Uso de la computadora

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Search for 'Gemini API' on Google.",
    tools=[{"type": "computer_use", "environment": "browser"}]
)

print(interaction)

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

const ai = new GoogleGenAI();

const interaction = await ai.interactions.create({
  model: 'gemini-3.8-flash',
  input: "Search for 'Gemini API' on Google.",
  tools: [{ type: "computer_use", environment: "browser" }]
});

console.log(interaction);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.ComputerUse;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.EnvironmentEnum;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model("gemini-3.8-flash")
        .input(InteractionsInput.of("Search for 'Gemini API' on Google."))
        .tools(
            Arrays.asList(
                ComputerUse.builder().environment(EnvironmentEnum.BROWSER).build()))
        .build();

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

System.out.println(interaction);

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput("Search for 'Gemini API' on Google."),
            Tools: []interactions.Tool{
                interactions.NewTool(interactions.ComputerUse{
                    Environment: interactions.EnvironmentEnumBrowser.ToPointer(),
                }),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(res.Interaction)
}

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model='gemini-3.8-flash',
    input="Find a flight from SF to Hawaii on Jun 30th, coming back on Jul 6th",
    tools=[
        {
            "type": "computer_use",
            "environment": "browser",
            "enable_prompt_injection_detection": True
        }
    ]
)

print(interaction)

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

const ai = new GoogleGenAI();

const interaction = await ai.interactions.create({
  model: 'gemini-3.8-flash',
  input: "Find a flight from SF to Hawaii on Jun 30th, coming back on Jul 6th",
  tools: [
    {
      type: "computer_use",
      environment: "browser",
      enable_prompt_injection_detection: true
    }
  ]
});

console.log(interaction);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.ComputerUse;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.EnvironmentEnum;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model("gemini-3.8-flash")
        .input(
            InteractionsInput.of(
                "Find a flight from SF to Hawaii on Jun 30th, coming back on Jul 6th"))
        .tools(
            Arrays.asList(
                ComputerUse.builder()
                    .environment(EnvironmentEnum.BROWSER)
                    .enablePromptInjectionDetection(true)
                    .build()))
        .build();

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

System.out.println(interaction);

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput("Find a flight from SF to Hawaii on Jun 30th, coming back on Jul 6th"),
            Tools: []interactions.Tool{
                interactions.NewTool(interactions.ComputerUse{
                    Environment:                    interactions.EnvironmentEnumBrowser.ToPointer(),
                    EnablePromptInjectionDetection: genai.Ptr(true),
                }),
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(res.Interaction)
}

curl -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Find me a flight from SF to Hawaii on Jun 30th, coming back on Jul 6th. Start by navigating directly to flights.google.com",
    "tools": [
      {
        "type": "computer_use",
        "environment": "browser",
        "enable_prompt_injection_detection": true
      }
    ]
  }'

from typing import Any, List, Tuple
import time

def denormalize_x(x: int, screen_width: int) -> int:
    """Convert normalized x coordinate (0-1000) to actual pixel coordinate."""
    return int(x / 1000 * screen_width)

def denormalize_y(y: int, screen_height: int) -> int:
    """Convert normalized y coordinate (0-1000) to actual pixel coordinate."""
    return int(y / 1000 * screen_height)

def execute_function_calls(interaction, page, screen_width, screen_height):
    results = []
    function_calls = [
        step for step in interaction.steps if step.type == "function_call"
    ]

    for function_call in function_calls:
        action_result = {}
        fname = function_call.name
        args = function_call.arguments
        print(f"  -> Executing: {fname} (Intent: {args.get('intent', 'N/A')})")

        try:
            if fname == "open_app":
                pass # Handled / already open
            elif fname in ("click", "double_click", "triple_click", "middle_click", "right_click", "move", "long_press"):
                actual_x = denormalize_x(args["x"], screen_width)
                actual_y = denormalize_y(args["y"], screen_height)

                if fname == "click":
                    page.mouse.click(actual_x, actual_y)
                elif fname == "double_click":
                    page.mouse.dblclick(actual_x, actual_y)
                elif fname == "right_click":
                    page.mouse.click(actual_x, actual_y, button="right")
                elif fname == "middle_click":
                    page.mouse.click(actual_x, actual_y, button="middle")
                elif fname == "move":
                    page.mouse.move(actual_x, actual_y)
            elif fname == "type":
                actual_x = denormalize_x(args["x"], screen_width) if "x" in args else None
                actual_y = denormalize_y(args["y"], screen_height) if "y" in args else None
                text = args["text"]
                press_enter = args.get("press_enter", False)

