await ImportSettings.load(session)
|
||||
|
||||
now = datetime.now(UTC)
|
||||
due_now = 0
|
||||
next_due_at: datetime | None = None
|
||||
for s in rows:
|
||||
if s.last_checked_at is None:
|
||||
due_now += 1
|
||||
continue
|
||||
nca = compute_next_check_at(s, s.artist, settings)
|
||||
if nca is None or nca <= now:
|
||||
due_now += 1
|
||||
elif next_due_at is None or nca < next_due_at:
|
||||
next_due_at = nca
|
||||
|
||||
cooldowns = await active_platform_cooldowns(session)
|
||||
|
||||
return {
|
||||
"last_tick_at": last_tick_at,
|
||||
"next_due_at": next_due_at.isoformat() if next_due_at else None,
|
||||
"due_now": due_now,
|
||||
"auto_sources": len(rows),
|
||||
"platform_cooldowns": {p: dt.isoformat() for p, dt in cooldowns.items()},
|
||||
}
|
||||
|
||||
@@ -63,6 +63,7 @@ class SeriesService:
|
||||
ImageRecord.sha256,
|
||||
ImageRecord.mime,
|
||||
ImageRecord.path,
|
||||
ImageRecord.thumbnail_path,
|
||||
)
|
||||
.join(ImageRecord, ImageRecord.id == SeriesPage.image_id)
|
||||
.where(SeriesPage.series_tag_id == series_tag_id)
|
||||
@@ -75,7 +76,7 @@ class SeriesService:
|
||||
{
|
||||
"image_id": r.image_id,
|
||||
"page_number": r.page_number,
|
||||
"thumbnail_url": thumbnail_url(r.sha256, r.mime),
|
||||
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
|
||||
"image_url": f"/images/{r.path.split('/images/', 1)[-1]}",
|
||||
}
|
||||
for r in rows
|
||||
|
||||
@@ -34,7 +34,7 @@ class ShowcaseService:
|
||||
"mime": r.mime,
|
||||
"width": r.width,
|
||||
"height": r.height,
|
||||
"thumbnail_url": thumbnail_url(r.sha256, r.mime),
|
||||
"thumbnail_url": thumbnail_url(r.thumbnail_path, r.sha256, r.mime),
|
||||
}
|
||||
for r in rows
|
||||
]
|
||||
|
||||
@@ -62,6 +62,7 @@ class SourceRecord:
|
||||
check_interval_override: int | None
|
||||
consecutive_failures: int
|
||||
next_check_at: str | None
|
||||
backfill_runs_remaining: int
|
||||
|
||||
def to_dict(self) -> dict:
|
||||
return {
|
||||
@@ -78,6 +79,7 @@ class SourceRecord:
|
||||
"check_interval_override": self.check_interval_override,
|
||||
"consecutive_failures": self.consecutive_failures,
|
||||
"next_check_at": self.next_check_at,
|
||||
"backfill_runs_remaining": self.backfill_runs_remaining,
|
||||
}
|
||||
|
||||
|
||||
@@ -85,6 +87,11 @@ class SourceRecord:
|
||||
|
||||
_EDITABLE = {"enabled", "url", "config_overrides", "check_interval_override", "platform"}
|
||||
|
||||
# Plan #544 follow-up: newly created enabled sources pre-arm backfill so
|
||||
# their first N polls walk gallery-dl's full post history with the longer
|
||||
# timeout (matches the manual "Deep scan" button's default).
|
||||
_NEW_SOURCE_BACKFILL_RUNS = 3
|
||||
|
||||
|
||||
class SourceService:
|
||||
def __init__(self, session: AsyncSession):
|
||||
@@ -120,9 +127,7 @@ class SourceService:
|
||||
return config
|
||||
|
||||
async def _load_settings(self) -> ImportSettings:
|
||||
return (await self.session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
)).scalar_one()
|
||||
return await ImportSettings.load(self.session)
|
||||
|
||||
def _build_record(
|
||||
self, source: Source, artist: Artist, settings: ImportSettings,
|
||||
@@ -142,6 +147,7 @@ class SourceService:
|
||||
check_interval_override=source.check_interval_override,
|
||||
consecutive_failures=source.consecutive_failures or 0,
|
||||
next_check_at=nxt.isoformat() if nxt else None,
|
||||
backfill_runs_remaining=source.backfill_runs_remaining or 0,
|
||||
)
|
||||
|
||||
async def _row_to_record(self, source: Source) -> SourceRecord:
|
||||
@@ -151,14 +157,27 @@ class SourceService:
|
||||
settings = await self._load_settings()
|
||||
return self._build_record(source, artist, settings)
|
||||
|
||||
async def list(self, artist_id: int | None = None) -> list[SourceRecord]:
|
||||
stmt = (
|
||||
select(Source, Artist)
|
||||
.join(Artist, Artist.id == Source.artist_id)
|
||||
.order_by(Artist.name.asc(), Source.id.asc())
|
||||
)
|
||||
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:
|
||||
# Pre-alembic-0030 sidecar synthetic anchors
|
||||
# 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(
|
||||
Source.consecutive_failures.desc(), Artist.name.asc(),
|
||||
)
|
||||
else:
|
||||
stmt = stmt.order_by(Artist.name.asc(), Source.id.asc())
|
||||
rows = (await self.session.execute(stmt)).all()
|
||||
settings = await self._load_settings()
|
||||
return [self._build_record(s, a, settings) for s, a in rows]
|
||||
@@ -190,10 +209,21 @@ class SourceService:
|
||||
select(func.count(Source.id)).where(Source.artist_id == artist_id)
|
||||
)).scalar_one()
|
||||
|
||||
# Plan #544 follow-up: a freshly added subscription has no archive
|
||||
# yet, so the first few polls would walk the full post history in
|
||||
# tick mode and trip exit:20 after ~20 contiguous archive hits —
|
||||
# except there are none yet, so tick mode would walk forever and
|
||||
# blow the wall-clock cap. Pre-arm backfill so the initial syncs
|
||||
# use the longer timeout + skip:True walk. Tick mode resumes once
|
||||
# the budget is spent or the queue drains.
|
||||
# Disabled sources (incl. sidecar synthetics, url='sidecar:...')
|
||||
# are never polled, so leave their counter at 0.
|
||||
backfill_runs = _NEW_SOURCE_BACKFILL_RUNS if enabled else 0
|
||||
source = Source(
|
||||
artist_id=artist_id, platform=platform, url=url,
|
||||
enabled=enabled, config_overrides=config_overrides,
|
||||
check_interval_override=check_interval_override,
|
||||
backfill_runs_remaining=backfill_runs,
|
||||
)
|
||||
self.session.add(source)
|
||||
try:
|
||||
@@ -253,6 +283,25 @@ class SourceService:
|
||||
await self.session.commit()
|
||||
return await self._row_to_record(source)
|
||||
|
||||
async def set_backfill_runs(
|
||||
self, source_id: int, runs: int,
|
||||
) -> SourceRecord:
|
||||
"""Plan #544: arm a source for backfill mode. The next `runs`
|
||||
download runs will use gallery-dl's full-walk config (skip: True
|
||||
+ 30-min timeout) instead of the catch-up default. Runs must be
|
||||
1..10 — bigger is rejected to keep the operator from accidentally
|
||||
setting a runaway budget."""
|
||||
if not isinstance(runs, int) or runs < 1 or runs > 10:
|
||||
raise ValueError("runs must be an integer in [1, 10]")
|
||||
source = (await self.session.execute(
|
||||
select(Source).where(Source.id == source_id)
|
||||
)).scalar_one_or_none()
|
||||
if source is None:
|
||||
raise LookupError(f"source id={source_id} not found")
|
||||
source.backfill_runs_remaining = runs
|
||||
await self.session.commit()
|
||||
return await self._row_to_record(source)
|
||||
|
||||
async def delete(self, source_id: int) -> None:
|
||||
source = (await self.session.execute(
|
||||
select(Source).where(Source.id == source_id)
|
||||
|
||||
@@ -115,12 +115,17 @@ class TagDirectoryService:
|
||||
.subquery()
|
||||
)
|
||||
stmt = (
|
||||
select(sub.c.tag_id, ImageRecord.sha256, ImageRecord.mime)
|
||||
select(
|
||||
sub.c.tag_id,
|
||||
ImageRecord.sha256,
|
||||
ImageRecord.mime,
|
||||
ImageRecord.thumbnail_path,
|
||||
)
|
||||
.join(ImageRecord, ImageRecord.id == sub.c.image_record_id)
|
||||
.where(sub.c.rn <= 3)
|
||||
.order_by(sub.c.tag_id, sub.c.rn)
|
||||
)
|
||||
out: dict[int, list[str]] = {}
|
||||
for tag_id, sha, mime in (await self.session.execute(stmt)).all():
|
||||
out.setdefault(tag_id, []).append(thumbnail_url(sha, mime))
|
||||
for tag_id, sha, mime, tp in (await self.session.execute(stmt)).all():
|
||||
out.setdefault(tag_id, []).append(thumbnail_url(tp, sha, mime))
|
||||
return out
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
"""Per-invocation async session factory for Celery task modules.
|
||||
|
||||
Async engine connections are bound to the event loop. Each Celery task
|
||||
runs its async body under a fresh ``asyncio.run()`` loop, so it needs its
|
||||
own engine created (and disposed) within that loop — a process-wide async
|
||||
engine would reuse loop-bound connections across tasks and raise "attached
|
||||
to a different loop". So unlike the process-wide sync engine in
|
||||
``_sync_engine.py``, this returns a fresh engine per call; the caller
|
||||
disposes it (``await engine.dispose()``) when its loop ends.
|
||||
"""
|
||||
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
|
||||
from ..config import get_config
|
||||
|
||||
|
||||
def async_session_factory():
|
||||
"""Return ``(sessionmaker, engine)`` bound to a fresh async engine."""
|
||||
cfg = get_config()
|
||||
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
|
||||
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
|
||||
@@ -246,9 +246,7 @@ def prune_backups() -> dict:
|
||||
SessionLocal = _sync_session_factory()
|
||||
counts = {"db_deleted": 0, "images_deleted": 0, "files_unlinked": 0}
|
||||
with SessionLocal() as session:
|
||||
s = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
s = ImportSettings.load_sync(session)
|
||||
for kind, keep in (
|
||||
("db", s.backup_db_keep_last_n),
|
||||
("images", s.backup_images_keep_last_n),
|
||||
@@ -286,9 +284,7 @@ def backup_db_nightly() -> dict:
|
||||
either {'skipped': '<reason>'} or {'dispatched': '<task_id>'}."""
|
||||
SessionLocal = _sync_session_factory()
|
||||
with SessionLocal() as session:
|
||||
s = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
s = ImportSettings.load_sync(session)
|
||||
nightly_enabled = s.backup_db_nightly_enabled
|
||||
configured_hour = s.backup_db_nightly_hour_utc
|
||||
if not nightly_enabled:
|
||||
|
||||
@@ -3,12 +3,9 @@
|
||||
import asyncio
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.exc import DBAPIError, OperationalError
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
|
||||
from ..celery_app import celery
|
||||
from ..config import get_config
|
||||
from ..models import ImportSettings
|
||||
from ..services.credential_crypto import CredentialCrypto
|
||||
from ..services.credential_service import CredentialService
|
||||
@@ -16,18 +13,13 @@ from ..services.download_service import DownloadService
|
||||
from ..services.gallery_dl import GalleryDLService
|
||||
from ..services.importer import Importer
|
||||
from ..services.thumbnailer import Thumbnailer
|
||||
from ._async_session import async_session_factory
|
||||
from .import_file import _sync_session_factory
|
||||
|
||||
IMAGES_ROOT = Path("/images")
|
||||
_KEY_PATH = IMAGES_ROOT / "secrets" / "credential_key.b64"
|
||||
|
||||
|
||||
def _async_session_factory():
|
||||
cfg = get_config()
|
||||
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
|
||||
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
|
||||
|
||||
|
||||
@celery.task(
|
||||
name="backend.app.tasks.download.download_source",
|
||||
bind=True,
|
||||
@@ -44,13 +36,11 @@ def download_source(self, source_id: int) -> int:
|
||||
"""Returns the DownloadEvent.id."""
|
||||
|
||||
async def _run():
|
||||
async_factory, async_engine = _async_session_factory()
|
||||
async_factory, async_engine = async_session_factory()
|
||||
SyncFactory = _sync_session_factory()
|
||||
try:
|
||||
with SyncFactory() as sync_session:
|
||||
settings = sync_session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
settings = ImportSettings.load_sync(sync_session)
|
||||
rate_limit = settings.download_rate_limit_seconds
|
||||
validate_files = settings.download_validate_files
|
||||
|
||||
@@ -64,9 +54,7 @@ def download_source(self, source_id: int) -> int:
|
||||
async with async_factory() as async_session:
|
||||
cred_service = CredentialService(async_session, crypto)
|
||||
with SyncFactory() as sync_session:
|
||||
sync_settings = sync_session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
sync_settings = ImportSettings.load_sync(sync_session)
|
||||
importer = Importer(
|
||||
session=sync_session,
|
||||
images_root=IMAGES_ROOT,
|
||||
|
||||
@@ -167,9 +167,7 @@ def enqueue_import(task_id: int, task_type: str) -> None:
|
||||
|
||||
def _do_import(session, task, import_task_id: int) -> dict:
|
||||
"""Actual work, called from inside the resilience wrapper."""
