From da5e38ce9c1fe2ba4854952eac0cc2a694e1c38b Mon Sep 17 00:00:00 2001 From: moe-berri Date: Fri, 4 Sep 2026 16:33:16 -0700 Subject: [PATCH] refactor(shadow_eval): state the cap's constraint without the rationale --- litellm/integrations/shadow_eval_logger.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/litellm/integrations/shadow_eval_logger.py b/litellm/integrations/shadow_eval_logger.py index 2c56ecb8721..fc82ebafe09 100644 --- a/litellm/integrations/shadow_eval_logger.py +++ b/litellm/integrations/shadow_eval_logger.py @@ -60,9 +60,8 @@ _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 deployment carrying an elevated reasoning_effort spends a tight cap before it ever -# answers, and the truncated reply is recorded as an unparseable verdict. +# Covers the judge's reasoning tokens as well as its small JSON answer: a judge deployment +# carrying an elevated reasoning_effort spends a tight cap before it ever answers. JUDGE_MAX_OUTPUT_TOKENS: Final = 4096 _MAX_ERROR_CHARS: Final = 500