受管代理快速入门

本指南将引导您使用 Antigravity 代理，在 Gemini API 上创建和使用受管理的代理。您将进行首次代理调用、继续多轮对话、流式传输响应、从沙盒下载文件，以及使用 Antigravity 托管式代理。

运行您的首次智能体互动

对 Interactions API 的单次调用会预配 Linux 沙盒、运行代理循环并返回结果。您将定义三个参数：

  • 传入 agent 作为 "antigravity-preview-05-2026",，这是我们预定义的通用受管代理的当前版本。
  • 定义 environment="remote"，以预配新的初始沙盒环境。

  • 创建输入，定义您希望代理执行的操作。

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    environment="remote",
)

# Print the agent's final output
print(f"Interaction ID: {interaction.id}")
print(f"Environment ID: {interaction.environment_id}")
print(f"Output: {interaction.output_text}")

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    environment: "remote",
});

console.log(`Interaction ID: ${interaction.id}`);
console.log(`Environment ID: ${interaction.environment_id}`);

console.log(`Output: ${interaction.output_text}`);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "antigravity-preview-05-2026",
    "input": [{"type": "text", "text": "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents."}],
    "environment": {"type": "remote"}
}'

响应会返回一个 Interaction 对象。存储 interaction.id 和 interaction.environment_id，以便在同一沙盒中继续对话。使用 interaction.output_text 可访问智能体的最终回答。interaction.steps 列出了智能体采取的每个步骤（推理、工具调用、代码执行）。

继续对话（多回合）

该 API 会跟踪两个独立的状态维度：

  • 对话上下文：聊天记录、推理轨迹、工具使用情况、使用 previous_interaction_id。
  • 环境状态：使用 environment 的文件、已安装的软件包和沙盒状态。

在各自的位置传递这两个实参以恢复：

Python

interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    previous_interaction_id=interaction.id,
    environment=interaction.environment_id,
    input="Now plot the Fibonacci sequence as a line chart and save it as chart.png.",
)

print(interaction_2.output_text)

JavaScript

const interaction2 = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    previous_interaction_id: interaction.id,
    environment: interaction.environment_id,
    input: "Now plot the Fibonacci sequence as a line chart and save it as chart.png.",
}, { timeout: 300_000 });

console.log(interaction2.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "antigravity-preview-05-2026",
    "previous_interaction_id": "interaction_id_from_step_1",
    "environment": "environment_id_from_step_1",
    "input": [{"type": "text", "text": "Now plot the Fibonacci sequence as a line chart and save it as chart.png."}]
}'

回合 1 (fibonacci.txt) 中的文件会保留到回合 2。智能体还会保留对话上下文。

您可以独立混搭使用这些功能：

  • 清除对话，保留文件：省略 previous_interaction_id，仅使用 environment 传递环境 ID，以便在同一工作区中进行新的对话。
  • 保留对话，新工作区：传递 previous_interaction_id，为全新沙盒设置 environment="remote"。

自动压缩上下文

在长时间的多回合对话中，推理步骤、工具调用和大型文件内容的原始历史记录可能会快速增长，并占用大量上下文空间。为防止出现令牌限制错误并保持代理的专注度（防止出现“上下文腐烂”），Managed Agents API 在大约 13.5 万个令牌时会执行原生上下文压缩步骤。这个过程是自动进行的。

以流式传输回答

对于长时间运行的任务，您可以流式传输响应，以实时查看代理的工作情况：

Python

from google import genai

client = genai.Client()

stream = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Read Hacker News, summarize the top 5 stories, and save the results as a PDF.",
    environment="remote",
    stream=True,
)

for event in stream:
    print(event)

JavaScript

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

const client = new GoogleGenAI({});

const stream = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Read Hacker News, summarize the top 5 stories, and save the results as a PDF.",
    environment: "remote",
    stream: true,
});

for await (const event of stream) {
    console.log(event);
}

REST

curl -N -s -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "antigravity-preview-05-2026",
    "input": "Read Hacker News, summarize the top 5 stories, and save the results as a PDF.",
    "environment": "remote",
    "stream": true
}'

