Let a deterministic guard override the fallback classifier per description 🟩

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

domain/data_transformation/guarded_column_classifier.py

@@ -28,4 +28,15 @@ class GuardedColumnClassifier(ColumnClassifier[E]):
         self._fallback = fallback
 
     def classify(self, descriptions: set[str]) -> dict[str, E]:
-        raise NotImplementedError
+        guarded: dict[str, E] = {}
+        misses: set[str] = set()
+        for description in descriptions:
+            member = self._guard(description)
+            if member is not None:
+                guarded[description] = member
+            else:
+                misses.add(description)
+        # Only the misses reach the fallback — a fully-guarded batch never calls it.
+        if misses:
+            guarded.update(self._fallback.classify(misses))
+        return guarded