部分模型调用官方代码时只能输出思考无法输出回复

官方调用模式如下：

from openai import OpenAI
import os

# 初始化OpenAI客户端
client = OpenAI(
    # 如果没有配置环境变量，请用百炼API Key替换：api_key="sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)

reasoning_content = ""  # 定义完整思考过程
answer_content = ""     # 定义完整回复
is_answering = False   # 判断是否结束思考过程并开始回复

# 创建聊天完成请求
completion = client.chat.completions.create(
    model="deepseek-r1",  # 此处以 deepseek-r1 为例，可按需更换模型名称
    messages=[
        {"role": "user", "content": "9.9和9.11谁大"}
    ],
    stream=True,
    # 解除以下注释会在最后一个chunk返回Token使用量
    # stream_options={
    #     "include_usage": True
    # }
)

print("\n" + "=" * 20 + "思考过程" + "=" * 20 + "\n")

for chunk in completion:
    # 如果chunk.choices为空，则打印usage
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
    else:
        delta = chunk.choices[0].delta
        # 打印思考过程
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None:
            print(delta.reasoning_content, end='', flush=True)
            reasoning_content += delta.reasoning_content
        else:
            # 开始回复
            if delta.content != "" and is_answering == False:
                print("\n" + "=" * 20 + "完整回复" + "=" * 20 + "\n")
                is_answering = True
            # 打印回复过程
            print(delta.content, end='', flush=True)
            answer_content += delta.content

问题原因是判断思考数据时没有判断思考数据为空字符串

#delta.reasoning_content增加delta.reasoning_content不等于空值的判断
if hasattr(delta, 'reasoning_content') and delta.reasoning_content != None and delta.reasoning_content != '':
#同理delta.content增加不等于None的判断
if delta.content != "" and delta.content != None and is_answering == False:

以下是模型回复的几个例子

三、deepseek-v3输出思考过程是在content中，输出模式跟其他模型完全不同，这个可能得特殊处理，但API示例用的同一套代码误导严重

建议不使用deepseek-v3模型，输出毫无规律，随性至极。

目前看出的问题：
1、content中<\think><\/think>标签无闭合，markdown无法识别
2、chunk中会包含content='思考过程===================='等意义不明的信息。

2025-02-26 13:00:55,044 - INFO - chunk == ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content='', function_call=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=, model='deepseek-v3', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
2025-02-26 13:00:55,044 - INFO - chunk == ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content='================', function_call=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=, model='deepseek-v3', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
2025-02-26 13:00:55,124 - INFO - chunk == ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content='====', function_call=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=, model='deepseek-v3', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
2025-02-26 13:00:55,297 - INFO - chunk == ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content='完整', function_call=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=, model='deepseek-v3', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
2025-02-26 13:00:55,789 - INFO - chunk == ChatCompletionChunk(id='', choices=[Choice(delta=ChoiceDelta(content='思考过程====================', function_call=None, role=None, tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=, model='deepseek-v3', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)