Interactions API 現已正式發布。建議使用這個 API，存取所有最新功能和模型。

Google 會運用 AI 技術將內容翻譯成你偏好的語言，但可能會出錯。

代管代理程式中的環境

環境是受管理的 Linux 沙箱，可為代理提供隔離空間，用來執行程式碼及保存檔案。這些環境與互動情境無關，因此您可以在多個互動中重複使用相同環境，或隨時重新開始。

以下範例示範如何使用新的遠端環境建立互動，並擷取其 ID：

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    input: "Install pandas and matplotlib, verify the imports, and print the versions.",
    environment: "remote",
});

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

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Install pandas and matplotlib, verify the imports, and print the versions."))
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println("Environment ID: " + interaction.environmentId().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Install pandas and matplotlib, verify the imports, and print the versions.",
    "environment": "remote"
}'

`environment` 參數

environment 參數接受三種形式：

表單	範例	使用時機
`"remote"`	`environment="remote"`	佈建新的沙箱。
環境 ID	`environment="env_abc123"`	重複使用現有沙箱及其所有檔案和套件。
設定物件	`environment={...}`	使用來源、網路規則、環境變數或組合，佈建新的沙箱。

下列範例示範使用 environment 參數的三種方式。

Python

from google import genai

client = genai.Client()

# Fresh sandbox
interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Write a hello world script.",
    environment="remote",
)

# Reuse an existing sandbox
interaction_2 = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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-09-2026",
    input: "Write a hello world script.",
    environment: "remote",
});

// Reuse an existing sandbox
const interaction2 = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    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-09-2026",
    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);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

// Fresh sandbox
CreateAgentInteraction params1 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Write a hello world script."))
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();
Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params1)).interaction().get();

// Reuse an existing sandbox
CreateAgentInteraction params2 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Modify the script to accept a name argument."))
    .environment(CreateAgentInteractionEnvironment.of(interaction.environmentId().orElse("")))
    .previousInteractionId(interaction.id().orElse(""))
    .build();
Interaction interaction2 = client.interactions.create(CreateInteractionRequestBody.of(params2)).interaction().get();

// New sandbox with sources
Environment env3 = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.REPOSITORY)
            .source("https://github.com/octocat/Spoon-Knife")
            .target("/workspace/spoon-knife")
            .build()
    ))
    .build();

CreateAgentInteraction params3 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("List all files and summarize the project."))
    .environment(CreateAgentInteractionEnvironment.of(env3))
    .build();
Interaction interaction3 = client.interactions.create(CreateInteractionRequestBody.of(params3)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

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" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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: $GEMINI_API_KEY" \
-d "{
    \"agent\": \"antigravity-preview-09-2026\",
    \"input\": [{\"type\": \"text\", \"text\": \"Modify the script to accept a name argument.\"}],
    \"environment\": \"$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" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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"
            }
        ]
    }
}'

設定環境

設定環境的方法之一是告訴代理程式需要安裝的項目。並處理依附元件解析和疑難排解。環境準備就緒後，請儲存 environment_id 並重複使用。

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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-09-2026",
    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-09-2026",
    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-09-2026",
    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-09-2026",
    input: "Using the tools in /workspace/tools, list the files.",
    environment: interaction.environment_id,
    previous_interaction_id: interaction2.id,
});
console.log(interaction.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateAgentInteraction params1 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Install pandas, matplotlib, and seaborn. Verify all imports work and print the installed versions."))
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();
Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params1)).interaction().get();

// Reuse the configured environment
CreateAgentInteraction params2 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Clone https://github.com/octocat/Spoon-Knife into /workspace/tools. Run the test suite and fix any missing dependencies."))
    .environment(CreateAgentInteractionEnvironment.of(interaction.environmentId().orElse("")))
    .previousInteractionId(interaction.id().orElse(""))
    .build();
Interaction interaction2 = client.interactions.create(CreateInteractionRequestBody.of(params2)).interaction().get();

// Reuse the configured environment
CreateAgentInteraction params3 = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Using the tools in /workspace/tools, list the files."))
    .environment(CreateAgentInteractionEnvironment.of(interaction.environmentId().orElse("")))
    .previousInteractionId(interaction2.id().orElse(""))
    .build();
Interaction interaction3 = client.interactions.create(CreateInteractionRequestBody.of(params3)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

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" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Install pandas, matplotlib, and seaborn. Verify all imports work and print the installed versions.",
    "environment": "remote"
}'

從來源掛接

如果您確切知道代理程式需要哪些檔案，請在單一呼叫中掛接這些檔案，而非進行疊代。environment 設定物件接受 sources 陣列，其中包含三種型別：

來源類型	`type`值	說明	限制
Git 存放區	`repository`	從網址將存放區複製到 `target` 的沙箱中。	500 MB
Cloud Storage	`gcs`	將 Cloud Storage 中的檔案或目錄複製到 `target` 的沙箱。	2 GB
內嵌內容	`inline`	將原始文字內容寫入沙箱中 `target` 的檔案。	每個檔案 1 MB，總計 2 MB

