Alibaba Cloud Model Studio:ストリーミング出力

from openai import OpenAI
import os

client = OpenAI(
    # リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
    # 環境変数を設定していない場合は、次の行をご利用の Model Studio API キーに置き換えてください： api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 中国 (北京) リージョンのモデルを使用する場合は、base_url を https://dashscope.aliyuncs.com/compatible-mode/v1 に置き換えてください。
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-vl-plus",  # これを他のマルチモーダルモデルに置き換え、それに応じてメッセージを修正できます。
    messages=[
        {"role": "user",
        "content": [{"type": "image_url",
                    "image_url": {"url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},},
                    {"type": "text", "text": "画像にはどのようなシーンが描かれていますか？"}]}],
    stream=True,
  # stream_options={"include_usage": True}
)
full_content = ""
print("ストリーミング出力コンテンツ：")
for chunk in completion:
    # stream_options.include_usage が True の場合、最後のチャンクの choices フィールドは空のリストになるため、スキップする必要があります。トークン使用量は chunk.usage から取得できます。
    if chunk.choices and chunk.choices[0].delta.content != "":
        full_content += chunk.choices[0].delta.content
        print(chunk.choices[0].delta.content)
print(f"完全なコンテンツ： {full_content}")

# ======= 重要 =======
# 中国 (北京) リージョンのモデルを使用する場合は、ベース URL を https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions に置き換えてください。
# リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
# === 実行前にこのコメントを削除してください ===

curl --location 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'Content-Type: application/json' \
--data '{
    "model": "qwen3-vl-plus",
    "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"
          }
        },
        {
          "type": "text",
          "text": "画像にはどのようなシーンが描かれていますか？"
        }
      ]
    }
  ],
    "stream":true,
    "stream_options":{"include_usage":true}
}'

import os
from dashscope import MultiModalConversation
import dashscope
# 中国 (北京) リージョンのモデルを使用する場合は、base_url を https://dashscope.aliyuncs.com/api/v1 に置き換えてください。
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {
        "role": "user",
        "content": [
            {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
            {"text": "画像にはどのようなシーンが描かれていますか？"}
        ]
    }
]

responses = MultiModalConversation.call(
    # リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
    # 環境変数を設定していない場合は、次の行をご利用の Model Studio API キーに置き換えてください： api_key="sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model='qwen3-vl-plus',  #  これを他のマルチモーダルモデルに置き換え、それに応じてメッセージを修正できます。
    messages=messages,
    stream=True,
    incremental_output=True)
    
full_content = ""
print("ストリーミング出力コンテンツ：")
for response in responses:
    if response["output"]["choices"][0]["message"].content:
        print(response.output.choices[0].message.content[0]['text'])
        full_content += response.output.choices[0].message.content[0]['text']
print(f"完全なコンテンツ： {full_content}")

import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Map;

import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import io.reactivex.Flowable;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        // 中国 (北京) リージョンのモデルを使用する場合は、base_url を https://dashscope.aliyuncs.com/api/v1 に置き換えてください。
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        // 可変マップを作成する必要があります。
        MultiModalMessage userMessage = MultiModalMessage.builder().role(Role.USER.getValue())
                .content(Arrays.asList(Collections.singletonMap("image", "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"),
                        Collections.singletonMap("text", "画像にはどのようなシーンが描かれていますか？"))).build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
                // 環境変数を設定していない場合は、次の行をご利用の Model Studio API キーに置き換えてください： .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-vl-plus")  //  これを他のマルチモーダルモデルに置き換え、それに応じてメッセージを修正できます。
                .messages(Arrays.asList(userMessage))
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(item -> {
            try {
                List<Map<String, Object>> content = item.getOutput().getChoices().get(0).getMessage().getContent();
                    // コンテンツが存在し、空でないことを確認します。
                if (content != null &&  !content.isEmpty()) {
                    System.out.println(content.get(0).get("text"));
                    }
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

    public static void main(String[] args) {
        try {
            streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= 重要 =======
# リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
# 中国 (北京) リージョンのモデルを使用する場合は、ベース URL を https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation に置き換えてください。
# === 実行前にこのコメントを削除してください ===

