DeepSeek V4 Thinking mode config not support, error message: 400 The reasoning_content in the thinking mode must be passed back to the API.

[MoonYear530]

config.yaml:

  - name: DeepSeek-V4-Flash
    provider: openai
    model: deepseek-v4-flash
    roles:
      - chat
      - edit
    capabilities:
      - tool_use
    apiBase: https://api.deepseek.com
    apiKey: ${{ secrets.DEEPSEEK_API_KEY }}
    contextLength: 1000000
    requestOptions:
      extraBodyProperties:
        thinking:
          type: "enabled"
    defaultCompletionOptions:
      temperature: 0.6
      maxTokens: 384000
      reasoning: true
      reasoning_effort: "high"
      stream: true

And then, Error handling model response:

There was an error handling the response from DeepSeek-Think. Please try to submit your message again.

400 The reasoning_content in the thinking mode must be passed back to the API.

[MoonYear530]

close duplicate discussion