bvandeusen
3f92669f12
Promotes the prediction store-floor from the TAGGER_STORE_FLOOR env (default 0.05) to a DB-backed, Settings-UI-tunable ml_settings column (default 0.70). Storing every tag down to 0.05 from a ~10k-tag tagger is what grew image_record's TOAST to ~100 GB; the suggestion path already filters at 0.70 and the centroid/learned path covers lower-confidence preferred tags, so the sub-0.70 tail is redundant. Foundation for plan-task #764 (backfill + reclaim land next; this only changes the write gate for NEW imports). - ml_settings.tagger_store_floor (migration 0044, default 0.70) - tagger.Tagger.infer(store_floor=...); ml task passes settings.tagger_store_floor - ML admin GET/PATCH expose it; PATCH rejects a category suggestion threshold below the floor (nothing below the floor is stored, so the gap surfaces nothing) — server backstop for the UI slider clamp - Settings → ML: store-floor slider + caption; category sliders min-bound to it Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
84 lines
3.0 KiB
Python
84 lines
3.0 KiB
Python
import pytest
|
|
|
|
from backend.app.celery_app import celery
|
|
from backend.app.models import 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
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_and_patch_settings(client):
|
|
resp = await client.get("/api/ml/settings")
|
|
assert resp.status_code == 200
|
|
body = await resp.get_json()
|
|
# Default raised 0.50 → 0.70 on 2026-06-02 (alembic 0033) — 0.50
|
|
# was too noisy in practice. The 0.70 default keeps the rail
|
|
# signal-rich without hiding everything like the original 0.95.
|
|
assert body["suggestion_threshold_general"] == pytest.approx(0.70)
|
|
# Retired threshold columns must not appear in the payload.
|
|
assert "suggestion_threshold_artist" not in body
|
|
assert "suggestion_threshold_copyright" not in body
|
|
|
|
resp = await client.patch(
|
|
"/api/ml/settings", json={"suggestion_threshold_general": 0.90}
|
|
)
|
|
assert resp.status_code == 200
|
|
assert (await resp.get_json())["suggestion_threshold_general"] == pytest.approx(0.90)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_tagger_store_floor_default_and_patch(client):
|
|
body = await (await client.get("/api/ml/settings")).get_json()
|
|
assert body["tagger_store_floor"] == pytest.approx(0.70)
|
|
|
|
resp = await client.patch("/api/ml/settings", json={"tagger_store_floor": 0.6})
|
|
assert resp.status_code == 200
|
|
assert (await resp.get_json())["tagger_store_floor"] == pytest.approx(0.6)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_suggestion_threshold_below_store_floor_rejected(client):
|
|
# Invariant (#764): a category threshold can't sit below the store floor —
|
|
# nothing below the floor is stored, so the gap would surface nothing.
|
|
# Floor defaults to 0.70; pushing general down to 0.50 must 400.
|
|
resp = await client.patch(
|
|
"/api/ml/settings", json={"suggestion_threshold_general": 0.50}
|
|
)
|
|
assert resp.status_code == 400
|
|
assert "tagger_store_floor" in (await resp.get_json())["error"]
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_backfill_and_recompute_trigger(client):
|
|
r1 = await client.post("/api/ml/backfill")
|
|
assert r1.status_code == 202
|
|
r2 = await client.post("/api/ml/recompute-centroids")
|
|
assert r2.status_code == 202
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_rename_tag(client, db):
|
|
tag = await TagService(db).find_or_create("oldname", TagKind.character)
|
|
await db.commit()
|
|
resp = await client.patch(f"/api/tags/{tag.id}", json={"name": "New Name"})
|
|
assert resp.status_code == 200
|
|
assert (await resp.get_json())["name"] == "New Name"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_rename_collision_409(client, db):
|
|
svc = TagService(db)
|
|
await svc.find_or_create("Taken", TagKind.character)
|
|
other = await svc.find_or_create("Mover", TagKind.character)
|
|
await db.commit()
|
|
resp = await client.patch(f"/api/tags/{other.id}", json={"name": "Taken"})
|
|
assert resp.status_code == 409
|