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.REPOSITORY)
            .source("https://github.com/octocat/Spoon-Knife")
            .target("/workspace/spoon-knife")
            .build(),
        Source.builder()
            .type(SourceType.GCS)
            .source("gs://cloud-samples-data/bigquery/us-states/")
            .target("/workspace/gcs-data")
            .build(),
        Source.builder()
            .type(SourceType.INLINE)
            .content("# Project Notes\n\n- Analyze state population data\n- Create visualizations\n")
            .target("/workspace/notes/readme.md")
            .build()
    ))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("List all files under /workspace and describe what you find."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

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" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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"
            }
        ]
    }
}'

您可以結合這兩種方法：以宣告方式掛接已知來源，然後透過後續互動疊代，安裝套件或執行設定指令碼。新增自訂來源時，您無法將根目錄 (/) 設為目標，必須指定子目錄。

吊人胃口的情節片段

您也可以將.agents/hooks.json設定檔和自訂攔截指令碼掛載至沙箱，強制執行安全防護措施，或在工具執行時執行自動驗證。如需結構定義和程式碼範例，請參閱「掛鉤」。

私人來源

您也可以在網路設定中驗證來源網域，從私人 GitHub 存放區或私人 Cloud Storage bucket 下載檔案。

其中一個選項是儲存以 ID 參照的憑證，這樣您只要儲存一次密鑰，所有需要該來源的環境都能參照：

"network": {
    "allowlist": [
        { "domain": "github.com", "credential": "github-production" },
        { "domain": "*" }
    ]
}

您也可以使用 transform 內嵌設定標頭，如下列範例所示。輸出 Proxy 會以相同方式套用這兩種形式，且無論是哪一種形式，密鑰都不會進入沙箱。

如果是私人 Git 存放區，請使用 Basic 驗證，並提供 GitHub 個人存取權杖 (PAT)。使用 x-oauth-basic 做為使用者名稱，對權杖進行編碼：

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

Python

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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: "*"
                }
            ]
        }
    },
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;
import java.util.Map;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.REPOSITORY)
            .source("https://github.com/your-org/backend")
            .target("/backend-app")
            .build()
    ))
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("github.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Basic YOUR_BASE64_TOKEN"
                    )))
                    .build(),
                AllowlistEntry.builder()
                    .domain("*")
                    .build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Run the test for my backend app and fix any issue."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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": "*"
                }
            ]
        }
    }
}'

如果是私人 Cloud Storage bucket，請使用標準 OAuth 2.0 不記名權杖：

gcloud auth print-access-token

Python

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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: "*"
                }
            ]
        }
    },
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;
import java.util.Map;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.GCS)
            .source("gs://my-private-bucket/data")
            .target("/workspace")
            .build()
    ))
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("*.googleapis.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer YOUR_GCS_TOKEN"
                    )))
                    .build(),
                AllowlistEntry.builder()
                    .domain("*")
                    .build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Analyze the discrepancies across the data in workspace"))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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": "*"
                }
            ]
        }
    }
}'

預先安裝軟體

沙箱會在 Ubuntu 上執行，並預先安裝執行階段和常見套件。代理程式可在執行階段使用 pip install 或 npm install 安裝其他套件。重複使用相同的 environment_id 時，互動期間安裝的套件會保留下來。

類別	預先安裝的套件
UNIX 工具	`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`

環境變數

使用 env 欄位在沙箱內設定環境變數。每個項目都會將變數名稱對應至設定的常值字串，或是對應至儲存的憑證 (用於密鑰)。代理程式會以任何殼層中的方式查看這些變數，因此從程序環境讀取資料的工具和指令碼會擷取這些變數，不需要額外接線。

欄位	類型	說明
`env`	`object`	變數名稱對應至值的對應。值可以是常值 `string`，也可以是 `{"credential": "credential-id"}` 形式的憑證參照。

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Build the project and run the test suite.",
    environment={
        "type": "remote",
        "env": {
            "NODE_ENV": "production",
            "LOG_LEVEL": "debug",
            "API_TOKEN": {"credential": "my-api-token"},
        },
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Build the project and run the test suite.",
    environment: {
        type: "remote",
        env: {
            NODE_ENV: "production",
            LOG_LEVEL: "debug",
            API_TOKEN: { credential: "my-api-token" },
        },
    },
});

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" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": [{"type": "text", "text": "Build the project and run the test suite."}],
    "environment": {
        "type": "remote",
        "env": {
            "NODE_ENV": "production",
            "LOG_LEVEL": "debug",
            "API_TOKEN": {"credential": "my-api-token"}
        }
    }
}'

變數適用於代理程式在該互動中執行的每個指令，包括殼層指令、建構步驟，以及啟動的任何程序。

這兩種值類型的行為不同。系統會將字串常值以純文字形式寫入容器。憑證參照不是：變數會收到預留位置，且輸出 Proxy 只會在傳送至該憑證信任網域的外送要求中，替換為實際密鑰。如要瞭解運作方式，請參閱「將憑證設為環境變數」。

