Ambienti in Managed Agents

Gli ambienti sono sandbox Linux gestite che offrono agli agenti un luogo isolato in cui eseguire il codice e rendere persistenti i file. Sono separati dal contesto dell'interazione, quindi puoi riutilizzare lo stesso ambiente in più interazioni o ricominciare da zero in qualsiasi momento.

Il seguente esempio mostra come creare un'interazione con un nuovo ambiente remoto e recuperarne l'ID:

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"
}'

Parametro environment

Il parametro environment accetta tre forme:

Modulo Esempio Quando utilizzarle
"remote" environment="remote" Esegui il provisioning di una nuova sandbox.
ID ambiente environment="env_abc123" Riutilizza una sandbox esistente con tutti i relativi file e pacchetti.
Oggetto di configurazione environment={...} Esegui il provisioning di una nuova sandbox con origini, regole di rete o entrambe.

Gli esempi seguenti mostrano i tre modi di utilizzare il parametro 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"
            }
        ]
    }
}'

Configurare un ambiente

Un modo per configurare un ambiente è dire all'agente cosa devi installare. Gestisce la risoluzione e la risoluzione dei problemi relativi alle dipendenze. Una volta pronto l'ambiente, salva environment_id e riutilizzalo.

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"
}'

Montare da un'origine

Se sai esattamente quali file deve utilizzare l'agente, montali in una singola chiamata anziché iterare. L'oggetto di configurazione environment accetta un array sources con tre tipi:

Tipo di origine Valore type Descrizione Limite
Repository Git repository Clona un repository da un URL nella sandbox in target. 500 MB
Cloud Storage gcs Copia un file o una directory da Cloud Storage nella sandbox in target. 2 GB
Contenuti incorporati inline Scrive i contenuti di testo non elaborati in un file nella sandbox all'indirizzo target. 1 MB per file, 2 MB totali

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"
            }
        ]
    }
}'

Puoi combinare entrambi gli approcci: monta le origini note in modo dichiarativo, quindi esegui l'iterazione con interazioni di follow-up per installare pacchetti o eseguire script di configurazione. Non puoi impostare la radice (/) come target quando aggiungi una fonte personalizzata, devi sempre specificare una sottodirectory.

Origini private

Puoi anche scaricare da repository GitHub privati o bucket Cloud Storage privati aggiungendo le credenziali nella configurazione di rete:

Per i repository Git privati, utilizza l'autenticazione Basic con il tuo token di accesso personale (PAT) di GitHub. Codifica il token utilizzando x-oauth-basic come nome utente:

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": "*"
                }
            ]
        }
    }
}'

Per i bucket Cloud Storage privati, utilizza un token di connessione OAuth 2.0 standard:

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 preinstallato

La sandbox viene eseguita su Ubuntu e include runtime e pacchetti comuni preinstallati. L'agente può installare pacchetti aggiuntivi in fase di runtime utilizzando pip install o npm install. I pacchetti installati durante un'interazione vengono mantenuti quando riutilizzi lo stesso environment_id.

Categoria Pacchetti preinstallati
Strumenti 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

Configurazione di rete

Per impostazione predefinita, gli ambienti hanno accesso alla rete in uscita senza limitazioni. Utilizza il campo network per limitare il traffico in uscita a domini specifici. Ogni regola specifica un domain e un oggetto transform facoltativo per inserire le intestazioni nelle richieste corrispondenti. Queste intestazioni possono essere uniche per interazione e puoi aggiornarle per lo stesso ambiente.

Campo Tipo Descrizione
domain string Dominio da corrispondere. Utilizza un nome host esatto o * per tutti i domini.
transform object Oggetto contenente coppie chiave-valore semplici che rappresentano le intestazioni da inserire nelle richieste corrispondenti, ad es. {"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": "*"}
            ]
        }
    }
}'

Quando viene impostata una lista consentita, sono consentite solo le richieste ai domini elencati esplicitamente. Puoi utilizzare i caratteri jolly per trovare la corrispondenza con i sottodomini (ad es. {"domain": "*.example.com"}), ma tieni presente che non viene trovata la corrispondenza con il dominio principale example.com, che deve essere aggiunto separatamente. Per consentire tutto il resto del traffico, ad esempio il routing di domini non elencati senza intestazioni inserite, aggiungi {"domain": "*"} come voce catch-all.

Credenziali

Puoi aggiungere le credenziali che l'agente deve utilizzare aggiungendo trasformazioni di intestazione. Le credenziali vengono inserite nelle rispettive intestazioni HTTP da un proxy di uscita e non vengono mai esposte all'interno della sandbox come variabili di ambiente o 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>"
                    }
                }
            ]
        }
    }
}'

Disattivare l'accesso alla rete

Per bloccare tutto l'accesso alla rete in uscita, imposta network su 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"
    }
}'

Ciclo di vita dell'ambiente

Gli ambienti seguono questo ciclo di vita:

Stato Comportamento
Creato Fornito quando un'interazione specifica environment: "remote" o un oggetto di configurazione.
Attivi Esecuzione mentre è in corso un'interazione.
Inattivo Auto-snapshot e si interrompe dopo 15 minuti di inattività.
Offline Conservati per 7 giorni dall'ultima attività. Può essere ripreso passando il relativo ID.
Eliminato Rimossa dal sistema.

Scaricare file dall'ambiente

L'agente crea file all'interno della sandbox durante l'esecuzione. Puoi scaricare l'istantanea completa dell'ambiente come file tar utilizzando l'API Files:

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

Prezzi e risorse

Ogni ambiente viene eseguito con allocazioni di risorse fisse:

Risorsa Valore
CPU 4 core
Memoria 16 GB

Il calcolo dell'ambiente (CPU, memoria, esecuzione sandbox) non viene fatturato durante il periodo di anteprima. Consulta la pagina Prezzi per i costi dei token agente.

Limitazioni

  • Stato dell'anteprima:gli ambienti e gli agenti gestiti sono in anteprima. Funzionalità e schemi possono cambiare.
  • Dimensioni delle fonti inline: le fonti inline sono limitate a 1 MB per file e a 2 MB in totale per tutti i file.
  • Dimensioni origine: i repository Git sono limitati a 500 MB e i repository Cloud Storage a 2 GB.
  • Avvio dell'ambiente:il provisioning di un nuovo ambiente richiede fino a circa 5 secondi. I repository di origine di grandi dimensioni potrebbero aumentare questo tempo.
  • Supporto dei file: l'agente è attualmente limitato alla lettura di file di testo e immagini. Il supporto dei file binari non è ancora disponibile.
  • Nessun montaggio dalla radice:non puoi impostare la radice (/) come target quando aggiungi un'origine personalizzata, devi sempre specificare una sottodirectory.

Passaggi successivi