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen3-vl-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"image": "https://dashscope.oss-cn-beijing.aliyuncs.com/images/dog_and_girl.jpeg"},
                    {"text": "画像にはどのようなシーンが描かれていますか？"}
                ]
            }
        ]
    },
    "parameters": {
        "incremental_output": true
    }
}'

サンプルコード

from openai import OpenAI
import os

# OpenAI クライアントを初期化します。
client = OpenAI(
    # 環境変数を設定していない場合は、次の行を Model Studio API キーに置き換えます：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

messages = [{"role": "user", "content": "Who are you?"}]

completion = client.chat.completions.create(
    model="qwen-plus",  # 必要に応じて、他のディープシンキングモデルに置き換えることができます。
    messages=messages,
    # enable_thinking パラメーターは思考プロセスを有効にします。このパラメーターは qwen3-30b-a3b-thinking-2507、qwen3-235b-a22b-thinking-2507、および QwQ モデルではサポートされていません。
    extra_body={"enable_thinking": True},
    stream=True,
    # stream_options={
    #     "include_usage": True
    # },
)

reasoning_content = ""  # 完全な思考プロセス
answer_content = ""  # 完全な応答
is_answering = False  # 応答フェーズが開始されたかどうか
print("\n" + "=" * 20 + "Thinking process" + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        print("\nUsage:")
        print(chunk.usage)
        continue

    delta = chunk.choices[0].delta

    # 思考コンテンツのみを収集します。
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
        reasoning_content += delta.reasoning_content

    # コンテンツを受信し、応答を開始します。
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + "Full response" + "=" * 20 + "\n")
            is_answering = True
        print(delta.content, end="", flush=True)
        answer_content += delta.content

戻り結果

====================Thinking process====================

Okay, the user is asking "Who are you?". I need to provide an accurate and friendly answer. First, I must confirm my identity: Qwen, developed by the Tongyi Lab at Alibaba Group. Next, I should explain my main functions, such as answering questions, creating text, and logical reasoning. I need to maintain a friendly tone and avoid being too technical to make the user feel at ease. I should also avoid complex jargon to keep the answer simple and clear. Additionally, I might add some interactive elements, inviting the user to ask more questions to encourage further conversation. Finally, I'll check if I've missed any important information, such as my Chinese name "Tongyi Qianwen" and English name "Qwen", and my parent company and lab. I need to ensure the answer is comprehensive and meets the user's expectations.
====================Full response====================

Hello! I am Qwen, a large-scale language model developed by the Tongyi Lab at Alibaba Group. I can answer questions, create text, perform logical reasoning, write code, and more, all to provide users with high-quality information and services. You can call me Qwen, or just Tongyi Qianwen. How can I help you?

サンプルコード

import OpenAI from "openai";
import process from 'process';

// OpenAI クライアントを初期化します。
const openai = new OpenAI({
    apiKey: process.env.DASHSCOPE_API_KEY, // 環境変数から読み取ります
    baseURL: 'https://dashscope-intl.aliyuncs.com/compatible-mode/v1'
});

let reasoningContent = '';
let answerContent = '';
let isAnswering = false;

async function main() {
    try {
        const messages = [{ role: 'user', content: 'Who are you?' }];
        const stream = await openai.chat.completions.create({
            // 必要に応じて、他の Qwen3 または QwQ モデルに置き換えることができます。
            model: 'qwen-plus',
            messages,
            stream: true,
            // enable_thinking パラメーターは思考プロセスを有効にします。このパラメーターは qwen3-30b-a3b-thinking-2507、qwen3-235b-a22b-thinking-2507、および QwQ モデルではサポートされていません。
            enable_thinking: true
        });
        console.log('\n' + '='.repeat(20) + 'Thinking process' + '='.repeat(20) + '\n');

        for await (const chunk of stream) {
            if (!chunk.choices?.length) {
                console.log('\nUsage:');
                console.log(chunk.usage);
                continue;
            }

            const delta = chunk.choices[0].delta;
            
            // 思考コンテンツのみを収集します。
            if (delta.reasoning_content !== undefined && delta.reasoning_content !== null) {
                if (!isAnswering) {
                    process.stdout.write(delta.reasoning_content);
                }
                reasoningContent += delta.reasoning_content;
            }

