feat(fc2b): schema migration 0003 — ML pipeline tables

Renames image_record.wd14_* -> tagger_* (we're on Camie now, not WD14).
Adds tag_allowlist (auto-apply opt-in, per-tag confidence),
tag_suggestion_rejection (per-image dismissals), tag_alias (composite
(string, category) -> canonical tag, resolved at read time),
tag_reference_embedding (per-tag SigLIP centroids), and the ml_settings
singleton (per-category + centroid thresholds, model version pins).

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

backend/app/models/__init__.py

@@ -9,9 +9,14 @@ from .image_record import ImageRecord
 from .import_batch import ImportBatch
 from .import_settings import ImportSettings
 from .import_task import ImportTask
+from .ml_settings import MLSettings
 from .post import Post
 from .source import Source
 from .tag import Tag, TagKind, image_tag
+from .tag_alias import TagAlias
+from .tag_allowlist import TagAllowlist
+from .tag_reference_embedding import TagReferenceEmbedding
+from .tag_suggestion_rejection import TagSuggestionRejection
 
 __all__ = [
     "Base",
@@ -28,4 +33,9 @@ __all__ = [
     "ImportBatch",
     "ImportTask",
     "ImportSettings",
+    "MLSettings",
+    "TagAlias",
+    "TagAllowlist",
+    "TagReferenceEmbedding",
+    "TagSuggestionRejection",
 ]

backend/app/models/image_record.py

@@ -56,8 +56,8 @@ class ImageRecord(Base):
     )
 
     # ML fields (populated by FC-2's ml-worker)
-    wd14_predictions: Mapped[dict | None] = mapped_column(JSON, nullable=True)
-    wd14_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
+    tagger_predictions: Mapped[dict | None] = mapped_column(JSON, nullable=True)
+    tagger_model_version: Mapped[str | None] = mapped_column(String(128), nullable=True)
     # 1152 = SigLIP-so400m embedding dim. Swapping models in FC-2 may require
     # a column-width migration.
     siglip_embedding: Mapped[list[float] | None] = mapped_column(Vector(1152), nullable=True)

backend/app/models/ml_settings.py

@@ -0,0 +1,42 @@
+"""MLSettings — single-row table holding ML pipeline tunables."""
+
+from datetime import datetime
+
+from sqlalchemy import CheckConstraint, DateTime, Float, Integer, String, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class MLSettings(Base):
+    __tablename__ = "ml_settings"
+    __table_args__ = (CheckConstraint("id = 1", name="ck_ml_settings_singleton"),)
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True)
+    suggestion_threshold_artist: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.30
+    )
+    suggestion_threshold_character: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.50
+    )
+    suggestion_threshold_copyright: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.50
+    )
+    suggestion_threshold_general: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.95
+    )
+    centroid_similarity_threshold: Mapped[float] = mapped_column(
+        Float, nullable=False, default=0.55
+    )
+    min_reference_images: Mapped[int] = mapped_column(
+        Integer, nullable=False, default=5
+    )
+    tagger_model_version: Mapped[str] = mapped_column(
+        String(128), nullable=False, default="camie-tagger-v2"
+    )
+    embedder_model_version: Mapped[str] = mapped_column(
+        String(128), nullable=False, default="siglip-so400m-patch14-384"
+    )
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/models/tag_alias.py

@@ -0,0 +1,24 @@
+"""TagAlias — maps a model's (name, category) prediction to the operator's
+canonical tag. Resolved at suggestion-read time so raw predictions stay
+unmolested in image_record.tagger_predictions.
+"""
+
+from datetime import datetime
+
+from sqlalchemy import DateTime, ForeignKey, String, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class TagAlias(Base):
+    __tablename__ = "tag_alias"
+
+    alias_string: Mapped[str] = mapped_column(String(255), primary_key=True)
+    alias_category: Mapped[str] = mapped_column(String(32), primary_key=True)
+    canonical_tag_id: Mapped[int] = mapped_column(
+        ForeignKey("tag.id", ondelete="CASCADE"), nullable=False, index=True
+    )
+    created_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/models/tag_allowlist.py

@@ -0,0 +1,26 @@
+"""TagAllowlist — tags the operator opted-in to auto-apply via maintenance."""
+
+from datetime import datetime
+
+from sqlalchemy import CheckConstraint, DateTime, Float, ForeignKey, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class TagAllowlist(Base):
+    __tablename__ = "tag_allowlist"
+    __table_args__ = (
+        CheckConstraint(
+            "min_confidence > 0 AND min_confidence <= 1",
+            name="ck_tag_allowlist_confidence_range",
+        ),
+    )
+
+    tag_id: Mapped[int] = mapped_column(
+        ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True
+    )
+    min_confidence: Mapped[float] = mapped_column(Float, nullable=False, default=0.95)
+    added_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/models/tag_reference_embedding.py

@@ -0,0 +1,23 @@
+"""TagReferenceEmbedding — per-tag centroid (mean SigLIP embedding of members)."""
+
+from datetime import datetime
+
+from pgvector.sqlalchemy import Vector
+from sqlalchemy import DateTime, ForeignKey, Integer, String, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class TagReferenceEmbedding(Base):
+    __tablename__ = "tag_reference_embedding"
+
+    tag_id: Mapped[int] = mapped_column(
+        ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True
+    )
+    embedding: Mapped[list[float]] = mapped_column(Vector(1152), nullable=False)
+    reference_count: Mapped[int] = mapped_column(Integer, nullable=False)
+    model_version: Mapped[str] = mapped_column(String(128), nullable=False)
+    updated_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )

backend/app/models/tag_suggestion_rejection.py

@@ -0,0 +1,25 @@
+"""TagSuggestionRejection — per-image dismissed suggestions.
+
+Prevents re-suggestion AND prevents allowlist auto-apply on that image.
+"""
+
+from datetime import datetime
+
+from sqlalchemy import DateTime, ForeignKey, func
+from sqlalchemy.orm import Mapped, mapped_column
+
+from .base import Base
+
+
+class TagSuggestionRejection(Base):
+    __tablename__ = "tag_suggestion_rejection"
+
+    image_record_id: Mapped[int] = mapped_column(
+        ForeignKey("image_record.id", ondelete="CASCADE"), primary_key=True
+    )
+    tag_id: Mapped[int] = mapped_column(
+        ForeignKey("tag.id", ondelete="CASCADE"), primary_key=True, index=True
+    )
+    rejected_at: Mapped[datetime] = mapped_column(
+        DateTime(timezone=True), nullable=False, server_default=func.now()
+    )