                if actual_x is not None and actual_y is not None:
                    page.mouse.click(actual_x, actual_y)
                # Clear field first
                page.keyboard.press("Meta+A")
                page.keyboard.press("Backspace")
                page.keyboard.type(text)
                if press_enter:
                    page.keyboard.press("Enter")
            elif fname == "navigate":
                page.goto(args["url"])
            elif fname == "go_back":
                page.go_back()
            elif fname == "go_forward":
                page.go_forward()
            elif fname == "wait":
                time.sleep(args.get("seconds", 1))
            else:
                print(f"Warning: Custom or unhandled function {fname}")

            page.wait_for_load_state(timeout=5000)
            time.sleep(1)

        except Exception as e:
            print(f"Error executing {fname}: {e}")
            action_result = {"error": str(e)}

        results.append((fname, function_call.id, action_result))

    return results

function denormalizeX(x, screenWidth) {
    // Convert normalized x coordinate (0-1000) to actual pixel coordinate.
    return Math.floor((x / 1000) * screenWidth);
}

function denormalizeY(y, screenHeight) {
    // Convert normalized y coordinate (0-1000) to actual pixel coordinate.
    return Math.floor((y / 1000) * screenHeight);
}

async function executeFunctionCalls(interaction, page, screenWidth, screenHeight) {
    const results = [];
    const functionCalls = interaction.steps.filter(step => step.type === "function_call");

    for (const functionCall of functionCalls) {
        const actionResult = {};
        const fname = functionCall.name;
        const args = functionCall.arguments;
        console.log(`  -> Executing: ${fname} (Intent: ${args.intent || 'N/A'})`);

        try {
            if (fname === "open_app") {
                // Handled / already open
            } else if (["click", "double_click", "triple_click", "middle_click", "right_click", "move", "long_press"].includes(fname)) {
                const actualX = denormalizeX(args.x, screenWidth);
                const actualY = denormalizeY(args.y, screenHeight);

                if (fname === "click") {
                    await page.mouse.click(actualX, actualY);
                } else if (fname === "double_click") {
                    await page.mouse.dblclick(actualX, actualY);
                } else if (fname === "right_click") {
                    await page.mouse.click(actualX, actualY, { button: "right" });
                } else if (fname === "middle_click") {
                    await page.mouse.click(actualX, actualY, { button: "middle" });
                } else if (fname === "move") {
                    await page.mouse.move(actualX, actualY);
                }
            } else if (fname === "type") {
                const actualX = args.x !== undefined ? denormalizeX(args.x, screenWidth) : null;
                const actualY = args.y !== undefined ? denormalizeY(args.y, screenHeight) : null;
                const text = args.text;
                const pressEnter = args.press_enter || false;

                if (actualX !== null && actualY !== null) {
                    await page.mouse.click(actualX, actualY);
                }
                // Clear field first
                await page.keyboard.press("Meta+A");
                await page.keyboard.press("Backspace");
                await page.keyboard.type(text);
                if (pressEnter) {
                    await page.keyboard.press("Enter");
                }
            } else if (fname === "navigate") {
                await page.goto(args.url);
            } else if (fname === "go_back") {
                await page.goBack();
            } else if (fname === "go_forward") {
                await page.goForward();
            } else if (fname === "wait") {
                await new Promise(resolve => setTimeout(resolve, (args.seconds || 1) * 1000));
            } else {
                console.log(`Warning: Custom or unhandled function ${fname}`);
            }

            await page.waitForLoadState('load', { timeout: 5000 }).catch(() => {});
            await new Promise(resolve => setTimeout(resolve, 1000));
        } catch (e) {
            console.log(`Error executing ${fname}: ${e}`);
            actionResult.error = e.message;
        }

        results.push([fname, functionCall.id, actionResult]);
    }

    return results;
}

import com.google.genai.gaos.models.interactions.FunctionCallStep;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.Step;
import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

class ActionExecutor {
  int denormalizeX(int x, int screenWidth) {
    return (int) (x / 1000.0 * screenWidth);
  }

  int denormalizeY(int y, int screenHeight) {
    return (int) (y / 1000.0 * screenHeight);
  }

