Implement support for segments with an optional categories key

tests/test_framework_chunking.py

@@ -25,3 +25,19 @@ def test_chunk_transcript_batches_sections_by_token_limit():
     assert len(sections) == 2
     assert [segment.segment.id for segment in sections[0].segments] == [1, 2]
     assert [segment.segment.id for segment in sections[1].segments] == [3]
+
+
+def test_chunk_transcript_prompt_payload_includes_categories_when_present():
+    transcript = parse_transcript_json(
+        """
+        [
+          {"id": 1, "speaker": "A", "start": 0.0, "end": 1.0, "text": "one", "categories": ["intro", "aside"]}
+        ]
+        """
+    )
+
+    sections = chunk_transcript(transcript, max_section_tokens=8, estimator=FakeEstimator())
+
+    assert sections[0].prompt_payload() == [
+        {"id": 1, "original_text": "one", "categories": ["intro", "aside"]}
+    ]