網路設定

根據預設，環境具有不受限制的輸出網路存取權。使用 network 欄位將輸出流量限制在特定網域。每項規則都會指定 domain，以及選用的 credential (用於插入已儲存的密鑰) 和選用的 transform 物件 (用於將標頭插入相符的要求)。這些標頭在每次互動中可能都不相同，您也可以更新相同環境的標頭。

欄位	類型	說明
`domain`	`string`	要比對的網域。使用確切主機名稱或 `*` 代表所有網域。
`credential`	`string`	儲存的憑證 ID。輸出 Proxy 會解析該標頭，並在要求時插入驗證標頭。
`transform`	`object`	物件，內含代表要插入相符要求的標頭的扁平鍵/值組合，例如 `{"Authorization": "Bearer ..."}`。

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    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);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;
import java.util.Map;

Client client = new Client();

Environment env = Environment.builder()
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("api.github.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer ghp_your_github_token"
                    )))
                    .build(),
                AllowlistEntry.builder().domain("pypi.org").build(),
                AllowlistEntry.builder().domain("*").build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Fetch the latest issues from the GitHub API for my-org/my-repo."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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": "*"}
            ]
        }
    }
}'

設定許可清單後，系統只會允許對明確列出的網域提出要求。您可以使用萬用字元比對子網域 (例如 {"domain": "*.example.com"})，但請注意，這不會比對根網域 example.com，您必須另外新增根網域。如要允許所有其他流量 (例如轉送未列出的網域，且不插入標頭)，請新增 {"domain": "*"} 做為萬用項目。

憑證

驗證外送流量的方式有兩種：透過 ID 參照儲存的憑證，以及在允許清單規則中內嵌 transform。出口 Proxy 會同時套用在連線上，因此無論如何，密碼都不會進入沙箱，也不會出現在互動酬載中。

如果想儲存密碼並重複使用，請使用代管憑證。專案中的每個環境、代理程式和觸發條件都可以參照相同 ID，您可以在一處輪替 ID。

Python

from google import genai

client = genai.Client()

# Store the secret once
client.credentials.create(
    id="github-production",
    type="bearer_token",
    token="ghp_your_github_token",
)

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Fetch the latest issues from the GitHub API for my-org/my-repo.",
    environment={
        "type": "remote",
        "network": {
            "allowlist": [
                {"domain": "api.github.com", "credential": "github-production"},
                {"domain": "*"},
            ]
        },
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

// Store the secret once
await client.credentials.create({
    id: "github-production",
    type: "bearer_token",
    token: "ghp_your_github_token",
});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Fetch the latest issues from the GitHub API for my-org/my-repo.",
    environment: {
        type: "remote",
        network: {
            allowlist: [
                { domain: "api.github.com", credential: "github-production" },
                { domain: "*" },
            ]
        }
    },
});

console.log(interaction.output_text);

REST

# Store the secret once
curl -X POST "https://generativelanguage.googleapis.com/v1beta/credentials" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "id": "github-production",
    "type": "bearer_token",
    "token": "ghp_your_github_token"
}'

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Fetch the latest issues from the GitHub API for my-org/my-repo.",
    "environment": {
        "type": "remote",
        "network": {
            "allowlist": [
                { "domain": "api.github.com", "credential": "github-production" },
                { "domain": "*" }
            ]
        }
    }
}'

oauth2憑證也會自行重新整理存取權杖，因此權杖過期時，長時間執行的互動不會中斷。如需憑證類型和管理作業的完整清單，請參閱「憑證」。

您也可以使用 transform 內嵌設定標頭。如果值屬於單一呼叫，例如您在建立互動前產生的權杖，就適合使用這個方法。以這種方式設定的標頭會由相同的輸出 Proxy 注入，絕不會在沙箱中以環境變數或檔案的形式公開。

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-09-2026",
    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-09-2026",
    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);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.nio.charset.StandardCharsets;
import java.util.List;
import java.util.Map;

// Fetch a short-lived access token from your local gcloud CLI
Process process = new ProcessBuilder("gcloud", "auth", "print-access-token").start();
String gcloudToken = new String(process.getInputStream().readAllBytes(), StandardCharsets.UTF_8).trim();

Client client = new Client();

Environment env = Environment.builder()
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("storage.googleapis.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer " + gcloudToken
                    )))
                    .build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("List the files in gs://my-bucket/reports/ using the GCS JSON API."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "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>"
                    }
                }
            ]
        }
    }
}'

credential 和 transform 可以出現在同一條規則中。系統會先套用憑證，然後合併頂端的 transform，因此如果兩者都設定相同的金鑰，系統會採用明確的 transform 標頭。常見模式是驗證標頭的憑證，以及服務預期會一併提供的額外標頭的 transform。

停用網路存取權

如要封鎖所有傳出網路存取權，請將 network 設為 disabled：

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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-09-2026",
    input: "Analyze the local files only.",
    environment: {
        type: "remote",
        network: "disabled",
    },
});

console.log(interaction.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.NetworkEnum;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

