US07-03: Harden Media and Metadata Edge Cases (#85)

photo_pipeline/models/__init__.py

@@ -7,6 +7,7 @@ Alembic environment relies on.
 from photo_pipeline.models.albums import AlbumProposal
 from photo_pipeline.models.archives import ArchiveLocation, ArchiveOperation, ArchivePlan
 from photo_pipeline.models.assets import Asset, AssetPath
+from photo_pipeline.models.exif import ExifProjection
 from photo_pipeline.models.duplicates import (
     DuplicateCluster,
     DuplicateMember,
@@ -28,6 +29,7 @@ __all__ = [
     "DuplicateCluster",
     "DuplicateMember",
     "DuplicateNegativeLink",
+    "ExifProjection",
     "Job",
     "JobItem",
     "JobEvent",

photo_pipeline/models/exif.py

@@ -0,0 +1,33 @@
+"""The durable EXIF projection per asset and stage (concept §3, US07-03).
+
+One row per ``(asset_id, stage)``: what the stage wanted written, what the file
+looked like afterwards, and whether anything outside the stage's ownership moved.
+``state = divergent`` is the whole point of the table — it survives restarts, keeps
+the asset out of stages that require verified metadata, and gives a human something
+to look at instead of a silent repair.
+"""
+
+from __future__ import annotations
+
+from datetime import datetime
+
+from sqlalchemy import DateTime, ForeignKey, Integer, String
+from sqlalchemy.orm import Mapped, mapped_column
+
+from photo_pipeline.db import Base
+
+
+class ExifProjection(Base):
+    __tablename__ = "exif_projections"
+
+    asset_id: Mapped[str] = mapped_column(ForeignKey("assets.id"), primary_key=True)
+    stage: Mapped[str] = mapped_column(String, primary_key=True)  # safety | analysis
+    id: Mapped[str] = mapped_column(String, nullable=False)
+    projection_version: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
+    desired_json: Mapped[str | None] = mapped_column(String)
+    divergent_fields: Mapped[str | None] = mapped_column(String)  # JSON array
+    result_file_sha256: Mapped[str | None] = mapped_column(String)
+    state: Mapped[str] = mapped_column(String, nullable=False)  # verified|divergent|failed
+    error_code: Mapped[str | None] = mapped_column(String)
+    verified_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))
+    updated_at: Mapped[datetime | None] = mapped_column(DateTime(timezone=True))