Back to Details

gemini-interactions-api

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Gemini Interactions API Skill

Gemini Interactions API 技能指南

This skill provides instructions for authenticating, connecting to, and utilizing the stateful, server-managed Gemini Interactions API on Gemini Enterprise Agent Platform.
The Interactions API is the modern, recommended way to execute Generative AI agent conversations, background research tasks, multi-turn chats, and structured, multi-step workflows.
[!IMPORTANT] CRITICAL: Unified SDK & Latest Models
  • Unified SDK: Use the Google Gen AI SDK (
    google-genai >= 2.0.0
     for Python, 
    @google/genai >= 2.0.0
     for JS/TS). Legacy SDKs like 
    google-cloud-aiplatform
    , 
    @google-cloud/vertexai
    , and 
    google-generativeai
    are strictly unsupported for Interactions.
  • Latest Models Only: Use 
    gemini-3.1-pro-preview
    , 
    gemini-3.1-flash-lite
    , 
    gemini-3-flash-preview
    , 
    gemini-2.5-pro
    , or 
    gemini-2.5-flash
    . Refer to the latest model versions to check for new updates. Legacy models (
    gemini-2.0-*
    , 
    gemini-1.5-*
    ) are deprecated and do not support interactions.
  • Turn-Scoped Parameters: Parameters like 
    tools
    , 
    system_instruction
    , and 
    generation_config
    are turn-scoped. They MUST be passed with each interaction request.
本技能文档提供了在Gemini Enterprise Agent Platform上进行认证、连接以及使用有状态、服务器托管的Gemini Interactions API的操作说明。
Interactions API是执行生成式AI代理对话、后台研究任务、多轮聊天以及结构化多步骤工作流的现代化推荐方案。
[!IMPORTANT] 重要提示：统一SDK与最新模型
  • 统一SDK：请使用Google Gen AI SDK（Python版本需**
    google-genai >= 2.0.0
    ，JS/TS版本需
    @google/genai >= 2.0.0
    **）。旧版SDK如
    google-cloud-aiplatform
    、
    @google-cloud/vertexai
    和
    google-generativeai
    完全不支持Interactions功能。
  • 仅使用最新模型：请使用
    gemini-3.1-pro-preview
    、
    gemini-3.1-flash-lite
    、
    gemini-3-flash-preview
    、
    gemini-2.5-pro
    或
    gemini-2.5-flash
    。可参考最新模型版本查看更新信息。旧版模型（
    gemini-2.0-*
    、
    gemini-1.5-*
    ）已被弃用，不支持Interactions功能。
  • 轮次作用域参数：
    tools
    、
    system_instruction
    和
    generation_config
    等参数属于轮次作用域，必须随每次交互请求一并传递。

1. Authentication

1. 身份认证

Before running any code, ensure you are authenticated with Application Default Credentials (ADC) and have the necessary API enabled.
  1. Login:
    bash
    gcloud auth application-default login
  2. Enable API (if not already enabled):
    bash
    gcloud services enable aiplatform.googleapis.com
在运行任何代码之前，请确保已通过Application Default Credentials（ADC）完成身份认证，并启用了所需的API。
  1. 登录：
    bash
    gcloud auth application-default login
  2. 启用API（若尚未启用）：
    bash
    gcloud services enable aiplatform.googleapis.com

2. Client Initialization

2. 客户端初始化

You can initialize the client using environment variables (recommended) or by passing explicit configuration parameters.
你可以使用环境变量（推荐方式）或传入显式配置参数来初始化客户端。

Option A: Environment Variables (Recommended)

选项A：环境变量（推荐）

Configure environment variables to let the SDK automatically resolve settings:
bash
export GOOGLE_GENAI_USE_ENTERPRISE=true
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="global"
配置环境变量，让SDK自动解析设置：
bash
export GOOGLE_GENAI_USE_ENTERPRISE=true
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="global"

Python

Python

python
from google import genai
python
from google import genai

The SDK automatically picks up the environment variables

SDK会自动读取环境变量

client = genai.Client()
undefined
client = genai.Client()
undefined

TypeScript/JavaScript

TypeScript/JavaScript

typescript
import { GoogleGenAI } from "@google/genai";

// The SDK automatically picks up the environment variables
const ai = new GoogleGenAI();
typescript
import { GoogleGenAI } from "@google/genai";

// SDK会自动读取环境变量
const ai = new GoogleGenAI();

