refactor(ml): drop dead tagger/suggestion settings + columns (#1199)

Hygiene follow-up to the Camie retirement (#1189) — these were left inert to
bound that change; nothing reads them now. Migration 0068 drops:
- ml_settings: tagger_store_floor, tagger_model_version, suggestion_threshold_
  character/general (already dead pre-retirement — scoring uses per-head
  thresholds), video_min_tag_frames (only the deleted video-prediction
  aggregator used it).
- image_record: tagger_model_version (no writer), centroid_scores (dead JSON
  cache, no reader).

Also: ml_admin _EDITABLE/GET/_validate pruned (dropped the store-floor invariant
+ video_min_tag_frames check); MLThresholdSliders trimmed to a video-embedding
card (interval + max frames only); importer no longer resets the dropped cols;
download_models drops the Camie fetch; stale CASCADE comments in cleanup_service
no longer name the removed tables. Tests updated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

tests/test_api_ml_admin.py

@@ -19,19 +19,18 @@ 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
+    assert body["head_min_positives"] == 8
+    # Retired tagger/suggestion-threshold columns are gone from the payload
+    # (Camie retirement #1189/#1199).
+    assert "suggestion_threshold_general" not in body
+    assert "tagger_store_floor" not in body
+    assert "tagger_model_version" not in body
 
     resp = await client.patch(
-        "/api/ml/settings", json={"suggestion_threshold_general": 0.90}
+        "/api/ml/settings", json={"head_min_positives": 12}
     )
     assert resp.status_code == 200
-    assert (await resp.get_json())["suggestion_threshold_general"] == pytest.approx(0.90)
+    assert (await resp.get_json())["head_min_positives"] == 12
 
 
 @pytest.mark.asyncio
@@ -55,55 +54,29 @@ async def test_embedder_model_settable_and_empty_rejected(client):
 
 
 @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."""
+async def test_video_settings_default_and_patch(client):
+    """#747: video frame-sampling 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},
+        json={"video_frame_interval_seconds": 5, "video_max_frames": 40},
     )
     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):
+async def test_video_max_frames_below_one_rejected(client):
     resp = await client.patch(
-        "/api/ml/settings",
-        json={"video_max_frames": 10, "video_min_tag_frames": 20},
+        "/api/ml/settings", json={"video_max_frames": 0},
     )
     assert resp.status_code == 400
-    assert "video_min_tag_frames" in (await resp.get_json())["error"]
+    assert "video_max_frames" in (await resp.get_json())["error"]
 
 
 @pytest.mark.asyncio

tests/test_download_models.py

@@ -1,6 +1,6 @@
 """download_models tests. No network in CI; we test the 'already present →
-skip' short-circuit by faking the expected files, and that main() wires
-both ensure_* calls.
+skip' short-circuit by faking the expected files, and that main() wires the
+SigLIP fetch. (Camie download retired with the tagger, #1199.)
 """
 
 from unittest.mock import patch
@@ -8,29 +8,6 @@ from unittest.mock import patch
 from backend.app.scripts import download_models as dm
 
 
-def test_ensure_camie_skips_when_present(tmp_path, monkeypatch):
-    """v2 layout (HF Camais03/camie-tagger-v2): the ONNX file is named
-    camie-tagger-v2.onnx (not model.onnx) and tags ship inside
-    camie-tagger-v2-metadata.json (not selected_tags.csv). Both at root.
-    Updated 2026-05-25 after the actual repo layout was confirmed via
-    WebFetch — the old assertion pinned the v1 filenames."""
-    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
-    camie = tmp_path / "camie"
-    camie.mkdir(parents=True)
-    (camie / "camie-tagger-v2.onnx").write_bytes(b"x")
-    (camie / "camie-tagger-v2-metadata.json").write_text("{}")
-    with patch.object(dm, "_snapshot") as snap:
-        dm.ensure_camie()
-        snap.assert_not_called()
-
-
-def test_ensure_camie_downloads_when_missing(tmp_path, monkeypatch):
-    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
-    with patch.object(dm, "_snapshot") as snap:
-        dm.ensure_camie()
-        snap.assert_called_once()
-
-
 def test_ensure_siglip_skips_when_present(tmp_path, monkeypatch):
     monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
     sig = tmp_path / "siglip"
@@ -42,9 +19,15 @@ def test_ensure_siglip_skips_when_present(tmp_path, monkeypatch):
         snap.assert_not_called()
 
 
-def test_main_calls_both(monkeypatch):
+def test_ensure_siglip_downloads_when_missing(tmp_path, monkeypatch):
+    monkeypatch.setattr(dm, "MODEL_ROOT", tmp_path)
+    with patch.object(dm, "_snapshot") as snap:
+        dm.ensure_siglip()
+        snap.assert_called_once()
+
+
+def test_main_fetches_siglip(monkeypatch):
     calls = []
-    monkeypatch.setattr(dm, "ensure_camie", lambda: calls.append("camie"))
     monkeypatch.setattr(dm, "ensure_siglip", lambda: calls.append("siglip"))
     assert dm.main() == 0
-    assert calls == ["camie", "siglip"]
+    assert calls == ["siglip"]

tests/test_migration_0003.py

@@ -20,12 +20,15 @@ def test_new_tables_registered():
 
 def test_image_record_columns_renamed():
     cols = {c.name for c in ImageRecord.__table__.columns}
-    # tagger_predictions (the renamed wd14_predictions) was later dropped in
-    # migration 0046 — predictions live in image_prediction now (#768).
-    assert "tagger_model_version" in cols
+    # Legacy tagger columns are all gone: tagger_predictions/wd14_* dropped in
+    # 0046, tagger_model_version + centroid_scores dropped in 0068 (#1199, Camie
+    # retirement). The SigLIP embedding columns are the live ML fields.
+    assert "siglip_embedding" in cols
+    assert "siglip_model_version" in cols
+    assert "tagger_model_version" not in cols
+    assert "centroid_scores" not in cols
     assert "tagger_predictions" not in cols
     assert "wd14_predictions" not in cols
-    assert "wd14_model_version" not in cols
 
 
 def test_tag_alias_composite_pk():