Merge pull request 'v26.05.25.2: supersede + sidecar enrichment, scan toast feedback, CI uv + pip cache + durations' (#12) from dev into main

This commit was merged in pull request #12.
This commit is contained in:
2026-05-25 14:30:25 -04:00
4 changed files with 146 additions and 4 deletions
+31 -3
View File
@@ -24,11 +24,26 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Cache pip wheels
uses: actions/cache@v4
with:
path: ~/.cache/pip
key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
restore-keys: |
pip-${{ runner.os }}-py314-
- name: Install Python deps
# ruff is pre-installed in the ci-python image (see CI-Runner/CI-python/
# Dockerfile's RUFF_VERSION). Per FabledRulebook ci-runners.md, toolchain
# versions live on the runner image, not here.
run: pip install -r requirements.txt pytest pytest-asyncio
# uv: 5-10x faster wheel resolve than pip for cold caches.
# Falls back to pip install on uv-missing runners (older images).
run: |
if command -v uv >/dev/null 2>&1; then
uv pip install --system -r requirements.txt pytest pytest-asyncio
else
pip install -r requirements.txt pytest pytest-asyncio
fi
- name: Ruff lint
run: ruff check backend/ tests/ alembic/
@@ -99,6 +114,14 @@ jobs:
steps:
- uses: actions/checkout@v4
- name: Cache pip wheels
uses: actions/cache@v4
with:
path: ~/.cache/pip
key: pip-${{ runner.os }}-py314-${{ hashFiles('requirements.txt') }}
restore-keys: |
pip-${{ runner.os }}-py314-
- name: Integration suite (resolve service IPs, migrate, test)
run: |
set -eux
@@ -119,6 +142,11 @@ jobs:
(echo > "/dev/tcp/$PG_IP/5432") >/dev/null 2>&1 && break
sleep 2
done
pip install -r requirements.txt pytest pytest-asyncio
# uv when available (5-10x faster wheel resolve); fall back to pip.
if command -v uv >/dev/null 2>&1; then
uv pip install --system -r requirements.txt pytest pytest-asyncio
else
pip install -r requirements.txt pytest pytest-asyncio
fi
alembic upgrade head
pytest tests/ -v -m integration
pytest tests/ -v -m integration --durations=25
+25
View File
@@ -722,6 +722,15 @@ class Importer:
row id (so tags/series/curation stay attached). ML is cleared so
the import task re-derives it on the new pixels.
After the file swap, the new file's adjacent gallery-dl sidecar
(if any) is applied via _apply_sidecar — operator-flagged
2026-05-25: scanning a GS download dir with smaller IR-migrated
images on the receiving end used to swap files but lose the GS
sidecar's post metadata entirely. _apply_sidecar is additive
(find-or-create Post / Source / ImageProvenance, NULL-only
primary_post_id update) so any pre-existing Post linkage
survives untouched.
If `new_path` is provided, `source` is assumed to ALREADY be at
that path (FC-3c attach_in_place case) — skip the copy step.
Otherwise the file is copied via _copy_to_library."""
@@ -751,6 +760,22 @@ class Importer:
self.session.flush()
self.session.commit()
# Sidecar enrichment from the new (larger) file's location.
# _apply_sidecar resolves artist from the sidecar itself if the
# existing row has none, and is internally guarded against
# missing-or-malformed sidecars (silent return).
try:
self._apply_sidecar(existing, source, None)
except Exception as exc:
# Don't unwind the supersede DB swap if sidecar parsing
# blows up unexpectedly — the file replacement is the
# critical operation, sidecar is enrichment.
log.warning(
"sidecar enrichment failed during supersede of "
"image_record.id=%s from %s: %s",
existing.id, source, exc,
)
for stale in (old_path, old_thumb):
if not stale or stale == str(dest):
# If the supersede kept the file in place (new_path == old
+20
View File
@@ -56,7 +56,27 @@ export const useImportStore = defineStore('import', () => {
triggerError.value = null
try {
await api.post('/api/import/trigger', { body: { mode: 'quick' } })
// Acknowledge immediately so the click isn't invisible. scan_directory
// can finalize the batch synchronously when every file in /import is
// already on a non-failed ImportTask (operator-flagged 2026-05-25:
// 233k existing tasks → all paths in skip-set → files_seen=0 →
// batch flashes 'running' for <100ms then 'complete' before the
// first refreshStatus() lands; UI never sees the active state).