  List<Map<String, Object>> executeFunctionCalls(
      Interaction interaction, int screenWidth, int screenHeight) {
    List<Map<String, Object>> results = new ArrayList<>();

    for (Step step : interaction.steps().orElse(Collections.emptyList())) {
      if (step instanceof FunctionCallStep) {
        FunctionCallStep functionCall = (FunctionCallStep) step;
        String fname = functionCall.name().orElse("");
        Map<String, Object> args = functionCall.arguments().orElse(Collections.emptyMap());
        Map<String, Object> actionResult = new HashMap<>();

        System.out.println(
            "  -> Executing: " + fname + " (Intent: " + args.getOrDefault("intent", "N/A") + ")");

        try {
          if (fname.equals("click")) {
            int actualX = denormalizeX(((Number) args.get("x")).intValue(), screenWidth);
            int actualY = denormalizeY(((Number) args.get("y")).intValue(), screenHeight);
            // Perform mouse click at (actualX, actualY) using your browser automation library
          } else if (fname.equals("type")) {
            String text = (String) args.get("text");
            // Type text into active element using your browser automation library
          } else if (fname.equals("navigate")) {
            String url = (String) args.get("url");
            // Navigate browser to url
          }
        } catch (Exception e) {
          actionResult.put("error", e.getMessage());
        }

        Map<String, Object> entry = new HashMap<>();
        entry.put("name", fname);
        entry.put("callId", functionCall.id().orElse(""));
        entry.put("result", actionResult);
        results.add(entry);
      }
    }
    return results;
  }
}

package main

import (
    "fmt"

    "google.golang.org/genai/interactions/models/interactions"
)

func denormalizeX(x, screenWidth int) int {
    return int(float64(x) / 1000.0 * float64(screenWidth))
}

func denormalizeY(y, screenHeight int) int {
    return int(float64(y) / 1000.0 * float64(screenHeight))
}

func executeFunctionCalls(interaction *interactions.Interaction, screenWidth, screenHeight int) []map[string]any {
    var results []map[string]any

    for _, step := range interaction.Steps {
        if functionCall := step.FunctionCallStep; functionCall != nil {
            fname := functionCall.Name
            args := functionCall.Arguments
            actionResult := map[string]any{}

            intent := args["intent"]
            if intent == nil {
                intent = "N/A"
            }
            fmt.Printf("  -> Executing: %s (Intent: %v)\n", fname, intent)

            switch fname {
            case "click":
                xVal, _ := args["x"].(float64)
                yVal, _ := args["y"].(float64)
                actualX := denormalizeX(int(xVal), screenWidth)
                actualY := denormalizeY(int(yVal), screenHeight)
                _ = actualX
                _ = actualY
                // Perform mouse click at (actualX, actualY) using your browser automation library
            case "type":
                text, _ := args["text"].(string)
                _ = text
                // Type text into active element using your browser automation library
            case "navigate":
                url, _ := args["url"].(string)
                _ = url
                // Navigate browser to url
            }

            results = append(results, map[string]any{
                "name":   fname,
                "callId": functionCall.ID,
                "result": actionResult,
            })
        }
    }
    return results
}

func main() {
    // Example helper usage with an Interaction response
}

import json
import base64

def get_function_responses(page, results):
    screenshot_bytes = page.screenshot(type="png")
    current_url = page.url
    function_responses = []
    for name, call_id, result in results:
        function_responses.append({
            "type": "function_result",
            "name": name,
            "call_id": call_id,
            "result": [
                {
                    "type": "text",
                    "text": json.dumps({"url": current_url, **result})
                },
                {
                    "type": "image",
                    "data": base64.b64encode(screenshot_bytes).decode("utf-8"),
                    "mime_type": "image/png"
                }
            ]
        })
    return function_responses

async function getFunctionResponses(page, results) {
    const screenshotBuffer = await page.screenshot({ type: 'png' });
    const screenshotBase64 = screenshotBuffer.toString('base64');
    const currentUrl = page.url();
    const functionResponses = [];