            // コンテンツを受信した後、返信を開始します。
            if (delta.content !== undefined && delta.content) {
                if (!isAnswering) {
                    console.log('\n' + '='.repeat(20) + 'Full response' + '='.repeat(20) + '\n');
                    isAnswering = true;
                }
                process.stdout.write(delta.content);
                answerContent += delta.content;
            }
        }
    } catch (error) {
        console.error('Error:', error);
    }
}

main();

実行結果

====================Thinking process====================

Okay, the user is asking "Who are you?". I need to answer with my identity. First, I should clearly state that I am Qwen, a large-scale language model developed by Alibaba Cloud. Next, I can mention my main functions, such as answering questions, creating text, and logical reasoning. I should also emphasize my multilingual support, including Chinese and English, so the user knows I can handle requests in different languages. Additionally, I might need to explain my application scenarios, such as helping with study, work, and daily life. However, the user's question is quite direct, so I should keep it concise. I also need to ensure a friendly tone and invite the user to ask further questions. I will check for any missing important information, such as my version or latest updates, but the user probably doesn't need that level of detail. Finally, I will confirm the answer is accurate and free of errors.
====================Full response====================

I am Qwen, a large-scale language model developed by the Tongyi Lab at Alibaba Group. I can perform various tasks such as answering questions, creating text, logical reasoning, and coding. I support multiple languages, including Chinese and English. If you have any questions or need help, feel free to let me know!

サンプルコード

curl -X POST https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen-plus",
    "messages": [
        {
            "role": "user", 
            "content": "Who are you?"
        }
    ],
    "stream": true,
    "stream_options": {
        "include_usage": true
    },
    "enable_thinking": true
}'

戻り値

data: {"choices":[{"delta":{"content":null,"role":"assistant","reasoning_content":""},"index":0,"logprobs":null,"finish_reason":null}],"object":"chat.completion.chunk","usage":null,"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

.....

data: {"choices":[{"finish_reason":"stop","delta":{"content":"","reasoning_content":null},"index":0,"logprobs":null}],"object":"chat.completion.chunk","usage":null,"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

data: {"choices":[],"object":"chat.completion.chunk","usage":{"prompt_tokens":10,"completion_tokens":360,"total_tokens":370},"created":1745485391,"system_fingerprint":null,"model":"qwen-plus","id":"chatcmpl-e2edaf2c-8aaf-9e54-90e2-b21dd5045503"}

data: [DONE]

サンプルコード

import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = "https://dashscope-intl.aliyuncs.com/api/v1/"

messages = [{"role": "user", "content": "Who are you?"}]

completion = Generation.call(
    # 環境変数を設定していない場合は、次の行を Model Studio API キーに置き換えます：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 必要に応じて、他のディープシンキングモデルに置き換えることができます。
    model="qwen-plus",
    messages=messages,
    result_format="message", # オープンソースの Qwen3 モデルは "message" のみをサポートします。より良い体験のために、他のモデルでもこのパラメーターを "message" に設定することを推奨します。
    # ディープシンキングを有効にします。このパラメーターは、qwen3-30b-a3b-thinking-2507、qwen3-235b-a22b-thinking-2507、および QwQ モデルには効果がありません。
    enable_thinking=True,
    stream=True,
    incremental_output=True, # オープンソースの Qwen3 モデルは true のみをサポートします。より良い体験のために、他のモデルでもこのパラメーターを true に設定することを推奨します。
)

# 完全な思考プロセスを定義します。
reasoning_content = ""
# 完全な応答を定義します。
answer_content = ""
# 思考プロセスが完了し、応答が生成されているかどうかを判断します。
is_answering = False

print("=" * 20 + "Thinking process" + "=" * 20)

for chunk in completion:
    # 思考プロセスと応答の両方が空の場合は、何もしません。
    if (
        chunk.output.choices[0].message.content == ""
        and chunk.output.choices[0].message.reasoning_content == ""
    ):
        pass
    else:
        # 現在のパートが思考プロセスの場合。
        if (
            chunk.output.choices[0].message.reasoning_content != ""
            and chunk.output.choices[0].message.content == ""
        ):
            print(chunk.output.choices[0].message.reasoning_content, end="", flush=True)
            reasoning_content += chunk.output.choices[0].message.reasoning_content
        # 現在のパートが応答の場合。
        elif chunk.output.choices[0].message.content != "":
            if not is_answering:
                print("\n" + "=" * 20 + "Full response" + "=" * 20)
                is_answering = True
            print(chunk.output.choices[0].message.content, end="", flush=True)
            answer_content += chunk.output.choices[0].message.content

