[FEATURE]The latest version of DeepSeek is incompatible with reasoning_content.

[ZangXincz]

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

LLM Call Failed │
│ Error: OpenAI API call failed: Error code: 400 - {'error': {'message': 'The reasoning_content in the thinking mode │
│ must be passed back to the API.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}

[CrewAIEventsBus] Warning: Event pairing mismatch. 'llm_call_failed' closed 'agent_execution_started' (expected
'llm_call_started')
ERROR:crewai.flow.flow:Error executing listener call_llm_native_tools: Error code: 400 - {'error': {'message': 'The reasoning_content in the thinking mode must be passed back to the API.', 'type': 'invalid_request_error', 'param': None, 'code': 'invalid_request_error'}}

The latest version of DeepSeek has added DeepSeek-V4-Flash and DeepSeek-V4-Pro. In the thinking mode, in addition to the "content" parameter, it will also return the "reasoning_content" parameter. Currently, this may not be compatible.

Describe the solution you'd like

Hope to achieve better compatibility with the return type of deepseek

Describe alternatives you've considered

No response

Additional context

No response

Willingness to Contribute

I can test the feature once it's implemented