    for (const [name, callId, result] of results) {
        functionResponses.push({
            type: "function_result",
            name: name,
            call_id: callId,
            result: [
                {
                    type: "text",
                    text: JSON.stringify({ url: currentUrl, ...result })
                },
                {
                    type: "image",
                    data: screenshotBase64,
                    mime_type: "image/png"
                }
            ]
        });
    }
    return functionResponses;
}

import com.google.genai.gaos.models.interactions.FunctionResultStep;
import com.google.genai.gaos.models.interactions.FunctionResultStepResultUnion;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Base64;
import java.util.List;
import java.util.Map;

class StateCapturer {
  List<Step> getFunctionResponses(
      byte[] screenshotBytes, String currentUrl, List<Map<String, Object>> results) {
    List<Step> functionResponses = new ArrayList<>();
    String base64Screenshot = Base64.getEncoder().encodeToString(screenshotBytes);

    for (Map<String, Object> entry : results) {
      String name = (String) entry.get("name");
      String callId = (String) entry.get("callId");
      String jsonResult = String.format("{\"url\": \"%s\"}", currentUrl);

      FunctionResultStep responseStep =
          FunctionResultStep.builder()
              .name(name)
              .callId(callId)
              .result(
                  FunctionResultStepResultUnion.of(
                      Arrays.asList(
                          TextContent.builder().text(jsonResult).build(),
                          ImageContent.builder()
                              .data(base64Screenshot)
                              .mimeType(ImageContentMimeType.IMAGE_PNG)
                              .build())))
              .build();
      functionResponses.add(responseStep);
    }
    return functionResponses;
  }
}

package main

import (
    "encoding/base64"
    "fmt"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
)

func getFunctionResponses(screenshotBytes []byte, currentURL string, results []map[string]any) []interactions.Step {
    var functionResponses []interactions.Step
    base64Screenshot := base64.StdEncoding.EncodeToString(screenshotBytes)

    for _, entry := range results {
        name, _ := entry["name"].(string)
        callID, _ := entry["callId"].(string)
        jsonResult := fmt.Sprintf(`{"url": "%s"}`, currentURL)

        responseStep := interactions.NewStep(interactions.FunctionResultStep{
            Name:   genai.Ptr(name),
            CallID: callID,
            Result: interactions.NewFunctionResultStepResultUnion([]interactions.FunctionResultSubcontent{
                interactions.NewFunctionResultSubcontent(interactions.TextContent{
                    Text: jsonResult,
                }),
                interactions.NewFunctionResultSubcontent(interactions.ImageContent{
                    Data:     genai.Ptr(base64Screenshot),
                    MimeType: interactions.ImageContentMimeType("image/png").ToPointer(),
                }),
            }),
        })
        functionResponses = append(functionResponses, responseStep)
    }
    return functionResponses
}

func main() {
    // Example helper usage to build FunctionResultStep responses
}

import time
from typing import Any, List, Tuple
from playwright.sync_api import sync_playwright

from google import genai

client = genai.Client()

# Constants for screen dimensions
SCREEN_WIDTH = 1440
SCREEN_HEIGHT = 900

# Setup Playwright
print("Initializing browser...")
playwright = sync_playwright().start()
browser = playwright.chromium.launch(headless=False)
context = browser.new_context(viewport={"width": SCREEN_WIDTH, "height": SCREEN_HEIGHT})
page = context.new_page()

# Define helper functions. Copy/paste from steps 3 and 4
# def denormalize_x(...)
# def denormalize_y(...)
# def execute_function_calls(...)
# def get_function_responses(...)

try:
    # Go to initial page
    page.goto("https://ai.google.dev/gemini-api/docs")

    # Take initial screenshot
    initial_screenshot = page.screenshot(type="png")
    USER_PROMPT = "Go to ai.google.dev/gemini-api/docs and search for pricing."
    print(f"Goal: {USER_PROMPT}")

    # First interaction
    interaction = client.interactions.create(
        model='gemini-3.8-flash',
        input=[
            {"type": "text", "text": USER_PROMPT},
            {"type": "image", "data": base64.b64encode(initial_screenshot).decode("utf-8"), "mime_type": "image/png"}
        ],
        tools=[{
            "type": "computer_use",
            "environment": "browser",
            "enable_prompt_injection_detection": True
        }]
    )

