Files
FabledCurator/tests/test_ml_allowlist.py
T
bvandeusen c8b815afe6
CI / lint (push) Successful in 2s
CI / frontend-build (push) Successful in 17s
CI / backend-lint-and-test (push) Successful in 27s
CI / integration (push) Successful in 3m12s
feat(ml): clamp allowlist min_confidence to the tagger store floor
Consumer #4 of the store-floor change (#764). An allowlist tag can't
auto-apply more permissively than the ingest floor — predictions below
tagger_store_floor aren't stored, so a lower min_confidence behaves
identically to the floor. update_threshold now clamps to max(value, floor);
the AllowlistTable confidence input min-binds to the live floor and clamps
on edit. Keeps the stored threshold honest about actual apply behavior.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-10 13:52:20 -04:00

121 lines
4.1 KiB
Python

import pytest
from sqlalchemy import select
from backend.app.models import TagAllowlist, TagKind, TagSuggestionRejection
from backend.app.models.tag import image_tag
from backend.app.services.ml.allowlist import AllowlistService
from backend.app.services.tag_service import TagService
pytestmark = pytest.mark.integration
async def _make_image(db):
from backend.app.models import ImageRecord
img = ImageRecord(
path="/images/x.jpg", sha256="x" * 64, size_bytes=1,
mime="image/jpeg", width=1, height=1,
origin="imported_filesystem", integrity_status="unknown",
)
db.add(img)
await db.flush()
return img
@pytest.mark.asyncio
async def test_accept_applies_and_allowlists(db):
img = await _make_image(db)
tag = await TagService(db).find_or_create("Hero", TagKind.character)
svc = AllowlistService(db)
newly_added = await svc.accept(img.id, tag.id)
assert newly_added is True
applied = (
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 applied == "ml_accepted"
assert await db.get(TagAllowlist, tag.id) is not None
@pytest.mark.asyncio
async def test_accept_idempotent_allowlist(db):
img = await _make_image(db)
tag = await TagService(db).find_or_create("Hero2", TagKind.character)
svc = AllowlistService(db)
assert await svc.accept(img.id, tag.id) is True
assert await svc.accept(img.id, tag.id) is False
@pytest.mark.asyncio
async def test_reject_applied_tag_records_rejection(db):
img = await _make_image(db)
tag = await TagService(db).find_or_create("Removeme", TagKind.general)
svc = AllowlistService(db)
await svc.accept(img.id, tag.id)
await svc.reject_applied_tag(img.id, tag.id)
still_applied = (
await db.execute(
select(image_tag.c.tag_id)
.where(image_tag.c.image_record_id == img.id)
.where(image_tag.c.tag_id == tag.id)
)
).scalar_one_or_none()
assert still_applied is None
rej = await db.get(TagSuggestionRejection, (img.id, tag.id))
assert rej is not None
@pytest.mark.asyncio
async def test_dismiss_records_rejection(db):
img = await _make_image(db)
tag = await TagService(db).find_or_create("Dismissme", TagKind.general)
await AllowlistService(db).dismiss(img.id, tag.id)
assert await db.get(TagSuggestionRejection, (img.id, tag.id)) is not None
@pytest.mark.asyncio
async def test_add_alias_and_accept(db):
img = await _make_image(db)
canonical = await TagService(db).find_or_create(
"Canonical Char", TagKind.character
)
svc = AllowlistService(db)
await svc.add_alias_and_accept(
img.id, "model_char_name", "character", canonical.id
)
from backend.app.services.ml.aliases import AliasService
resolved = await AliasService(db).resolve("model_char_name", "character")
assert resolved.id == canonical.id
assert await db.get(TagAllowlist, canonical.id) is not None
@pytest.mark.asyncio
async def test_update_threshold_and_remove(db):
tag = await TagService(db).find_or_create("Thr", TagKind.general)
svc = AllowlistService(db)
img = await _make_image(db)
await svc.accept(img.id, tag.id)
await svc.update_threshold(tag.id, 0.80)
row = await db.get(TagAllowlist, tag.id)
assert abs(row.min_confidence - 0.80) < 1e-6
await svc.remove(tag.id)
assert await db.get(TagAllowlist, tag.id) is None
@pytest.mark.asyncio
async def test_update_threshold_clamped_to_store_floor(db):
# A min_confidence below the store floor (default 0.70) is clamped up —
# predictions below the floor aren't stored, so a lower threshold can't
# apply more permissively than the floor (#764).
tag = await TagService(db).find_or_create("Lowthr", TagKind.general)
svc = AllowlistService(db)
img = await _make_image(db)
await svc.accept(img.id, tag.id)
await svc.update_threshold(tag.id, 0.30)
row = await db.get(TagAllowlist, tag.id)
assert abs(row.min_confidence - 0.70) < 1e-6