|
||||
settings = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
settings = ImportSettings.load_sync(session)
|
||||
import_root = Path(settings.import_scan_path)
|
||||
batch = session.get(ImportBatch, task.batch_id)
|
||||
deep = bool(batch and batch.scan_mode == "deep")
|
||||
|
||||
@@ -10,7 +10,14 @@ from PIL import Image
|
||||
from sqlalchemy import and_, delete, or_, select, update
|
||||
|
||||
from ..celery_app import celery
|
||||
from ..models import DownloadEvent, ImageRecord, ImportSettings, ImportTask, TaskRun
|
||||
from ..models import (
|
||||
DownloadEvent,
|
||||
ImageRecord,
|
||||
ImportSettings,
|
||||
ImportTask,
|
||||
Source,
|
||||
TaskRun,
|
||||
)
|
||||
from ..utils.phash import compute_phash
|
||||
from ._sync_engine import sync_session_factory as _sync_session_factory
|
||||
|
||||
@@ -34,6 +41,13 @@ ARCHIVE_STUCK_THRESHOLD_MINUTES = 40
|
||||
# flip to terminal 'failed' and never enter this loop.
|
||||
MAX_RECOVERY_ATTEMPTS = 3
|
||||
ORPHAN_PENDING_THRESHOLD_MINUTES = 30
|
||||
|
||||
# DownloadEvent (pending|running) recovery threshold. download_source has
|
||||
# time_limit=1200s (20 min); 30 min is 10 min past that, so a legitimately-
|
||||
# running task is never killed by the sweep. Operator-confirmed 2026-05-29
|
||||
# after 43 sources stranded at "last check never" by the in-flight guard.
|
||||
DOWNLOAD_STALL_THRESHOLD_MINUTES = 30
|
||||
|
||||
OLD_TASK_DAYS = 7
|
||||
PHASH_PAGE = 500
|
||||
VERIFY_PAGE = 200
|
||||
@@ -448,6 +462,65 @@ def verify_integrity() -> int:
|
||||
return total
|
||||
|
||||
|
||||
@celery.task(name="backend.app.tasks.maintenance.recover_stalled_download_events")
|
||||
def recover_stalled_download_events() -> int:
|
||||
"""Recover DownloadEvent rows stuck pending/running past the worker hard kill.
|
||||
|
||||
The scan tick (scheduler_service.select_due_sources →
|
||||
tasks.scan._tick_due_sources_async) inserts DownloadEvent(status='pending')
|
||||
and fires download_source.delay(). If that task dies before finalizing the
|
||||
event — worker OOM/SIGKILL, lost task, or a gallery-dl that didn't unwind
|
||||
on the 1200s hard time_limit — the event stays in-flight forever. The next
|
||||
tick then skips that source because of the in-flight guard (scan.py:168)
|
||||
and Source.last_checked_at never updates; the operator sees "last check
|
||||
never" in the Subscriptions health column, permanently.
|
||||
|
||||
This sweep flips matching events to 'error', stamps each affected Source's
|
||||
last_checked_at + last_error and bumps consecutive_failures (once per
|
||||
source, not per event — backoff is exponential on that count so an N-event
|
||||
bump would inflate the next interval by 2^N for no reason). The source
|
||||
becomes re-queueable on the next tick and the health dot goes amber.
|
||||
|
||||
Operator-confirmed 2026-05-29 (43-row strand pile in production).
|
||||
"""
|
||||
SessionLocal = _sync_session_factory()
|
||||
now = datetime.now(UTC)
|
||||
cutoff = now - timedelta(minutes=DOWNLOAD_STALL_THRESHOLD_MINUTES)
|
||||
msg = "stranded by recovery sweep (no terminal status after time_limit)"
|
||||
with SessionLocal() as session:
|
||||
# UPDATE...RETURNING the source_ids in one round trip — keeps us off
|
||||
# the psycopg 65535-param ceiling that SELECT-then-UPDATE-WHERE-IN
|
||||
# would hit on a large strand pile.
|
||||
result = session.execute(
|
||||
update(DownloadEvent)
|
||||
.where(DownloadEvent.status.in_(["pending", "running"]))
|
||||
.where(DownloadEvent.started_at < cutoff)
|
||||
.values(status="error", finished_at=now, error=msg)
|
||||
.returning(DownloadEvent.source_id)
|
||||
)
|
||||
returned = result.all()
|
||||
if not returned:
|
||||
session.commit()
|
||||
return 0
|
||||
events_recovered = len(returned)
|
||||
source_ids = list({row.source_id for row in returned})
|
||||
session.execute(
|
||||
update(Source)
|
||||
.where(Source.id.in_(source_ids))
|
||||
.values(
|
||||
consecutive_failures=Source.consecutive_failures + 1,
|
||||
last_error=msg,
|
||||
last_checked_at=now,
|
||||
)
|
||||
)
|
||||
session.commit()
|
||||
log.info(
|
||||
"recover_stalled_download_events: recovered %d events across %d sources",
|
||||
events_recovered, len(source_ids),
|
||||
)
|
||||
return events_recovered
|
||||
|
||||
|
||||
@celery.task(name="backend.app.tasks.maintenance.cleanup_old_download_events")
|
||||
def cleanup_old_download_events() -> int:
|
||||
"""FC-3d: delete terminal DownloadEvent rows older than the configured
|
||||
@@ -460,9 +533,7 @@ def cleanup_old_download_events() -> int:
|
||||
"""
|
||||
SessionLocal = _sync_session_factory()
|
||||
with SessionLocal() as session:
|
||||
settings = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
settings = ImportSettings.load_sync(session)
|
||||
retention_days = settings.download_event_retention_days
|
||||
cutoff = datetime.now(UTC) - timedelta(days=retention_days)
|
||||
result = session.execute(
|
||||
|
||||
@@ -1,175 +0,0 @@
|
||||
"""FC-5 run_migration Celery task.
|
||||
|
||||
Dispatches to the right migrator based on `kind`. Updates MigrationRun
|
||||
row's status/counts/finished_at as it runs. Failures set status='error'
|
||||
with the error message preserved.
|
||||
|
||||
kinds: gs_ingest, ir_ingest, tag_apply, ml_queue, verify, cleanup
|
||||
(backup + rollback retired 2026-05-24 → see /api/system/backup/*)
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
|
||||
from ..celery_app import celery
|
||||
from ..config import get_config
|
||||
from ..models import MigrationRun
|
||||
from ..services.credential_crypto import CredentialCrypto
|
||||
from ..services.migrators import cleanup as cleanup_mod
|
||||
from ..services.migrators import gs_ingest, ir_ingest, ml_queue, tag_apply, verify
|
||||
|
||||
log = logging.getLogger(__name__)
|
||||
|
||||
IMAGES_ROOT = Path("/images")
|
||||
_KEY_PATH = IMAGES_ROOT / "secrets" / "credential_key.b64"
|
||||
|
||||
|
||||
def _async_session_factory():
|
||||
cfg = get_config()
|
||||
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
|
||||
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
|
||||
|
||||
|
||||
async def _update_run(
|
||||
db: AsyncSession, run_id: int, *,
|
||||
status: str | None = None, counts: dict | None = None,
|
||||
error: str | None = None, finished_at: datetime | None = None,
|
||||
metadata_patch: dict | None = None,
|
||||
) -> None:
|
||||
run = (await db.execute(
|
||||
select(MigrationRun).where(MigrationRun.id == run_id)
|
||||
)).scalar_one()
|
||||
if status is not None:
|
||||
run.status = status
|
||||
if counts is not None:
|
||||
run.counts = counts
|
||||
if error is not None:
|
||||
run.error = error
|
||||
if finished_at is not None:
|
||||
run.finished_at = finished_at
|
||||
if metadata_patch:
|
||||
run.metadata_ = {**(run.metadata_ or {}), **metadata_patch}
|
||||
await db.commit()
|
||||
|
||||
|
||||
async def _run_async(run_id: int, kind: str, params: dict) -> dict:
|
||||
factory, engine = _async_session_factory()
|
||||
try:
|
||||
async with factory() as db:
|
||||
await _update_run(db, run_id, status="running")
|
||||
try:
|
||||
if kind in ("backup", "rollback"):
|
||||
raise ValueError(
|
||||
f"kind {kind!r} retired in FC-3h; "
|
||||
"use /api/system/backup/* instead"
|
||||
)
|
||||
|
||||
elif kind == "gs_ingest":
|
||||
fc_crypto = CredentialCrypto(_KEY_PATH)
|
||||
counts = await gs_ingest.migrate_async(
|
||||
db, data=params["data"],
|
||||
fc_crypto=fc_crypto,
|
||||
dry_run=params.get("dry_run", False),
|
||||
)
|
||||
await _update_run(
|
||||
db, run_id, status="ok", counts=counts,
|
||||
finished_at=datetime.now(UTC),
|
||||
)
|
||||
return counts
|
||||
|
||||
elif kind == "ir_ingest":
|
||||
counts = await ir_ingest.migrate_async(
|
||||
db, data=params["data"],
|
||||
images_root=IMAGES_ROOT,
|
||||
dry_run=params.get("dry_run", False),
|
||||
)
|
||||
await _update_run(
|
||||
db, run_id, status="ok", counts=counts,
|
||||
finished_at=datetime.now(UTC),
|
||||
)
|
||||
return counts
|
||||
|
||||
elif kind == "tag_apply":
|
||||
result = await tag_apply.apply_async(
|
||||
db, images_root=IMAGES_ROOT,
|
||||
dry_run=params.get("dry_run", False),
|
||||
)
|
||||
await _update_run(
|
||||
db, run_id, status="ok",
|
||||
counts=result["counts"],
|
||||
finished_at=datetime.now(UTC),
|
||||
metadata_patch={"unmatched": result["unmatched"]},
|
||||
)
|
||||
return result
|
||||
|
||||
elif kind == "ml_queue":
|
||||
count = await ml_queue.queue_all_unprocessed_async(db)
|
||||
await _update_run(
|
||||
db, run_id, status="ok",
|
||||
counts={"rows_processed": count, "rows_inserted": 0,
|
||||
"rows_skipped": 0, "files_copied": 0,
|
||||
"bytes_copied": 0, "conflicts": 0},
|
||||
finished_at=datetime.now(UTC),
|
||||
)
|
||||
return {"queued": count}
|
||||
|
||||
elif kind == "verify":
|
||||
checks = await verify.verify_async(db, expected=params.get("expected"))
|
||||
sample = await verify.verify_sha256_sample(
|
||||
db, sample_size=params.get("sample_size", 20),
|
||||
)
|
||||
await _update_run(
|
||||
db, run_id, status="ok",
|
||||
counts={"rows_processed": sample["sample_size"],
|
||||
"rows_inserted": 0, "rows_skipped": 0,
|
||||
"files_copied": 0, "bytes_copied": 0,
|
||||
"conflicts": sample["mismatched"] + sample["missing"]},
|
||||
finished_at=datetime.now(UTC),
|
||||
metadata_patch={"checks": checks, "sample": sample},
|
||||
)
|
||||
return {"checks": checks, "sample": sample}
|
||||
|
||||
elif kind == "cleanup":
|
||||
slug = params.get("slug")
|
||||
if not slug:
|
||||
raise ValueError("cleanup requires params.slug")
|
||||
result = await cleanup_mod.cleanup_artist_async(
|
||||
db, slug=slug, images_root=IMAGES_ROOT,
|
||||
dry_run=params.get("dry_run", False),
|
||||
source_path_prefix=params.get("source_path_prefix"),
|
||||
)
|
||||
await _update_run(
|
||||
db, run_id, status="ok",
|
||||
counts=result["counts"],
|
||||
finished_at=datetime.now(UTC),
|
||||
metadata_patch={
|
||||
"artist": result["artist"],
|
||||
"summary": result["summary"],
|
||||
},
|
||||
)
|
||||
return result
|
||||
|
||||
else:
|
||||
raise ValueError(f"unknown kind: {kind}")
|
||||
|
||||
except Exception as exc:
|
||||
log.exception("migration kind=%s failed", kind)
|
||||
await _update_run(
|
||||
db, run_id, status="error", error=str(exc),
|
||||
finished_at=datetime.now(UTC),
|
||||
)
|
||||
raise
|
||||
finally:
|
||||
await engine.dispose()
|
||||
|
||||
|
||||
@celery.task(name="backend.app.tasks.migration.run_migration", bind=True, acks_late=True)
|
||||
def run_migration(self, run_id: int, kind: str, params: dict) -> dict:
|
||||
"""FC-5: dispatch a migration kind. Updates MigrationRun row as it goes."""
|
||||
return asyncio.run(_run_async(run_id, kind, params))
|
||||
@@ -12,13 +12,12 @@ from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
|
||||
|
||||
from ..celery_app import celery
|
||||
from ..config import get_config
|
||||
from ..models import DownloadEvent, ImportBatch, ImportSettings, ImportTask
|
||||
from ..services.archive_extractor import is_archive
|
||||
from ..services.scheduler_service import select_due_sources
|
||||
from ..services.scheduler_service import record_tick, select_due_sources
|
||||
from ._async_session import async_session_factory
|
||||
from ._sync_engine import sync_session_factory as _sync_session_factory
|
||||
|
||||
|
||||
@@ -45,9 +44,7 @@ def scan_directory(self, triggered_by: str = "manual",
|
||||
batch id."""
|
||||
SessionLocal = _sync_session_factory()
|
||||
with SessionLocal() as session:
|
||||
settings = session.execute(
|
||||
select(ImportSettings).where(ImportSettings.id == 1)
|
||||
).scalar_one()
|
||||
settings = ImportSettings.load_sync(session)
|
||||
import_root = Path(settings.import_scan_path)
|
||||
|
||||
batch = ImportBatch(
|
||||
@@ -141,16 +138,12 @@ def scan_directory(self, triggered_by: str = "manual",
|
||||
# --- FC-3d: periodic source-check tick ------------------------------------
|
||||
|
||||
|
||||
def _async_session_factory():
|
||||
cfg = get_config()
|
||||
engine = create_async_engine(cfg.database_url, future=True, pool_pre_ping=True)
|
||||
return async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False), engine
|
||||
|
||||
|
||||
async def _tick_due_sources_async() -> dict:
|
||||
factory, engine = _async_session_factory()
|
||||
factory, engine = async_session_factory()
|
||||
try:
|
||||
async with factory() as session:
|
||||
# Prove the scheduler is alive even on empty ticks (UI reads this).
|
||||
await record_tick(session)
|
||||
due = await select_due_sources(session)
|
||||
if not due:
|
||||
return {
|
||||
|
||||
@@ -20,14 +20,32 @@ IMAGES_ROOT = Path("/images")
|
||||
THUMB_MAGIC_JPEG = b"\xff\xd8\xff"
|
||||
THUMB_MAGIC_PNG = b"\x89PNG\r\n\x1a\n"
|
||||
|
||||
# Minimum file size for a thumbnail to count as valid. Anything smaller
|
||||
# is almost certainly truncated/corrupt — a legitimate 400×400 JPEG@85
|
||||
# bottoms out around 2KB even on a solid-color image; 400×400 PNG starts
|
||||
# around 1KB. 256 bytes is well below any real thumbnail and well above
|
||||
# header-only corrupt files (~8-12 bytes). Operator-flagged 2026-06-01:
|
||||
# header-only corrupt files were silently passing the magic-byte check
|
||||
# and backfill counted them as "ok" — so broken-image tiles in the UI
|
||||
# never got regenerated even after running backfill.
|
||||
MIN_THUMB_BYTES = 256
|
||||
|
||||
|
||||
def _thumb_is_valid(path: Path) -> bool:
|
||||
"""Return True iff `path` exists and starts with a JPEG or PNG magic header.