    # Agent Loop
    turn_limit = 5
    for i in range(turn_limit):
        print(f"\n--- Turn {i+1} ---")

        has_function_calls = any(
            step.type == "function_call"
            for step in interaction.steps
        )
        if not has_function_calls:
            text_response = " ".join([
                content_block.text for step in interaction.steps if step.type == "model_output"
                for content_block in step.content if content_block.type == "text"
            ])
            print("Agent finished:", text_response)
            break

        print("Executing actions...")
        results = execute_function_calls(interaction, page, SCREEN_WIDTH, SCREEN_HEIGHT)

        print("Capturing state...")
        function_responses = get_function_responses(page, results)

        # Continue conversation with function responses
        interaction = client.interactions.create(
            model='gemini-3.8-flash',
            previous_interaction_id=interaction.id,
            input=function_responses,
            tools=[{
                "type": "computer_use",
                "environment": "browser",
                "enable_prompt_injection_detection": True
            }]
        )

finally:
    # Cleanup
    print("\nClosing browser...")
    browser.close()
    playwright.stop()

import { chromium } from 'playwright';
import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI();

// Constants for screen dimensions
const SCREEN_WIDTH = 1440;
const SCREEN_HEIGHT = 900;

console.log("Initializing browser...");
const browser = await chromium.launch({ headless: false });
const context = await browser.newContext({
    viewport: { width: SCREEN_WIDTH, height: SCREEN_HEIGHT }
});
const page = await context.newPage();

// Define helper functions. Copy/paste from steps 3 and 4:
// function denormalizeX(...)
// function denormalizeY(...)
// async function executeFunctionCalls(...)
// async function getFunctionResponses(...)

try {
    // Go to initial page
    await page.goto("https://ai.google.dev/gemini-api/docs");

    // Take initial screenshot
    const initialScreenshotBuffer = await page.screenshot({ type: 'png' });
    const initialScreenshotBase64 = initialScreenshotBuffer.toString('base64');
    const USER_PROMPT = "Go to ai.google.dev/gemini-api/docs and search for pricing.";
    console.log(`Goal: ${USER_PROMPT}`);

    // First interaction
    let interaction = await ai.interactions.create({
        model: 'gemini-3.8-flash',
        input: [
            { type: 'text', text: USER_PROMPT },
            { type: 'image', data: initialScreenshotBase64, mime_type: 'image/png' }
        ],
        tools: [{
            type: 'computer_use',
            environment: 'browser',
            enable_prompt_injection_detection: true
        }]
    });

    // Agent Loop
    const turnLimit = 5;
    for (let i = 0; i < turnLimit; i++) {
        console.log(`\n--- Turn ${i + 1} ---`);

        const hasFunctionCalls = interaction.steps.some(step => step.type === "function_call");
        if (!hasFunctionCalls) {
            const textResponses = [];
            for (const step of interaction.steps) {
                if (step.type === "model_output") {
                    for (const contentBlock of step.content || []) {
                        if (contentBlock.type === "text") {
                            textResponses.push(contentBlock.text);
                        }
                    }
                }
            }
            console.log("Agent finished:", textResponses.join(" "));
            break;
        }

        console.log("Executing actions...");
        const results = await executeFunctionCalls(interaction, page, SCREEN_WIDTH, SCREEN_HEIGHT);

        console.log("Capturing state...");
        const functionResponses = await getFunctionResponses(page, results);

        // Continue conversation with function responses
        interaction = await ai.interactions.create({
            model: 'gemini-3.8-flash',
            previous_interaction_id: interaction.id,
            input: functionResponses,
            tools: [{
                type: 'computer_use',
                environment: 'browser',
                enable_prompt_injection_detection: true
            }]
        });
    }
} finally {
    // Cleanup
    console.log("\nClosing browser...");
    await browser.close();
}

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.ComputerUse;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.EnvironmentEnum;
import com.google.genai.gaos.models.interactions.FunctionCallStep;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Base64;
import java.util.Collections;
import java.util.List;

Client client = new Client();

// Constants for screen dimensions
int screenWidth = 1440;
int screenHeight = 900;

