Merge nucleic/sleek-ember-seal-uady into dev

tests/test_purpose_data.py

@@ -84,6 +84,26 @@ class CurationTests(unittest.TestCase):
                 near_duplicate_threshold=0.92,
             )
 
+    def test_reviewed_semantic_exclusions_fail_closed_on_corpus_drift(self):
+        first = source(example(0, prompt="Plan the cache migration", purpose="planning"), 1)
+        second = source(
+            example(1, prompt="Propose a cache migration plan", purpose="planning"), 2
+        )
+        decision = {
+            "droppedPromptHash": purpose_data.prompt_hash(second.value["prompt"]),
+            "matchedPromptHash": purpose_data.prompt_hash(first.value["prompt"]),
+            "similarity": 0.98,
+        }
+        result = purpose_data.exclude_reviewed_duplicates(
+            [first, second], [decision]
+        )
+        self.assertEqual([first], result.records)
+        self.assertEqual("semantic-reviewed", result.duplicates[0].kind)
+        with self.assertRaisesRegex(
+            purpose_data.DataError, "no longer matches the curated corpus"
+        ):
+            purpose_data.exclude_reviewed_duplicates([first], [decision])
+
 
 class SplitTests(unittest.TestCase):
     def test_split_is_deterministic_stratified_and_keeps_vague_out_of_train(self):