|
||||
"""Return True iff `path` exists, starts with a JPEG or PNG magic
|
||||
header, AND is at least MIN_THUMB_BYTES on disk.
|
||||
|
||||
The on-disk thumbnail format is set by services/thumbnailer.py — JPEG for
|
||||
opaque sources, PNG for alpha sources. Anything else (missing file, OSError,
|
||||
truncated, wrong magic) is invalid.
|
||||
The on-disk thumbnail format is set by services/thumbnailer.py — JPEG
|
||||
for opaque sources, PNG for alpha sources. Anything else (missing
|
||||
file, OSError, truncated below the size floor, wrong magic) is
|
||||
invalid and gets re-enqueued.
|
||||
"""
|
||||
try:
|
||||
size = path.stat().st_size
|
||||
except OSError:
|
||||
return False
|
||||
if size < MIN_THUMB_BYTES:
|
||||
return False
|
||||
try:
|
||||
with path.open("rb") as f:
|
||||
head = f.read(12)
|
||||
@@ -42,6 +60,59 @@ def _thumb_is_valid(path: Path) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
def _run_backfill_scan() -> dict:
|
||||
"""Synchronous scan logic shared by the Celery task and the API
|
||||
endpoint. Returns {enqueued, ok, regenerated, scanned}.
|
||||
|
||||
Operator-flagged 2026-06-01: the original task was fire-and-forget,
|
||||
so the admin UI couldn't show what backfill actually found —
|
||||
operator saw \"Enqueued.\" with no counts and assumed nothing was
|
||||
happening. Now the API runs this synchronously and returns the
|
||||
real numbers; the periodic Celery task wraps it too."""
|
||||
from sqlalchemy import select, update
|
||||
|
||||
SessionLocal = _sync_session_factory()
|
||||
enqueued = 0
|
||||
ok = 0
|
||||
regenerated = 0
|
||||
scanned = 0
|
||||
last_id = 0
|
||||
with SessionLocal() as session:
|
||||
while True:
|
||||
rows = session.execute(
|
||||
select(ImageRecord.id, ImageRecord.thumbnail_path)
|
||||
.where(ImageRecord.id > last_id)
|
||||
.order_by(ImageRecord.id.asc())
|
||||
.limit(500)
|
||||
).all()
|
||||
if not rows:
|
||||
break
|
||||
scanned += len(rows)
|
||||
for image_id, thumb_path in rows:
|
||||
if thumb_path is None:
|
||||
generate_thumbnail.delay(image_id)
|
||||
enqueued += 1
|
||||
elif _thumb_is_valid(Path(thumb_path)):
|
||||
ok += 1
|
||||
else:
|
||||
session.execute(
|
||||
update(ImageRecord)
|
||||
.where(ImageRecord.id == image_id)
|
||||
.values(thumbnail_path=None)
|
||||
)
|
||||
generate_thumbnail.delay(image_id)
|
||||
enqueued += 1
|
||||
regenerated += 1
|
||||
session.commit()
|
||||
last_id = rows[-1][0]
|
||||
return {
|
||||
"scanned": scanned,
|
||||
"enqueued": enqueued,
|
||||
"ok": ok,
|
||||
"regenerated": regenerated,
|
||||
}
|
||||
|
||||
|
||||
@celery.task(
|
||||
name="backend.app.tasks.thumbnail.generate_thumbnail",
|
||||
bind=True,
|
||||
@@ -84,48 +155,15 @@ def backfill_thumbnails(self) -> dict:
|
||||
"""Scan ImageRecord and enqueue generate_thumbnail for rows whose
|
||||
thumbnail is missing, gone from disk, or has wrong magic bytes.
|
||||
|
||||
Keyset paginates by id ASC, page size 500. NULLs out thumbnail_path for
|
||||
rows that point at a missing or corrupt file before enqueueing — keeps
|
||||
the DB self-consistent on partial runs and makes re-runs safe.
|
||||
Keyset paginates by id ASC, page size 500. NULLs out thumbnail_path
|
||||
for rows that point at a missing or corrupt file before enqueueing —
|
||||
keeps the DB self-consistent on partial runs and makes re-runs safe.
|
||||
|
||||
Returns {"enqueued": N, "ok": M, "regenerated": K} where:
|
||||
- enqueued = total generate_thumbnail.delay() calls
|
||||
- ok = rows whose existing thumbnail file is valid (skipped)
|
||||
- regenerated = subset of enqueued that had a non-NULL thumbnail_path
|
||||
cleared (i.e. missing + corrupt)
|
||||
Returns {scanned, enqueued, ok, regenerated} where:
|
||||
- scanned = total rows examined
|
||||
- enqueued = total generate_thumbnail.delay() calls
|
||||
- ok = rows whose existing thumbnail file is valid (skipped)
|
||||
- regenerated = subset of enqueued that had a non-NULL
|
||||
thumbnail_path cleared (i.e. missing + corrupt)
|
||||
"""
|
||||
from sqlalchemy import select, update
|
||||
|
||||
SessionLocal = _sync_session_factory()
|
||||
enqueued = 0
|
||||
ok = 0
|
||||
regenerated = 0
|
||||
last_id = 0
|
||||
with SessionLocal() as session:
|
||||
while True:
|
||||
rows = session.execute(
|
||||
select(ImageRecord.id, ImageRecord.thumbnail_path)
|
||||
.where(ImageRecord.id > last_id)
|
||||
.order_by(ImageRecord.id.asc())
|
||||
.limit(500)
|
||||
).all()
|
||||
if not rows:
|
||||
break
|
||||
for image_id, thumb_path in rows:
|
||||
if thumb_path is None:
|
||||
generate_thumbnail.delay(image_id)
|
||||
enqueued += 1
|
||||
elif _thumb_is_valid(Path(thumb_path)):
|
||||
ok += 1
|
||||
else:
|
||||
session.execute(
|
||||
update(ImageRecord)
|
||||
.where(ImageRecord.id == image_id)
|
||||
.values(thumbnail_path=None)
|
||||
)
|
||||
generate_thumbnail.delay(image_id)
|
||||
enqueued += 1
|
||||
regenerated += 1
|
||||
session.commit()
|
||||
last_id = rows[-1][0]
|
||||
return {"enqueued": enqueued, "ok": ok, "regenerated": regenerated}
|
||||
return _run_backfill_scan()
|
||||
|
||||
@@ -0,0 +1,33 @@
|
||||
"""Subprocess entrypoint for safe_probe.probe_archive — see safe_probe.py.
|
||||
|
||||
probe_archive spawns this via subprocess (not multiprocessing.Process)
|
||||
because Celery's prefork worker pool runs tasks in DAEMON processes and
|
||||
Python's multiprocessing forbids daemon processes from spawning children
|
||||
("AssertionError: daemonic processes are not allowed to have children",
|
||||
operator-flagged 2026-05-30 — every archive import failed at task
|
||||
startup). subprocess has no such restriction; we still get crash-
|
||||
isolation because a probe segfault/OOM exits non-zero rather than
|
||||
killing the worker.
|
||||
|
||||
Prints a single JSON line on stdout: {"status": "ok"|"error",
|
||||
"detail": "..."?}. Exit code 0 for clean outcomes; non-zero exit
|
||||
(signal / OOM-kill / unhandled exception) is the poison-pill signature
|
||||
the parent maps to ProbeResult(crashed=True).
|
||||
"""
|
||||
import json
|
||||
import sys
|
||||
|
||||
from .safe_probe import _run_probe
|
||||
|
||||
|
||||
def main() -> int:
|
||||
if len(sys.argv) != 2:
|
||||
print(json.dumps({"status": "error", "detail": "usage: <path>"}))
|
||||
return 2
|
||||
status, detail = _run_probe(sys.argv[1])
|
||||
print(json.dumps({"status": status, "detail": detail}))
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -28,8 +28,8 @@ Operator-requested 2026-05-28 (Layer 3).
|
||||
"""
|
||||
|
||||
import json
|
||||
import multiprocessing as mp
|
||||
import subprocess
|
||||
import sys
|
||||
from dataclasses import dataclass
|
||||
from pathlib import Path
|
||||
|
||||
@@ -40,6 +40,13 @@ ARCHIVE_PROBE_TIMEOUT_SECONDS = 120
|
||||
# art-pack archives while stopping a few-KB zip that expands to TB).
|
||||
MAX_ARCHIVE_UNCOMPRESSED_BYTES = 4 * 1024 * 1024 * 1024
|
||||
|
||||
# Repo root for the subprocess cwd so `python -m backend.app.utils.*`
|
||||
# resolves regardless of where Celery / pytest started. backend/app/utils
|
||||
# = parents[0]; backend/app = parents[1]; backend = parents[2]; repo root
|
||||
# = parents[3].
|
||||
_REPO_ROOT = Path(__file__).resolve().parents[3]
|
||||
_PROBE_RUNNER_MODULE = "backend.app.utils._archive_probe_runner"
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProbeResult:
|
||||
@@ -91,54 +98,68 @@ def probe_video(path: Path, *, timeout: float = VIDEO_PROBE_TIMEOUT_SECONDS) ->
|
||||
|
||||
|
||||
def probe_archive(path: Path, *, timeout: float = ARCHIVE_PROBE_TIMEOUT_SECONDS) -> ProbeResult:
|
||||
"""Bomb-size guard + isolated integrity test for an archive."""
|
||||
ctx = mp.get_context("spawn")
|
||||
q = ctx.Queue()
|
||||
proc = ctx.Process(target=_archive_probe_target, args=(str(path), q))
|
||||
proc.start()
|
||||
proc.join(timeout)
|
||||
if proc.is_alive():
|
||||
proc.terminate()
|
||||
proc.join(5)
|
||||
"""Bomb-size guard + isolated integrity test for an archive.
|
||||
|
||||
Runs via subprocess (not multiprocessing.Process) because Celery's
|
||||
prefork worker pool is daemon-mode and Python's multiprocessing
|
||||
forbids daemon processes from spawning children ("AssertionError:
|
||||
daemonic processes are not allowed to have children"). subprocess
|
||||
has no such restriction and still gives the crash isolation: a probe
|
||||
segfault/OOM exits non-zero rather than killing the worker.
|
||||
"""
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-m", _PROBE_RUNNER_MODULE, str(path)],
|
||||
capture_output=True, text=True, timeout=timeout,
|
||||
cwd=str(_REPO_ROOT),
|
||||
)
|
||||
except subprocess.TimeoutExpired:
|
||||
return ProbeResult(ok=False, crashed=True, reason="archive probe timed out")
|
||||
if proc.exitcode != 0:
|
||||
# Negative exitcode = killed by signal (segfault); positive =
|
||||
# the child os._exit'd or was OOM-killed. Either way the file
|
||||
# hard-crashed the probe — the poison-pill signature.
|
||||
if result.returncode != 0:
|
||||
# Negative = killed by signal (segfault); positive = unhandled
|
||||
# exception or OOM-kill. Either way: poison-pill signature.
|
||||
return ProbeResult(
|
||||
ok=False, crashed=True,
|
||||
reason=f"archive probe crashed (exit {proc.exitcode})",
|
||||
reason=f"archive probe crashed (exit {result.returncode})",
|
||||
)
|
||||
last_line = result.stdout.strip().splitlines()[-1:] or [""]
|
||||
try:
|
||||
outcome = q.get(timeout=5)
|
||||
except Exception: # noqa: BLE001 — empty queue / broken pipe
|
||||
return ProbeResult(ok=False, crashed=True, reason="archive probe produced no result")
|
||||
status, detail = outcome
|
||||
if status == "ok":
|
||||
outcome = json.loads(last_line[0])
|
||||
except json.JSONDecodeError as exc:
|
||||
return ProbeResult(
|
||||
ok=False, crashed=True,
|
||||
reason=f"archive probe produced no parseable result: {exc}",
|
||||
)
|
||||
if outcome.get("status") == "ok":
|
||||
return ProbeResult(ok=True)
|
||||
return ProbeResult(ok=False, crashed=False, reason=detail)
|
||||
return ProbeResult(
|
||||
ok=False, crashed=False,
|
||||
reason=outcome.get("detail") or "archive probe rejected",
|
||||
)
|
||||
|
||||
|
||||
def _archive_probe_target(path_str: str, q) -> None:
|
||||
"""Runs in the spawned child. Reads member sizes (bomb guard) then
|
||||
runs the format's integrity test. Puts ('ok', None) or
|
||||
('error', reason). A crash/OOM here never reaches the queue — the
|
||||
parent reads the non-zero exit code instead."""
|
||||
def _run_probe(path_str: str) -> tuple[str, str | None]:
|
||||
"""Pure-Python body of the archive probe — bomb-guard + integrity test.
|
||||
|
||||
Returns ('ok', None) or ('error', reason). Caught exceptions become
|
||||
clean 'error' rejections; uncaught crashes in the subprocess become
|
||||
non-zero exit codes (poison-pill signature) handled by probe_archive.
|
||||
|
||||
Exposed at the module level so the subprocess runner and tests both
|
||||
call the same code path.