window.__fcToast?.({ text: 'Scan triggered', type: 'success' })
await refreshStatus()
// Re-poll twice over ~5s to catch quick-finalize transitions and
// surface a result toast either way.
setTimeout(async () => {
await refreshStatus()
if (!activeBatch.value) {
// Either scan completed with zero new files, or it never visibly
// started. Fetch the freshest task to differentiate.
window.__fcToast?.({
text: 'Scan complete — no new files (everything already on an ImportTask row)',
type: 'info',
})
}
}, 2000)
} catch (e) {
triggerError.value = e.message
window.__fcToast?.({ text: `Scan failed: ${e.message}`, type: 'error' })
+70 -1
View File
@@ -10,7 +10,15 @@ import pytest
from PIL import Image
from sqlalchemy import func, select
from backend.app.models import ImageRecord, ImportSettings, Tag, TagKind
from backend.app.models import (
ImageProvenance,
ImageRecord,
ImportSettings,
Post,
Source,
Tag,
TagKind,
)
from backend.app.models.tag import image_tag
from backend.app.services.importer import Importer, SkipReason
from backend.app.services.thumbnailer import Thumbnailer
@@ -141,6 +149,67 @@ def test_smaller_existing_is_superseded(importer, import_layout):
assert Path(row.path).exists()
def test_supersede_applies_new_file_sidecar(importer, import_layout):
"""Operator-flagged 2026-05-25: scanning the GS download dir should
supersede smaller IR-migrated images AND wire up the GS sidecar's
Post/Source/ImageProvenance. Previously _supersede swapped the file
but ignored the sidecar entirely."""
import json
import_root, _ = import_layout
# Stage 1: a small, sidecar-less image (the "IR migration" precondition).
small = import_root / "ir-migration-folder" / "small.png"
_write(small, (60, 130, 200), (200, 200))
r1 = importer.import_one(small)
assert r1.status == "imported"
eid = r1.image_id
# Stage 2: a larger version of the same image (same phash) WITH a
# gallery-dl JSON sidecar adjacent. Live in a separate folder to
# simulate the GS download dir.
big = import_root / "Maewix" / "patreon" / "01_big.png"
_write(big, (60, 130, 200), (900, 900))
sidecar_path = big.with_suffix(big.suffix + ".json")
sidecar_path.parent.mkdir(parents=True, exist_ok=True)
sidecar_path.write_text(json.dumps({
"category": "patreon",
"id": 555,
"url": "https://www.patreon.com/posts/555",
"title": "Set 1",
"content": "<p>The big version</p>",
"page_count": 1,
"published_at": "2025-08-01T00:00:00+00:00",
"artist": "Maewix",
}))
r2 = importer.import_one(big)
assert r2.status == "superseded"
assert r2.image_id == eid
importer.session.expire_all()
# Row preserved, file replaced, sidecar metadata wired up.
row = importer.session.get(ImageRecord, eid)
assert row.width == 900 and row.height == 900
post = importer.session.execute(
select(Post).where(Post.external_post_id == "555")
).scalar_one()
assert post.post_title == "Set 1"
assert "big version" in (post.description or "")
source = importer.session.execute(
select(Source).where(Source.id == post.source_id)
).scalar_one()
assert source.platform == "patreon"
prov_count = importer.session.execute(
select(func.count(ImageProvenance.id))
.where(ImageProvenance.image_record_id == eid)
.where(ImageProvenance.post_id == post.id)
).scalar_one()
assert prov_count == 1
def test_threshold_controls_match(importer, import_layout):
# Structurally distinct images (orthogonal splits) are far apart in
# phash space, so a tight threshold keeps them independent rather than