[BUG] Open researcher get 400 error from litellm after planning step when using deepseek-r1 (CodeAgent)

Describe the bug
I'm using open researcher with deepseek-r1 using litellmmodel. The CodeAgent after the planning steps would create an input message that contains two consecutive message from "assistant". See the following screenshot from the open-telemetry.

The first assistant message is from the "initial_facts" step while the second assistant message was from the "initial_planning" step.

This message would cause the deepseek-r1 model to return a 400 error code.

Code to reproduce the error
open researcher with deepseek-r1 as model

Error logs (if any)

Error in generating model output:
litellm.BadRequestError: OpenAIException - Error code: 400 - {'error': {'code': 'invalid_parameter_error', 'param':
None, 'message': '<400> InternalError.Algo.InvalidParameter: An unknown error occurred due to an unsupported input
format.', 'type': 'invalid_request_error'}, 'id': 'chatcmpl-df620c7e-749a-999e-b873-bc32d7a6112a', 'request_id':
'df620c7e-749a-999e-b873-bc32d7a6112a'}

Packages version:
1.8.1

Additional context
Add any other context about the problem here.

Start in the Open Researcher CodeAgent message construction after the initial_facts and initial_planning steps, using the reported deepseek-r1 and LiteLLM reproduction. Trace how those steps become the model input and compare the resulting message sequence with the provider's accepted format. Done means the reproduction no longer sends consecutive assistant messages and the request succeeds.