Environment env = Environment.builder()
    .network(Network.of(NetworkEnum.DISABLED))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Analyze the local files only."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Analyze the local files only.",
    "environment": {
        "type": "remote",
        "network": "disabled"
    }
}'

重新整理憑證

存取權杖和短期 API 金鑰等內嵌權杖會過期。您可以在下次互動時傳遞現有 environment_id 和新的 network 設定，藉此重新整理這些設定。新的網路規則會完全取代先前的規則，但環境的檔案系統狀態 (已安裝的套件、檔案、存放區) 會保留。

如果您改用已儲存的憑證，則不需要這個屬性。oauth2 憑證會自行重新整理，且輪替任何憑證都是憑證上的 PATCH，不會影響參照該憑證的任何許可清單規則。

Python

from google import genai

client = genai.Client()

# First interaction: use an initial token
first = client.interactions.create(
    agent="antigravity-preview-09-2026",
    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 INITIAL_TOKEN"
                    },
                }
            ]
        },
    },
)

# Later: refresh the token on the same environment
result = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Now download the file reports/q1.csv from the same bucket.",
    environment={
        "type": "remote",
        "environment_id": first.environment_id,
        "network": {
            "allowlist": [
                {
                    "domain": "storage.googleapis.com",
                    "transform": {
                        "Authorization": "Bearer REFRESHED_TOKEN"
                    },
                }
            ]
        },
    },
)

print(result.output_text)

JavaScript

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

const client = new GoogleGenAI({});

// First interaction: use an initial token
const first = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    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 INITIAL_TOKEN"
                    },
                }
            ]
        }
    },
});

// Later: refresh the token on the same environment
const result = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Now download the file reports/q1.csv from the same bucket.",
    environment: {
        type: "remote",
        environment_id: first.environment_id,
        network: {
            allowlist: [
                {
                    domain: "storage.googleapis.com",
                    transform: {
                        "Authorization": "Bearer REFRESHED_TOKEN"
                    },
                }
            ]
        }
    },
});

console.log(result.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;
import java.util.Map;

Client client = new Client();

// First interaction: use an initial token
Environment initialEnv = Environment.builder()
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("storage.googleapis.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer INITIAL_TOKEN"
                    )))
                    .build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction firstParams = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("List the files in gs://my-bucket/reports/ using the GCS JSON API."))
    .environment(CreateAgentInteractionEnvironment.of(initialEnv))
    .build();

Interaction first = client.interactions.create(CreateInteractionRequestBody.of(firstParams)).interaction().get();

// Later: refresh the token on the same environment
Environment refreshedEnv = Environment.builder()
    .environmentId(first.environmentId().orElse(""))
    .network(Network.of(EnvironmentNetworkEgressAllowlist.of(
        Allowlist.builder()
            .allowlist(List.of(
                AllowlistEntry.builder()
                    .domain("storage.googleapis.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer REFRESHED_TOKEN"
                    )))
                    .build()
            ))
            .build()
    )))
    .build();

CreateAgentInteraction secondParams = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Now download the file reports/q1.csv from the same bucket."))
    .environment(CreateAgentInteractionEnvironment.of(refreshedEnv))
    .build();

Interaction result = client.interactions.create(CreateInteractionRequestBody.of(secondParams)).interaction().get();
System.out.println(result.outputText().orElse(""));

REST

# Use the environment_id from a previous interaction
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Now download the file reports/q1.csv from the same bucket.",
    "environment": {
        "type": "remote",
        "environment_id": "<ENVIRONMENT_ID_FROM_PREVIOUS_INTERACTION>",
        "network": {
            "allowlist": [
                {
                    "domain": "storage.googleapis.com",
                    "transform": {
                        "Authorization": "Bearer REFRESHED_TOKEN"
                    }
                }
            ]
        }
    }
}'

環境生命週期

環境的生命週期如下：

州	行為
已建立	當互動指定 `environment: "remote"` 或設定物件時，系統會佈建此物件。
進行中	在互動進行期間執行。
閒置	自動拍攝快照，並在閒置 15 分鐘後停止。
離線	自上次活動起保留 7 天。傳遞 ID 即可繼續。
已刪除	7 天 TTL 保留期限到期後，系統會自動移除，您也可以手動刪除。

Environments API

您可以使用 Environments API，以程式輔助方式管理沙箱工作階段。列舉環境可讓您探索有效的工作階段 ID，並在用戶端連線於長時間執行的工作期間終止時，復原狀態。您也可以檢查工作階段中繼資料，並在工作流程結束時明確刪除環境，不必等待自動 TTL 到期。

可列出環境

列出專案所屬的有效環境。使用分頁參數控制回應批量大小。

Python

from google import genai

client = genai.Client()

response = client.environments.list(page_size=10)
for env in response.environments:
    print(f"Environment ID: {env.id}, Status: {env.status}")

JavaScript

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

const client = new GoogleGenAI({});

const response = await client.environments.list({ page_size: 10 });
for (const env of response.environments) {
    console.log(`Environment ID: ${env.id}, Status: ${env.status}`);
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.environments.Environment;
import com.google.genai.gaos.models.environments.ListEnvironmentsResponse;
import java.util.List;