// Capture initial screenshot from browser driver (e.g. Playwright)
byte[] initialScreenshot = new byte[0];
String base64Screenshot = Base64.getEncoder().encodeToString(initialScreenshot);
String userPrompt = "Go to ai.google.dev/gemini-api/docs and search for pricing.";
System.out.println("Goal: " + userPrompt);

ComputerUse computerUseTool =
    ComputerUse.builder()
        .environment(EnvironmentEnum.BROWSER)
        .enablePromptInjectionDetection(true)
        .build();

CreateModelInteraction initialParams =
    CreateModelInteraction.builder()
        .model("gemini-3.8-flash")
        .input(
            InteractionsInput.ofContent(
                Arrays.asList(
                    TextContent.builder().text(userPrompt).build(),
                    ImageContent.builder()
                        .data(base64Screenshot)
                        .mimeType(ImageContentMimeType.IMAGE_PNG)
                        .build())))
        .tools(Arrays.asList(computerUseTool))
        .build();

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

int turnLimit = 5;
for (int i = 0; i < turnLimit; i++) {
  System.out.println("\n--- Turn " + (i + 1) + " ---");

  boolean hasFunctionCalls =
      interaction.steps().orElse(Collections.emptyList()).stream()
          .anyMatch(step -> step instanceof FunctionCallStep);

  if (!hasFunctionCalls) {
    StringBuilder textResponse = new StringBuilder();
    for (Step step : interaction.steps().orElse(Collections.emptyList())) {
      if (step instanceof ModelOutputStep) {
        for (Content contentBlock :
            ((ModelOutputStep) step).content().orElse(Collections.emptyList())) {
          if (contentBlock instanceof TextContent) {
            textResponse.append(((TextContent) contentBlock).text().orElse("")).append(" ");
          }
        }
      }
    }
    System.out.println("Agent finished: " + textResponse.toString().trim());
    break;
  }

  System.out.println("Executing actions and capturing state...");
  // Execute function calls against browser driver and capture List<Step> functionResponses
  List<Step> functionResponses = new ArrayList<>();

  CreateModelInteraction nextParams =
      CreateModelInteraction.builder()
          .model("gemini-3.8-flash")
          .previousInteractionId(interaction.id().get())
          .input(InteractionsInput.ofStep(functionResponses))
          .tools(Arrays.asList(computerUseTool))
          .build();

  interaction =
      client.interactions.create(CreateInteractionRequestBody.of(nextParams)).interaction().get();
}

package main

import (
    "context"
    "encoding/base64"
    "fmt"
    "log"
    "strings"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    // Constants for screen dimensions
    screenWidth := 1440
    screenHeight := 900
    _ = screenWidth
    _ = screenHeight

    // Capture initial screenshot from browser driver (e.g. Playwright)
    initialScreenshot := []byte{}
    base64Screenshot := base64.StdEncoding.EncodeToString(initialScreenshot)
    userPrompt := "Go to ai.google.dev/gemini-api/docs and search for pricing."
    fmt.Println("Goal:", userPrompt)

    computerUseTool := interactions.NewTool(interactions.ComputerUse{
        Environment:                    interactions.EnvironmentEnumBrowser.ToPointer(),
        EnablePromptInjectionDetection: genai.Ptr(true),
    })

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput([]interactions.Content{
                interactions.NewContent(interactions.TextContent{Text: userPrompt}),
                interactions.NewContent(interactions.ImageContent{
                    Data:     genai.Ptr(base64Screenshot),
                    MimeType: interactions.ImageContentMimeType("image/png").ToPointer(),
                }),
            }),
            Tools: []interactions.Tool{computerUseTool},
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    interaction := res.Interaction

    turnLimit := 5
    for i := 0; i < turnLimit; i++ {
        fmt.Printf("\n--- Turn %d ---\n", i+1)

        hasFunctionCalls := false
        for _, step := range interaction.Steps {
            if step.FunctionCallStep != nil {
                hasFunctionCalls = true
                break
            }
        }

        if !hasFunctionCalls {
            var parts []string
            for _, step := range interaction.Steps {
                if outStep := step.ModelOutputStep; outStep != nil {
                    for _, contentBlock := range outStep.Content {
                        if textContent := contentBlock.TextContent; textContent != nil {
                            parts = append(parts, textContent.GetText())
                        }
                    }
                }
            }
            fmt.Println("Agent finished:", strings.TrimSpace(strings.Join(parts, " ")))
            break
        }

