bvandeusen
369e3de684
Video tag noise root cause: frames were a FIXED count (6) max-pooled — a tag firing on one frame survived at peak confidence, and a fixed count under-samples long multi-scene videos so real scene-local tags looked like noise. Redesign (operator-steered): - Sample at a fixed CADENCE — one frame every `video_frame_interval_seconds` (default 4) across the 5–95% window — so a tag's frame-presence reflects real screen time independent of video length. Capped at `video_max_frames` (default 64): a long video stretches the spacing instead of exploding into hundreds of inferences, bounding per-video cost on the single ml-worker (per-frame ffmpeg timeout also cut 60s→30s). - Aggregate with `_aggregate_video_predictions`: keep a tag only if it appears in >= `video_min_tag_frames` sampled frames (≈ that many × interval seconds on screen — duration-independent noise rejection), with confidence = MEAN over the frames it appears in (not max). Clamps the threshold to the sample count so a 1–2-frame short video still tags. - All three knobs are DB-backed ml_settings (migration 0053), patchable via /api/ml/settings + sliders in the ML settings card — replaces the VIDEO_ML_FRAMES env var (product-not-project). Tests: aggregation drops one-frame noise + means corroborated tags + clamps on short videos; settings round-trip + min>max validation. Replaced the _maxpool_predictions unit test. NOTE: this is the QUALITY half of #747. The perf half — the ml-worker runs CPU-only — is GPU enablement, tracked separately in #872. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
114 lines
4.1 KiB
Python
114 lines
4.1 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_video_tagging_settings_default_and_patch(client):
|
|
"""#747: video cadence/noise knobs are exposed + patchable."""
|
|
body = await (await client.get("/api/ml/settings")).get_json()
|
|
assert body["video_frame_interval_seconds"] == pytest.approx(4.0)
|
|
assert body["video_max_frames"] == 64
|
|
assert body["video_min_tag_frames"] == 3
|
|
|
|
resp = await client.patch(
|
|
"/api/ml/settings",
|
|
json={"video_frame_interval_seconds": 5, "video_max_frames": 40,
|
|
"video_min_tag_frames": 4},
|
|
)
|
|
assert resp.status_code == 200
|
|
out = await resp.get_json()
|
|
assert out["video_frame_interval_seconds"] == pytest.approx(5.0)
|
|
assert out["video_max_frames"] == 40
|
|
assert out["video_min_tag_frames"] == 4
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_video_min_tag_frames_above_max_rejected(client):
|
|
resp = await client.patch(
|
|
"/api/ml/settings",
|
|
json={"video_max_frames": 10, "video_min_tag_frames": 20},
|
|
)
|
|
assert resp.status_code == 400
|
|
assert "video_min_tag_frames" 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
|