Deep Research Gemini kini tersedia dalam pratinjau dengan perencanaan kolaboratif, visualisasi, dukungan MCP, dan lainnya.

Google uses AI technology to translate content into your preferred language. AI translations can contain errors.

Lingkungan di Agen Terkelola

Lingkungan adalah sandbox Linux terkelola yang memberi agen tempat terisolasi untuk menjalankan kode dan menyimpan file. Lingkungan ini dipisahkan dari konteks interaksi, sehingga Anda dapat menggunakan kembali lingkungan yang sama di beberapa interaksi atau memulai dari awal kapan saja.

Contoh berikut menunjukkan cara membuat interaksi dengan lingkungan jarak jauh baru dan mengambil ID-nya:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Install pandas and matplotlib, verify the imports, and print the versions.",
    environment="remote",
)

print(f"Environment ID: {interaction.environment_id}")

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Install pandas and matplotlib, verify the imports, and print the versions.",
    environment: "remote",
});

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

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": "Install pandas and matplotlib, verify the imports, and print the versions.",
    "environment": "remote"
}'

Parameter `environment`

Parameter environment menerima tiga bentuk:

Bentuk	Contoh	Kapan digunakan
`"remote"`	`environment="remote"`	Menyediakan sandbox baru.
ID Lingkungan	`environment="env_abc123"`	Menggunakan kembali sandbox yang ada dengan semua file dan paketnya.
Objek konfigurasi	`environment={...}`	Menyediakan sandbox baru dengan sumber, aturan jaringan, atau keduanya.

Contoh berikut menunjukkan tiga cara menggunakan parameter environment.

Python

from google import genai

client = genai.Client()

# Fresh sandbox
interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a hello world script.",
    environment="remote",
)

# Reuse an existing sandbox
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Modify the script to accept a name argument.",
    environment=interaction.environment_id,
    previous_interaction_id=interaction.id,
)

# New sandbox with sources
interaction_3 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="List all files and summarize the project.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/octocat/Spoon-Knife",
                "target": "/workspace/spoon-knife",
            }
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

// Fresh sandbox
const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Write a hello world script.",
    environment: "remote",
});

// Reuse an existing sandbox
const interaction2 = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Modify the script to accept a name argument.",
    environment: interaction.environment_id,
    previous_interaction_id: interaction.id,
});

// New sandbox with sources
const interaction3 = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "List all files and summarize the project.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/octocat/Spoon-Knife",
                target: "/workspace/spoon-knife",
            },
        ],
    },
});

console.log(interaction.output_text);

REST

# Fresh sandbox
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 hello world script."}],
    "environment": "remote"
}'

# Reuse an existing sandbox (replace $ENV_ID and $INTERACTION_ID with values from the previous response)
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d "{
    \"agent\": \"antigravity-preview-05-2026\",
    \"input\": [{\"type\": \"text\", \"text\": \"Modify the script to accept a name argument.\"}],
    \"environment\": \"$ENV_ID\",
    \"previous_interaction_id\": \"$INTERACTION_ID\"
}"

# New sandbox with sources
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": "List all files and summarize the project."}],
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/octocat/Spoon-Knife",
                "target": "/workspace/spoon-knife"
            }
        ]
    }
}'

Mengonfigurasi lingkungan

Salah satu cara untuk menyiapkan lingkungan adalah dengan memberi tahu agen apa yang perlu diinstal. Cara ini menangani resolusi dan pemecahan masalah dependensi. Setelah lingkungan siap, simpan environment_id dan gunakan kembali.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Install pandas, matplotlib, and seaborn. Verify all imports work and print the installed versions.",
    environment="remote",
)

# Reuse the configured environment
interaction_2 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Clone https://github.com/octocat/Spoon-Knife into /workspace/tools. Run the test suite and fix any missing dependencies.",
    environment=interaction.environment_id,
    previous_interaction_id=interaction.id,
)