流式传输会返回一个步差分的可迭代对象，其中包含增量文本、推理令牌和工具调用更新。如需详细了解如何流式传输回答，请参阅流式传输指南。

从环境中下载文件

当代理在沙盒内创建文件时。使用 Files API 通过直接 HTTP 请求（尚无 SDK 方法）下载这些文件：

Python

import os
import requests
import tarfile

env_id = interaction.environment_id
api_key = os.environ["GEMINI_API_KEY"]

response = requests.get(
    f"https://generativelanguage.googleapis.com/v1beta/files/environment-{env_id}:download",
    params={"alt": "media"},
    headers={"x-goog-api-key": api_key},
    allow_redirects=True,
)

with open("snapshot.tar", "wb") as f:
    f.write(response.content)

with tarfile.open("snapshot.tar") as tar:
    tar.extractall(path="extracted_snapshot")

JavaScript

import fs from "fs";
import { execSync } from "child_process";

const envId = interaction.environment_id;
const apiKey = process.env.GEMINI_API_KEY || "";

const url = `https://generativelanguage.googleapis.com/v1beta/files/environment-${envId}:download?alt=media`;
const response = await fetch(url, {
    headers: {
        "x-goog-api-key": apiKey,
    },
});

if (!response.ok) {
    throw new Error(`Failed to download file: ${response.statusText}`);
}

const buffer = Buffer.from(await response.arrayBuffer());
fs.writeFileSync("snapshot.tar", buffer);

if (!fs.existsSync("extracted_snapshot")) {
    fs.mkdirSync("extracted_snapshot");
}
execSync("tar -xf snapshot.tar -C extracted_snapshot");

console.log(fs.readdirSync("extracted_snapshot"));

REST

curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/files/environment-$ENV_ID:download?alt=media" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-o snapshot.tar

tar -xf snapshot.tar -C extracted_snapshot

保存受管代理

在之前的步骤中，我们使用了默认的 Antigravity 代理，并对其进行了内嵌自定义。在迭代配置（指令、技能和环境）后，您可以将其保存为受管理的代理。这样一来，您就可以通过 ID 调用该配置，而无需重复配置。

保存代理时，您需要定义 base_environment（从来源定义或通过派生现有环境来定义）。代理将针对每次新互动使用此环境。

来自来源：内嵌定义来源，或从 GitHub 或 Cloud Storage 等其他来源定义来源。

Python

agent = client.agents.create(
    id="fibonacci-analyst",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a math analysis agent. Generate sequences, visualize them, and export results as PDF reports.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always include a chart and a summary table in your reports.",
            },
            {
                "type": "repository",
                "source": "https://github.com/your-org/skills",
                "target": ".agents/skills"
            }
        ],
    },
)

print(f"Saved agent: {agent.id}")

JavaScript

const agent = await client.agents.create({
    id: "fibonacci-analyst",
    base_agent: "antigravity-preview-05-2026",
    system_instruction: "You are a math analysis agent. Generate sequences, visualize them, and export results as PDF reports.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always include a chart and a summary table in your reports.",
            },
            {
                type: "repository",
                source: "https://github.com/your-org/skills",
                target: ".agents/skills"
            }
        ],
    },
});

console.log(`Saved agent: ${agent.id}`);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "id": "fibonacci-analyst",
    "base_agent": "antigravity-preview-05-2026",
    "system_instruction": "You are a math analysis agent. Generate sequences, visualize them, and export results as PDF reports.",
    "base_environment": {
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always include a chart and a summary table in your reports."
            },
            {
                "type": "repository",
                "source": "https://github.com/your-org/skills",
                "target": ".agents/skills"
            }
        ]
    }
}'

调用受管理的代理

保存受管理的代理后，您可以通过 ID 调用它。每次调用都会派生出基本环境，因此每次运行都是从干净的状态开始的：

Python

result = client.interactions.create(
    agent="fibonacci-analyst",
    input="Generate the first 50 prime numbers, plot their distribution, and save a PDF report.",
    environment="remote",
)

print(result.output_text)

JavaScript

const result = await client.interactions.create({
    agent: "fibonacci-analyst",
    input: "Generate the first 50 prime numbers, plot their distribution, and save a PDF report.",
    environment: "remote",
}, {
    timeout: 300_000,
});

console.log(result.output_text);

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "fibonacci-analyst",
    "environment": "remote",
    "input": "Generate the first 50 prime numbers, plot their distribution, and save a PDF report."
}'

后续步骤