|
||||
"""
|
||||
path = Path(path_str)
|
||||
ext = path.suffix.lower()
|
||||
try:
|
||||
total, test_bad = _inspect_archive(path, ext)
|
||||
except Exception as exc: # noqa: BLE001 — clean rejection
|
||||
q.put(("error", f"{type(exc).__name__}: {exc}"))
|
||||
return
|
||||
return ("error", f"{type(exc).__name__}: {exc}")
|
||||
if total is not None and total > MAX_ARCHIVE_UNCOMPRESSED_BYTES:
|
||||
gib = total / (1024 ** 3)
|
||||
q.put(("error", f"uncompressed size {gib:.1f} GiB exceeds the bomb-guard cap"))
|
||||
return
|
||||
return ("error", f"uncompressed size {gib:.1f} GiB exceeds the bomb-guard cap")
|
||||
if test_bad is not None:
|
||||
q.put(("error", f"integrity test failed at member {test_bad!r}"))
|
||||
return
|
||||
q.put(("ok", None))
|
||||
return ("error", f"integrity test failed at member {test_bad!r}")
|
||||
return ("ok", None)
|
||||
|
||||
|
||||
def _inspect_archive(path: Path, ext: str):
|
||||
|
||||
@@ -259,6 +259,29 @@ browser.runtime.onMessage.addListener(async (msg) => {
|
||||
return { error: e.message };
|
||||
}
|
||||
|
||||
case 'PROBE_SOURCE':
|
||||
try {
|
||||
return await api.probeSource(msg.url);
|
||||
} catch (e) {
|
||||
return { error: e.message };
|
||||
}
|
||||
|
||||
case 'OPEN_ARTIST_PAGE': {
|
||||
// apiUrl is configured with the /api suffix (see
|
||||
// options/options.html placeholder); the SPA artist route is
|
||||
// /artist/:slug, served from the same origin. Strip /api so the
|
||||
// browser-level URL hits the Vue router, not the JSON API.
|
||||
const base = (api.baseUrl || '').replace(/\/+$/, '').replace(/\/api$/, '');
|
||||
const slug = encodeURIComponent(msg.slug || '');
|
||||
if (!base || !slug) return { error: 'apiUrl or slug missing' };
|
||||
try {
|
||||
await browser.tabs.create({ url: `${base}/artist/${slug}` });
|
||||
return { success: true };
|
||||
} catch (e) {
|
||||
return { error: e.message };
|
||||
}
|
||||
}
|
||||
|
||||
default:
|
||||
return { error: `Unknown message type: ${msg.type}` };
|
||||
}
|
||||
|
||||
@@ -5,11 +5,26 @@
|
||||
background: rgb(20, 23, 26); color: rgb(244, 186, 122);
|
||||
font: 500 14px/1.2 system-ui, sans-serif;
|
||||
box-shadow: 0 4px 16px rgba(0, 0, 0, 0.4); cursor: pointer;
|
||||
transition: transform 100ms ease;
|
||||
transition: transform 100ms ease, background 150ms ease, color 150ms ease;
|
||||
}
|
||||
.fc-add-source-btn:hover { transform: translateY(-1px); }
|
||||
.fc-add-source-btn:disabled { opacity: 0.6; cursor: wait; }
|
||||
|
||||
/* state colors map to the FC palette: parchment-on-slate base,
|
||||
accent-orange for new, sage for already-subscribed, amber-warning for
|
||||
artist-exists-but-source-missing. All readable on the dark base. */
|
||||
.fc-add-source-btn--new {
|
||||
background: rgb(20, 23, 26); color: rgb(244, 186, 122);
|
||||
}
|
||||
.fc-add-source-btn--artist-match {
|
||||
background: rgb(28, 23, 16); color: rgb(255, 200, 120);
|
||||
border: 1px solid rgb(180, 130, 60);
|
||||
}
|
||||
.fc-add-source-btn--source-match {
|
||||
background: rgb(18, 28, 20); color: rgb(140, 220, 160);
|
||||
border: 1px solid rgb(80, 160, 100);
|
||||
}
|
||||
|
||||
.fc-toast {
|
||||
all: revert;
|
||||
position: fixed; bottom: 84px; right: 24px; z-index: 2147483647;
|
||||
|
||||
@@ -2,6 +2,10 @@
|
||||
if (window.__fc_addsource_injected) return;
|
||||
window.__fc_addsource_injected = true;
|
||||
|
||||
// Cached probe result for the current URL so click-handlers know which
|
||||
// action to dispatch without round-tripping again.
|
||||
let currentProbe = null;
|
||||
|
||||
evaluate();
|
||||
|
||||
const reEval = () => evaluate();
|
||||
@@ -9,38 +13,116 @@
|
||||
const origPush = history.pushState;
|
||||
history.pushState = function () { origPush.apply(this, arguments); reEval(); };
|
||||
|
||||
function evaluate() {
|
||||
const platform = getPlatformFromUrl(window.location.href);
|
||||
const onArtist = platform && isArtistPage(window.location.href, platform);
|
||||
let btn = document.getElementById('fc-add-source-btn');
|
||||
if (onArtist && !btn) injectButton();
|
||||
else if (!onArtist && btn) btn.remove();
|
||||
async function evaluate() {
|
||||
const url = window.location.href;
|
||||
const platform = getPlatformFromUrl(url);
|
||||
const onArtist = platform && isArtistPage(url, platform);
|
||||
const btn = document.getElementById('fc-add-source-btn');
|
||||
if (!onArtist) {
|
||||
if (btn) btn.remove();
|
||||
currentProbe = null;
|
||||
return;
|
||||
}
|
||||
// On artist pages, ask the backend what state the URL is in BEFORE
|
||||
// injecting the button — so the chip can render the right state on
|
||||
// first paint instead of flashing the generic "Add" copy and
|
||||
// updating afterwards.
|
||||
let probe;
|
||||
try {
|
||||
probe = await browser.runtime.sendMessage({ type: 'PROBE_SOURCE', url });
|
||||
} catch (e) {
|
||||
probe = { error: e?.message || 'probe failed' };
|
||||
}
|
||||
currentProbe = probe;
|
||||
if (probe?.state === 'unknown_platform') {
|
||||
if (btn) btn.remove();
|
||||
return;
|
||||
}
|
||||
renderButton(probe);
|
||||
}
|
||||
|
||||
function injectButton() {
|
||||
const btn = document.createElement('button');
|
||||
btn.id = 'fc-add-source-btn';
|
||||
function renderButton(probe) {
|
||||
let btn = document.getElementById('fc-add-source-btn');
|
||||
if (!btn) {
|
||||
btn = document.createElement('button');
|
||||
btn.id = 'fc-add-source-btn';
|
||||
btn.addEventListener('click', onClick);
|
||||
document.body.appendChild(btn);
|
||||
}
|
||||
// Reset state classes so re-renders (SPA navigation) don't stack.
|
||||
btn.className = 'fc-add-source-btn';
|
||||
btn.textContent = '+ Add to FabledCurator';
|
||||
btn.addEventListener('click', onClick);
|
||||
document.body.appendChild(btn);
|
||||
btn.classList.add(`fc-add-source-btn--${stateModifier(probe)}`);
|
||||
btn.textContent = labelFor(probe);
|
||||
btn.disabled = false;
|
||||
}
|
||||
|
||||
function stateModifier(probe) {
|
||||
if (!probe || probe.error) return 'new';
|
||||
return ({
|
||||
source_match: 'source-match',
|
||||
artist_match: 'artist-match',
|
||||
new: 'new',
|
||||
})[probe.state] || 'new';
|
||||
}
|
||||
|
||||
function labelFor(probe) {
|
||||
if (!probe || probe.error) return '+ Add to FabledCurator';
|
||||
const platformName = platformDisplayName(probe.platform);
|
||||
const artistName = probe.artist?.name;
|
||||
switch (probe.state) {
|
||||
case 'source_match':
|
||||
return `✓ In FabledCurator · ${platformName}`;
|
||||
case 'artist_match':
|
||||
return `+ Add ${platformName} source to ${artistName || 'artist'}`;
|
||||
case 'new':
|
||||
default:
|
||||
return '+ Add to FabledCurator';
|
||||
}
|
||||
}
|
||||
|
||||
function platformDisplayName(key) {
|
||||
return PLATFORMS[key]?.name || key || '';
|
||||
}
|
||||
|
||||
async function onClick() {
|
||||
const btn = document.getElementById('fc-add-source-btn');
|
||||
if (!btn) return;
|
||||
btn.disabled = true;
|
||||
const original = btn.textContent;
|
||||
const probe = currentProbe;
|
||||
|
||||
if (probe?.state === 'source_match') {
|
||||
btn.textContent = 'Opening…';
|
||||
try {
|
||||
const r = await browser.runtime.sendMessage({
|
||||
type: 'OPEN_ARTIST_PAGE',
|
||||
slug: probe.artist?.slug,
|
||||
});
|
||||
if (r?.error) showToast(`Error: ${r.error}`, 'error');
|
||||
} catch (e) {
|
||||
showToast(`Error: ${e.message}`, 'error');
|
||||
} finally {
|
||||
btn.disabled = false;
|
||||
btn.textContent = original;
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
btn.textContent = 'Adding…';
|
||||
try {
|
||||
const r = await browser.runtime.sendMessage({
|
||||
type: 'ADD_AS_SOURCE',
|
||||
url: window.location.href,
|
||||
});
|
||||
if (r.error) {
|
||||
if (r?.error) {
|
||||
showToast(`Error: ${r.error}`, 'error');
|
||||
} else {
|
||||
const verb = r.created_source ? 'Added' : 'Already a source for';
|
||||
showToast(`${verb} ${r.artist?.name || 'artist'} (${r.source?.platform || ''})`, 'success');
|
||||
// Re-probe so the chip flips green without waiting for the next
|
||||
// navigation.
|
||||
evaluate();
|
||||
return;
|
||||
}
|
||||
} catch (e) {
|
||||
showToast(`Error: ${e.message}`, 'error');
|
||||
|
||||
@@ -83,6 +83,12 @@ class FabledCuratorAPI {
|
||||
quickAddSource(url) {
|
||||
return this.request('POST', '/extension/quick-add-source', { url });
|
||||
}
|
||||
probeSource(url) {
|
||||
// Read-only existence check. Drives the content-script chip's
|
||||
// color/copy BEFORE the operator clicks Add.
|
||||
const qs = new URLSearchParams({ url }).toString();
|
||||
return this.request('GET', `/extension/probe?${qs}`);
|
||||
}
|
||||
|
||||
// Connection test = the cheapest read with auth.
|
||||
testConnection() {
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
{
|
||||
"manifest_version": 3,
|
||||
"name": "FabledCurator",
|
||||
"version": "1.0.5",
|
||||
"version": "1.0.6",
|
||||
"description": "Export cookies from supported platforms to FabledCurator and add creators as sources in one click.",
|
||||
|
||||
"browser_specific_settings": {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"name": "fabledcurator-extension",
|
||||
"version": "1.0.5",
|
||||
"version": "1.0.6",
|
||||
"private": true,
|
||||
"description": "Firefox extension for FabledCurator",
|
||||
"scripts": {
|
||||
|
||||
@@ -26,6 +26,8 @@
|
||||
"vue-tsc": "^2.0.0",
|
||||
"vite-plugin-vuetify": "^2.0.0",
|
||||
"sass": "^1.71.0",
|
||||
"vitest": "^2.1.0"
|
||||
"vitest": "^2.1.0",
|
||||
"@vue/test-utils": "^2.4.0",
|
||||
"happy-dom": "^15.0.0"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -0,0 +1,146 @@
|
||||
<template>
|
||||
<v-menu location="bottom start" :close-on-content-click="false">
|
||||
<template #activator="{ props }">
|
||||
<button
|
||||
v-bind="props" type="button"
|
||||
class="fc-pulse" :class="`fc-pulse--${schedHealth}`"
|
||||
:aria-label="`pipeline: ${running} running, ${queued} queued, ${failing} failing`"
|
||||
>
|
||||
<span class="fc-pulse__dot" />
|
||||
<span v-if="running" class="fc-pulse__stat">
|
||||
<v-icon size="13">mdi-progress-download</v-icon>{{ running }}
|
||||
</span>
|
||||
<span v-if="queued" class="fc-pulse__stat">
|
||||
<v-icon size="13">mdi-tray-full</v-icon>{{ queued }}
|
||||
</span>
|
||||
<span v-if="failing" class="fc-pulse__stat fc-pulse__stat--err">
|
||||
<v-icon size="13">mdi-alert-circle</v-icon>{{ failing }}
|
||||
</span>
|
||||
<span v-if="!running && !queued && !failing" class="fc-pulse__idle">idle</span>
|
||||
</button>
|
||||
</template>
|
||||
|
||||
<v-card min-width="300" class="fc-pulse__panel pa-3">
|
||||
<div class="fc-pulse__row">
|
||||
<span class="fc-pulse__rowdot" :class="`fc-pulse--${schedHealth}`" />
|
||||
<strong>Scheduler</strong>
|
||||
<v-spacer />
|
||||
<span class="fc-pulse__muted">{{ schedLabel }}</span>
|
||||
</div>
|
||||
|
||||
<div class="fc-pulse__sec">
|
||||
<div class="fc-pulse__sechead">Queues</div>
|
||||
<div v-if="busyQueues.length === 0" class="fc-pulse__muted">All idle</div>
|
||||
<div v-for="q in busyQueues" :key="q.name" class="fc-pulse__qrow">
|
||||
<span>{{ q.name }}</span><v-spacer /><strong>{{ q.depth }}</strong>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="fc-pulse__sec fc-pulse__grid">
|
||||
<div><span class="fc-pulse__muted">Running</span><div class="fc-pulse__big">{{ running }}</div></div>
|
||||
<div><span class="fc-pulse__muted">Queued</span><div class="fc-pulse__big">{{ queued }}</div></div>
|
||||
<div>
|
||||
<span class="fc-pulse__muted">Failures 24h</span>
|
||||
<div class="fc-pulse__big" :class="{ 'fc-pulse__big--err': failing }">{{ failing }}</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<RouterLink
|
||||
class="fc-pulse__link"
|
||||
:to="{ path: '/subscriptions', query: { tab: 'downloads' } }"
|
||||
>Open downloads →</RouterLink>
|
||||
</v-card>
|
||||
</v-menu>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { computed, onMounted, onUnmounted } from 'vue'
|
||||
|
||||
import { useSystemActivityStore } from '../stores/systemActivity.js'
|
||||
import { formatRelative } from '../utils/date.js'
|
||||
|
||||
const store = useSystemActivityStore()
|
||||
|
||||
// Beat ticks every 60s; flag the scheduler stale past ~3 min.
