diff --git a/tests/test_split_prefill.py b/tests/test_split_prefill.py
index 66e5f6bc..3c36fb5d 100644
--- a/tests/test_split_prefill.py
+++ b/tests/test_split_prefill.py
@@ -1389,7 +1389,11 @@ def run(cuda_graphs):
                 pytest.fail("decode request did not reach its second recurrent step")
             assert split_request.phase is RequestPhase.PREFILLING_RECURRENT
             assert split_request.num_prefilled_tokens == 0
-            assert split_request.num_preluded_tokens == 2
+            # WCPB stages prompt chunks in a prelude wavefront: with
+            # total_ut_steps=4, prefill_chunk_size=2 and a 4-token budget, both
+            # of this prompt's chunks are staged together. num_prefilled_tokens
+            # stays 0 because the final recurrent depth has not completed.
+            assert split_request.num_preluded_tokens == 4
 
             graph_counts = None
             if e.model_runner.graphs is not None: