diff --git a/litellm/integrations/shadow_eval_logger.py b/litellm/integrations/shadow_eval_logger.py
index b554c4bc668..2c56ecb8721 100644
--- a/litellm/integrations/shadow_eval_logger.py
+++ b/litellm/integrations/shadow_eval_logger.py
@@ -60,12 +60,9 @@ _MAX_CONCURRENT_SHADOW_TASKS: Final = 16
 _MAX_JUDGE_RESPONSE_CHARS: Final = 8_000
 _MAX_JUDGE_PROMPT_CHARS: Final = 24_000
 
-# The judge answers with a small JSON object, but the cap covers reasoning tokens too. A
-# judge_model deployment configured with an elevated reasoning_effort or thinking budget
-# (a realistic pick: an admin's best reasoning model doubling as the judge) spends most or
-# all of a tight cap on that reasoning, invisibly to this call, and the reply arrives empty
-# or truncated mid-object, which the attempt records as an unparseable verdict. Headroom is
-# free: max_tokens is a ceiling, and only generated tokens bill.
+# The judge answers with a small JSON object, but the cap covers reasoning tokens too: a
+# judge deployment carrying an elevated reasoning_effort spends a tight cap before it ever
+# answers, and the truncated reply is recorded as an unparseable verdict.
 JUDGE_MAX_OUTPUT_TOKENS: Final = 4096
 
 _MAX_ERROR_CHARS: Final = 500
diff --git a/tests/test_litellm/integrations/test_shadow_eval_logger.py b/tests/test_litellm/integrations/test_shadow_eval_logger.py
index 367ad758772..9fcbd116f63 100644
--- a/tests/test_litellm/integrations/test_shadow_eval_logger.py
+++ b/tests/test_litellm/integrations/test_shadow_eval_logger.py
@@ -120,12 +120,12 @@ def _router(
     return router
 
 
-def _reasoning_judge_router(reasoning_tokens, verdict='{"preference": "A", "confidence": 0.9}'):
+def _reasoning_judge_router(
+    reasoning_tokens: int, verdict: str = '{"preference": "A", "confidence": 0.9}'
+) -> MagicMock:
     """A router whose judge arm reasons before it answers, the way a deployment carrying an
-    elevated reasoning_effort does. Reasoning is billed against the caller's own max_tokens
-    and the reply is cut off at that cap, so a cap that does not clear the reasoning budget
-    yields a truncated verdict or no verdict at all. One character stands in for one token,
-    which is what makes the cap the thing under test."""
+    elevated reasoning_effort does: reasoning bills against the caller's own max_tokens and
+    the reply is cut off at that cap. One character stands in for one token."""
     router = MagicMock()
     router.model_group_alias = {}
     router.get_model_list = MagicMock(return_value=[{"litellm_params": {"model": "openai/gpt-4o-mini"}}])