|
||||
const STALE_MS = 180_000
|
||||
const summary = computed(() => store.summary)
|
||||
const running = computed(() => summary.value?.running ?? 0)
|
||||
const queued = computed(() => summary.value?.queued_total ?? 0)
|
||||
const failing = computed(() => summary.value?.failing ?? 0)
|
||||
|
||||
const schedHealth = computed(() => {
|
||||
const t = summary.value?.scheduler?.last_tick_at
|
||||
if (!t) return 'unknown'
|
||||
return (Date.now() - new Date(t).getTime()) <= STALE_MS ? 'ok' : 'stale'
|
||||
})
|
||||
const schedLabel = computed(() => {
|
||||
const s = summary.value?.scheduler
|
||||
if (!s) return '—'
|
||||
const ran = formatRelative(s.last_tick_at, { nullText: 'never' })
|
||||
if (s.due_now > 0) return `ran ${ran} · ${s.due_now} due`
|
||||
return `ran ${ran}`
|
||||
})
|
||||
const busyQueues = computed(() => {
|
||||
const q = summary.value?.queues || {}
|
||||
return Object.entries(q)
|
||||
.filter(([, depth]) => typeof depth === 'number' && depth > 0)
|
||||
.map(([name, depth]) => ({ name, depth }))
|
||||
})
|
||||
|
||||
const POLL_MS = 8000
|
||||
let timer = null
|
||||
onMounted(() => {
|
||||
store.loadSummary()
|
||||
timer = setInterval(() => {
|
||||
if (!document.hidden) store.loadSummary()
|
||||
}, POLL_MS)
|
||||
})
|
||||
onUnmounted(() => { if (timer) clearInterval(timer) })
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.fc-pulse {
|
||||
display: inline-flex; align-items: center; gap: 6px;
|
||||
padding: 3px 8px; border-radius: 999px;
|
||||
background: rgb(var(--v-theme-on-surface) / 0.08);
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
font-size: 0.78rem; font-variant-numeric: tabular-nums;
|
||||
cursor: pointer; border: 0;
|
||||
}
|
||||
.fc-pulse:hover { background: rgb(var(--v-theme-on-surface) / 0.16); }
|
||||
.fc-pulse__dot {
|
||||
width: 8px; height: 8px; border-radius: 50%; flex: 0 0 auto;
|
||||
background: rgb(var(--v-theme-on-surface-variant));
|
||||
}
|
||||
.fc-pulse--ok .fc-pulse__dot,
|
||||
.fc-pulse--ok.fc-pulse__rowdot { background: rgb(var(--v-theme-success)); }
|
||||
.fc-pulse--stale .fc-pulse__dot,
|
||||
.fc-pulse--stale.fc-pulse__rowdot { background: rgb(var(--v-theme-error)); }
|
||||
.fc-pulse__stat { display: inline-flex; align-items: center; gap: 2px; }
|
||||
.fc-pulse__stat--err { color: rgb(var(--v-theme-error)); }
|
||||
.fc-pulse__idle {
|
||||
text-transform: uppercase; letter-spacing: 0.06em;
|
||||
color: rgb(var(--v-theme-on-surface-variant)); font-size: 0.68rem;
|
||||
}
|
||||
|
||||
.fc-pulse__panel { background: rgb(var(--v-theme-surface)); }
|
||||
.fc-pulse__row { display: flex; align-items: center; gap: 8px; }
|
||||
.fc-pulse__rowdot {
|
||||
width: 9px; height: 9px; border-radius: 50%;
|
||||
background: rgb(var(--v-theme-on-surface-variant));
|
||||
}
|
||||
.fc-pulse__muted { color: rgb(var(--v-theme-on-surface-variant)); font-size: 0.8rem; }
|
||||
.fc-pulse__sec { margin-top: 12px; }
|
||||
.fc-pulse__sechead {
|
||||
font-size: 0.72rem; text-transform: uppercase; letter-spacing: 0.05em;
|
||||
color: rgb(var(--v-theme-on-surface-variant)); margin-bottom: 4px;
|
||||
}
|
||||
.fc-pulse__qrow { display: flex; align-items: center; font-size: 0.85rem; padding: 2px 0; }
|
||||
.fc-pulse__grid { display: flex; gap: 16px; }
|
||||
.fc-pulse__big { font-size: 1.3rem; font-weight: 700; font-variant-numeric: tabular-nums; }
|
||||
.fc-pulse__big--err { color: rgb(var(--v-theme-error)); }
|
||||
.fc-pulse__link {
|
||||
display: inline-block; margin-top: 14px;
|
||||
color: rgb(var(--v-theme-accent)); text-decoration: none; font-size: 0.85rem;
|
||||
}
|
||||
</style>
|
||||
@@ -8,6 +8,7 @@
|
||||
<span class="fc-health" :title="health.label">
|
||||
<v-icon size="x-small" :color="health.color">{{ health.icon }}</v-icon>
|
||||
</span>
|
||||
<PipelineStatusChip />
|
||||
</div>
|
||||
|
||||
<nav class="fc-links">
|
||||
@@ -29,6 +30,7 @@
|
||||
import { computed, onMounted } from 'vue'
|
||||
import router, { FRONT_DOOR } from '../router.js'
|
||||
import { useSystemStore } from '../stores/system.js'
|
||||
import PipelineStatusChip from './PipelineStatusChip.vue'
|
||||
|
||||
const system = useSystemStore()
|
||||
onMounted(() => system.refreshHealth())
|
||||
|
||||
@@ -35,6 +35,7 @@
|
||||
|
||||
<script setup>
|
||||
import { computed } from 'vue'
|
||||
import { formatLocalDate } from '../../utils/date.js'
|
||||
|
||||
const props = defineProps({
|
||||
name: { type: String, required: true },
|
||||
@@ -52,7 +53,7 @@ const stats = computed(() => {
|
||||
parts.push(`${props.imageCount} image${props.imageCount === 1 ? '' : 's'}`)
|
||||
}
|
||||
if (props.lastAdded) {
|
||||
parts.push(`last added ${props.lastAdded.slice(0, 10)}`)
|
||||
parts.push(`last added ${formatLocalDate(props.lastAdded)}`)
|
||||
}
|
||||
return parts.join(' · ')
|
||||
})
|
||||
|
||||
@@ -28,10 +28,11 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { onMounted, onUnmounted, ref, watch } from 'vue'
|
||||
import { onMounted, ref, watch } from 'vue'
|
||||
import { RouterLink } from 'vue-router'
|
||||
|
||||
import { usePostsStore } from '../../stores/posts.js'
|
||||
import { useInfiniteScroll } from '../../composables/useInfiniteScroll.js'
|
||||
import PostCard from '../posts/PostCard.vue'
|
||||
|
||||
const props = defineProps({
|
||||
@@ -42,7 +43,6 @@ defineEmits(['switch-tab'])
|
||||
|
||||
const store = usePostsStore()
|
||||
const sentinel = ref(null)
|
||||
let observer = null
|
||||
|
||||
async function reload () {
|
||||
await store.loadInitial({ artist_id: props.artistId, platform: null })
|
||||
@@ -50,19 +50,9 @@ async function reload () {
|
||||
|
||||
watch(() => props.artistId, reload)
|
||||
|
||||
onMounted(async () => {
|
||||
await reload()
|
||||
observer = new IntersectionObserver((entries) => {
|
||||
if (entries.some(e => e.isIntersecting)) {
|
||||
store.loadMore()
|
||||
}
|
||||
}, { rootMargin: '400px 0px' })
|
||||
if (sentinel.value) observer.observe(sentinel.value)
|
||||
})
|
||||
useInfiniteScroll(sentinel, () => store.loadMore(), { rootMargin: '400px 0px' })
|
||||
|
||||
onUnmounted(() => {
|
||||
if (observer) observer.disconnect()
|
||||
})
|
||||
onMounted(reload)
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
|
||||
@@ -62,6 +62,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { onMounted, ref } from 'vue'
|
||||
|
||||
import DestructiveConfirmModal from '../modal/DestructiveConfirmModal.vue'
|
||||
@@ -94,7 +95,7 @@ async function onPreview() {
|
||||
try {
|
||||
preview.value = await store.previewMinDim(minW.value, minH.value)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Preview failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Preview failed: ${e.message}`, type: 'error' })
|
||||
} finally {
|
||||
busy.value = false
|
||||
}
|
||||
@@ -108,12 +109,12 @@ function onDeleteClick() {
|
||||
async function onConfirmedDelete(token) {
|
||||
try {
|
||||
const res = await store.deleteMinDim(minW.value, minH.value, token)
|
||||
window.__fcToast?.({
|
||||
toast({
|
||||
text: `Deleted ${res.deleted} image(s)`, type: 'success',
|
||||
})
|
||||
preview.value = null
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Delete failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Delete failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
@@ -93,6 +93,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { onMounted, onUnmounted, ref } from 'vue'
|
||||
|
||||
import DestructiveConfirmModal from '../modal/DestructiveConfirmModal.vue'
|
||||
@@ -124,7 +125,7 @@ function startPoll(id) {
|
||||
if (fresh.status !== 'running') stopPoll()
|
||||
} catch (e) {
|
||||
stopPoll()
|
||||
window.__fcToast?.({ text: `Audit poll failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Audit poll failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}, 5000)
|
||||
}
|
||||
@@ -142,7 +143,7 @@ async function onStart() {
|
||||
audit.value = await store.getAudit(res.audit_id)
|
||||
startPoll(res.audit_id)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Scan start failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Scan start failed: ${e.message}`, type: 'error' })
|
||||
} finally {
|
||||
busy.value = false
|
||||
}
|
||||
@@ -155,7 +156,7 @@ async function onCancel() {
|
||||
audit.value = await store.getAudit(audit.value.id)
|
||||
stopPoll()
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Cancel failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Cancel failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
|
||||
@@ -167,12 +168,12 @@ function onApplyClick() {
|
||||
async function onConfirmedApply(token) {
|
||||
try {
|
||||
const res = await store.applyAudit(audit.value.id, token)
|
||||
window.__fcToast?.({
|
||||
toast({
|
||||
text: `Deleted ${res.deleted} image(s)`, type: 'success',
|
||||
})
|
||||
audit.value = await store.getAudit(audit.value.id)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Apply failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Apply failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
@@ -80,6 +80,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { onMounted, onUnmounted, ref } from 'vue'
|
||||
|
||||
import DestructiveConfirmModal from '../modal/DestructiveConfirmModal.vue'
|
||||
@@ -109,7 +110,7 @@ function startPoll(id) {
|
||||
if (fresh.status !== 'running') stopPoll()
|
||||
} catch (e) {
|
||||
stopPoll()
|
||||
window.__fcToast?.({ text: `Audit poll failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Audit poll failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}, 5000)
|
||||
}
|
||||
@@ -125,7 +126,7 @@ async function onStart() {
|
||||
audit.value = await store.getAudit(res.audit_id)
|
||||
startPoll(res.audit_id)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Scan start failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Scan start failed: ${e.message}`, type: 'error' })
|
||||
} finally {
|
||||
busy.value = false
|
||||
}
|
||||
@@ -138,7 +139,7 @@ async function onCancel() {
|
||||
audit.value = await store.getAudit(audit.value.id)
|
||||
stopPoll()
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Cancel failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Cancel failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
|
||||
@@ -150,12 +151,12 @@ function onApplyClick() {
|
||||
async function onConfirmedApply(token) {
|
||||
try {
|
||||
const res = await store.applyAudit(audit.value.id, token)
|
||||
window.__fcToast?.({
|
||||
toast({
|
||||
text: `Deleted ${res.deleted} image(s)`, type: 'success',
|
||||
})
|
||||
audit.value = await store.getAudit(audit.value.id)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Apply failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Apply failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
@@ -33,6 +33,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { computed, ref, watch } from 'vue'
|
||||
|
||||
import { copyText } from '../../utils/clipboard.js'
|
||||
@@ -119,7 +120,7 @@ async function onCopy () {
|
||||
if (copiedTimer) clearTimeout(copiedTimer)
|
||||
copiedTimer = setTimeout(() => { copied.value = false }, 1500)
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Copy failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Copy failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
@@ -26,6 +26,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { onMounted, ref } from 'vue'
|
||||
import { useCredentialsStore } from '../../stores/credentials.js'
|
||||
import { copyText } from '../../utils/clipboard.js'
|
||||
@@ -39,9 +40,9 @@ async function copyKey() {
|
||||
if (!store.extensionKey) return
|
||||
try {
|
||||
await copyText(store.extensionKey)
|
||||
globalThis.window?.__fcToast?.({ text: 'Copied', type: 'success' })
|
||||
toast({ text: 'Copied', type: 'success' })
|
||||
} catch {
|
||||
globalThis.window?.__fcToast?.({ text: 'Copy failed', type: 'error' })
|
||||
toast({ text: 'Copy failed', type: 'error' })
|
||||
}
|
||||
}
|
||||
|
||||
@@ -50,7 +51,7 @@ function confirmRotate() { showRotateConfirm.value = true }
|
||||
async function doRotate() {
|
||||
showRotateConfirm.value = false
|
||||
await store.rotateKey()
|
||||
globalThis.window?.__fcToast?.({ text: 'Key rotated', type: 'success' })
|
||||
toast({ text: 'Key rotated', type: 'success' })
|
||||
}
|
||||
</script>
|
||||
|
||||
|
||||
@@ -32,6 +32,8 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { formatLocalDate } from '../../utils/date.js'
|
||||
|
||||
defineProps({
|
||||
platform: { type: Object, required: true },
|
||||
credential: { type: Object, default: null },
|
||||
@@ -39,8 +41,7 @@ defineProps({
|
||||
defineEmits(['replace', 'remove'])
|
||||
|
||||
function fmtDate(iso) {
|
||||
if (!iso) return '—'
|
||||
return iso.slice(0, 10)
|
||||
return iso ? formatLocalDate(iso) : '—'
|
||||
}
|
||||
</script>
|
||||
|
||||
|
||||
@@ -30,8 +30,9 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { ref, computed, onMounted, onUnmounted, watch } from 'vue'
|
||||
import { ref, computed } from 'vue'
|
||||
import { usePolyMasonry } from '../../composables/usePolyMasonry.js'
|
||||
import { useInfiniteScroll } from '../../composables/useInfiniteScroll.js'
|
||||
|
||||
const props = defineProps({
|
||||
items: { type: Array, default: () => [] },
|
||||
@@ -78,20 +79,18 @@ function aspectStyle(item) {
|
||||
return { aspectRatio: `${w} / ${h}` }
|
||||
}
|
||||
|
||||
let observer = null
|
||||
function attachObserver() {
|
||||
if (observer) observer.disconnect()
|
||||
if (!sentinelEl.value) return
|
||||
observer = new IntersectionObserver(([entry]) => {
|
||||
if (entry.isIntersecting && props.hasMore && !props.loading) {
|
||||
emit('load-more')
|
||||
}
|
||||
}, { rootMargin: '600px' })
|
||||
observer.observe(sentinelEl.value)
|
||||
}
|
||||
watch(sentinelEl, attachObserver)
|
||||
onMounted(attachObserver)
|
||||
onUnmounted(() => observer && observer.disconnect())
|
||||
// Larger rootMargin than the composable default (600px) because the
|
||||
// sentinel sits at the BOTTOM of the masonry container, whose height is
|
||||
// the MAX of the column heights. A single tall image (long manga page,
|
||||
// panorama) in one column pushes the sentinel way past the visible
|
||||
// bottom of the SHORTER columns — the user reads the short-column
|
||||
// bottoms long before the sentinel comes into view, and load-more
|
||||
// fires too late. 2400px ≈ 2-3 screen-heights of pre-emptive trigger,
|
||||
// comfortably covering typical tall-image heights. Operator-flagged
|
||||
// 2026-05-30.
