发送请求前：ChatClientRequest[prompt=Prompt{messages=[UserMessage{content='你是谁?', metadata={messageType=USER}, messageType=USER}], modelOptions=org.springframework.ai.ollama.api.OllamaChatOptions@4ba55f9}, context={}]
接收到响应：ChatClientResponse[chatResponse=ChatResponse [metadata={ id: , usage: DefaultUsage{promptTokens=32, completionTokens=68, totalTokens=100}, rateLimit: org.springframework.ai.chat.metadata.EmptyRateLimit@13c1dc2c }, generations=[Generation[assistantMessage=AssistantMessage [messageType=ASSISTANT, toolCalls=[], textContent=我是Qwen，一个由阿里云开发的超大规模语言模型，我被命名为"通义千问"。我的英文名是GPT，中文名称为通义千问。我是阿里巴巴集团研发的AI助手，专门负责回答各种问题和提供信息。如果你有任何疑问或需要帮助，请随时告诉我！, metadata={messageType=ASSISTANT}], chatGenerationMetadata=DefaultChatGenerationMetadata[finishReason='stop', filters=0, metadata=0]]]], context={}]

 http://localhost:18088/ai?question=你是谁?

发送请求前：ChatClientRequest[prompt=Prompt{messages=[UserMessage{content='你是谁?', metadata={messageType=USER}, messageType=USER}], modelOptions=OpenAiChatOptions{model='qwen3.6-plus, frequencyPenalty=null, logitBias=null, logprobs=null, topLogprobs=null, maxTokens=null, maxCompletionTokens=null, n=null, outputModalities=null, outputAudio=null, presencePenalty=null, responseFormat=null, streamOptions=null, streamUsage=, seed=null, stop=null, temperature=null, topP=null, toolChoice=null, user='null', parallelToolCalls=null, store=null, metadata=null, reasoningEffort='null', verbosity='null', serviceTier='null', extraBody=null, toolCallbacks=[], toolNames=[], internalToolExecutionEnabled=null, toolContext={}}}, context={}]
接收到响应：ChatClientResponse[chatResponse=ChatResponse [metadata={ id: chatcmpl-ea261beb-99b9-92be-bb3d-a34f6ed63bab, usage: DefaultUsage{promptTokens=12, completionTokens=229, totalTokens=241}, rateLimit: org.springframework.ai.chat.metadata.EmptyRateLimit@7962b136 }, generations=[Generation[assistantMessage=AssistantMessage [messageType=ASSISTANT, toolCalls=[], textContent=我是 Qwen（通义千问），由阿里巴巴集团旗下通义实验室研发的大语言模型。有什么我可以帮你的吗？, metadata={role=assistant, messageType=ASSISTANT, refusal=, finishReason=STOP, annotations=[{}], index=0, id=chatcmpl-ea261beb-99b9-92be-bb3d-a34f6ed63bab}], chatGenerationMetadata=DefaultChatGenerationMetadata[finishReason='STOP', filters=0, metadata=0]]]], context={}]

 流式 http://localhost:18088/ai3?question=你好?

发送流式请求：ChatClientRequest[prompt=Prompt{messages=[UserMessage{content='你好', metadata={messageType=USER}, messageType=USER}], modelOptions=OpenAiChatOptions{model='qwen3.6-plus, frequencyPenalty=null, logitBias=null, logprobs=null, topLogprobs=null, maxTokens=null, maxCompletionTokens=null, n=null, outputModalities=null, outputAudio=null, presencePenalty=null, responseFormat=null, streamOptions=null, streamUsage=, seed=null, stop=null, temperature=null, topP=null, toolChoice=null, user='null', parallelToolCalls=null, store=null, metadata=null, reasoningEffort='null', verbosity='null', serviceTier='null', extraBody=null, toolCallbacks=[], toolNames=[], internalToolExecutionEnabled=null, toolContext={}}}, context={}]
收到流式响应片段：ChatClientResponse[chatResponse=ChatResponse [metadata={ id: chatcmpl-ff85a1d8-a06d-93d9-a4ad-9a93ae97b44a, usage: DefaultUsage{promptTokens=0, completionTokens=0, totalTokens=0}, rateLimit: org.springframework.ai.chat.metadata.EmptyRateLimit@47351de9 }, generations=[Generation[assistantMessage=AssistantMessage [messageType=ASSISTANT, toolCalls=[], textContent=, metadata={chunkChoice=Choice{delta=Delta{content=null, functionCall=, refusal=, role=assistant, toolCalls=, additionalProperties={reasoning_content=Here}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}, role=assistant, messageType=ASSISTANT, finishReason=_UNKNOWN, refusal=, annotations=[], index=0, id=chatcmpl-ff85a1d8-a06d-93d9-a4ad-9a93ae97b44a}], chatGenerationMetadata=DefaultChatGenerationMetadata[finishReason='_UNKNOWN', filters=0, metadata=0]]]], context={}]
收到流式响应片段：ChatClientResponse[chatResponse=ChatResponse [metadata={ id: chatcmpl-ff85a1d8-a06d-93d9-a4ad-9a93ae97b44a, usage: DefaultUsage{promptTokens=0, completionTokens=0, totalTokens=0}, rateLimit: org.springframework.ai.chat.metadata.EmptyRateLimit@4b41b0d7 }, generations=[Generation[assistantMessage=AssistantMessage [messageType=ASSISTANT, toolCalls=[], textContent=, metadata={chunkChoice=Choice{delta=Delta{content=null, functionCall=, refusal=, role=, toolCalls=, additionalProperties={reasoning_content='s a thinking process}}, finishReason=null, index=0, logprobs=null, additionalProperties={}}, role=assistant, messageType=ASSISTANT, finishReason=_UNKNOWN, refusal=, annotations=[], index=0, id=chatcmpl-ff85a1d8-a06d-93d9-a4ad-9a93ae97b44a}], chatGenerationMetadata=DefaultChatGenerationMetadata[finishReason='_UNKNOWN', filters=0, metadata=0]]]], context={}]
收到流式响应片段：ChatClientResponse[chatResponse=ChatResponse [metadata={ id: chatcmpl-ff85a1d8-a06d-93d9-a4ad-9a93ae97b44a, usage: DefaultUsage{promptTokens=0, completionTokens=0, totalTokens=0}, rateLimit: org.springframework.ai.chat.metadata.EmptyRateLimit@5a01eb0 }, generations=[Generation[assistantMessage=AssistantMessage [messageType=ASSISTANT, toolCalls=[], textContent=, metadata={chunkChoice=Choice{delta=Delta{content=null, functionCall=, refusal=, role=, toolCalls=, additionalProperties={reasoning_content=:

 7、