Client client = new Client();

ListEnvironmentsResponse response = client.environments.listEnvironments()
    .pageSize(10)
    .call()
    .listEnvironmentsResponse()
    .get();

for (Environment env : response.environments().orElse(List.of())) {
    System.out.println("Environment ID: " + env.id().orElse("") + ", Status: " + env.status().orElse(null));
}

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments?pageSize=10" \
-H "x-goog-api-key: $GEMINI_API_KEY"

回應類似於下列內容：

{
  "environments": [
    {
      "id": "140128b2a13c12c00a5a0d8cf7af9469",
      "status": "active"
    },
    {
      "id": "362b738275a1d74af6f1c62bc050da73",
      "status": "active"
    }
  ],
  "next_page_token": "Cj...5aE="
}

取得環境

依資源名稱擷取特定環境的中繼資料和設定詳細資料。

Python

from google import genai

client = genai.Client()

env = client.environments.get(id="YOUR_ENVIRONMENT_ID")
print(f"Environment ID: {env.id}, Status: {env.status}")

JavaScript

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

const client = new GoogleGenAI({});

const env = await client.environments.get("YOUR_ENVIRONMENT_ID");
console.log(`Environment ID: ${env.id}, Status: ${env.status}`);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.environments.Environment;

Client client = new Client();

Environment env = client.environments.getEnvironment("YOUR_ENVIRONMENT_ID").environment().get();
System.out.println("Environment ID: " + env.id().orElse("") + ", Status: " + env.status().orElse(null));

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments/YOUR_ENVIRONMENT_ID" \
-H "x-goog-api-key: $GEMINI_API_KEY"

回應類似於下列內容：

{
  "id": "140128b2a13c12c00a5a0d8cf7af9469",
  "status": "active",
  "sources": [
    {
      "type": "repository",
      "source": "https://github.com/octocat/Spoon-Knife",
      "target": "/workspace/spoon-knife"
    }
  ],
  "network": {
    "allowlist": [
      {
        "domain": "api.github.com"
      },
      {
        "domain": "github.com"
      }
    ]
  }
}

可刪除環境

工作或管道完成後，請明確終止並刪除環境，以清理沙箱資源。

Python

from google import genai

client = genai.Client()

client.environments.delete(id="YOUR_ENVIRONMENT_ID")

JavaScript

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

const client = new GoogleGenAI({});

await client.environments.delete("YOUR_ENVIRONMENT_ID");

Java

import com.google.genai.Client;

Client client = new Client();

client.environments.deleteEnvironment("YOUR_ENVIRONMENT_ID");

REST

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/environments/YOUR_ENVIRONMENT_ID" \
-H "x-goog-api-key: $GEMINI_API_KEY"

管理環境中的檔案

代理程式會在執行期間建立及修改沙箱內的檔案。您可以瀏覽目錄內容、取得檔案中繼資料、下載個別檔案或整個目錄 (以 tar 封存檔形式)，以及上傳檔案或將封存檔直接解壓縮至環境中。沙箱環境的儲存空間須遵守合理使用限制。

列出目錄中的檔案

查詢參數

參數	類型	說明
`recursive`	布林值	當 `true` 時，會遞迴列出所有檔案和目錄。預設值：`false`。

Python

from google import genai

client = genai.Client()

# List root directory
response = client.environments.files.list(
    environment="YOUR_ENVIRONMENT_ID",
    path="",
)
for file in response.files:
    print(f"{file.name} ({file.type}) - {file.path}")

# List a subdirectory recursively
response = client.environments.files.list(
    environment="YOUR_ENVIRONMENT_ID",
    path="src",
    recursive=True,
)
for file in response.files:
    print(f"{file.name} ({file.type}) - {file.path}")

JavaScript

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

const client = new GoogleGenAI({});

// List root directory
const response = await client.environments.files.list({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "",
});
for (const file of response.files) {
    console.log(`${file.name} (${file.type}) - ${file.path}`);
}

// List a subdirectory recursively
const srcResponse = await client.environments.files.list({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "src",
    recursive: true,
});
for (const file of srcResponse.files) {
    console.log(`${file.name} (${file.type}) - ${file.path}`);
}

REST

# List root directory
curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

# List a subdirectory
curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files/src" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

# List all files recursively
curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files?recursive=true" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

回應會傳回 files 陣列，其中包含每個項目的中繼資料：

{
  "files": [
    {
      "name": "config",
      "path": "config",
      "type": "DIRECTORY",
      "created": "2026-08-12T07:44:18Z",
      "modified": "2026-08-12T07:44:18Z"
    },
    {
      "name": "main.py",
      "path": "src/main.py",
      "type": "FILE",
      "size_bytes": "15",
      "mime_type": "text/x-python; charset=utf-8",
      "created": "2026-08-12T07:44:20Z",
      "modified": "2026-08-12T07:44:20Z"
    }
  ]
}