|
||||
useInfiniteScroll(sentinelEl, () => {
|
||||
if (props.hasMore && !props.loading) emit('load-more')
|
||||
}, { rootMargin: '2400px' })
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
@@ -100,32 +99,54 @@ onUnmounted(() => observer && observer.disconnect())
|
||||
.fc-masonry__item {
|
||||
display: block; padding: 0; border: 0; background: none;
|
||||
cursor: pointer; width: 100%;
|
||||
overflow: hidden; border-radius: 4px;
|
||||
}
|
||||
.fc-masonry__item img {
|
||||
width: 100%; height: auto; display: block; border-radius: 4px;
|
||||
width: 100%; height: auto; display: block;
|
||||
background: rgb(var(--v-theme-surface-light));
|
||||
/* IR-parity hover: zoom + brighten the thumbnail (style.css ~1772). */
|
||||
transition: transform 0.3s ease, filter 0.3s ease;
|
||||
}
|
||||
.fc-masonry__item:hover img {
|
||||
transform: scale(1.03);
|
||||
filter: brightness(1.1);
|
||||
}
|
||||
.fc-masonry__sentinel {
|
||||
display: flex; justify-content: center; padding: 32px 0; min-height: 60px;
|
||||
}
|
||||
.fc-masonry__end { text-align: center; padding: 32px 0; }
|
||||
|
||||
/* IR-parity stagger fade-in for showcase entry / shuffle. 60ms between
|
||||
items, 250ms each — matches IR's `itemFadeIn` keyframe (style.css
|
||||
~line 1834). Honors prefers-reduced-motion. */
|
||||
/* Cascade entry: each tile flips up out of a backward tilt and settles
|
||||
into place, one at a time — more pronounced than a plain fade so the
|
||||
showcase reads as an "experience" (operator-flagged 2026-05-28). The
|
||||
`both` fill holds the hidden/tilted 0% state until each tile's staggered
|
||||
turn; the cubic-bezier overshoots slightly past flat then settles.
|
||||
Honors prefers-reduced-motion. Tunables: tilt (-28deg), stagger (70ms),
|
||||
duration (0.6s). */
|
||||
@keyframes fc-masonry-item-in {
|
||||
from { opacity: 0; transform: translateY(12px); }
|
||||
to { opacity: 1; transform: translateY(0); }
|
||||
0% {
|
||||
opacity: 0;
|
||||
transform: perspective(1000px) rotateX(-28deg) translateY(26px) scale(0.95);
|
||||
}
|
||||
55% { opacity: 1; }
|
||||
100% {
|
||||
opacity: 1;
|
||||
transform: perspective(1000px) rotateX(0deg) translateY(0) scale(1);
|
||||
}
|
||||
}
|
||||
.fc-masonry__item--anim {
|
||||
animation: fc-masonry-item-in 0.25s ease forwards;
|
||||
animation-delay: calc(var(--stagger-index, 0) * 60ms);
|
||||
opacity: 0;
|
||||
transform-origin: center top;
|
||||
backface-visibility: hidden;
|
||||
animation: fc-masonry-item-in 0.6s cubic-bezier(0.34, 1.45, 0.64, 1) both;
|
||||
animation-delay: calc(var(--stagger-index, 0) * 70ms);
|
||||
}
|
||||
@media (prefers-reduced-motion: reduce) {
|
||||
.fc-masonry__item--anim {
|
||||
animation: none;
|
||||
opacity: 1;
|
||||
transform: none;
|
||||
}
|
||||
.fc-masonry__item img { transition: none; }
|
||||
.fc-masonry__item:hover img { transform: none; }
|
||||
}
|
||||
</style>
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
</v-card-title>
|
||||
<v-card-text>
|
||||
<p class="text-caption" style="opacity: 0.75">
|
||||
{{ event.started_at }} → {{ event.finished_at || '(running)' }}
|
||||
{{ formatDateTime(event.started_at) }} → {{ event.finished_at ? formatDateTime(event.finished_at) : '(running)' }}
|
||||
({{ fmtDuration(event.summary?.duration_seconds) }})
|
||||
</p>
|
||||
|
||||
@@ -35,20 +35,53 @@
|
||||
</ul>
|
||||
</template>
|
||||
|
||||
<template v-if="event.error">
|
||||
<div class="fc-dl-blockhead mt-4">
|
||||
<h3 class="text-subtitle-2">Error</h3>
|
||||
<v-btn
|
||||
size="x-small" variant="text" prepend-icon="mdi-content-copy"
|
||||
@click="onCopy('Error', event.error)"
|
||||
>Copy</v-btn>
|
||||
</div>
|
||||
<pre class="fc-dl-pre">{{ event.error }}</pre>
|
||||
</template>
|
||||
|
||||
<template v-if="errorsWarnings">
|
||||
<h3 class="text-subtitle-2 mt-4">Errors & warnings</h3>
|
||||
<div class="fc-dl-blockhead mt-4">
|
||||
<h3 class="text-subtitle-2">Errors & warnings</h3>
|
||||
<v-btn
|
||||
size="x-small" variant="text" prepend-icon="mdi-content-copy"
|
||||
@click="onCopy('Errors & warnings', errorsWarnings)"
|
||||
>Copy</v-btn>
|
||||
</div>
|
||||
<pre class="fc-dl-pre">{{ errorsWarnings }}</pre>
|
||||
</template>
|
||||
|
||||
<v-expansion-panels class="mt-4">
|
||||
<v-expansion-panel>
|
||||
<v-expansion-panel-title>Raw stdout</v-expansion-panel-title>
|
||||
<v-expansion-panel-title>
|
||||
<span>Raw stdout</span>
|
||||
<v-spacer />
|
||||
<v-btn
|
||||
size="x-small" variant="text" prepend-icon="mdi-content-copy"
|
||||
class="me-2"
|
||||
@click.stop="onCopy('stdout', event.metadata?.stdout || '')"
|
||||
>Copy</v-btn>
|
||||
</v-expansion-panel-title>
|
||||
<v-expansion-panel-text>
|
||||
<pre class="fc-dl-pre">{{ event.metadata?.stdout || '(empty)' }}</pre>
|
||||
</v-expansion-panel-text>
|
||||
</v-expansion-panel>
|
||||
<v-expansion-panel>
|
||||
<v-expansion-panel-title>Raw stderr</v-expansion-panel-title>
|
||||
<v-expansion-panel-title>
|
||||
<span>Raw stderr</span>
|
||||
<v-spacer />
|
||||
<v-btn
|
||||
size="x-small" variant="text" prepend-icon="mdi-content-copy"
|
||||
class="me-2"
|
||||
@click.stop="onCopy('stderr', event.metadata?.stderr || '')"
|
||||
>Copy</v-btn>
|
||||
</v-expansion-panel-title>
|
||||
<v-expansion-panel-text>
|
||||
<pre class="fc-dl-pre">{{ event.metadata?.stderr || '(empty)' }}</pre>
|
||||
</v-expansion-panel-text>
|
||||
@@ -56,6 +89,10 @@
|
||||
</v-expansion-panels>
|
||||
</v-card-text>
|
||||
<v-card-actions>
|
||||
<v-btn
|
||||
variant="text" prepend-icon="mdi-content-copy"
|
||||
@click="onCopy('All diagnostics', allDiagnostics)"
|
||||
>Copy all diagnostics</v-btn>
|
||||
<v-spacer />
|
||||
<v-btn variant="text" @click="onClose(false)">Close</v-btn>
|
||||
</v-card-actions>
|
||||
@@ -64,8 +101,12 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { computed } from 'vue'
|
||||
|
||||
import { copyText } from '../../utils/clipboard.js'
|
||||
import { formatDateTime } from '../../utils/date.js'
|
||||
|
||||
const props = defineProps({ event: { type: Object, default: null } })
|
||||
const emit = defineEmits(['close'])
|
||||
|
||||
@@ -74,6 +115,32 @@ const summary = computed(() => props.event?.metadata?.import_summary || {})
|
||||
const quarantinedPaths = computed(() => props.event?.metadata?.quarantined_paths || [])
|
||||
const errorsWarnings = computed(() => props.event?.metadata?.stderr_errors_warnings || '')
|
||||
|
||||
// One combined block for "research the issue elsewhere" — header line +
|
||||
// error + full stdout/stderr. Built lazily from the current event.
|
||||
const allDiagnostics = computed(() => {
|
||||
const e = props.event
|
||||
if (!e) return ''
|
||||
const md = e.metadata || {}
|
||||
return [
|
||||
`event #${e.id} · ${e.platform || '—'} · ${e.artist_name || '—'}`,
|
||||
`status: ${e.status}`,
|
||||
`started: ${e.started_at} finished: ${e.finished_at || '(running)'}`,
|
||||
e.error ? `\n--- error ---\n${e.error}` : '',
|
||||
errorsWarnings.value ? `\n--- errors & warnings ---\n${errorsWarnings.value}` : '',
|
||||
`\n--- stdout ---\n${md.stdout || '(empty)'}`,
|
||||
`\n--- stderr ---\n${md.stderr || '(empty)'}`,
|
||||
].filter(Boolean).join('\n')
|
||||
})
|
||||
|
||||
async function onCopy(label, text) {
|
||||
try {
|
||||
await copyText(text || '')
|
||||
toast({ text: `${label} copied`, type: 'success' })
|
||||
} catch (e) {
|
||||
toast({ text: `Copy failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
|
||||
const statusColor = computed(() => ({
|
||||
ok: 'success', error: 'error', running: 'info',
|
||||
pending: 'secondary', skipped: 'warning',
|
||||
@@ -114,4 +181,8 @@ function onClose() {
|
||||
word-break: break-all;
|
||||
}
|
||||
.fc-dl-quar { padding-left: 1.5rem; font-size: 0.85rem; }
|
||||
.fc-dl-blockhead {
|
||||
display: flex; align-items: center; justify-content: space-between;
|
||||
gap: 0.5rem;
|
||||
}
|
||||
</style>
|
||||
|
||||
@@ -86,11 +86,14 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { computed, ref } from 'vue'
|
||||
import { RouterLink } from 'vue-router'
|
||||
|
||||
import PlatformChip from '../subscriptions/PlatformChip.vue'
|
||||
import { useSourcesStore } from '../../stores/sources.js'
|
||||
import { downloadStatusColor, downloadStatusIcon, downloadStatusLabel } from '../../utils/downloadStatus.js'
|
||||
import { formatDateTime } from '../../utils/date.js'
|
||||
|
||||
const props = defineProps({ event: { type: Object, required: true } })
|
||||
defineEmits(['open'])
|
||||
@@ -98,21 +101,12 @@ defineEmits(['open'])
|
||||
const sourcesStore = useSourcesStore()
|
||||
const retrying = ref(false)
|
||||
|
||||
const _STATUS = {
|
||||
ok: { color: 'success', icon: 'mdi-check-circle', label: 'Completed' },
|
||||
error: { color: 'error', icon: 'mdi-alert-circle', label: 'Failed' },
|
||||
running: { color: 'info', icon: 'mdi-progress-clock', label: 'Running' },
|
||||
pending: { color: 'grey', icon: 'mdi-clock-outline', label: 'Queued' },
|
||||
skipped: { color: 'warning', icon: 'mdi-skip-next', label: 'Skipped' },
|
||||
}
|
||||
const statusColor = computed(() => _STATUS[props.event.status]?.color || 'grey')
|
||||
const statusIcon = computed(() => _STATUS[props.event.status]?.icon || 'mdi-help-circle')
|
||||
const statusLabel = computed(() => _STATUS[props.event.status]?.label || props.event.status)
|
||||
const statusColor = computed(() => downloadStatusColor(props.event.status))
|
||||
const statusIcon = computed(() => downloadStatusIcon(props.event.status))
|
||||
const statusLabel = computed(() => downloadStatusLabel(props.event.status))
|
||||
|
||||
function fmtTime(iso) {
|
||||
if (!iso) return '—'
|
||||
// 2026-05-27 23:36 — second granularity is in the row's title attr
|
||||
return iso.slice(0, 16).replace('T', ' ')
|
||||
return iso ? formatDateTime(iso) : '—'
|
||||
}
|
||||
function fmtDuration(sec) {
|
||||
if (sec == null) return '—'
|
||||
@@ -131,12 +125,12 @@ async function onRetry() {
|
||||
retrying.value = true
|
||||
try {
|
||||
await sourcesStore.checkNow(props.event.source_id)
|
||||
globalThis.window?.__fcToast?.({
|
||||
toast({
|
||||
text: `Source check re-queued`, type: 'success',
|
||||
})
|
||||
} catch (e) {
|
||||
const isInFlight = !!e?.body?.download_event_id
|
||||
globalThis.window?.__fcToast?.({
|
||||
toast({
|
||||
text: isInFlight ? 'Already running' : `Retry failed: ${e?.detail || e?.message || e}`,
|
||||
type: isInFlight ? 'info' : 'error',
|
||||
})
|
||||
|
||||
@@ -32,8 +32,9 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { onMounted, onUnmounted, ref, watch } from 'vue'
|
||||
import { ref } from 'vue'
|
||||
import { useGalleryStore } from '../../stores/gallery.js'
|
||||
import { useInfiniteScroll } from '../../composables/useInfiniteScroll.js'
|
||||
import GalleryItem from './GalleryItem.vue'
|
||||
|
||||
defineEmits(['open'])
|
||||
@@ -41,22 +42,9 @@ defineEmits(['open'])
|
||||
const store = useGalleryStore()
|
||||
const sentinelEl = ref(null)
|
||||
|
||||
let observer = null
|
||||
|
||||
function attachObserver() {
|
||||
if (observer) observer.disconnect()
|
||||
if (!sentinelEl.value) return
|
||||
observer = new IntersectionObserver(([entry]) => {
|
||||
if (entry.isIntersecting && store.hasMore && !store.loading) {
|
||||
store.loadMore()
|
||||
}
|
||||
}, { rootMargin: '600px' })
|
||||
observer.observe(sentinelEl.value)
|
||||
}
|
||||
|
||||
watch(sentinelEl, attachObserver)
|
||||
onMounted(() => attachObserver())
|
||||
onUnmounted(() => observer && observer.disconnect())
|
||||
useInfiniteScroll(sentinelEl, () => {
|
||||
if (store.hasMore && !store.loading) store.loadMore()
|
||||
})
|
||||
|
||||
function dateHeaderId(group) { return `fc-month-${group.year}-${group.month}` }
|
||||
|
||||
|
||||
@@ -48,10 +48,11 @@ function onSearch(q) {
|
||||
if (!query) { results.value = []; return }
|
||||
loading.value = true
|
||||
try {
|
||||
// Scope the autocomplete to the prediction's category where it maps
|
||||
// to a tag kind. 'copyright' has no tag kind; search unscoped there.
