fix: guard against empty choices and message=None in LLM response

response.choices[0].message.content raises IndexError (empty choices) or
AttributeError (message=None on filtered content) during dataset generation.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

dataset/qa_dataset.py

@@ -177,6 +177,8 @@ Answer:"""
             messages=[{"role": "user", "content": prompt}],
             temperature=0.3,
         )
+        if not response.choices or response.choices[0].message is None:
+            raise ValueError("LLM returned empty or filtered response")
         return response.choices[0].message.content