# Reuse the configured environment
interaction_3 = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Using the tools in /workspace/tools, list the files.",
    environment=interaction.environment_id,
    previous_interaction_id=interaction_2.id,
)

print(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: "Install pandas, matplotlib, and seaborn. Verify all imports work and print the installed versions.",
    environment: "remote",
});

const interaction2 = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Clone https://github.com/octocat/Spoon-Knife into /workspace/tools. Run the test suite and fix any missing dependencies.",
    environment: interaction.environment_id,
    previous_interaction_id: interaction.id,
});

const interaction3 = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Using the tools in /workspace/tools, list the files.",
    environment: interaction.environment_id,
    previous_interaction_id: interaction2.id,
});
console.log(interaction.output_text);

REST

# Create interaction
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": "Install pandas, matplotlib, and seaborn. Verify all imports work and print the installed versions.",
    "environment": "remote"
}'

Memasang dari sumber

Jika Anda tahu persis file yang dibutuhkan agen, pasang file tersebut dalam satu panggilan, bukan dengan melakukan iterasi. Objek konfigurasi environment menerima array sources dengan tiga jenis:

Jenis sumber	Nilai `type`	Deskripsi	Batas
Repositori Git	`repository`	Meng-clone repositori dari URL ke sandbox di `target`.	500 MB
Cloud Storage	`gcs`	Menyalin file atau direktori dari Cloud Storage ke sandbox di `target`.	2 GB
Konten inline	`inline`	Menulis konten teks mentah ke file di sandbox di `target`.	1 MB per file, total 2 MB

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="List all files under /workspace and describe what you find.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/octocat/Spoon-Knife",
                "target": "/workspace/spoon-knife",
            },
            {
                "type": "gcs",
                "source": "gs://cloud-samples-data/bigquery/us-states/",
                "target": "/workspace/gcs-data",
            },
            {
                "type": "inline",
                "content": "# Project Notes\n\n- Analyze state population data\n- Create visualizations\n",
                "target": "/workspace/notes/readme.md",
            },
        ],
    },
)

print(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: "List all files under /workspace and describe what you find.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/octocat/Spoon-Knife",
                target: "/workspace/spoon-knife",
            },
            {
                type: "gcs",
                source: "gs://cloud-samples-data/bigquery/us-states/",
                target: "/workspace/gcs-data",
            },
            {
                type: "inline",
                content: "# Project Notes\n\n- Analyze state population data\n- Create visualizations\n",
                target: "/workspace/notes/readme.md",
            },
        ],
    },
});

console.log(interaction.output_text);

REST

# Create interaction with sources
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": "List all files under /workspace and describe what you find.",
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/octocat/Spoon-Knife",
                "target": "/workspace/spoon-knife"
            },
            {
                "type": "gcs",
                "source": "gs://cloud-samples-data/bigquery/us-states/",
                "target": "/workspace/gcs-data"
            },
            {
                "type": "inline",
                "content": "# Project Notes\n\n- Analyze state population data\n- Create visualizations\n",
                "target": "/workspace/notes/readme.md"
            }
        ]
    }
}'

Anda dapat menggabungkan kedua pendekatan: memasang sumber yang diketahui secara deklaratif, lalu melakukan iterasi dengan interaksi lanjutan untuk menginstal paket atau menjalankan skrip penyiapan. Anda tidak dapat menetapkan root (/) sebagai target saat menambahkan sumber kustom. Anda harus selalu menentukan subdirektori.

