Uso del computer

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.6-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-3.6-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