Computer Use

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-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-3.5-flash',
  input: "Search for 'Gemini API' on Google.",
  tools: [{ type: "computer_use", environment: "browser" }]
});

console.log(interaction);

{
  "steps": [
    {
      "type": "function_call",
      "name": "click",
      "arguments": {
        "x": 450,
        "y": 120,
        "intent": "Click the search box to type the destination."
      }
    }
  ]
}

{
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "I will type the search query into the search bar."
        }
      ]
    },
    {
      "type": "function_call",
      "name": "type_text_at",
      "arguments": {
        "x": 371,
        "y": 470,
        "text": "highly rated smart fridges",
        "press_enter": 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 in ("open_web_browser", "open_app"):
                pass # Handled / already open
            elif fname in ("click", "click_at", "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 in ("click", "click_at"):
                    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 in ("type", "type_text_at"):
                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_web_browser" || fname === "open_app") {
                // Handled / already open
            } else if (["click", "click_at", "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" || fname === "click_at") {
                    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" || fname === "type_text_at") {
                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 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 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-3.5-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-3.5-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-3.5-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-3.5-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();
}

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-3.5-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-3.5-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
    ]
});

from google import genai

client = genai.Client()

# Define custom tools here
custom_functions = [...]  # Describe parameters as function declarations

excluded_functions = [
    "open_web_browser",
    "wait_5_seconds",
    "go_back",
    "go_forward",
    "search",
    "navigate",
    "hover_at",
    "scroll_document",
    "key_combination",
    "drag_and_drop",
]

interaction = client.interactions.create(
    model='gemini-2.5-computer-use-preview-10-2025',
    input="Open Chrome, then long-press at 200,400.",
    tools=[
        {
            "type": "computer_use",
            "environment": "browser",
            "excluded_predefined_functions": excluded_functions
        },
        *custom_functions
    ]
)

print(interaction)

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

const ai = new GoogleGenAI();

// Define custom tools here
const customFunctions = [...]; // Describe parameters as function declarations

const excludedFunctions = [
    "open_web_browser",
    "wait_5_seconds",
    "go_back",
    "go_forward",
    "search",
    "navigate",
    "hover_at",
    "scroll_document",
    "key_combination",
    "drag_and_drop",
];

const interaction = await ai.interactions.create({
    model: 'gemini-2.5-computer-use-preview-10-2025',
    input: "Open Chrome, then long-press at 200,400.",
    tools: [
        {
            type: "computer_use",
            environment: "browser",
            excluded_predefined_functions: excludedFunctions
        },
        ...customFunctions
    ]
});

console.log(interaction);

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Clean up the local folder by archiving old logs.",
    tools=[
        {
            "type": "computer_use",
            "environment": "desktop",
            "disabled_safety_policies": [
                "data_modification"
            ]
        }
    ]
)

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

const ai = new GoogleGenAI();

const interaction = await ai.interactions.create({
    model: "gemini-3.5-flash",
    input: "Clean up the local folder by archiving old logs.",
    tools: [
        {
            type: "computer_use",
            environment: "desktop",
            disabled_safety_policies: [
                "data_modification"
            ]
        }
    ]
});

def get_safety_confirmation(safety_decision):
    # Prompt user for confirmation
    print(f"Safety confirmation required: {safety_decision.get('explanation', '')}")
    return "CONTINUE" # Or TERMINATE

# Inside execute_function_calls, check for safety_decision:
if 'safety_decision' in function_call.arguments:
    decision = get_safety_confirmation(function_call.arguments['safety_decision'])
    if decision == "TERMINATE":
        break
    # Include safety_acknowledgement inside the action result
    action_result["safety_acknowledgement"] = True