Option B: Explicit Inline Parameters

选项B：显式内联参数

Alternatively, pass configuration values directly inside your code:
或者，直接在代码中传入配置值：

Python

Python

python
from google import genai
import google.auth

_, project_id = google.auth.default()
client = genai.Client(enterprise=True, project=project_id, location="global")
python
from google import genai
import google.auth

_, project_id = google.auth.default()
client = genai.Client(enterprise=True, project=project_id, location="global")

TypeScript/JavaScript

TypeScript/JavaScript

typescript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
    enterprise: {
        project: "your-project-id",
        location: "global"
    }
});
typescript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
    enterprise: {
        project: "your-project-id",
        location: "global"
    }
});

3. Core Interactions API Usage

3. Interactions API核心用法

Quick Start (Single-Turn)

快速入门（单轮对话）

Submit a single prompt and read the final text response. Under the modern schema, output content is retrieved from the 
steps
list.
提交单个提示并读取最终文本响应。在现代架构下，输出内容从
steps
列表中获取。

Python

Python

python
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain serverless computing in one sentence."
)
python
interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Explain serverless computing in one sentence."
)

Output text is located under steps

输出文本位于steps下

print(interaction.steps[-1].content[0].text)
undefined
print(interaction.steps[-1].content[0].text)
undefined

TypeScript/JavaScript

TypeScript/JavaScript

typescript
const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain serverless computing in one sentence."
});
console.log(interaction.steps[interaction.steps.length - 1].content[0].text);
typescript
const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Explain serverless computing in one sentence."
});
console.log(interaction.steps[interaction.steps.length - 1].content[0].text);

Stateful Conversation (Multi-Turn)

有状态对话（多轮对话）

Interactions are stateful by default. Store the conversation state in the cloud and reference it in the subsequent turn using 
previous_interaction_id
.
Interactions默认是有状态的。将对话状态存储在云端，并在后续轮次中使用
previous_interaction_id
引用该状态。

Python

Python

python
undefined
python
undefined

Turn 1: Introduce ourselves

第一轮：自我介绍

turn1 = client.interactions.create( model="gemini-3-flash-preview", input="Hi! My name is John. I am working on AI agents.", store=True ) print(f"Turn 1: {turn1.steps[-1].content[0].text}")
turn1 = client.interactions.create( model="gemini-3-flash-preview", input="Hi! My name is John. I am working on AI agents.", store=True ) print(f"Turn 1: {turn1.steps[-1].content[0].text}")

Turn 2: Refer back to the stored turn state

第二轮：引用已存储的对话状态

turn2 = client.interactions.create( model="gemini-3-flash-preview", input="What is my name?", previous_interaction_id=turn1.id ) print(f"Turn 2: {turn2.steps[-1].content[0].text}")
undefined
turn2 = client.interactions.create( model="gemini-3-flash-preview", input="What is my name?", previous_interaction_id=turn1.id ) print(f"Turn 2: {turn2.steps[-1].content[0].text}")
undefined

TypeScript/JavaScript

TypeScript/JavaScript

typescript
// Turn 1
const turn1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Hi! My name is John. I am working on AI agents.",
    store: true
});

// Turn 2
const turn2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "What is my name?",
    previousInteractionId: turn1.id
});
console.log(turn2.steps[turn2.steps.length - 1].content[0].text);
typescript
// 第一轮
const turn1 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Hi! My name is John. I am working on AI agents.",
    store: true
});

// 第二轮
const turn2 = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "What is my name?",
    previousInteractionId: turn1.id
});
console.log(turn2.steps[turn2.steps.length - 1].content[0].text);

Real-Time Streaming

实时流式传输

Stream responses in real-time. Passing 
stream=True
returns an iterable chunk generator.
实时流式获取响应。传入
stream=True
会返回一个可迭代的分片生成器。

Python

Python

python
response = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Write a short poem about debugging.",
    stream=True
)

for chunk in response:
    if chunk.steps:
        step = chunk.steps[-1]
        if step.content and step.content[0].text:
            print(step.content[0].text, end="", flush=True)
print()
python
response = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Write a short poem about debugging.",
    stream=True
)

for chunk in response:
    if chunk.steps:
        step = chunk.steps[-1]
        if step.content and step.content[0].text:
            print(step.content[0].text, end="", flush=True)
print()

