bvandeusen
485387ff0b
Heads + CCIP are the tag source and head auto-apply is the earned propagation.
The Camie tagger ran only to feed the allowlist bulk-apply (its ImagePrediction
rows had no other consumer), and the allowlist was a SECOND, un-earned auto-apply
path firing in parallel with heads on every accept — exactly the un-earned spray
the v2 pivot replaced. Retire both.
Behavior change: accepting a suggestion now applies the tag to THAT image only
(source='ml_accepted', a head-training positive) — it no longer allowlists +
fans the tag across the library via Camie. Propagation is heads' earned
auto-apply. (Loses instant cold-start propagation for booru-vocab tags; that was
un-earned and bypassed the precision gate.)
- tag_and_embed is now EMBED-ONLY (no Camie load/infer, no ImagePrediction
writes); backfill enqueues it for images with no embedding.
- Removed: services/ml/tagger.py, apply_allowlist_tags + helpers + daily beat +
every enqueue caller (accept/alias/merge/per-image), api/allowlist.py +
blueprint, ImagePrediction + TagAllowlist models/tables (migration 0067),
AllowlistTable.vue + allowlist store, the accept coverage-projection payload.
- AllowlistService gutted to accept/dismiss/undismiss/reject (the rejection store
the rail still needs); accept returns nothing, API returns {accepted, tag_id}.
- tag merge no longer repoints/triggers the allowlist; _keep_as_alias now keys on
ML-applied image_tag sources (incl. head_auto) instead of the allowlist.
- UI: MLBackfillCard relabelled to embedding-only; accept toast simplified;
MaintenancePanel drops the allowlist tile.
Left for a follow-up hygiene pass (now-inert, harmless): the dead settings
columns (tagger_store_floor, tagger_model_version, suggestion_threshold_*,
video_min_tag_frames), image_record.tagger_model_version, MLThresholdSliders
trim, and the Camie model download in download_models.py.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
126 lines
4.2 KiB
Python
126 lines
4.2 KiB
Python
import pytest
|
|
from sqlalchemy import select
|
|
|
|
from backend.app.celery_app import celery
|
|
from backend.app.models import ImageRecord, MLSettings, TagHead, TagKind
|
|
from backend.app.services.tag_service import TagService
|
|
|
|
pytestmark = pytest.mark.integration
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def eager():
|
|
celery.conf.task_always_eager = True
|
|
yield
|
|
celery.conf.task_always_eager = False
|
|
|
|
|
|
async def _img(db, sha="s" * 64):
|
|
img = ImageRecord(
|
|
path=f"/images/{sha}.jpg", sha256=sha, size_bytes=1,
|
|
mime="image/jpeg", width=1, height=1,
|
|
origin="imported_filesystem", integrity_status="unknown",
|
|
)
|
|
db.add(img)
|
|
await db.commit()
|
|
return img
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_suggestions(client, db):
|
|
# Suggestions come from a trained head now (Camie/centroid removed): an image
|
|
# whose embedding aligns with the head surfaces that concept.
|
|
s = (await db.execute(select(MLSettings).where(MLSettings.id == 1))).scalar_one()
|
|
img = ImageRecord(
|
|
path="/images/headsug.jpg", sha256="h" * 64, size_bytes=1,
|
|
mime="image/jpeg", width=1, height=1, origin="imported_filesystem",
|
|
integrity_status="unknown", siglip_embedding=[3.0] + [0.0] * 1151,
|
|
)
|
|
db.add(img)
|
|
await db.flush()
|
|
tag = await TagService(db).find_or_create("sword", TagKind.general)
|
|
db.add(TagHead(
|
|
tag_id=tag.id, embedding_version=s.embedder_model_version,
|
|
weights=[1.0] + [0.0] * 1151, bias=0.0, suggest_threshold=0.5,
|
|
auto_apply_threshold=None, n_pos=10, n_neg=30,
|
|
ap=0.8, precision_cv=0.9, recall=0.6,
|
|
))
|
|
await db.commit()
|
|
resp = await client.get(f"/api/images/{img.id}/suggestions")
|
|
assert resp.status_code == 200
|
|
body = await resp.get_json()
|
|
general = body["by_category"].get("general", [])
|
|
s2 = next(x for x in general if x["canonical_tag_id"] == tag.id)
|
|
assert s2["source"] == "head"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_accept_requires_tag_id(client, db):
|
|
img = await _img(db)
|
|
resp = await client.post(
|
|
f"/api/images/{img.id}/suggestions/accept", json={}
|
|
)
|
|
assert resp.status_code == 400
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_accept_applies_tag_to_image(client, db):
|
|
# Camie/allowlist retired (#1189): accept applies the tag to THIS image
|
|
# (source='ml_accepted', a head-training positive) — no bulk allowlist
|
|
# fan-out anymore.
|
|
from backend.app.models.tag import image_tag
|
|
|
|
img = await _img(db)
|
|
tag = await TagService(db).find_or_create("AcceptMe", TagKind.character)
|
|
await db.commit()
|
|
resp = await client.post(
|
|
f"/api/images/{img.id}/suggestions/accept", json={"tag_id": tag.id}
|
|
)
|
|
assert resp.status_code == 200
|
|
assert (await resp.get_json())["accepted"] is True
|
|
src = (await db.execute(
|
|
select(image_tag.c.source)
|
|
.where(image_tag.c.image_record_id == img.id)
|
|
.where(image_tag.c.tag_id == tag.id)
|
|
)).scalar_one()
|
|
assert src == "ml_accepted"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_dismiss(client, db):
|
|
img = await _img(db)
|
|
tag = await TagService(db).find_or_create("DismissMe", TagKind.general)
|
|
await db.commit()
|
|
resp = await client.post(
|
|
f"/api/images/{img.id}/suggestions/dismiss", json={"tag_id": tag.id}
|
|
)
|
|
assert resp.status_code == 204
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_undismiss_reverses_rejection(client, db):
|
|
img = await _img(db)
|
|
tag = await TagService(db).find_or_create("UndismissMe", TagKind.general)
|
|
await db.commit()
|
|
await client.post(
|
|
f"/api/images/{img.id}/suggestions/dismiss", json={"tag_id": tag.id}
|
|
)
|
|
resp = await client.post(
|
|
f"/api/images/{img.id}/suggestions/undismiss", json={"tag_id": tag.id}
|
|
)
|
|
assert resp.status_code == 204
|
|
# Idempotent: un-rejecting again (nothing to clear) is still a 204.
|
|
resp2 = await client.post(
|
|
f"/api/images/{img.id}/suggestions/undismiss", json={"tag_id": tag.id}
|
|
)
|
|
assert resp2.status_code == 204
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_alias_requires_fields(client, db):
|
|
img = await _img(db)
|
|
resp = await client.post(
|
|
f"/api/images/{img.id}/suggestions/alias", json={"alias_string": "x"}
|
|
)
|
|
assert resp.status_code == 400
|