        fmt.Println("Executing actions and capturing state...")
        // Execute function calls against browser driver and capture []interactions.Step functionResponses
        var functionResponses []interactions.Step

        nextRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
            Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
                Model:                 interactions.Model("gemini-3.8-flash"),
                PreviousInteractionID: interaction.ID,
                Input:                 interactions.NewInteractionsInput(functionResponses),
                Tools:                 []interactions.Tool{computerUseTool},
            }),
        })
        if err != nil {
            log.Fatal(err)
        }
        interaction = nextRes.Interaction
    }
}

from google import genai

client = genai.Client()

yield_to_user_tool = {
    "type": "function",
    "name": "yield_to_user",
    "description": "Yields control back to the user for assistance or verification when an automated action is unsafe or ambiguous.",
    "parameters": {
        "type": "object",
        "properties": {
            "reason": {
                "type": "string",
                "description": "The reason why the agent is yielding control to the human."
            }
        },
        "required": ["reason"]
    }
}

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Click the submit button. If you need a second factor authentication code, ask me.",
    tools=[
        {
            "type": "computer_use",
            "environment": "mobile",
            "excluded_predefined_functions": ["click"]
        },
        yield_to_user_tool
    ]
)

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

const ai = new GoogleGenAI();

const yieldToUserTool = {
    type: "function",
    name: "yield_to_user",
    description: "Yields control back to the user for assistance or verification when an automated action is unsafe or ambiguous.",
    parameters: {
        type: "object",
        properties: {
            reason: {
                type: "string",
                description: "The reason why the agent is yielding control to the human."
            }
        },
        required: ["reason"]
    }
};

const interaction = await ai.interactions.create({
    model: "gemini-3.8-flash",
    input: "Click the submit button. If you need a second factor authentication code, ask me.",
    tools: [
        {
            type: "computer_use",
            environment: "mobile",
            excluded_predefined_functions: ["click"]
        },
        yieldToUserTool
    ]
});

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.ComputerUse;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.EnvironmentEnum;
import com.google.genai.gaos.models.interactions.Function;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

Client client = new Client();

Map<String, Object> reasonProp = new HashMap<>();
reasonProp.put("type", "string");
reasonProp.put("description", "The reason why the agent is yielding control to the human.");

Map<String, Object> properties = new HashMap<>();
properties.put("reason", reasonProp);

Map<String, Object> parameters = new HashMap<>();
parameters.put("type", "object");
parameters.put("properties", properties);
parameters.put("required", Collections.singletonList("reason"));

Function yieldToUserTool =
    Function.builder()
        .name("yield_to_user")
        .description(
            "Yields control back to the user for assistance or verification when an automated action is unsafe or ambiguous.")
        .parameters(parameters)
        .build();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model("gemini-3.8-flash")
        .input(
            InteractionsInput.of(
                "Click the submit button. If you need a second factor authentication code, ask me."))
        .tools(
            Arrays.asList(
                ComputerUse.builder()
                    .environment(EnvironmentEnum.MOBILE)
                    .excludedPredefinedFunctions(Arrays.asList("click"))
                    .build(),
                yieldToUserTool))
        .build();

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

package main

import (
    "context"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    yieldToUserTool := interactions.NewTool(interactions.Function{
        Name:        genai.Ptr("yield_to_user"),
        Description: genai.Ptr("Yields control back to the user for assistance or verification when an automated action is unsafe or ambiguous."),
        Parameters: map[string]any{
            "type": "object",
            "properties": map[string]any{
                "reason": map[string]any{
                    "type":        "string",
                    "description": "The reason why the agent is yielding control to the human.",
                },
            },
            "required": []string{"reason"},
        },
    })

    _, err = client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateModelInteraction{
            Model: interactions.Model("gemini-3.8-flash"),
            Input: interactions.NewInteractionsInput("Click the submit button. If you need a second factor authentication code, ask me."),
            Tools: []interactions.Tool{
                interactions.NewTool(interactions.ComputerUse{
                    Environment:                 interactions.EnvironmentEnumMobile.ToPointer(),
                    ExcludedPredefinedFunctions: []string{"click"},
                }),
                yieldToUserTool,
            },
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
}