|
||||
const kind = ['artist', 'character'].includes(props.category)
|
||||
? props.category : null
|
||||
// Scope the autocomplete to the prediction's category where it
|
||||
// maps to a tag kind. Only 'character' surfaces as both a
|
||||
// suggestion category and a tag kind now ('artist' + 'copyright'
|
||||
// retired); other categories search unscoped.
|
||||
const kind = props.category === 'character' ? 'character' : null
|
||||
const params = { q: query, limit: 20 }
|
||||
if (kind) params.kind = kind
|
||||
results.value = await api.get('/api/tags/autocomplete', { params })
|
||||
|
||||
@@ -92,7 +92,16 @@ let prevBodyOverflow = null
|
||||
// own keystrokes.
|
||||
function onKeyDown(ev) {
|
||||
if (ev.key === 'Escape') {
|
||||
if (isTextEntry(ev.target)) return
|
||||
// Escape closes the modal even from inside a text input — that's
|
||||
// the universal "get me out of here" expectation, and the
|
||||
// autofocused tag-entry field would otherwise trap focus with no
|
||||
// visible escape (operator-flagged 2026-06-01). EXCEPTION: when a
|
||||
// nested Vuetify overlay is open (v-menu autocomplete dropdown,
|
||||
// FandomPicker v-dialog, per-suggestion 3-dot menu), let that
|
||||
// overlay's own Esc handling fire instead of closing the whole
|
||||
// modal mid-interaction. Vuetify marks open overlays with
|
||||
// `.v-overlay--active`.
|
||||
if (document.querySelector('.v-overlay--active')) return
|
||||
ev.preventDefault()
|
||||
emit('close')
|
||||
} else if (ev.key === 'ArrowLeft') {
|
||||
|
||||
@@ -10,17 +10,30 @@
|
||||
density="compact"
|
||||
>{{ state.error }}</v-alert>
|
||||
|
||||
<template v-else>
|
||||
<!-- Cards scroll independently of the section title + attachments
|
||||
below them. Cap at ~2.5 cards visible (operator-asked 2026-06-01:
|
||||
keeps the Tags section anchored below at a consistent position;
|
||||
the half-visible third card hints there's more). -->
|
||||
<div v-else class="fc-prov__cards">
|
||||
<article
|
||||
v-for="e in state.entries" :key="e.provenance_id" class="fc-prov__card"
|
||||
>
|
||||
<div class="fc-prov__head">
|
||||
<span class="fc-prov__platform">{{ e.source.platform }}</span>
|
||||
<!-- Posts with no live subscription have source=null (alembic
|
||||
0030); render an explicit "filesystem import" affordance
|
||||
instead of a platform chip. -->
|
||||
<span class="fc-prov__platform">
|
||||
{{ e.source?.platform ?? 'filesystem import' }}
|
||||
</span>
|
||||
<span v-if="postDate(e)" class="fc-prov__date">{{ postDate(e) }}</span>
|
||||
</div>
|
||||
<div class="fc-prov__post">
|
||||
{{ e.post.title || `Post ${e.post.external_post_id}` }}
|
||||
</div>
|
||||
<button
|
||||
type="button" class="fc-prov__post"
|
||||
:title="`Open ${postTitle(e)} in the posts feed for ${e.artist.name}`"
|
||||
@click="openPost(e.post.id, e.artist.id)"
|
||||
>
|
||||
{{ postTitle(e) }}
|
||||
</button>
|
||||
<div class="fc-prov__meta">
|
||||
<RouterLink :to="`/artist/${e.artist.slug}`">
|
||||
by {{ e.artist.name }}
|
||||
@@ -29,17 +42,13 @@
|
||||
· {{ e.post.attachment_count }} files
|
||||
</span>
|
||||
</div>
|
||||
<div class="fc-prov__actions">
|
||||
<div v-if="e.post.description_html" class="fc-prov__actions">
|
||||
<a
|
||||
v-if="e.post.url" :href="e.post.url"
|
||||
target="_blank" rel="noopener noreferrer"
|
||||
>↗ View original post</a>
|
||||
<a href="#" @click.prevent="openPost(e.post.id)">
|
||||
View images from this post
|
||||
</a>
|
||||
href="#" @click.prevent="toggleDesc(e.provenance_id)"
|
||||
>{{ expanded[e.provenance_id] ? 'Hide description ▴' : 'Show description ▾' }}</a>
|
||||
</div>
|
||||
<div
|
||||
v-if="e.post.description_html"
|
||||
v-if="e.post.description_html && expanded[e.provenance_id]"
|
||||
class="fc-prov__desc" v-html="e.post.description_html"
|
||||
/>
|
||||
</article>
|
||||
@@ -58,7 +67,7 @@
|
||||
</RouterLink>
|
||||
</div>
|
||||
</article>
|
||||
</template>
|
||||
</div>
|
||||
|
||||
<div v-if="attachments.length" class="fc-prov__attach">
|
||||
<h4 class="fc-prov__attach-title">Attachments</h4>
|
||||
@@ -74,16 +83,27 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { computed, watch } from 'vue'
|
||||
import { computed, reactive, watch } from 'vue'
|
||||
import { useRouter } from 'vue-router'
|
||||
import { useModalStore } from '../../stores/modal.js'
|
||||
import { useProvenanceStore } from '../../stores/provenance.js'
|
||||
import { formatPostDate } from '../../utils/date.js'
|
||||
import { toPlainText } from '../../utils/htmlSanitize.js'
|
||||
|
||||
const modal = useModalStore()
|
||||
const prov = useProvenanceStore()
|
||||
const router = useRouter()
|
||||
|
||||
// Per-post description collapse state (keyed by provenance_id). Default
|
||||
// collapsed so multiple posts don't each eat ~180px of the panel — the
|
||||
// operator flagged the descriptions consuming a lot of real estate
|
||||
// 2026-05-28. Reset when the viewed image changes.
|
||||
const expanded = reactive({})
|
||||
function toggleDesc(id) { expanded[id] = !expanded[id] }
|
||||
watch(() => modal.currentImageId, () => {
|
||||
for (const k of Object.keys(expanded)) delete expanded[k]
|
||||
})
|
||||
|
||||
watch(
|
||||
() => modal.currentImageId,
|
||||
(id) => { if (id != null) prov.loadForImage(id) },
|
||||
@@ -120,9 +140,22 @@ const show = computed(() => {
|
||||
const attachments = computed(() => state.value?.attachments || [])
|
||||
|
||||
function postDate(e) { return formatPostDate(e.post.date) }
|
||||
function postTitle(e) {
|
||||
// Titles can arrive as stored HTML (e.g. "<strong>…</strong>"); render
|
||||
// as plain text (the CSS makes it bold).
|
||||
return toPlainText(e.post.title) || `Post ${e.post.external_post_id}`
|
||||
}
|
||||
|
||||
function openPost(postId) {
|
||||
router.push({ path: '/gallery', query: { post_id: postId } })
|
||||
function openPost(postId, artistId) {
|
||||
// Land on the post in the posts feed (in context), not the gallery
|
||||
// image grid. Scope the feed to this artist so the user lands in
|
||||
// that creator's stream, not the global one — operator-flagged
|
||||
// 2026-06-01. PostsView reads `artist_id` from the query string
|
||||
// (PostsView.vue line ~92) and filters via post_feed_service.
|
||||
router.push({
|
||||
path: '/posts',
|
||||
query: { post_id: postId, artist_id: artistId },
|
||||
})
|
||||
modal.close()
|
||||
}
|
||||
</script>
|
||||
@@ -135,6 +168,18 @@ function openPost(postId) {
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
margin-bottom: 12px;
|
||||
}
|
||||
.fc-prov__cards {
|
||||
/* 2.5 cards-worth at the typical collapsed card height (~108px each
|
||||
incl. 10px gap). Slightly under to ensure the third card's bottom
|
||||
edge is clipped — the visual cue that there's more below. */
|
||||
max-height: 270px;
|
||||
overflow-y: auto;
|
||||
/* Hairline scrollbar that doesn't compete with content. */
|
||||
scrollbar-width: thin;
|
||||
scrollbar-color: rgb(var(--v-theme-surface-light)) transparent;
|
||||
/* Pad-right so the scrollbar gutter doesn't squeeze card borders. */
|
||||
padding-right: 4px;
|
||||
}
|
||||
.fc-prov__card {
|
||||
border: 1px solid rgb(var(--v-theme-surface-light));
|
||||
border-radius: 6px; padding: 10px 12px; margin-bottom: 10px;
|
||||
@@ -145,8 +190,21 @@ function openPost(postId) {
|
||||
text-transform: lowercase;
|
||||
}
|
||||
.fc-prov__post {
|
||||
font-weight: 600; margin: 4px 0;
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
/* Clickable title — opens the post in the artist-scoped feed
|
||||
(operator-flagged 2026-06-01: title IS the primary action, the
|
||||
prior "View post" link was redundant). Styled as a button-link:
|
||||
accent color, underline on hover, focus ring for keyboard nav. */
|
||||
display: block; width: 100%; text-align: left;
|
||||
background: none; border: none; padding: 0;
|
||||
font: inherit; font-weight: 700;
|
||||
margin: 4px 0;
|
||||
color: rgb(var(--v-theme-accent));
|
||||
cursor: pointer;
|
||||
}
|
||||
.fc-prov__post:hover { text-decoration: underline; }
|
||||
.fc-prov__post:focus-visible {
|
||||
outline: 2px solid rgb(var(--v-theme-accent));
|
||||
outline-offset: 2px; border-radius: 3px;
|
||||
}
|
||||
.fc-prov__meta {
|
||||
font-size: 13px; color: rgb(var(--v-theme-on-surface-variant));
|
||||
|
||||
@@ -1,19 +1,33 @@
|
||||
<template>
|
||||
<!-- Chip-card row: visible border + hover/focus state unifies the
|
||||
name, score, and action buttons as one "object" (operator-asked
|
||||
2026-06-01). The row itself is informational; the explicit
|
||||
Accept button + 3-dot menu are the action affordances. -->
|
||||
<div class="fc-suggestion">
|
||||
<span class="fc-suggestion__name">
|
||||
{{ suggestion.display_name }}
|
||||
<span v-if="suggestion.creates_new_tag" class="fc-suggestion__new"
|
||||
title="No matching tag yet — accepting creates it">+new</span>
|
||||
title="No matching tag yet — accepting creates it">+ new</span>
|
||||
</span>
|
||||
<span class="fc-suggestion__score">{{ scorePct }}</span>
|
||||
<v-btn
|
||||
icon="mdi-plus" size="x-small" variant="text" color="accent"
|
||||
class="fc-suggestion__accept"
|
||||
size="small" variant="tonal" color="accent"
|
||||
density="compact" rounded="pill"
|
||||
:aria-label="`Accept ${suggestion.display_name}`"
|
||||
@click="$emit('accept', suggestion)"
|
||||
/>
|
||||
>
|
||||
Accept
|
||||
</v-btn>
|
||||
<v-menu>
|
||||
<template #activator="{ props }">
|
||||
<v-btn icon="mdi-dots-vertical" size="x-small" variant="text" v-bind="props" />
|
||||
<v-btn
|
||||
class="fc-suggestion__menu"
|
||||
icon="mdi-dots-vertical" size="small"
|
||||
variant="outlined" density="compact"
|
||||
:aria-label="`More actions for ${suggestion.display_name}`"
|
||||
v-bind="props"
|
||||
/>
|
||||
</template>
|
||||
<v-list density="compact">
|
||||
<v-list-item @click="$emit('alias', suggestion)">
|
||||
@@ -38,17 +52,45 @@ const scorePct = computed(() => `${Math.round(props.suggestion.score * 100)}%`)
|
||||
|
||||
<style scoped>
|
||||
.fc-suggestion {
|
||||
display: flex; align-items: center; gap: 6px;
|
||||
padding: 2px 0;
|
||||
display: flex; align-items: center; gap: 8px;
|
||||
padding: 6px 10px; margin-bottom: 4px;
|
||||
background: rgb(var(--v-theme-surface));
|
||||
border: 1px solid rgb(var(--v-theme-surface-light));
|
||||
border-radius: 6px;
|
||||
transition: background 120ms ease, border-color 120ms ease;
|
||||
}
|
||||
.fc-suggestion:hover {
|
||||
background: rgb(var(--v-theme-surface-light));
|
||||
border-color: rgb(var(--v-theme-accent), 0.4);
|
||||
}
|
||||
.fc-suggestion__name {
|
||||
flex: 1; min-width: 0;
|
||||
font-size: 14px;
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
overflow: hidden; text-overflow: ellipsis; white-space: nowrap;
|
||||
}
|
||||
.fc-suggestion__name { flex: 1; min-width: 0; }
|
||||
.fc-suggestion__new {
|
||||
font-size: 10px; color: rgb(var(--v-theme-accent));
|
||||
margin-left: 4px;
|
||||
display: inline-block;
|
||||
font-size: 10px; font-weight: 600;
|
||||
color: rgb(var(--v-theme-accent));
|
||||
background: rgba(var(--v-theme-accent), 0.12);
|
||||
border: 1px solid rgb(var(--v-theme-accent), 0.4);
|
||||
padding: 1px 6px; border-radius: 999px;
|
||||
margin-left: 6px;
|
||||
text-transform: uppercase; letter-spacing: 0.04em;
|
||||
}
|
||||
.fc-suggestion__score {
|
||||
flex: 0 0 auto; min-width: 38px; text-align: right;
|
||||
font-size: 11px;
|
||||
color: rgb(var(--v-theme-on-surface-variant, var(--v-theme-on-surface)));
|
||||
font-family: 'JetBrains Mono', monospace;
|
||||
}
|
||||
/* Vuetify's compact density doesn't shrink the tonal button enough
|
||||
for a tight row; clamp the min-width so Accept stays compact. */
|
||||
.fc-suggestion__accept :deep(.v-btn__content) {
|
||||
font-size: 12px; letter-spacing: 0.02em;
|
||||
}
|
||||
.fc-suggestion__menu {
|
||||
flex: 0 0 auto;
|
||||
}
|
||||
</style>
|
||||
|
||||
@@ -22,7 +22,7 @@
|
||||
<SuggestionsCategoryGroup
|
||||
v-if="store.byCategory.general && store.byCategory.general.length"
|
||||
label="General" :items="store.byCategory.general"
|
||||
collapsible :default-open="false"
|
||||
collapsible :default-open="true"
|
||||
@accept="onAccept" @alias="onAlias" @dismiss="store.dismiss"
|
||||
/>
|
||||
</template>
|
||||
@@ -38,15 +38,21 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { computed, ref, watch } from 'vue'
|
||||
import { useSuggestionsStore, CATEGORY_LABELS } from '../../stores/suggestions.js'
|
||||
import { useModalStore } from '../../stores/modal.js'
|
||||
import SuggestionsCategoryGroup from './SuggestionsCategoryGroup.vue'
|
||||
import AliasPickerDialog from './AliasPickerDialog.vue'
|
||||
|
||||
const props = defineProps({ imageId: { type: Number, required: true } })
|
||||
const store = useSuggestionsStore()
|
||||
const modal = useModalStore()
|
||||
|
||||
const peopleCats = ['artist', 'character', 'copyright']
|
||||
// 'artist' (FC-2d-vii-c) and 'copyright' (2026-06-01) retired as
|
||||
// suggestion categories. Only 'character' remains as a people-style
|
||||
// category alongside the general bucket.