# 完全な思考プロセスと応答を印刷するには、次のコードのコメントを解除して実行します。
# print("=" * 20 + "Full thinking process" + "=" * 20 + "\n")
# print(f"{reasoning_content}")
# print("=" * 20 + "Full response" + "=" * 20 + "\n")
# print(f"{answer_content}")

実行結果

====================Thinking process====================
Okay, the user is asking, "Who are you?" I need to answer this question. First, I must clarify my identity: Qwen, a large-scale language model developed by Alibaba Cloud. Next, I should explain my functions and purposes, such as answering questions, creating text, and logical reasoning. I should also emphasize my goal of being a helpful assistant to users, providing help and support.

When responding, I should maintain a conversational tone and avoid using technical jargon or complex sentence structures. I can use friendly expressions, like "Hello there! ~", to make the conversation more natural. I also need to ensure the information is accurate and does not omit key points, such as my developer, main functions, and application scenarios.

I should also consider potential follow-up questions from the user, such as specific application examples or technical details. So, I can subtly set up opportunities in my answer to guide the user to ask more questions. For example, by mentioning, "Whether it's a question about daily life or a professional field, I can do my best to help," which is both comprehensive and open-ended.

Finally, I will check if the response is fluent, without repetition or redundancy, ensuring it is concise and clear. I will also maintain a balance between being friendly and professional, so the user feels that I am both approachable and reliable.
====================Full response====================
Hello there! ~ I am Qwen, a large-scale language model developed by Alibaba Cloud. I can answer questions, create text, perform logical reasoning, write code, and more, all to provide help and support to users. Whether it's a question about daily life or a professional field, I can do my best to help. How can I assist you?

サンプルコード

// dashscope SDK バージョン >= 2.19.4
import java.util.Arrays;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.alibaba.dashscope.aigc.generation.Generation;
import com.alibaba.dashscope.aigc.generation.GenerationParam;
import com.alibaba.dashscope.aigc.generation.GenerationResult;
import com.alibaba.dashscope.common.Message;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import io.reactivex.Flowable;
import java.lang.System;
import com.alibaba.dashscope.utils.Constants;

public class Main {
    static {
        Constants.baseHttpApiUrl="https://dashscope-intl.aliyuncs.com/api/v1";
    }
    private static final Logger logger = LoggerFactory.getLogger(Main.class);
    private static StringBuilder reasoningContent = new StringBuilder();
    private static StringBuilder finalContent = new StringBuilder();
    private static boolean isFirstPrint = true;

    private static void handleGenerationResult(GenerationResult message) {
        String reasoning = message.getOutput().getChoices().get(0).getMessage().getReasoningContent();
        String content = message.getOutput().getChoices().get(0).getMessage().getContent();

        if (!reasoning.isEmpty()) {
            reasoningContent.append(reasoning);
            if (isFirstPrint) {
                System.out.println("====================Thinking process====================");
                isFirstPrint = false;
            }
            System.out.print(reasoning);
        }

        if (!content.isEmpty()) {
            finalContent.append(content);
            if (!isFirstPrint) {
                System.out.println("\n====================Full response====================");
                isFirstPrint = true;
            }
            System.out.print(content);
        }
    }
    private static GenerationParam buildGenerationParam(Message userMsg) {
        return GenerationParam.builder()
                // 環境変数を設定していない場合は、次の行を Model Studio API キーに置き換えます：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen-plus")
                .enableThinking(true)
                .incrementalOutput(true)
                .resultFormat("message")
                .messages(Arrays.asList(userMsg))
                .build();
    }
    public static void streamCallWithMessage(Generation gen, Message userMsg)
            throws NoApiKeyException, ApiException, InputRequiredException {
        GenerationParam param = buildGenerationParam(userMsg);
        Flowable<GenerationResult> result = gen.streamCall(param);
        result.blockingForEach(message -> handleGenerationResult(message));
    }

