bvandeusen
4daa3f2790
Make the SigLIP embedder an operator choice (drop-in to SigLIP 2:
google/siglip2-so400m-patch16-512 is a verified 1152-d model at 512px → no
schema change, better small-cue fidelity). A swap = set model + re-embed +
retrain, all operator-driven; the GPU agent does the re-embed so it's fast.
- settings: embedder_model_name is now a setting (migration 0065) alongside the
existing embedder_model_version; both editable + validated (non-empty) in the
ml admin API. The server embedder loads by HF name (AutoImageProcessor/Model,
model-agnostic), preferring the pre-downloaded local dir for the default so
existing deploys don't re-download; rebuilds on a name change.
- agent: new 'embed' job = whole-image SigLIP embedding (mean-pool video frames)
under the lease-announced model → POST /jobs/submit_embedding writes
image_record.siglip_embedding + siglip_model_version. The lease now announces
the model FROM THE SETTING (not a constant).
- re-embed routing: enqueue_gpu_backfill('embed') selects unembedded + stale-
version images; 'siglip' now re-embeds concept crops whose version != current
(so a swap re-triggers crops, not just the never-embedded back-catalogue). The
CPU ml-worker backfill no longer re-embeds on a version mismatch (it can't
churn the library at 512px) — the GPU agent owns version re-embeds. Daily
'embed' + 'siglip' beats self-heal.
- scoring: score_image only bags embeddings in the CURRENT model's space (whole-
image gated by siglip_model_version, concept regions by embedding_version) so a
mid-swap stale vector isn't scored by new-space heads; legacy NULL = current.
- UI: GpuAgentCard "Embedding model (advanced)" — edit name/version, Save, and
"Re-embed library (GPU)" (queues embed + siglip); points at SigLIP 2.
Tests: lease announces model + submit_embedding round-trip; enqueue 'embed'
selects stale/unembedded; stale-version excluded from scoring; embedder model
settable + empty rejected; siglip gate updated to current-version concept.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
134 lines
4.9 KiB
Python
134 lines
4.9 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_embedder_model_settable_and_empty_rejected(client):
|
|
# #1190: the embedder model name + version are operator-settable (a swap),
|
|
# and neither may be blanked.
|
|
body = await (await client.get("/api/ml/settings")).get_json()
|
|
assert body["embedder_model_name"] == "google/siglip-so400m-patch14-384"
|
|
|
|
ok = await client.patch("/api/ml/settings", json={
|
|
"embedder_model_name": "google/siglip2-so400m-patch16-512",
|
|
"embedder_model_version": "siglip2-so400m-patch16-512",
|
|
})
|
|
assert ok.status_code == 200
|
|
out = await ok.get_json()
|
|
assert out["embedder_model_name"] == "google/siglip2-so400m-patch16-512"
|
|
assert out["embedder_model_version"] == "siglip2-so400m-patch16-512"
|
|
|
|
bad = await client.patch("/api/ml/settings", json={"embedder_model_name": " "})
|
|
assert bad.status_code == 400
|
|
|
|
|
|
@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
|