fix(proxy): change model mismatch logs from WARNING to DEBUG (#20994)

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

@@ -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,

litellm/proxy/proxy_server.py

@@ -4915,7 +4915,7 @@ 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,