TypeScript/JavaScript

TypeScript/JavaScript

typescript
const responseStream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Write a short poem about debugging.",
    stream: true
});

for await (const chunk of responseStream) {
    if (chunk.steps) {
        const step = chunk.steps[chunk.steps.length - 1];
        if (step.content && step.content[0].text) {
            process.stdout.write(step.content[0].text);
        }
    }
}
console.log();
typescript
const responseStream = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Write a short poem about debugging.",
    stream: true
});

for await (const chunk of responseStream) {
    if (chunk.steps) {
        const step = chunk.steps[chunk.steps.length - 1];
        if (step.content && step.content[0].text) {
            process.stdout.write(step.content[0].text);
        }
    }
}
console.log();

Structured Output (Pydantic / Polymorphic 
response_format
)

结构化输出（Pydantic / 多态
response_format
）

Retrieve structured, type-safe JSON matching a schema. Under the modern Interactions API, a polymorphic 
response_format
argument directly takes the target schema structure.
获取与指定 schema 匹配的结构化、类型安全的JSON。在现代Interactions API中，多态
response_format
参数可直接传入目标schema结构。

Python

Python

python
from pydantic import BaseModel, Field

class Book(BaseModel):
    title: str = Field(description="The title of the book")
    author: str = Field(description="The book's author")
    year_published: int

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Recommend one famous sci-fi book.",
    response_format=Book
)
python
from pydantic import BaseModel, Field

class Book(BaseModel):
    title: str = Field(description="The title of the book")
    author: str = Field(description="The book's author")
    year_published: int

interaction = client.interactions.create(
    model="gemini-3-flash-preview",
    input="Recommend one famous sci-fi book.",
    response_format=Book
)

The text will be a valid JSON matching the Book schema

返回的文本是符合Book schema的有效JSON

print(interaction.steps[-1].content[0].text)
undefined
print(interaction.steps[-1].content[0].text)
undefined

TypeScript/JavaScript

TypeScript/JavaScript

typescript
import { Type } from "@google/genai";

const BookSchema = {
    type: Type.OBJECT,
    properties: {
        title: { type: Type.STRING, description: "The title of the book" },
        author: { type: Type.STRING, description: "The book's author" },
        yearPublished: { type: Type.INTEGER }
    },
    required: ["title", "author", "yearPublished"]
};

const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Recommend one famous sci-fi book.",
    responseFormat: BookSchema
});

console.log(interaction.steps[interaction.steps.length - 1].content[0].text);
typescript
import { Type } from "@google/genai";

const BookSchema = {
    type: Type.OBJECT,
    properties: {
        title: { type: Type.STRING, description: "The title of the book" },
        author: { type: Type.STRING, description: "The book's author" },
        yearPublished: { type: Type.INTEGER }
    },
    required: ["title", "author", "yearPublished"]
};

const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "Recommend one famous sci-fi book.",
    responseFormat: BookSchema
});

console.log(interaction.steps[interaction.steps.length - 1].content[0].text);

Function Calling (Agent Tool Use)

函数调用（代理工具使用）

Define local tools (functions) and submit execution results to the stateful interaction history.
定义本地工具（函数）并将执行结果提交到有状态的交互历史中。

Python

Python

python
def get_stock_price(ticker: str) -> float:
    """Gets the stock price for a given ticker symbol."""
    if ticker.upper() == "GOOG":
        return 175.50
    return 100.0
python
def get_stock_price(ticker: str) -> float:
    """Gets the stock price for a given ticker symbol."""
    if ticker.upper() == "GOOG":
        return 175.50
    return 100.0

Turn 1: Pass tools to the model

第一轮：向模型传递工具

interaction = client.interactions.create( model="gemini-3-flash-preview", input="What is the stock price of GOOG?", tools=[get_stock_price] )
last_step = interaction.steps[-1]
interaction = client.interactions.create( model="gemini-3-flash-preview", input="What is the stock price of GOOG?", tools=[get_stock_price] )
last_step = interaction.steps[-1]