Sumber pribadi

Anda juga dapat mendownload dari repositori Github pribadi atau bucket Cloud Storage pribadi dengan menambahkan kredensial dalam konfigurasi jaringan:

Untuk repositori Git pribadi, gunakan Basic autentikasi dengan GitHub Personal Access Token (PAT) Anda. Enkode token menggunakan x-oauth-basic sebagai nama pengguna:

echo -n "x-oauth-basic:ghp_YourPATHere" | base64

Python

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Run the test for my backend app and fix any issue.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/your-org/backend",
                "target": "/backend-app"
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "github.com",
                    "transform": {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    }
                },
                {
                    "domain": "*"
                }
            ]
        }
    }
)

JavaScript

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Run the test for my backend app and fix any issue.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/your-org/backend",
                target: "/backend-app"
            }
        ],
        network: {
            allowlist: [
                {
                    domain: "github.com",
                    transform: {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    }
                },
                {
                    domain: "*"
                }
            ]
        }
    },
});

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": "Run the test for my backend app and fix any issue.",
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/your-org/backend",
                "target": "/backend-app"
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "github.com",
                    "transform": {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    }
                },
                {
                    "domain": "*"
                }
            ]
        }
    }
}'

Untuk bucket Cloud Storage pribadi, gunakan token Bearer OAuth 2.0 standar:

gcloud auth print-access-token

Python

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Analyze the discrepancies across the data in workspace",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "gcs",
                "source": "gs://my-private-bucket/data",
                "target": "/workspace",
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "*.googleapis.com",
                    "transform": {
                        "Authorization": "Bearer YOUR_GCS_TOKEN"
                    }
                },
                {
                    "domain": "*"
                }
            ]
        }
    },
)

JavaScript

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Analyze the discrepancies across the data in workspace",
    environment: {
        type: "remote",
        sources: [
            {
                type: "gcs",
                source: "gs://my-private-bucket/data",
                target: "/workspace",
            }
        ],
        network: {
            allowlist: [
                {
                    domain: "storage.googleapis.com",
                    transform: {
                        "Authorization": "Bearer YOUR_GCS_TOKEN"
                    }
                },
                {
                    domain: "*"
                }
            ]
        }
    },
});

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": "Analyze the discrepancies across the data in workspace",
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "gcs",
                "source": "gs://my-private-bucket/data",
                "target": "/workspace"
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "storage.googleapis.com",
                    "transform": {
                        "Authorization": "Bearer YOUR_GCS_TOKEN"
                    }
                },
                {
                    "domain": "*"
                }
            ]
        }
    }
}'

Software yang telah diinstal sebelumnya

Sandbox berjalan di Ubuntu dan dilengkapi dengan runtime dan paket umum yang telah diinstal sebelumnya. Agen dapat menginstal paket tambahan saat runtime menggunakan pip install atau npm install. Paket yang diinstal selama interaksi akan tetap ada saat Anda menggunakan kembali environment_id yang sama.

Kategori	Paket yang telah diinstal sebelumnya
Alat UNIX	`curl`, `wget`, `git`, `rsync`, `unzip`, `ripgrep`, `fd-find`, `gawk`, `bc`, `tree`, `which`, `lsof`, `htop`, `jq`, `iproute2`, `procps`, `gcloud CLI`
Python 3.12	`numpy`, `pandas`, `requests`, `google-genai`, `beautifulsoup4`, `pyyaml`, `ast-grep-cli`
Node.js 22	`create-next-app`, `create-vite`, `typescript`

Konfigurasi jaringan

Secara default, lingkungan memiliki akses jaringan keluar yang tidak dibatasi. Gunakan kolom network untuk membatasi traffic keluar ke domain tertentu. Setiap aturan menentukan domain dan objek transform opsional untuk menyisipkan header ke dalam permintaan yang cocok. Header ini dapat bersifat unik per interaksi, dan Anda dapat memperbaruinya untuk lingkungan yang sama.

Kolom	Jenis	Deskripsi
`domain`	`string`	Domain yang akan dicocokkan. Gunakan nama host yang tepat atau `*` untuk semua domain.
`transform`	`object`	Objek yang berisi key-value pair datar yang mewakili header untuk disisipkan ke dalam permintaan yang cocok, misalnya `{"Authorization": "Bearer ..."}`.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Fetch the latest issues from the GitHub API for my-org/my-repo.",
    environment={
        "type": "remote",
        "network": {
            "allowlist": [
                {
                    "domain": "api.github.com",
                    "transform": {
                        "Authorization": "Bearer ghp_your_github_token"
                    },
                },
                {"domain": "pypi.org"},
                {"domain": "*"},
            ]
        },
    },
)

