### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

When I try to use opencode or any other harness like that using the litellm as a proxy , consuming sap ai core models it show me this error

"litellm.MidStreamFallbackError: litellm.APIConnectionError: 'MockValSer' object cannot be converted to 'SchemaSerializer'\nTraceback (most recent call last):\n File \"/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/streaming_handler.py\", line 2074, in __anext__\n obj_dict = processed_chunk.model_dump()\n File \"/app/.venv/lib/python3.13/site-packages/litellm/types/utils.py\", line 1791, in model_dump\n return super().model_dump(**kwargs)\n ~~~~~~~~~~~~~~~~~~^^^^^^^^^^\n File \"/app/.venv/lib/python3.13/site-packages/pydantic/main.py\", line 464, in model_dump\n return self.__pydantic_serializer__.to_python(\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^\n self,\n ^^^^^\n ...<12 lines>...\n serialize_as_any=serialize_as_any,\n ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^\n )\n ^\nTypeError: 'MockValSer' object cannot be converted to …