Check if the model requested a function call

检查模型是否请求了函数调用

if last_step.tool_calls: for call in last_step.tool_calls: if call.name == "get_stock_price": ticker_arg = call.args.get("ticker") price = get_stock_price(ticker_arg)
        # Turn 2: Submit function execution result statefully
        final_turn = client.interactions.create(
            model="gemini-3-flash-preview",
            input=f"The stock price for {ticker_arg} is ${price}.",
            previous_interaction_id=interaction.id
        )
        print(final_turn.steps[-1].content[0].text)
undefined
if last_step.tool_calls: for call in last_step.tool_calls: if call.name == "get_stock_price": ticker_arg = call.args.get("ticker") price = get_stock_price(ticker_arg)
        # 第二轮：有状态地提交函数执行结果
        final_turn = client.interactions.create(
            model="gemini-3-flash-preview",
            input=f"The stock price for {ticker_arg} is ${price}.",
            previous_interaction_id=interaction.id
        )
        print(final_turn.steps[-1].content[0].text)
undefined

TypeScript/JavaScript

TypeScript/JavaScript

typescript
import { Type } from "@google/genai";

// Define local tool
function getStockPrice({ ticker }: { ticker: string }): number {
    if (ticker.toUpperCase() === "GOOG") {
        return 175.50;
    }
    return 100.00;
}

// Turn 1: Pass tools to the model
const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "What is the stock price of GOOG?",
    tools: [{
        functionDeclarations: [{
            name: "getStockPrice",
            description: "Gets the stock price for a given ticker symbol.",
            parameters: {
                type: Type.OBJECT,
                properties: {
                    ticker: { type: Type.STRING, description: "The stock ticker symbol" }
                },
                required: ["ticker"]
            }
        }]
    }]
});

const lastStep = interaction.steps[interaction.steps.length - 1];
// Check if the model requested a function call
if (lastStep.toolCalls) {
    for (const call of lastStep.toolCalls) {
        if (call.name === "getStockPrice") {
            const tickerArg = call.args.ticker as string;
            const price = getStockPrice({ ticker: tickerArg });

            // Turn 2: Submit function execution result statefully
            const finalTurn = await ai.interactions.create({
                model: "gemini-3-flash-preview",
                input: `The stock price for ${tickerArg} is $${price}.`,
                previousInteractionId: interaction.id
            });
            console.log(finalTurn.steps[finalTurn.steps.length - 1].content[0].text);
        }
    }
}
typescript
import { Type } from "@google/genai";

// 定义本地工具
function getStockPrice({ ticker }: { ticker: string }): number {
    if (ticker.toUpperCase() === "GOOG") {
        return 175.50;
    }
    return 100.00;
}

// 第一轮：向模型传递工具
const interaction = await ai.interactions.create({
    model: "gemini-3-flash-preview",
    input: "What is the stock price of GOOG?",
    tools: [{
        functionDeclarations: [{
            name: "getStockPrice",
            description: "Gets the stock price for a given ticker symbol.",
            parameters: {
                type: Type.OBJECT,
                properties: {
                    ticker: { type: Type.STRING, description: "The stock ticker symbol" }
                },
                required: ["ticker"]
            }
        }]
    }]
});

const lastStep = interaction.steps[interaction.steps.length - 1];
// 检查模型是否请求了函数调用
if (lastStep.toolCalls) {
    for (const call of lastStep.toolCalls) {
        if (call.name === "getStockPrice") {
            const tickerArg = call.args.ticker as string;
            const price = getStockPrice({ ticker: tickerArg });

            // 第二轮：有状态地提交函数执行结果
            const finalTurn = await ai.interactions.create({
                model: "gemini-3-flash-preview",
                input: `The stock price for ${tickerArg} is $${price}.`,
                previousInteractionId: interaction.id
            });
            console.log(finalTurn.steps[finalTurn.steps.length - 1].content[0].text);
        }
    }
}

4. Accessing the Interactions API via REST

4. 通过REST访问Interactions API

For shell-based scripts, debugging, or non-Python/JS environments, you can communicate with the stateful Interactions API directly using raw HTTP/REST requests via 
curl
.
对于基于Shell的脚本、调试或非Python/JS环境，你可以通过
curl
直接使用原始HTTP/REST请求与有状态的Interactions API通信。

1. REST Endpoint

1. REST端点

The REST API endpoint for interactions is:
http
POST https://aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{LOCATION}/interactions
  • LOCATION: Use 
    global
    (or custom region if required).
  • PROJECT_ID: Your Google Cloud Project ID.
Interactions的REST API端点为：
http
POST https://aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{LOCATION}/interactions
  • LOCATION：使用
    global
    （如需自定义区域也可使用对应区域）。
  • PROJECT_ID：你的Google Cloud项目ID。

