Files
FabledCurator/tests/test_api_suggestions.py
T
bvandeusen ca1c17446c
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 17s
CI / backend-lint-and-test (push) Successful in 26s
CI / integration (push) Successful in 3m19s
feat(suggestions): heads are the suggestion source — Camie + centroid removed (#114 C)
The rail's Suggestions now come from the trained per-concept heads. SuggestionService.for_image scores the image's frozen SigLIP embedding against
every head (heads.score_image) and surfaces concepts above each head's own
suggest threshold; the typed-dropdown's min=0 "show everything" mode maps to a
flat floor so any head-scored concept can still be picked. Already-applied tags
drop; rejected tags stay flagged + reversible (unchanged).

REMOVED from the suggestion path (rule 22, no fallback): the Camie
ImagePrediction candidate/alias/merge pipeline and the per-tag centroid
augmentation, plus the now-dead SuggestionService internals (_load_predictions,
_threshold_for, _settings, self.aliases, self.centroids). Head suggestions are
always canonical tags, so raw_name/via_alias are null/false and the rail's
alias kebab is inert by data (its removal + the Camie ingest-tagger rip are the
flagged follow-up). for_selection (bulk consensus) now aggregates head
suggestions unchanged.

Tests rewritten to the head path: test_ml_suggestions (surfaces/applied/
rejected-reversible/override/no-embedding/no-heads), test_suggestions_bulk
(consensus), test_api_suggestions (get + dropped the Camie-alias roundtrip),
and test_ml_artist_retired (artist not head-eligible via _HEAD_KINDS).

DEPLOY NOTE: after this lands, the rail is empty until you run Train heads
(Settings → Tagging → Concept heads) — deploy, train, then the rail populates.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
2026-06-28 11:20:11 -04:00

142 lines
4.8 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, preds, sha="s" * 64):
from tests._prediction_helpers import seed_predictions
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()
await seed_predictions(db, img.id, preds)
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_then_applied(client, db):
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
body = await resp.get_json()
# #7b: a fresh accept newly-allowlists → projection payload for the toast.
assert body["allowlisted"] is True
assert body["tag_id"] == tag.id
assert body["tag_name"] == "AcceptMe"
assert "projected_count" in body
@pytest.mark.asyncio
async def test_accept_already_allowlisted_reports_not_new(client, db):
img1 = await _img(db, {}, sha="c" * 64)
img2 = await _img(db, {}, sha="d" * 64)
tag = await TagService(db).find_or_create("Twice", TagKind.character)
await db.commit()
first = await client.post(
f"/api/images/{img1.id}/suggestions/accept", json={"tag_id": tag.id}
)
assert (await first.get_json())["allowlisted"] is True
second = await client.post(
f"/api/images/{img2.id}/suggestions/accept", json={"tag_id": tag.id}
)
body = await second.get_json()
assert body["allowlisted"] is False # already on the allowlist
assert "projected_count" not in body
@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