fix(bedrock): filter LiteLLM-internal params from invoke request bodies

litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py

@@ -8,7 +8,10 @@ import httpx
 
 import litellm
 from litellm._logging import verbose_logger
-from litellm.litellm_core_utils.core_helpers import map_finish_reason
+from litellm.litellm_core_utils.core_helpers import (
+    filter_internal_params,
+    map_finish_reason,
+)
 from litellm.litellm_core_utils.logging_utils import track_llm_api_timing
 from litellm.litellm_core_utils.prompt_templates.factory import (
     cohere_message_pt,
@@ -168,6 +171,7 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
             for k, v in inference_params.items()
             if k not in self.aws_authentication_params
         }
+        inference_params = filter_internal_params(inference_params)
         request_data: dict = {}
         if provider == "cohere":
             if model.startswith("cohere.command-r"):

tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py

@@ -39,3 +39,20 @@ def test_transform_request_drops_stream_chunk_size(config, model):
     )
 
     assert "stream_chunk_size" not in json.dumps(request_body)
+
+
+def test_transform_request_drops_internal_params():
+    """LiteLLM-internal MCP params (e.g. skip_mcp_handler) are control flags used
+    inside LiteLLM and are not valid Bedrock inference parameters. Leaking them
+    into the provider request body makes Bedrock reject the request. The Converse
+    path already filters them via filter_internal_params; the invoke path must do
+    the same."""
+    request_body = AmazonInvokeConfig().transform_request(
+        model="mistral.mistral-7b-instruct-v0:2",
+        messages=[{"role": "user", "content": "hi"}],
+        optional_params={"skip_mcp_handler": True, "max_tokens": 10},
+        litellm_params={},
+        headers={},
+    )
+
+    assert "skip_mcp_handler" not in json.dumps(request_body)