feat(fc2b): add Camie tagger ONNX wrapper

CPU-only, lazy-loaded, process-singleton ONNX session. Parses Camie's
string-category selected_tags.csv (vs WD14's integer Danbooru ids).
STORE_FLOOR (0.05) keeps the stored predictions JSON compact;
SURFACED_CATEGORIES gates which categories the suggestion UI shows
(meta/rating/year stored but never surfaced).

Inference itself isn't unit-tested (1GB model not in CI); the missing-
model error path and pure-logic surface are. Full inference runs in the
local integration suite.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/test_ml_tagger.py

@@ -0,0 +1,41 @@
+"""Tagger unit tests. The ONNX model isn't available in CI (it's a 1GB
+download into /models), so these test the pure-logic surface: STORE_FLOOR
+constant, SURFACED_CATEGORIES set, TagPrediction dataclass, and the
+load()-missing-file error path. Full inference is exercised by the local
+integration suite against a real /models volume.
+"""
+
+import pytest
+
+from backend.app.services.ml.tagger import (
+    STORE_FLOOR,
+    SURFACED_CATEGORIES,
+    TagPrediction,
+    Tagger,
+    get_tagger,
+)
+
+
+def test_surfaced_categories():
+    assert SURFACED_CATEGORIES == {"artist", "character", "copyright", "general"}
+
+
+def test_store_floor_is_low():
+    assert 0 < STORE_FLOOR < 0.2
+
+
+def test_tag_prediction_dataclass():
+    p = TagPrediction(name="x", category="general", confidence=0.9)
+    assert p.name == "x"
+    assert p.category == "general"
+    assert p.confidence == 0.9
+
+
+def test_get_tagger_singleton():
+    assert get_tagger() is get_tagger()
+
+
+def test_load_raises_when_model_missing(tmp_path):
+    t = Tagger(model_dir=tmp_path / "nonexistent")
+    with pytest.raises(RuntimeError, match="model.onnx missing"):
+        t.load()