2. Set up Variables & Authentication Header

2. 设置变量与认证头

Set your target agent ID (e.g., model or custom agent path) and access token generated from Application Default Credentials:
bash
AGENT_ID="your-agent-id"
ACCESS_TOKEN=$(gcloud auth print-access-token)
设置目标代理ID（例如模型或自定义代理路径）以及从Application Default Credentials生成的访问令牌：
bash
AGENT_ID="your-agent-id"
ACCESS_TOKEN=$(gcloud auth print-access-token)

3. Single-Turn Interaction Payload

3. 单轮交互请求体

Send a request to start an interaction using the agent variable:
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Explain serverless computing in one sentence."
      }]
    }]
  }'
使用代理变量发送请求以启动交互：
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Explain serverless computing in one sentence."
      }]
    }]
  }'

Response Example

响应示例

A synchronous POST request returns a JSON object containing the conversation step details and unique identifiers:
json
{
  "id": "your-interaction-id",
  "status": "completed",
  "steps": [
    {
      "role": "model",
      "content": [
        {
          "type": "text",
          "text": "Serverless computing is a cloud execution model where the cloud provider dynamically manages the allocation and provisioning of servers, charging customers based on actual usage rather than pre-purchased capacity."
        }
      ]
    }
  ],
  "usage": {
    "total_tokens": 24751,
    "total_input_tokens": 23894,
    "total_output_tokens": 857
  },
  "created": "2026-05-08T10:44:43Z",
  "updated": "2026-05-08T10:44:43Z",
  "environment_id": "your-environment-id",
  "object": "interaction"
}
同步POST请求会返回包含对话步骤详情和唯一标识符的JSON对象：
json
{
  "id": "your-interaction-id",
  "status": "completed",
  "steps": [
    {
      "role": "model",
      "content": [
        {
          "type": "text",
          "text": "Serverless computing is a cloud execution model where the cloud provider dynamically manages the allocation and provisioning of servers, charging customers based on actual usage rather than pre-purchased capacity."
        }
      ]
    }
  ],
  "usage": {
    "total_tokens": 24751,
    "total_input_tokens": 23894,
    "total_output_tokens": 857
  },
  "created": "2026-05-08T10:44:43Z",
  "updated": "2026-05-08T10:44:43Z",
  "environment_id": "your-environment-id",
  "object": "interaction"
}

4. Multi-Turn Stateful Interaction Payload

4. 多轮有状态交互请求体

To continue an existing conversation statefully, specify the 
previous_interaction_id
in the JSON payload:
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "store": true,
    "previous_interaction_id": "YOUR_PREVIOUS_INTERACTION_ID",
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Can you elaborate on that?"
      }]
    }]
  }'
要继续现有对话的有状态会话，请在JSON请求体中指定
previous_interaction_id
：
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "store": true,
    "previous_interaction_id": "YOUR_PREVIOUS_INTERACTION_ID",
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Can you elaborate on that?"
      }]
    }]
  }'

5. Streaming Output Payload

5. 流式输出请求体

To stream updates in real time (Server-Sent Events format), pass 
"stream": true
in the payload:
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "stream": true,
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Write a long story about space travel."
      }]
    }]
  }'
The endpoint will return a chunked stream where each event begins with 
data:
containing JSON updates with the 
event_type
and step contents.
How 
curl
handles streaming: By default, when 
"stream": true
is passed, the server responds with 
Transfer-Encoding: chunked
and 
Content-Type: text/event-stream
(Server-Sent Events). 
curl
will automatically keep the connection open and print the incoming data chunks to 
stdout
in real time as they are pushed by the server. The user does not need to poll or pull further; the complete sequence of events streams continuously until completion.
要实时流式获取更新（Server-Sent Events格式），请在请求体中传入
"stream": true
：
bash
curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "stream": true,
    "input": [{
      "role": "user",
      "content": [{
        "type": "text",
        "text": "Write a long story about space travel."
      }]
    }]
  }'
端点会返回分片流，每个事件以
data:
开头，包含带有
event_type
和步骤内容的JSON更新。
curl处理流式传输的方式： 默认情况下，当传入
"stream": true
时，服务器会返回
Transfer-Encoding: chunked
和
Content-Type: text/event-stream
（Server-Sent Events）。curl会自动保持连接打开，并在服务器推送数据时实时将传入的数据分片打印到
stdout
。用户无需轮询或进一步拉取，完整的事件序列会持续流式传输直至完成。