Expanding Managed Agents in Gemini API: background tasks, remote MCP and more

1npm install @google/genai

1import { GoogleGenAI } from "@google/genai";
2
3const client = new GoogleGenAI({});
4
5// 1. Start a long-running analysis in the background
6const interaction = await client.interactions.create({
7  agent: "antigravity-preview-05-2026",
8  input: "Clone https://github.com/googleapis/js-genai, find all TODO comments in the source code, and categorize them by module and priority in a markdown report.",
9  environment: "remote",
10  background: true,
11});
12
13console.log(`Background task started. Interaction ID: ${interaction.id}`);
14
15// 2. Poll asynchronously without blocking an open HTTP socket
16let result = interaction;
17while (result.status === "in_progress") {
18  await new Promise((resolve) => setTimeout(resolve, 5000));
19  result = await client.interactions.get(interaction.id);
20}
21
22if (result.status === "completed") {
23  console.log("Task Completed:\n", result.output_text);
24} else {
25  console.error(`Task ended with status: ${result.status}`);
26}

1import { GoogleGenAI } from "@google/genai";
2
3const client = new GoogleGenAI({});
4
5const interaction = await client.interactions.create({
6  agent: "antigravity-preview-05-2026",
7  input: "Check our internal observability server for recent latency spikes in the auth service and correlate them with git commits.",
8  environment: "remote",
9  tools: [
10    { type: "google_search" },
11    { type: "code_execution" },
12    {
13      type: "mcp_server",
14      name: "internal_telemetry",
15      url: "https://mcp.internal.example.com/mcp",
16    },
17  ],
18});
19
20console.log(interaction.output_text);

1import { GoogleGenAI } from "@google/genai";
2
3const client = new GoogleGenAI({});
4
5// 1. Define a custom domain function
6const getWeatherTool = {
7  type: "function",
8  name: "get_weather",
9  description: "Gets the current weather for a given location.",
10  parameters: {
11    type: "object",
12    properties: {
13      location: {
14        type: "string",
15        description: "The city and country, e.g. San Francisco, USA",
16      },
17    },
18    required: ["location"],
19  },
20};
21
22// 2. Invoke the agent with both built-in code execution and custom functions
23const interaction = await client.interactions.create({
24  agent: "antigravity-preview-05-2026",
25  input: "Check the weather in Tokyo, write a Python script to convert the temperature to Fahrenheit, and save the result to weather.txt.",
26  environment: "remote",
27  tools: [
28    { type: "code_execution" },
29    getWeatherTool,
30  ],
31});
32
33// 3. Handle custom function execution cleanly
34if (interaction.status === "requires_action") {
35  // Filesystem and sandbox tools execute automatically and produce a matching function_result step.
36  // We filter for pending domain calls that require client-side execution.
37  const executedCalls = new Set(
38    interaction.steps
39      .filter((s) => s.type === "function_result")
40      .map((s) => s.call_id)
41  );
42
43  const pendingCalls = interaction.steps.filter(
44    (s) => s.type === "function_call" && !executedCalls.has(s.id)
45  );
46
47  for (const call of pendingCalls) {
48    console.log(`Executing client tool: ${call.name} (ID: ${call.id})`);
49    // Execute your local API/database query and send the function_result back in turn 2
50  }
51}

1import { GoogleGenAI } from "@google/genai";
2const client = new GoogleGenAI({});
3
4// 1. First interaction: use an initial token
5const first = await client.interactions.create({
6  agent: "antigravity-preview-05-2026",
7  input: "List the files in gs://my-bucket/reports/ using the GCS JSON API.",
8  environment: {
9    type: "remote",
10    network: {
11      allowlist: [
12        {
13          domain: "storage.googleapis.com",
14          transform: {
15            Authorization: "Bearer INITIAL_TOKEN",
16          },
17        },
18      ],
19    },
20  },
21});
22
23// 2. Later: refresh the token on the same environment
24const result = await client.interactions.create({
25  agent: "antigravity-preview-05-2026",
26  input: "Now download the file reports/q1.csv from the same bucket.",
27  environment: {
28    type: "remote",
29    environment_id: first.environment_id,
30    network: {
31      allowlist: [
32        {
33          domain: "storage.googleapis.com",
34          transform: {
35            Authorization: "Bearer REFRESHED_TOKEN",
36          },
37        },
38      ],
39    },
40  },
41});
42console.log(result.output_text);