|
||||
const peopleCats = ['character']
|
||||
function labelFor(c) { return CATEGORY_LABELS[c] || c }
|
||||
|
||||
const isEmpty = computed(() =>
|
||||
@@ -55,9 +61,20 @@ const isEmpty = computed(() =>
|
||||
|
||||
watch(() => props.imageId, (id) => { if (id != null) store.load(id) }, { immediate: true })
|
||||
|
||||
// After a successful accept/alias-accept, refresh the modal's current
|
||||
// tag list so TagPanel's chip rail reflects the newly-attached tag.
|
||||
// Operator-flagged 2026-06-01: the suggestion store dropped the
|
||||
// suggestion (correct) but didn't propagate the new tag back into the
|
||||
// modal store, so the chip rail looked unchanged even though the
|
||||
// backend had recorded the application. Mirrors the addExistingTag /
|
||||
// createAndAdd flows which already call reloadTags() after applying.
|
||||
async function onAccept(s) {
|
||||
try { await store.accept(s) }
|
||||
catch (e) { window.__fcToast?.({ text: `Accept failed: ${e.message}`, type: 'error' }) }
|
||||
try {
|
||||
await store.accept(s)
|
||||
await modal.reloadTags()
|
||||
} catch (e) {
|
||||
toast({ text: `Accept failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
|
||||
const aliasDialog = ref(false)
|
||||
@@ -67,8 +84,9 @@ async function onAliasConfirm(canonicalTagId) {
|
||||
try {
|
||||
await store.aliasAccept(aliasTarget.value, canonicalTagId)
|
||||
aliasDialog.value = false
|
||||
await modal.reloadTags()
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Alias failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Alias failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
<template>
|
||||
<div class="fc-tag-autocomplete">
|
||||
<v-text-field
|
||||
ref="inputRef"
|
||||
v-model="query"
|
||||
placeholder="Add tag (or kind:name — character/fandom/series)"
|
||||
density="compact" hide-details
|
||||
@@ -52,13 +53,21 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { computed, ref, watch } from 'vue'
|
||||
import { computed, nextTick, onMounted, ref, watch } from 'vue'
|
||||
import { useTagStore } from '../../stores/tags.js'
|
||||
import FandomPicker from './FandomPicker.vue'
|
||||
|
||||
const emit = defineEmits(['pick-existing', 'pick-new', 'cancel'])
|
||||
const store = useTagStore()
|
||||
|
||||
// Autofocus on modal open so the operator can type the moment the view
|
||||
// modal renders, no extra click required (operator-asked 2026-06-01).
|
||||
// Vuetify's v-text-field exposes .focus() on the component instance;
|
||||
// nextTick waits for the modal's mount to finish so the inner <input>
|
||||
// element exists.
|
||||
const inputRef = ref(null)
|
||||
onMounted(() => { nextTick(() => inputRef.value?.focus?.()) })
|
||||
|
||||
// Single text input; no kind dropdown. Client-side mirror of the
|
||||
// backend's parse_kind_prefix lives below — kept in sync with
|
||||
// KNOWN_KINDS in backend/app/utils/tag_prefix.py. The backend is the
|
||||
|
||||
@@ -7,7 +7,12 @@
|
||||
@keydown.enter="onCardClick"
|
||||
>
|
||||
<div class="fc-post-card__head">
|
||||
<v-chip size="x-small" variant="tonal">{{ post.source.platform }}</v-chip>
|
||||
<!-- Posts with no live subscription have source=null (alembic
|
||||
0030); show a "filesystem import" affordance instead of a
|
||||
platform chip. -->
|
||||
<v-chip size="x-small" variant="tonal">
|
||||
{{ post.source?.platform ?? 'filesystem import' }}
|
||||
</v-chip>
|
||||
<RouterLink
|
||||
:to="{ name: 'artist', params: { slug: post.artist.slug } }"
|
||||
class="fc-post-card__artist"
|
||||
@@ -25,7 +30,7 @@
|
||||
v-if="post.post_url"
|
||||
:href="post.post_url" target="_blank" rel="noopener"
|
||||
icon="mdi-open-in-new" size="x-small" variant="text"
|
||||
:aria-label="`open original post on ${post.source.platform}`"
|
||||
:aria-label="`open original post on ${post.source?.platform ?? 'web'}`"
|
||||
@click.stop
|
||||
/>
|
||||
<v-btn
|
||||
@@ -56,8 +61,8 @@
|
||||
</div>
|
||||
|
||||
<div class="fc-post-card__text">
|
||||
<h3 v-if="post.post_title" class="fc-post-card__title">
|
||||
{{ post.post_title }}
|
||||
<h3 v-if="plainTitle" class="fc-post-card__title">
|
||||
{{ plainTitle }}
|
||||
</h3>
|
||||
<h3 v-else class="fc-post-card__title fc-post-card__title--missing">
|
||||
Post {{ post.external_post_id }}
|
||||
@@ -80,8 +85,8 @@
|
||||
<!-- Expanded body: title, full mosaic, full sanitized HTML description,
|
||||
attachments. Lazy-loaded detail via getPostFull. -->
|
||||
<div v-else class="fc-post-card__expanded">
|
||||
<h2 v-if="post.post_title" class="fc-post-card__title-full">
|
||||
{{ post.post_title }}
|
||||
<h2 v-if="plainTitle" class="fc-post-card__title-full">
|
||||
{{ plainTitle }}
|
||||
</h2>
|
||||
<h2 v-else class="fc-post-card__title-full fc-post-card__title--missing">
|
||||
Post {{ post.external_post_id }}
|
||||
@@ -125,7 +130,7 @@ import { computed, ref } from 'vue'
|
||||
import { RouterLink } from 'vue-router'
|
||||
|
||||
import { usePostsStore } from '../../stores/posts.js'
|
||||
import { sanitizeHtml } from '../../utils/htmlSanitize.js'
|
||||
import { sanitizeHtml, toPlainText } from '../../utils/htmlSanitize.js'
|
||||
import PostEmptyThumbs from './PostEmptyThumbs.vue'
|
||||
import PostImageGrid from './PostImageGrid.vue'
|
||||
|
||||
@@ -149,6 +154,10 @@ const merged = computed(() => detail.value || props.post)
|
||||
const images = computed(() => merged.value.thumbnails || [])
|
||||
const attachments = computed(() => merged.value.attachments || [])
|
||||
|
||||
// Titles can arrive as stored HTML (e.g. "<strong>…</strong>"); render as
|
||||
// plain text — the CSS makes the title bold.
|
||||
const plainTitle = computed(() => toPlainText(props.post.post_title))
|
||||
|
||||
// Compact-view hero+rail derived from the feed-shape (capped 6).
|
||||
const hero = computed(() => props.post.thumbnails?.[0])
|
||||
const rail = computed(() => (props.post.thumbnails || []).slice(1, 4))
|
||||
@@ -312,7 +321,7 @@ function formatBytes (n) {
|
||||
|
||||
.fc-post-card__title {
|
||||
font-family: 'Fraunces', Georgia, serif;
|
||||
font-size: 18px; font-weight: 500;
|
||||
font-size: 18px; font-weight: 700;
|
||||
margin: 0 0 8px 0;
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
display: -webkit-box;
|
||||
@@ -369,7 +378,7 @@ function formatBytes (n) {
|
||||
.fc-post-card__title-full {
|
||||
font-family: 'Fraunces', Georgia, serif;
|
||||
font-size: 22px;
|
||||
font-weight: 500;
|
||||
font-weight: 700;
|
||||
margin: 0;
|
||||
color: rgb(var(--v-theme-on-surface));
|
||||
}
|
||||
|
||||
@@ -59,6 +59,8 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { formatRelative as fmtRelative } from '../../utils/date.js'
|
||||
|
||||
defineProps({ runs: { type: Array, default: () => [] } })
|
||||
defineEmits(['restore', 'delete', 'tag'])
|
||||
|
||||
@@ -92,13 +94,7 @@ function formatBytes(b) {
|
||||
return `${v.toFixed(i === 0 ? 0 : 1)} ${units[i]}`
|
||||
}
|
||||
function formatRelative(iso) {
|
||||
if (!iso) return '—'
|
||||
const then = new Date(iso).getTime()
|
||||
const diff = Math.max(0, (Date.now() - then) / 1000)
|
||||
if (diff < 60) return `${Math.floor(diff)}s ago`
|
||||
if (diff < 3600) return `${Math.floor(diff / 60)}m ago`
|
||||
if (diff < 86400) return `${Math.floor(diff / 3600)}h ago`
|
||||
return `${Math.floor(diff / 86400)}d ago`
|
||||
return fmtRelative(iso, { nullText: '—' })
|
||||
}
|
||||
</script>
|
||||
|
||||
|
||||
@@ -108,6 +108,7 @@
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { toast } from '../../utils/toast.js'
|
||||
import { computed, onMounted, ref } from 'vue'
|
||||
import { useApi } from '../../composables/useApi.js'
|
||||
import { copyText } from '../../utils/clipboard.js'
|
||||
@@ -147,7 +148,7 @@ async function loadKey() {
|
||||
apiKey.value = key
|
||||
} catch (e) {
|
||||
apiKey.value = ''
|
||||
window.__fcToast?.({
|
||||
toast({
|
||||
text: `Failed to load extension API key: ${e.message}`,
|
||||
type: 'error',
|
||||
})
|
||||
@@ -160,9 +161,9 @@ async function rotateKey() {
|
||||
const { key } = await api.post('/api/settings/extension_api_key/rotate')
|
||||
apiKey.value = key
|
||||
keyShown.value = true
|
||||
window.__fcToast?.({ text: 'Extension API key rotated.', type: 'success' })
|
||||
toast({ text: 'Extension API key rotated.', type: 'success' })
|
||||
} catch (e) {
|
||||
window.__fcToast?.({
|
||||
toast({
|
||||
text: `Rotate failed: ${e.message}`,
|
||||
type: 'error',
|
||||
})
|
||||
@@ -174,9 +175,9 @@ async function rotateKey() {
|
||||
async function copy(text, label) {
|
||||
try {
|
||||
await copyText(text)
|
||||
window.__fcToast?.({ text: `${label} copied.`, type: 'success' })
|
||||
toast({ text: `${label} copied.`, type: 'success' })
|
||||
} catch (e) {
|
||||
window.__fcToast?.({ text: `Copy failed: ${e.message}`, type: 'error' })
|
||||
toast({ text: `Copy failed: ${e.message}`, type: 'error' })
|
||||
}
|
||||
}
|
||||
</script>
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user