檔案輸入欄位

欄位	類型	說明
`name`	字串	檔案或目錄名稱。
`path`	字串	相對於環境根目錄的完整路徑。
`type`	字串	`FILE` 或 `DIRECTORY`。
`size_bytes`	字串	檔案大小 (以位元組為單位，僅限檔案)。
`mime_type`	字串	MIME 類型 (僅限檔案)。
`created`	字串	ISO 8601 建立時間戳記。
`modified`	字串	ISO 8601 最後修改時間戳記。

取得檔案中繼資料

依路徑取得特定檔案的中繼資料。

Python

from google import genai

client = genai.Client()

response = client.environments.files.list(
    environment="YOUR_ENVIRONMENT_ID",
    path="src/main.py",
)
file = response.files[0]
print(f"Name: {file.name}, Size: {file.size_bytes} bytes, Type: {file.mime_type}")

JavaScript

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

const client = new GoogleGenAI({});

const response = await client.environments.files.list({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "src/main.py",
});
const file = response.files[0];
console.log(`Name: ${file.name}, Size: ${file.size_bytes} bytes, Type: ${file.mime_type}`);

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files/src/main.py" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

回應會傳回以 files 陣列包裝的檔案中繼資料：

{
  "files": [
    {
      "name": "main.py",
      "path": "src/main.py",
      "type": "FILE",
      "size_bytes": "15",
      "mime_type": "text/x-python; charset=utf-8",
      "created": "2026-08-12T07:44:20Z",
      "modified": "2026-08-12T07:44:20Z"
    }
  ]
}

如果檔案不存在，API 會傳回 404 錯誤：

{
  "error": {
    "message": "Path 'nonexistent.txt' not found in environment 'ENV_ID'.",
    "code": "not_found"
  }
}

下載單一檔案

下載特定檔案的內容。在 SDK 中，請使用 download() 方法。在 REST 要求中，將 ?alt=media 查詢參數附加至檔案路徑。伺服器會傳回 200 OK，並串流處理原始檔案內容。

Python

from google import genai

client = genai.Client()

content = client.environments.files.download(
    environment="YOUR_ENVIRONMENT_ID",
    path="src/main.py",
)

with open("main.py", "wb") as f:
    f.write(content)

JavaScript

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

const client = new GoogleGenAI({});

const bytes = await client.environments.files.download({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "src/main.py",
});

fs.writeFileSync("main.py", Buffer.from(bytes));

REST

curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files/src/main.py?alt=media" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -o main.py

將目錄下載為 tar 封存檔

如要將整個目錄下載為 tar 封存檔，請使用 ?alt=media 要求目錄路徑。這會傳回 POSIX tar 檔案 (未經過 gzip 壓縮)。使用 recursive=true 納入巢狀子目錄。

Python

import tarfile
from google import genai

client = genai.Client()

# Download a subdirectory archive
archive = client.environments.files.download(
    environment="YOUR_ENVIRONMENT_ID",
    path="src",
)

with open("src.tar", "wb") as f:
    f.write(archive)

with tarfile.open("src.tar") as tar:
    tar.extractall(path="./extracted")

JavaScript

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

const client = new GoogleGenAI({});

// Download a subdirectory archive
const bytes = await client.environments.files.download({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "src",
});

fs.writeFileSync("src.tar", Buffer.from(bytes));
execSync("tar -xf src.tar -C ./extracted");

REST

# Download a subdirectory (top-level files only)
curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files/src?alt=media" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -o src.tar

# Download a subdirectory recursively (includes nested directories)
curl -L -X GET "https://generativelanguage.googleapis.com/v1beta/environments/$ENV_ID/files/config?alt=media&recursive=true" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -o config.tar

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

# Extract the archive
tar xf snapshot.tar -C ./extracted

行為矩陣

下表歸納了檔案和目錄端點、HTTP 方法和查詢參數的預期回應和封存行為：

要求	`alt`	`recursive`	`extract`	`overwrite`	回應
`GET /files`	(無)	(無)	-	-	根目錄的 JSON 清單
`GET /files/{path}` (檔案)	(無)	-	-	-	檔案的 JSON 中繼資料
`GET /files/{path}` (dir)	(無)	`false`	-	-	直屬子項的 JSON 清單
`GET /files/{path}` (dir)	(無)	`true`	-	-	所有子系的 JSON 清單
`GET /files/{path}?alt=media` (檔案)	`media`	-	-	-	原始檔案內容
`GET /files/{path}?alt=media` (dir)	`media`	`false`	-	-	目錄中直接檔案的 Tar 封存
`GET /files/{path}?alt=media` (dir)	`media`	`true`	-	-	以遞迴方式封存所有檔案的 Tar 封存檔
`GET /files?alt=media`	`media`	`false`	-	-	僅限根層級檔案的 Tar 封存檔
`PUT /files/{path}` (檔案)	-	-	`false`	`false`	在路徑中寫入檔案。如果已存在，則傳回 `409 Conflict`
`PUT /files/{path}?overwrite=true`	-	-	`false`	`true`	在路徑中寫入或覆寫檔案
`PUT /files/{path}?extract=true`	-	-	`true`	`false`	將封存檔解壓縮至目標目錄。如果存在任何目標檔案，則傳回 `409 Conflict`
`PUT /files/{path}?extract=true&overwrite=true`	-	-	`true`	`true`	解壓縮封存檔，並取代所有現有檔案

