From 887f4d993b1319054f7e3b8c8d00014492453490 Mon Sep 17 00:00:00 2001 From: Milan Date: Wed, 11 Feb 2026 23:41:43 +0200 Subject: [PATCH] fix(proxy): change model mismatch logs from WARNING to DEBUG Fixes #20990 PR #19943 added logging when the proxy overrides model names to prevent internal provider prefixes from leaking to clients. The behavior works correctly but logs a WARNING on every request with model mismatch. For high-traffic customers using model aliases or provider prefixes, this creates millions of warnings per day, flooding logs and causing disk space issues. Changed log level from WARNING to DEBUG since: - The model mismatch is expected behavior when using aliases - The override happens correctly regardless of log level - Operators can still enable with LITELLM_LOG=DEBUG for debugging Changes: - common_request_processing.py: 2 warnings -> debug (non-streaming) - proxy_server.py: 1 warning -> debug (streaming) --- litellm/proxy/common_request_processing.py | 4 ++-- litellm/proxy/proxy_server.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/litellm/proxy/common_request_processing.py b/litellm/proxy/common_request_processing.py index f33b241226..a02bc7f9e5 100644 --- a/litellm/proxy/common_request_processing.py +++ b/litellm/proxy/common_request_processing.py @@ -282,7 +282,7 @@ def _override_openai_response_model( if isinstance(response_obj, dict): downstream_model = response_obj.get("model") if downstream_model != requested_model: - verbose_proxy_logger.warning( + verbose_proxy_logger.debug( "%s: response model mismatch - requested=%r downstream=%r. Overriding response['model'] to requested model.", log_context, requested_model, @@ -301,7 +301,7 @@ def _override_openai_response_model( downstream_model = getattr(response_obj, "model", None) if downstream_model != requested_model: - verbose_proxy_logger.warning( + verbose_proxy_logger.debug( "%s: response model mismatch - requested=%r downstream=%r. Overriding response.model to requested model.", log_context, requested_model, diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index 6286d6dd1c..abfe80d377 100644 --- a/litellm/proxy/proxy_server.py +++ b/litellm/proxy/proxy_server.py @@ -4764,7 +4764,7 @@ def _restamp_streaming_chunk_model( chunk.get("model") if isinstance(chunk, dict) else getattr(chunk, "model", None) ) if not model_mismatch_logged and downstream_model != requested_model_from_client: - verbose_proxy_logger.warning( + verbose_proxy_logger.debug( "litellm_call_id=%s: streaming chunk model mismatch - requested=%r downstream=%r. Overriding model to requested.", request_data.get("litellm_call_id"), requested_model_from_client,