print(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: "Fetch the latest issues from the GitHub API for my-org/my-repo.",
    environment: {
        type: "remote",
        network: {
            allowlist: [
                {
                    domain: "api.github.com",
                    transform: {
                        "Authorization": "Bearer ghp_your_github_token"
                    },
                },
                { domain: "pypi.org" },
                { domain: "*" },
            ]
        }
    },
});

console.log(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": "Fetch the latest issues from the GitHub API for my-org/my-repo."}],
    "environment": {
        "type": "remote",
        "network": {
            "allowlist": [
                {
                    "domain": "api.github.com",
                    "transform": {
                        "Authorization": "Bearer ghp_your_github_token"
                    }
                },
                {"domain": "pypi.org"},
                {"domain": "*"}
            ]
        }
    }
}'

Jika daftar yang diizinkan ditetapkan, hanya permintaan ke domain yang tercantum secara eksplisit yang diizinkan. Anda dapat menggunakan karakter pengganti untuk mencocokkan subdomain (misalnya, {"domain": "*.example.com"}), tetapi perhatikan bahwa karakter pengganti ini tidak cocok dengan domain root example.com, yang harus ditambahkan secara terpisah. Untuk mengizinkan semua traffic lainnya, seperti merutekan domain yang tidak tercantum tanpa header yang disisipkan, tambahkan {"domain": "*"} sebagai entri catch-all.

Kredensial

Anda dapat menambahkan kredensial untuk digunakan agen dengan menambahkan transformasi header. Kredensial disisipkan di header HTTP masing-masing oleh proxy egress, dan tidak pernah diekspos di dalam sandbox sebagai variabel lingkungan atau file.

Python

import subprocess
from google import genai

# Fetch a short-lived access token from your local gcloud CLI
gcloud_token = subprocess.check_output(
    ["gcloud", "auth", "print-access-token"], text=True
).strip()

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="List the files in gs://my-bucket/reports/ using the GCS JSON API.",
    environment={
        "type": "remote",
        "network": {
            "allowlist": [
                {
                    "domain": "storage.googleapis.com",
                    "transform": {
                        "Authorization": f"Bearer {gcloud_token}"
                    },
                }
            ]
        },
    },
)

print(interaction.output_text)

JavaScript

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

import { execSync } from "child_process";

const gcloudToken = execSync("gcloud auth print-access-token").toString().trim();

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "List the files in gs://my-bucket/reports/ using the GCS JSON API.",
    environment: {
        type: "remote",
        network: {
            allowlist: [
                {
                    domain: "storage.googleapis.com",
                    transform: {
                        "Authorization": `Bearer ${gcloudToken}`
                    },
                }
            ]
        }
    },
});

console.log(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": "List the files in gs://my-bucket/reports/ using the GCS JSON API.",
    "environment": {
        "type": "remote",
        "network": {
            "allowlist": [
                {
                    "domain": "storage.googleapis.com",
                    "transform": {
                        "Authorization": "Bearer <YOUR_GCLOUD_TOKEN>"
                    }
                }
            ]
        }
    }
}'

Menonaktifkan akses jaringan

Untuk memblokir semua akses jaringan keluar, tetapkan network ke disabled:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Analyze the local files only.",
    environment={
        "type": "remote",
        "network": "disabled",
    },
)

print(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: "Analyze the local files only.",
    environment: {
        type: "remote",
        network: "disabled",
    },
});

console.log(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": "Analyze the local files only.",
    "environment": {
        "type": "remote",
        "network": "disabled"
    }
}'

Siklus proses lingkungan

Lingkungan mengikuti siklus proses ini:

Status	Perilaku
Dibuat	Disediakan saat interaksi menentukan `environment: "remote"` atau objek konfigurasi.
Aktif	Berjalan saat interaksi sedang berlangsung.
Tidak ada aktivitas	Snapshot otomatis dan berhenti setelah 15 menit tidak ada aktivitas.
Offline	Dipertahankan selama 7 hari sejak terakhir aktif. Dapat dilanjutkan dengan meneruskan ID-nya.
Dihapus	Dihapus dari sistem.