將檔案上傳至環境

使用 HTTP PUT，將個別檔案或目錄封存檔直接上傳至現有環境沙箱。如果父項目錄不存在，系統會自動建立。環境中的儲存空間須遵守公平使用限制。

上傳單一檔案

Python

from google import genai

client = genai.Client()

with open("local_file.txt", "rb") as f:
    result = client.environments.files.upload(
        environment="YOUR_ENVIRONMENT_ID",
        path="workspace/data/file.txt",
        file=f,
        mime_type="text/plain",
        overwrite=True,
    )

file = result.files[0]
print(f"Uploaded: {file.name} ({file.size_bytes} bytes)")

JavaScript

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

const client = new GoogleGenAI({});

const content = fs.readFileSync("local_file.txt");
const result = await client.environments.files.upload({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "workspace/data/file.txt",
    file: content,
    mime_type: "text/plain",
    overwrite: true,
});

const file = result.files[0];
console.log(`Uploaded: ${file.name} (${file.size_bytes} bytes)`);

REST

curl -X PUT "https://generativelanguage.googleapis.com/upload/v1beta/environments/$ENV_ID/files/workspace/data/file.txt" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: text/plain" \
  --data-binary @local_file.txt

回應會傳回上傳檔案的中繼資料，並以 files 陣列包裝，確保與清單和取得端點一致：

{
  "files": [
    {
      "name": "file.txt",
      "path": "workspace/data/file.txt",
      "type": "FILE",
      "size_bytes": "1024",
      "mime_type": "text/plain"
    }
  ]
}

上傳及解壓縮目錄封存檔

如要在單一要求中植入整個程式碼集或目錄結構，請使用 extract=true 上傳 .tar 或 .tar.gz 封存檔。

Python

from google import genai

client = genai.Client()

with open("source.tar.gz", "rb") as f:
    result = client.environments.files.upload(
        environment="YOUR_ENVIRONMENT_ID",
        path="workspace/src/",
        file=f,
        extract=True,
    )

for entry in result.files:
    print(f"Extracted: {entry.path}")

JavaScript

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

const client = new GoogleGenAI({});

const archive = fs.readFileSync("source.tar.gz");
const result = await client.environments.files.upload({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "workspace/src/",
    file: archive,
    extract: true,
});

for (const entry of result.files) {
    console.log(`Extracted: ${entry.path}`);
}

REST

curl -X PUT "https://generativelanguage.googleapis.com/upload/v1beta/environments/$ENV_ID/files/workspace/src/?extract=true" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/x-tar" \
  --data-binary @source.tar.gz

回應會列出封存作業寫入的每個檔案：

{
  "files": [
    {
      "name": "app.py",
      "path": "workspace/src/app.py",
      "type": "FILE",
      "size_bytes": "15",
      "mime_type": "text/x-python"
    },
    {
      "name": "requirements.txt",
      "path": "workspace/src/requirements.txt",
      "type": "FILE",
      "size_bytes": "17",
      "mime_type": "text/plain"
    }
  ]
}

透過支援續傳的工作階段上傳大型檔案

如果是大型酬載，或透過不可靠的連線上傳，請使用可恢復的工作階段，而不是在一個要求中傳送整個主體。支援續傳的上傳作業會將轉移作業分割成多個區塊，個別重試，因此即使作業中途失敗，也不必重新開始。

首先，請使用 uploadType=resumable 啟動工作階段。傳送空白主體，並使用 X-Upload-Content-Type 和 X-Upload-Content-Length 標頭宣告要上傳的酬載媒體類型和總大小：

PUT /upload/v1beta/environments/$ENV_ID/files/workspace/data/large_dataset.bin?uploadType=resumable HTTP/1.1
Host: generativelanguage.googleapis.com
X-Upload-Content-Type: application/octet-stream
X-Upload-Content-Length: 20971520
Content-Length: 0
x-goog-api-key: $GEMINI_API_KEY

回應會在 Location 標頭中攜帶工作階段網址。這個網址已包含 upload_id，因此不需要再次提供 API 金鑰：

HTTP/1.1 200 OK
Location: https://generativelanguage.googleapis.com/upload/v1beta/environments/$ENV_ID/files/workspace/data/large_dataset.bin?uploadType=resumable&upload_id=AJjja9bfHjiYlGi60pUazCaTuPY
Content-Length: 0

將酬載內容分塊上傳至該網址。每個區塊都會透過 Content-Range 標頭宣告自己的位元組範圍和總大小：

PUT /upload/v1beta/environments/$ENV_ID/files/workspace/data/large_dataset.bin?uploadType=resumable&upload_id=AJjja9bfHjiYlGi60pUazCaTuPY HTTP/1.1
Host: generativelanguage.googleapis.com
Content-Type: application/octet-stream
Content-Range: bytes 0-10485759/20971520
Content-Length: 10485760

