### Check for existing issues

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

### What happened?

"I noticed this issue while comparing the behavior with the official DeepSeek API documentation."

### Steps to Reproduce

"I noticed this while comparing the behavior with the official DeepSeek API documentation."

### Relevant log output

```shell "messages": [ { "role": "user", "content": "9.11 and 9.8, which is greater?" } ], "reasoning_effort": "medium", "extra_body": { "thinking": { "type": "enabled" } }。response："model": "/data/DeepSeek-V4-Flash", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "This is a trick question that often trips people up because of how we read numbers.\n\nWhile 9.11 is a larger *number* in terms of digits (eleven vs. eight), **9.8 is greater in value.**\n\nHere’s why:\n* 9.8 is the same as 9.80.\n* 9.80 is greater than 9.11.\n\nSo, **9.8 is greater than 9.11**.", "refusal": null, "annotations": null, "audio": null, "function_call": null, "tool_calls": [], "reasoning": null }, "logprobs": null, …