Mendownload file dari lingkungan

Agen membuat file di dalam sandbox selama eksekusi. Anda dapat mendownload snapshot lingkungan lengkap sebagai file tar menggunakan Files API:

Python

import os
import requests
import tarfile
from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a file environments_test.txt with content 'Environments' inside the sandbox.",
    environment="remote",
)

env_id = interaction.environment_id
api_key = os.environ.get("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_env.tar", "wb") as f:
    f.write(response.content)

os.makedirs("extracted_env_snapshot", exist_ok=True)
with tarfile.open("snapshot_env.tar") as tar:
    tar.extractall(path="extracted_env_snapshot")

print(os.listdir("extracted_env_snapshot"))

JavaScript

import { GoogleGenAI } from "@google/genai";
import { execSync } from "child_process";
import * as fs from "fs";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Write a file environments_test.txt with content 'Environments' inside the sandbox.",
    environment: "remote",
});

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_env.tar", buffer);

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

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

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Api-Revision: 2026-05-20" \
-d '{
    "agent": "antigravity-preview-05-2026",
    "input": "Write a file environments_test.txt with content '\''Environments'\'' inside the sandbox.",
    "environment": "remote"
}'
# Step 2: Download snapshot (reusing environment ID from Step 1)
# curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/files/environment-$ENV_ID:download?alt=media" \
#   -H "x-goog-api-key: $API_KEY" \
#   -o snapshot.tar

Harga &referensi

Setiap lingkungan berjalan dengan alokasi resource tetap:

Resource	Nilai
CPU	4 core
Memori	16 GB

Komputasi lingkungan (CPU, memori, eksekusi sandbox) tidak ditagih selama periode pratinjau. Lihat Harga untuk mengetahui biaya token agen.

Batasan

Status pratinjau: Lingkungan dan agen terkelola dalam status pratinjau. Fitur dan skema dapat berubah.
Ukuran sumber inline: Sumber inline dibatasi hingga 1 MB per file, dan total 2 MB di semua file.
Ukuran sumber: Repositori Git dibatasi hingga 500 MB dan repositori Cloud Storage hingga 2 GB.
Startup lingkungan: Penyediaan lingkungan baru memerlukan waktu hingga ~5 detik. Repositori sumber yang besar dapat meningkatkan waktu ini.
Dukungan file: Agen saat ini dibatasi untuk membaca file teks dan gambar. Dukungan file biner belum tersedia.
Tidak ada pemasangan dari root: Anda tidak dapat menetapkan root (/) sebagai target saat menambahkan sumber kustom. Anda harus selalu menentukan subdirektori.

Langkah berikutnya

Ringkasan Agen: Pelajari konsep inti agen terkelola.
Panduan memulai: Mulai membangun dengan percakapan multi-turn dan streaming.
Agen Antigravity: Jelajahi kemampuan, alat, dan harga untuk agen default.
Membuat Agen Kustom: Tentukan agen Anda sendiri menggunakan AGENTS.md dan SKILL.md.

Lingkungan di Agen Terkelola

Python

JavaScript

REST

Parameter environment

Python

JavaScript

REST

Mengonfigurasi lingkungan

Python

JavaScript

REST

Memasang dari sumber

Python

JavaScript

REST

Sumber pribadi

Python

JavaScript

REST

Python

JavaScript

REST

Software yang telah diinstal sebelumnya

Konfigurasi jaringan

Python

JavaScript

REST

Kredensial

Python

JavaScript

REST

Menonaktifkan akses jaringan

Python

JavaScript

REST

Siklus proses lingkungan

Mendownload file dari lingkungan

Python

JavaScript

REST

Harga &referensi

Batasan

Langkah berikutnya

Parameter `environment`