Handle zero-token source rows in code trace audit

runs/frontier-code-trace-v0/test_code_trace_preflight.py

@@ -20,6 +20,21 @@ class CodeTracePreflightTest(unittest.TestCase):
             source = root / "051315-051317.jsonl"
             with source.open("w") as stream:
                 for index in range(4501):
+                    if index == 100:
+                        stream.write(
+                            json.dumps(
+                                {
+                                    "chat_id": index,
+                                    "parent_chat_id": -1,
+                                    "timestamp": float(index),
+                                    "input_length": 0,
+                                    "output_length": 0,
+                                    "hash_ids": [],
+                                }
+                            )
+                            + "\n"
+                        )
+                        continue
                     input_tokens = 513 if index % 2 else 512
                     stream.write(
                         json.dumps(
@@ -53,6 +68,7 @@ class CodeTracePreflightTest(unittest.TestCase):
             self.assertEqual(
                 payload["selected"]["hash_contract"]["exact_source_block_size"], 512
             )
+            self.assertEqual(payload["selected"]["invalid_zero_token_rows"], 1)
             self.assertEqual(payload["max_model_len_recommendation"], 40960)
             output = root / "window"
             subprocess.run(
@@ -74,6 +90,7 @@ class CodeTracePreflightTest(unittest.TestCase):
         self.assertEqual(manifest["requests"], len(rows))
         self.assertGreaterEqual(manifest["duration_s"], 3600)
         self.assertEqual(rows[0]["sampling_u"], rows[1]["sampling_u"])
+        self.assertNotIn(100, {row["source_index"] for row in rows})
 
 
 if __name__ == "__main__":