    public static void main(String[] args) {
        try {
            Generation gen = new Generation();
            Message userMsg = Message.builder().role(Role.USER.getValue()).content("Who are you?").build();
            streamCallWithMessage(gen, userMsg);
//             最終結果を印刷します。
//            if (reasoningContent.length() > 0) {
//                System.out.println("\n====================Full response====================");
//                System.out.println(finalContent.toString());
//            }
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            logger.error("An exception occurred: {}", e.getMessage());
        }
        System.exit(0);
    }
}

戻り値

====================Thinking process====================
Okay, the user is asking "Who are you?". I need to answer based on my previous settings. First, my role is Qwen, a large-scale language model from Alibaba Group. I need to keep my language conversational, simple, and easy to understand.

The user might be new to me or wants to confirm my identity. I should first directly answer who I am, then briefly explain my functions and uses, such as answering questions, creating text, and coding. I also need to mention my multilingual support so the user knows I can handle requests in different languages.

Also, according to the guidelines, I need to maintain a human-like personality, so my tone should be friendly, and I might use emojis to add a touch of warmth. I might also need to guide the user to ask further questions or use my functions, for example, by asking them what they need help with.

I need to be careful not to use complex jargon and avoid being long-winded. I will check for any missed key points, such as multilingual support and specific capabilities. I will ensure the answer meets all requirements, including being conversational and concise.
====================Full response====================
Hello! I am Qwen, a large-scale language model from Alibaba Group. I can answer questions, create text such as stories, official documents, emails, and scripts, perform logical reasoning, write code, express opinions, and play games. I am proficient in multiple languages, including but not limited to Chinese, English, German, French, and Spanish. Is there anything I can help you with?

サンプルコード

# ======= 重要 =======
# リージョンごとに API キーは異なります。API キーを取得するには、https://www.alibabacloud.com/help/model-studio/get-api-key をご参照ください。
# 中国 (北京) リージョンのモデルを使用する場合は、URL を https://dashscope.aliyuncs.com/api/v1/services/aigc/text-generation/generation に置き換えます。
# === 実行前にこのコメントを削除してください ===
curl -X POST "https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text-generation/generation" \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-DashScope-SSE: enable" \
-d '{
    "model": "qwen-plus",
    "input":{
        "messages":[      
            {
                "role": "user",
                "content": "Who are you?"
            }
        ]
    },
    "parameters":{
        "enable_thinking": true,
        "incremental_output": true,
        "result_format": "message"
    }
}'

戻り値

id:1
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"Hmm","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":14,"input_tokens":11,"output_tokens":3},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:2
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":",","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":15,"input_tokens":11,"output_tokens":4},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:3
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" the user","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":16,"input_tokens":11,"output_tokens":5},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:4
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" is asking","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":17,"input_tokens":11,"output_tokens":6},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:5
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":" '","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":18,"input_tokens":11,"output_tokens":7},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}
......

id:358
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" help","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":373,"input_tokens":11,"output_tokens":362},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:359
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":",","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":374,"input_tokens":11,"output_tokens":363},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:360
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" feel free to","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":375,"input_tokens":11,"output_tokens":364},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:361
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" let me","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":376,"input_tokens":11,"output_tokens":365},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:362
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":" know","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":377,"input_tokens":11,"output_tokens":366},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:363
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"!","reasoning_content":"","role":"assistant"},"finish_reason":"null"}]},"usage":{"total_tokens":378,"input_tokens":11,"output_tokens":367},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}

id:364
event:result
:HTTP_STATUS/200
data:{"output":{"choices":[{"message":{"content":"","reasoning_content":"","role":"assistant"},"finish_reason":"stop"}]},"usage":{"total_tokens":378,"input_tokens":11,"output_tokens":367},"request_id":"25d58c29-c47b-9e8d-a0f1-d6c309ec58b1"}