<10 MB binary payload>

最後一個區塊以外的每個區塊都會傳回 308 Resume Incomplete。Range 標頭會告訴您伺服器已提交的位元組數，如果區塊失敗，您會從這裡繼續：

HTTP/1.1 308 Resume Incomplete
Range: bytes=0-10485759
Content-Length: 0

以相同方式傳送其餘區塊：

PUT /upload/v1beta/environments/$ENV_ID/files/workspace/data/large_dataset.bin?uploadType=resumable&upload_id=AJjja9bfHjiYlGi60pUazCaTuPY HTTP/1.1
Host: generativelanguage.googleapis.com
Content-Type: application/octet-stream
Content-Range: bytes 10485760-20971519/20971520
Content-Length: 10485760

<remaining 10 MB binary payload>

最後一個區塊會完成上傳作業，並傳回檔案中繼資料，與單次上傳作業的 files 信封相同：

{
  "files": [
    {
      "name": "large_dataset.bin",
      "path": "workspace/data/large_dataset.bin",
      "type": "FILE",
      "size_bytes": "20971520",
      "mime_type": "application/octet-stream"
    }
  ]
}

續傳工作階段也適用於 extract 和 overwrite。請在起始要求中設定這些查詢參數，而非個別區塊。

覆寫保護

根據預設，overwrite 為 false。如果目的地路徑已存在，要求會傳回 409 Conflict 錯誤，且不會寫入任何內容：

{
  "error": {
    "message": "Requested entity already exists",
    "code": "aborted"
  }
}

如要取代現有檔案或目錄，請設定 overwrite=true (或在 REST 中附加 ?overwrite=true)。使用 extract=true 時，系統會對封存中的每個檔案進行衝突檢查，因此如果存在任何目標檔案，要求就會失敗。

下載完整快照 (已淘汰)

如要將現有程式碼遷移至環境檔案 API，請按照下列步驟操作：

Python：將舊版檔案下載要求替換為：

archive = client.environments.files.download(
    environment="YOUR_ENVIRONMENT_ID",
    path="workspace",
)
with open("snapshot.tar", "wb") as f:
    f.write(archive)

JavaScript：將舊版檔案下載要求替換為：

const bytes = await client.environments.files.download({
    environment: "YOUR_ENVIRONMENT_ID",
    path: "workspace",
});
fs.writeFileSync("snapshot.tar", Buffer.from(bytes));

REST：將 GET /v1beta/files/environment-$ENV_ID:download?alt=media 替換為：

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

價格與資源

每個環境都會以固定的資源分配量執行：

資源	值
CPU	4 核心
記憶體	16 GB

在預先發布期間，系統不會收取環境運算 (CPU、記憶體、沙箱執行) 費用。如需瞭解代理程式權杖費用，請參閱「定價」。

限制

預覽狀態：環境和受管理代理程式目前處於預覽階段。功能和結構定義可能會有所異動。
內嵌來源大小：每個檔案的內嵌來源大小上限為 1 MB，所有檔案的內嵌來源大小總和上限為 2 MB。
來源大小：Git 存放區大小上限為 500 MB，Cloud Storage 存放區大小上限為 2 GB。
環境啟動：佈建新環境最多需要約 5 秒。如果來源存放區很大，可能需要較長的時間。
環境到期：系統會保留閒置的離線環境 7 天，然後使用自動 TTL 清理功能將其刪除。如果傳遞過期或無效的環境 ID，系統會傳回 404 Not Found 錯誤。
支援的檔案：目前僅限讀取文字和圖片檔。目前尚不支援二進位檔案。
無法從根目錄掛接：新增自訂來源時，您無法將根目錄 (/) 設為目標，必須一律指定子目錄。

後續步驟

代理程式總覽：瞭解受管理代理程式的核心概念。
快速入門導覽課程：開始建構多輪對話和串流。
Antigravity Agent：瞭解預設代理的功能、工具、模型選擇和價格。
建構自訂代理：使用 AGENTS.md 和 SKILL.md 定義專屬代理。
掛鉤：強制執行安全防護機制，並在沙箱中執行副作用驗證。

代管代理程式中的環境

Python

JavaScript

Java

REST

environment 參數

Python

JavaScript

Java

REST

設定環境

Python

JavaScript

Java

REST

從來源掛接

Python

JavaScript

Java

REST

吊人胃口的情節片段

私人來源

Python

JavaScript

Java

REST

Python

JavaScript

Java

REST

預先安裝軟體

環境變數

Python

JavaScript

REST

網路設定

Python

JavaScript

Java

REST

憑證

Python

JavaScript

REST

Python

JavaScript

Java

REST

停用網路存取權

Python

JavaScript

Java

REST

重新整理憑證

Python

JavaScript

Java

REST

環境生命週期

Environments API

可列出環境

Python

JavaScript

Java

REST

取得環境

Python

JavaScript

Java

REST

可刪除環境

Python

JavaScript

Java

REST

管理環境中的檔案

列出目錄中的檔案

查詢參數

Python

JavaScript

`environment` 參數