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

photo_pipeline/services/safety.py

@@ -108,9 +108,8 @@ from datetime import datetime, timezone
 from sqlalchemy import select
 from sqlalchemy.orm import sessionmaker
 
-from photo_pipeline.integrations import exiftool
-from photo_pipeline.models import Asset, SafetyReview
-from photo_pipeline.services import hashing
+from photo_pipeline.models import Asset, ExifProjection, SafetyReview
+from photo_pipeline.services import exif_checkpoint
 
 DECISIONS = {SFW, NSFW, "deferred"}
 
@@ -174,6 +173,14 @@ class SafetyService:
         with self._session_factory() as session:
             assets = list(session.scalars(_eligible_assets_query().order_by(Asset.current_path)))
             latest = self._latest_by_asset(session)
+            # One query, not one per asset: the reviewer needs to see a divergent
+            # checkpoint, which is neither "verified" nor a plain failure (US07-03).
+            projections = {
+                row.asset_id: row.state
+                for row in session.scalars(
+                    select(ExifProjection).where(ExifProjection.stage == "safety")
+                )
+            }
             rows = []
             for asset in assets:
                 review = latest.get(asset.id)
@@ -189,6 +196,7 @@ class SafetyService:
                         "decision": decision,
                         "suggested": classify(review.score) if review and review.score is not None else None,
                         "exif_verified": bool(review and review.exif_verified_at),
+                        "exif_state": projections.get(asset.id),
                     }
                 )
             return {"total": len(rows), "items": rows[offset : offset + limit]}
@@ -247,13 +255,24 @@ class SafetyService:
         result_sha256 = None
         if write_exif and decision in (SFW, NSFW) and path:
             ops = exif_projection(decision)
-            if exiftool.apply_keywords(path, add=ops["add"], remove=ops["remove"]):
-                # Read back: the chosen keyword present, the opposite absent.
-                keywords = exiftool.read_keyword_sets([path]).get(path, set())
-                opposite = NSFW if decision == SFW else SFW
-                if decision in keywords and opposite not in keywords:
-                    exif_verified_at = _now()
-                    result_sha256 = hashing.sha256_file(path)
+            # The full checkpoint: write the owned keyword, read the whole file back,
+            # and prove every field this stage does not own survived. A divergent
+            # result is recorded and left alone — it must not count as verified, so
+            # upload stays blocked until a human decides (US07-03).
+            result = exif_checkpoint.run(
+                path, add=tuple(ops["add"]), remove=tuple(ops["remove"])
+            )
+            exif_checkpoint.record(
+                self._session_factory,
+                asset_id=asset_id,
+                stage="safety",
+                result=result,
+                add=tuple(ops["add"]),
+                remove=tuple(ops["remove"]),
+            )
+            if result.verified:
+                exif_verified_at = result.verified_at
+                result_sha256 = result.sha256
 
         now = _now()
         with self._session_factory() as session: