Utiliza la herramienta de uso de la aplicación para agentes (versión preliminar)

Captura de pantalla de la inicialización de la ejecución de la herramienta para el uso del ordenador

Los siguientes extractos muestran cómo crear una versión del agente con la herramienta de uso del equipo, enviar una solicitud inicial con una captura de pantalla y realizar varias iteraciones para completar una tarea. Los fragmentos de Prompt Agents dependen del ejemplo de Python mantenido y del archivo auxiliar enlazado anteriormente. Seleccione Prompt Agents para usar Azure AI Projects SDK y crear un agente de indicaciones del lado del servidor, o Hosted Agents para usar el Agent Framework FoundryChatClient y crear un agente efímero dentro del proceso.

Agentes rápidos

from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import PromptAgentDefinition, ComputerUsePreviewTool

# Import shared helper functions
from computer_use_util import (
    SearchState,
    load_screenshot_assets,
    handle_computer_action_and_take_screenshot,
    print_final_output,
)

"""Main function to demonstrate Computer Use Agent functionality."""
# Initialize state machine
current_state = SearchState.INITIAL

# Load screenshot assets
try:
    screenshots = load_screenshot_assets()
    print("Successfully loaded screenshot assets")
except FileNotFoundError:
    print("Failed to load required screenshot assets. Use the maintained SDK sample on GitHub to get the helper file and images.")
    exit(1)

Creación de una versión del agente con la herramienta

# Format: "https://resource_name.ai.azure.com/api/projects/project_name"
PROJECT_ENDPOINT = "your_project_endpoint"

project = AIProjectClient(
    endpoint=PROJECT_ENDPOINT,
    credential=DefaultAzureCredential(),
)

computer_use_tool = ComputerUsePreviewTool(display_width=1026, display_height=769, environment="windows")

agent = project.agents.create_version(
    agent_name="ComputerUseAgent",
    definition=PromptAgentDefinition(
        model="computer-use-preview",
        instructions="""
        You are a computer automation assistant. 

        Be direct and efficient. When you reach the search results page, read and describe the actual search result titles and descriptions you can see.
        """,
        tools=[computer_use_tool],
    ),
    description="Computer automation agent with screen interaction capabilities.",
)
print(f"Agent created (id: {agent.id}, name: {agent.name})")

Iteración de la herramienta para procesar la captura de pantalla y realizar el paso siguiente

openai = project.get_openai_client()

# Initial request with screenshot - start with Bing search page
response = openai.responses.create(
    input=[
        {
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "I need you to help me search for 'OpenAI news'. Please type 'OpenAI news' and submit the search. Once you see search results, the task is complete.",
                },
                {
                    "type": "input_image",
                    "image_url": screenshots["browser_search"]["url"],
                    "detail": "high",
                },  # Start with Bing search page
            ],
        }
    ],
    extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
    truncation="auto",
)

print(f"Initial response received (ID: {response.id})")

Realizar varias iteraciones

Asegúrese de revisar cada iteración y acción. En el ejemplo de código siguiente se muestra una solicitud de API básica. Después de enviar la solicitud de API inicial, realice un bucle donde el código de la aplicación lleve a cabo la acción especificada. Envíe una captura de pantalla con cada turno para que el modelo pueda evaluar el estado actualizado del entorno. El ejemplo incluye un número máximo de iteraciones para evitar bucles infinitos, pero puede ajustarlo según sea necesario.

max_iterations = 10  # Allow enough iterations for completion
iteration = 0

while True:
    if iteration >= max_iterations:
        print(f"\nReached maximum iterations ({max_iterations}). Stopping.")
        break

    iteration += 1
    print(f"\n--- Iteration {iteration} ---")

    # Check for computer calls in the response
    computer_calls = [item for item in response.output if item.type == "computer_call"]

    if not computer_calls:
        print_final_output(response)
        break

    # Process the first computer call
    computer_call = computer_calls[0]
    action = computer_call.action
    call_id = computer_call.call_id

    # Never execute an action with pending safety checks without user approval.
    safety_checks = computer_call.pending_safety_checks or []
    if safety_checks:
      for check in safety_checks:
        print(f"Safety check: {check.code}: {check.message}")
      if input("Approve this action? Type yes to continue: ").lower() != "yes":
        print("Action rejected by the user.")
        break

    # Handle the action and get the screenshot info
    screenshot_info, current_state = handle_computer_action_and_take_screenshot(action, current_state, screenshots)

    # Regular response with just the screenshot
    response = openai.responses.create(
        previous_response_id=response.id,
        input=[
            {
                "call_id": call_id,
                "type": "computer_call_output",
                "acknowledged_safety_checks": safety_checks,
                "output": {
                    "type": "computer_screenshot",
                    "image_url": screenshot_info["url"],
                },
            }
        ],
        extra_body={"agent_reference": {"name": agent.name, "type": "agent_reference"}},
        truncation="auto",
    )

    print(f"Iteration {iteration}: response received (ID: {response.id})")

Limpieza

project.agents.delete_version(agent_name=agent.name, agent_version=agent.version)
print("Agent deleted")

Salida esperada

En el ejemplo siguiente se muestra la salida esperada al ejecutar el ejemplo de código anterior:

Successfully loaded screenshot assets
Agent created (id: ..., name: ComputerUseAgent, version: 1)
Starting computer automation session (initial screenshot: cua_browser_search.png)...
Initial response received (ID: ...)
--- Iteration 1 ---
Processing computer call (ID: ...)
  Typing text "OpenAI news" - Simulating keyboard input
  -> Action processed: type
Sending action result back to agent (using cua_search_typed.png)...
Follow-up response received (ID: ...)
--- Iteration 2 ---
Processing computer call (ID: ...)
    Click at (512, 384) - Simulating click on UI element
    -> Assuming click on Search button when search field was populated, displaying results.
    -> Action processed: click
Sending action result back to agent (using cua_search_results.png)...
Follow-up response received (ID: ...)
OpenAI news - Latest Updates
Agent deleted

Agentes hospedados

Este ejemplo usa FoundryChatClient del Microsoft Agent Framework e invoca get_computer_use_tool() para adjuntar la herramienta de vista previa para el uso del equipo. Instale el paquete con pip install agent-framework-foundry aiohttp, establezca FOUNDRY_PROJECT_ENDPOINT (apunte FOUNDRY_MODEL a una implementación computer-use-preview) e inicie sesión con az login. El bucle captura de pantalla es específico de la aplicación; consulte el archivo auxiliar de ejemplo ascendente al que se hace referencia a continuación.

import asyncio

from agent_framework import Agent
from agent_framework.foundry import FoundryChatClient
from azure.identity import AzureCliCredential


async def main() -> None:
    agent = Agent(
        client=FoundryChatClient(credential=AzureCliCredential()),
        instructions=(
            "You are a computer automation assistant. Be direct and efficient. "
            "When you reach the search results page, describe the actual result titles you can see."
        ),
        tools=[
            FoundryChatClient.get_computer_use_tool(
                environment="windows",
                display_width=1026,
                display_height=769,
            )
        ],
    )

    # Replace this with your screenshot capture + action handler loop.
    # See the upstream samples folder for a reference implementation.
    result = await agent.run(
        "Help me search for 'OpenAI news'. Type the query and submit the search."
    )
    print(f"Agent: {result.text}")


if __name__ == "__main__":
    asyncio.run(main())

Salida esperada

El agente emite acciones de uso del equipo (clics, pulsaciones de teclas, capturas de pantalla) hasta que se completa la tarea y, a continuación, describe la página a la que alcanzó:

Agent: I searched for "OpenAI news" in the address bar. The top results include articles from OpenAI's blog, TechCrunch, and The Verge ...

Para obtener una implementación completa de bucle de captura de pantalla, consulte los ejemplos del proveedor Foundry.

Ejemplo para el uso de un agente con la herramienta Uso de computadoras

En el ejemplo de código de C# siguiente se muestra cómo crear un agente con la herramienta de uso del equipo, enviar una solicitud inicial con una captura de pantalla y realizar varias iteraciones para completar una tarea. Seleccione Prompt Agents para usar el SDK de proyectos de IA de Azure para crear un agente de mensajes del lado servidor o Agentes hospedados para usar el marco del agente de Microsoft para crear un agente efímero en proceso.

Agentes rápidos

Para permitir que el agente use la herramienta de uso del equipo, use ResponseTool.CreateComputerTool() al configurar las herramientas del agente. En este ejemplo se usa código sincrónico. Para el uso asincrónico, consulte el ejemplo sample code en el SDK de Azure para .NET repositorio en GitHub.

using System;
using System.Runtime.CompilerServices;
using Azure.AI.Projects;
using Azure.AI.Extensions.OpenAI;
using Azure.Identity;

class ComputerUseDemo
{
    // Format: "https://resource_name.ai.azure.com/api/projects/project_name"
    private const string ProjectEndpoint = "your_project_endpoint";

    // Read image files using `ReadImageFile` method.
    private static BinaryData ReadImageFile(string name, [CallerFilePath] string pth = "")
    {
        var dirName = Path.GetDirectoryName(pth) ?? "";
        return new BinaryData(File.ReadAllBytes(Path.Combine(dirName, name)));
    }

    // Create a helper method to parse the ComputerTool outputs and to respond
    // to Agents queries with new screenshots. Note that throughout
    // this sample the media type for image is set. Agents support `image/jpeg`,
    // `image/png`, `image/gif` and `image/webp` media types.
    private static string ProcessComputerUseCall(ComputerCallResponseItem item, string oldScreenshot)
    {
        string currentScreenshot = "browser_search";
        switch (item.Action.Kind)
        {
            case ComputerCallActionKind.Type:
                Console.WriteLine($"  Typing text \"{item.Action.TypeText}\" - Simulating keyboard input");
                currentScreenshot = "search_typed";
                break;
            case ComputerCallActionKind.KeyPress:
                HashSet<string> codes = new(item.Action.KeyPressKeyCodes);
                if (codes.Contains("Return") || codes.Contains("ENTER"))
                {
                    // If we have typed the value to the search field, go to search results.
                    if (string.Equals(oldScreenshot, "search_typed"))
                    {
                        Console.WriteLine("  -> Detected ENTER key press, when search field was populated, displaying results.");
                        currentScreenshot = "search_results";
                    }
                    else
                    {
                        Console.WriteLine("  -> Detected ENTER key press, on results or unpopulated search, do nothing.");
                        currentScreenshot = oldScreenshot;
                    }
                }
                else
                {
                    Console.WriteLine($"  Key press: {item.Action.KeyPressKeyCodes.Aggregate("", (agg, next) => agg + "+" + next)} - Simulating key combination");
                }
                break;
            case ComputerCallActionKind.Click:
                Console.WriteLine($"  Click at ({item.Action.ClickCoordinates.Value.X}, {item.Action.ClickCoordinates.Value.Y}) - Simulating click on UI element");
                if (string.Equals(oldScreenshot, "search_typed"))
                {
                    Console.WriteLine("  -> Assuming click on Search button when search field was populated, displaying results.");
                    currentScreenshot = "search_results";
                }
                else
                {
                    Console.WriteLine("  -> Assuming click on Search on results or when search was not populated, do nothing.");
                    currentScreenshot = oldScreenshot;
                }
                break;
            case ComputerCallActionKind.Drag:
                string pathStr = item.Action.DragPath.ToArray().Select(p => $"{p.X}, {p.Y}").Aggregate("", (agg, next) => $"{agg} -> {next}");
                Console.WriteLine($"  Drag path: {pathStr} - Simulating drag operation");
                break;
            case ComputerCallActionKind.Scroll:
                Console.WriteLine($"  Scroll at ({item.Action.ScrollCoordinates.Value.X}, {item.Action.ScrollCoordinates.Value.Y}) - Simulating scroll action");
                break;
            case ComputerCallActionKind.Screenshot:
                Console.WriteLine("  Taking screenshot - Capturing current screen state");
                break;
            default:
                break;
        }
        Console.WriteLine($"  -> Action processed: {item.Action.Kind}");

        return currentScreenshot;
    }

    public static void Main()
    {
        // Create project client
        AIProjectClient projectClient = new(endpoint: new Uri(ProjectEndpoint), tokenProvider: new DefaultAzureCredential());

        // Read in three example screenshots and place them into a dictionary.
        Dictionary<string, BinaryData> screenshots = new() {
            { "browser_search", ReadImageFile("Assets/cua_browser_search.png")},
            { "search_typed", ReadImageFile("Assets/cua_search_typed.png")},
            { "search_results", ReadImageFile("Assets/cua_search_results.png")},
        };

        // Create a PromptAgentDefinition with ComputerTool.
        DeclarativeAgentDefinition agentDefinition = new(model: "computer-use-preview")
        {
            Instructions = "You are a computer automation assistant.\n\n" +
                            "Be direct and efficient. When you reach the search results page, read and describe the actual search result titles and descriptions you can see.",
            Tools = {
                ResponseTool.CreateComputerTool(
                    environment: new ComputerToolEnvironment("windows"),
                    displayWidth: 1026,
                    displayHeight: 769
                ),
            }
        };
        AgentVersion agentVersion = projectClient.AgentAdministrationClient.CreateAgentVersion(
            agentName: "myAgent",
            options: new(agentDefinition)
        );
        // Create an `ResponseResult` using `ResponseItem`, containing two `ResponseContentPart`:
        // one with the image and another with the text. In the loop, request Agent
        // while it is continuing to browse web. Finally, print the tool output message.
        ProjectResponsesClient responseClient = projectClient.ProjectOpenAIClient.GetProjectResponsesClientForAgent(agentVersion.Name);
        CreateResponseOptions responseOptions = new()
        {
            TruncationMode = ResponseTruncationMode.Auto,
            InputItems =
            {
                ResponseItem.CreateUserMessageItem(
                [
                    ResponseContentPart.CreateInputTextPart("I need you to help me search for 'OpenAI news'. Please type 'OpenAI news' and submit the search. Once you see search results, the task is complete."),
                    ResponseContentPart.CreateInputImagePart(imageBytes: screenshots["browser_search"], imageBytesMediaType: "image/png", imageDetailLevel: ResponseImageDetailLevel.High)
                ]),
            },
        };
        bool computerUseCalled = false;
        string currentScreenshot = "browser_search";
        int limitIteration = 10;
        ResponseResult response;
        do
        {
            response = responseClient.CreateResponse(responseOptions);
            computerUseCalled = false;
            responseOptions.InputItems.Clear();
            responseOptions.PreviousResponseId = response.Id;
            foreach (ResponseItem responseItem in response.OutputItems)
            {
                responseOptions.InputItems.Add(responseItem);
                if (responseItem is ComputerCallResponseItem computerCall)
                {
                  if (computerCall.PendingSafetyChecks.Count > 0)
                  {
                    throw new InvalidOperationException(
                      "Pause execution and obtain end-user approval before acknowledging safety checks."
                    );
                  }
                    currentScreenshot = ProcessComputerUseCall(computerCall, currentScreenshot);
                    responseOptions.InputItems.Add(ResponseItem.CreateComputerCallOutputItem(callId: computerCall.CallId, output: ComputerCallOutput.CreateScreenshotOutput(screenshotImageBytes: screenshots[currentScreenshot], screenshotImageBytesMediaType: "image/png")));
                    computerUseCalled = true;
                }
            }
            limitIteration--;
        } while (computerUseCalled && limitIteration > 0);
        Console.WriteLine(response.GetOutputText());

        // Clean up resources by deleting Agent.
        projectClient.AgentAdministrationClient.DeleteAgentVersion(agentName: agentVersion.Name, agentVersion: agentVersion.Version);
    }
}

Salida esperada

En el ejemplo siguiente se muestra la salida esperada al ejecutar el ejemplo de código anterior:

Agent created (id: ..., name: myAgent, version: 1)
Starting computer automation session (initial screenshot: cua_browser_search.png)...
Initial response received (ID: ...)
--- Iteration 1 ---
Processing computer call (ID: ...)
  Typing text "OpenAI news" - Simulating keyboard input
  -> Action processed: Type
Sending action result back to agent (using cua_search_typed.png)...
Follow-up response received (ID: ...)
--- Iteration 2 ---
Processing computer call (ID: ...)
  Click at (512, 384) - Simulating click on UI element
  -> Assuming click on Search button when search field was populated, displaying results.
  -> Action processed: Click
Sending action result back to agent (using cua_search_results.png)...
Follow-up response received (ID: ...)
OpenAI news - Latest Updates
Agent deleted

Agentes hospedados

Este ejemplo utiliza Microsoft Agent Framework y llama a AsAIAgent(...) en AIProjectClient junto con FoundryAITool.CreateComputerTool(...) desde Microsoft.Agents.AI.Foundry para proporcionar al agente la herramienta para usar el equipo. Instale los paquetes Microsoft.Agents.AI.Foundry y Azure.AI.Projects, establezca el AZURE_AI_PROJECT_ENDPOINT y las variables de entorno AZURE_AI_COMPUTER_USE_DEPLOYMENT_NAME e inicie sesión con az login. En este ejemplo se omiten los asistentes de captura de pantalla: consulte el ejemplo completo para las utilidades de recursos y bucles de acción.

using Azure.AI.Projects;
using Azure.Identity;
using Microsoft.Agents.AI;
using Microsoft.Agents.AI.Foundry;
using Microsoft.Extensions.AI;
using OpenAI.Responses;

string endpoint = Environment.GetEnvironmentVariable("AZURE_AI_PROJECT_ENDPOINT")
    ?? throw new InvalidOperationException("AZURE_AI_PROJECT_ENDPOINT is not set.");
string deploymentName = Environment.GetEnvironmentVariable("AZURE_AI_COMPUTER_USE_DEPLOYMENT_NAME") ?? "computer-use-preview";

AIProjectClient projectClient = new(new Uri(endpoint), new DefaultAzureCredential());
using IHostedFileClient fileClient = projectClient.GetProjectOpenAIClient().AsIHostedFileClient();

AIAgent agent = projectClient.AsAIAgent(
    model: deploymentName,
    name: "ComputerAgent",
    instructions: "You are a computer automation assistant.",
    tools: [FoundryAITool.CreateComputerTool(ComputerToolEnvironment.Browser, 1026, 769)]);

// Upload pre-captured screenshots that simulate browser state transitions.
// (See the full sample for ComputerUseUtil implementation.)
Dictionary<string, string> screenshots = await ComputerUseUtil.UploadScreenshotAssetsAsync(fileClient);

ChatClientAgentRunOptions runOptions = new()
{
    ChatOptions = new ChatOptions
    {
        RawRepresentationFactory = (_) => new CreateResponseOptions { TruncationMode = ResponseTruncationMode.Auto },
    }
};

ChatMessage message = new(ChatRole.User,
[
    new TextContent("Search for 'OpenAI news'. Type it and submit. Once you see results, the task is complete."),
    new AIContent { RawRepresentation = ResponseContentPart.CreateInputImagePart(imageFileId: screenshots["browser_search"], imageDetailLevel: ResponseImageDetailLevel.High) }
]);

AgentSession session = await agent.CreateSessionAsync();
AgentResponse response = await agent.RunAsync(message, session: session, options: runOptions);

// Loop: parse computer call actions from response, simulate them, return new screenshots.
for (int i = 0; i < 10; i++)
{
    ComputerCallResponseItem? computerCall = response.Messages
        .SelectMany(m => m.Contents)
        .Select(c => c.RawRepresentation as ComputerCallResponseItem)
        .FirstOrDefault(item => item is not null);

    if (computerCall is null) break;

    (_, string fileId) = await ComputerUseUtil.GetScreenshotAsync(computerCall.Action, default, screenshots);

    AIContent callOutput = new()
    {
        RawRepresentation = new ComputerCallOutputResponseItem(
            computerCall.CallId,
            output: ComputerCallOutput.CreateScreenshotOutput(screenshotImageFileId: fileId))
    };

    response = await agent.RunAsync([new ChatMessage(ChatRole.User, [callOutput])], session: session, options: runOptions);
}

await ComputerUseUtil.EnsureDeleteScreenshotAssetsAsync(fileClient, screenshots);
Console.WriteLine($"Response: {response.Text}");

Salida esperada

Una vez completado el bucle de acción, la respuesta final del agente describe la página a la que alcanzó:

Response: I searched for "OpenAI news" in the address bar. The top results include articles from OpenAI's blog, TechCrunch, and The Verge ...

Para obtener la implementación completa del asistente de captura de pantalla y el bucle de acción de un extremo a otro, consulte Agent_Step15_ComputerUse.

Ejemplo para el uso de un agente con la herramienta Uso de computadoras

El siguiente fragmento de TypeScript muestra cómo crear una versión del agente con la herramienta de uso del equipo, enviar una solicitud inicial con una captura de pantalla y realizar varias iteraciones. Importa un asistente local computerUseUtil.js y espera recursos de captura de pantalla que no se incluyen en este artículo. Trate el extracto como un esquema de integración y proporcione la ejecución de acciones gestionada por la aplicación, la captura de pantalla y la aprobación explícita de seguridad antes de dar por superadas las comprobaciones de seguridad pendientes.

import { DefaultAzureCredential } from "@azure/identity";
import { AIProjectClient } from "@azure/ai-projects";
import { createInterface } from "node:readline/promises";
import { stdin, stdout } from "node:process";
import {
  SearchState,
  loadScreenshotAssets,
  handleComputerActionAndTakeScreenshot,
  printFinalOutput,
  type ComputerAction,
} from "./computerUseUtil.js";

// Format: "https://resource_name.ai.azure.com/api/projects/project_name"
const PROJECT_ENDPOINT = "your_project_endpoint";

export async function main(): Promise<void> {
  // Initialize state machine
  let currentState = SearchState.INITIAL;

  // Load screenshot assets
  const screenshots = loadScreenshotAssets();
  console.log("Successfully loaded screenshot assets");

  // Create AI Project client
  const project = new AIProjectClient(PROJECT_ENDPOINT, new DefaultAzureCredential());
  const openai = project.getOpenAIClient();

  console.log("Creating Computer Use Agent...");
  const agent = await project.agents.createVersion("ComputerUseAgent", {
    kind: "prompt" as const,
    model: "computer-use-preview",
    instructions: `
You are a computer automation assistant.

Be direct and efficient. When you reach the search results page, read and describe the actual search result titles and descriptions you can see.
    `.trim(),
    tools: [
      {
        type: "computer_use_preview",
        display_width: 1026,
        display_height: 769,
        environment: "windows" as const,
      },
    ],
  });
  console.log(`Agent created (id: ${agent.id}, name: ${agent.name}, version: ${agent.version})`);

  // Initial request with screenshot - start with Bing search page
  console.log(
    "Starting computer automation session (initial screenshot: cua_browser_search.png)...",
  );
  let response = await openai.responses.create(
    {
      input: [
        {
          role: "user" as const,
          content: [
            {
              type: "input_text",
              text: "I need you to help me search for 'OpenAI news'. Please type 'OpenAI news' and submit the search. Once you see search results, the task is complete.",
            },
            {
              type: "input_image",
              image_url: screenshots.browser_search.url,
              detail: "high",
            },
          ],
        },
      ],
      truncation: "auto",
    },
    {
      body: { agent_reference: { name: agent.name, type: "agent_reference" } },
    },
  );

  console.log(`Initial response received (ID: ${response.id})`);

  // Main interaction loop with deterministic completion
  const maxIterations = 10; // Allow enough iterations for completion
  let iteration = 0;

  while (iteration < maxIterations) {
    iteration++;
    console.log(`\n--- Iteration ${iteration} ---`);

    // Check for computer calls in the response
    const computerCalls = response.output.filter((item) => item.type === "computer_call");

    if (computerCalls.length === 0) {
      printFinalOutput({
        output: response.output,
        status: response.status ?? "",
      });
      break;
    }

    // Process the first computer call
    const computerCall = computerCalls[0];
    const action: ComputerAction = computerCall.action;
    const callId: string = computerCall.call_id;

    // Never execute an action with pending safety checks without user approval.
    const safetyChecks = computerCall.pending_safety_checks ?? [];
    if (safetyChecks.length > 0) {
      for (const check of safetyChecks) {
        console.warn(`Safety check: ${check.code}: ${check.message}`);
      }
      const prompt = createInterface({ input: stdin, output: stdout });
      const answer = await prompt.question("Approve this action? Type yes to continue: ");
      prompt.close();
      if (answer.toLowerCase() !== "yes") {
        throw new Error("Action rejected by the user.");
      }
    }

    console.log(`Processing computer call (ID: ${callId})`);

    // Handle the action and get the screenshot info
    const [screenshotInfo, updatedState] = handleComputerActionAndTakeScreenshot(
      action,
      currentState,
      screenshots,
    );
    currentState = updatedState;

    console.log(`Sending action result back to agent (using ${screenshotInfo.filename})...`);
    // Regular response with just the screenshot
    response = await openai.responses.create(
      {
        previous_response_id: response.id,
        input: [
          {
            call_id: callId,
            type: "computer_call_output",
            acknowledged_safety_checks: safetyChecks,
            output: {
              type: "computer_screenshot",
              image_url: screenshotInfo.url,
            },
          },
        ],
        truncation: "auto",
      },
      {
        body: { agent_reference: { name: agent.name, type: "agent_reference" } },
      },
    );

    console.log(`Follow-up response received (ID: ${response.id})`);
  }

  if (iteration >= maxIterations) {
    console.log(`\nReached maximum iterations (${maxIterations}). Stopping.`);
  }

  // Clean up resources
  console.log("\nCleaning up...");
  await project.agents.deleteVersion(agent.name, agent.version);
  console.log("Agent deleted");

  console.log("\nComputer Use Agent sample completed!");
}

main().catch((err) => {
  console.error("The sample encountered an error:", err);
});

Salida esperada

En el ejemplo siguiente se muestra la salida esperada al ejecutar el ejemplo de código anterior:

Successfully loaded screenshot assets
Creating Computer Use Agent...
Agent created (id: ..., name: ComputerUseAgent, version: 1)
Starting computer automation session (initial screenshot: cua_browser_search.png)...
Initial response received (ID: ...)
--- Iteration 1 ---
Processing computer call (ID: ...)
  Typing text "OpenAI news" - Simulating keyboard input
  -> Action processed: type
Sending action result back to agent (using cua_search_typed.png)...
Follow-up response received (ID: ...)
--- Iteration 2 ---
Processing computer call (ID: ...)
    Click at (512, 384) - Simulating click on UI element
    -> Assuming click on Search button when search field was populated, displaying results.
    -> Action processed: click
Sending action result back to agent (using cua_search_results.png)...
Follow-up response received (ID: ...)
OpenAI news - Latest Updates
Cleaning up...
Agent deleted
Computer Use Agent sample completed!

Usar el uso del ordenador en un agente Java

Agregue la dependencia a pom.xml:

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-agents</artifactId>
    <version>2.4.0</version>
</dependency>

Crear un agente de uso de computadora

import com.azure.ai.agents.AgentsClient;
import com.azure.ai.agents.AgentsClientBuilder;
import com.azure.ai.agents.ResponsesClient;
import com.azure.ai.agents.models.*;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.openai.models.responses.Response;
import com.openai.models.responses.ResponseCreateParams;

import java.util.Collections;

public class ComputerUseExample {
    // Format: "https://resource_name.ai.azure.com/api/projects/project_name"
    private static final String PROJECT_ENDPOINT = "your_project_endpoint";

    public static void main(String[] args) {

        AgentsClientBuilder builder = new AgentsClientBuilder()
            .credential(new DefaultAzureCredentialBuilder().build())
            .endpoint(PROJECT_ENDPOINT);

        AgentsClient agentsClient = builder.buildAgentsClient();
        ResponsesClient responsesClient = builder.buildResponsesClient();

        // Create computer use tool
        ComputerUsePreviewTool tool = new ComputerUsePreviewTool(
            ComputerEnvironment.WINDOWS,
            1024,
            768
        );

        // Create agent with computer use tool
        PromptAgentDefinition agentDefinition = new PromptAgentDefinition("computer-use-preview")
            .setInstructions("You are a computer automation assistant.")
            .setTools(Collections.singletonList(tool));

        AgentVersionDetails agent = agentsClient.createAgentVersion("computer-use-agent", agentDefinition);
        System.out.printf("Agent created: %s (version %s)%n", agent.getName(), agent.getVersion());

        // Create a response with initial screenshot
        AgentReference agentReference = new AgentReference(agent.getName())
            .setVersion(agent.getVersion());

        Response response = responsesClient.createAzureResponse(
            new AzureCreateResponseOptions().setAgentReference(agentReference),
            ResponseCreateParams.builder()
                .input("Open the browser and navigate to microsoft.com"));

        System.out.println("Response: " + response.output());

        // The response will contain computer_call items with actions
        // to execute. Process each action, take screenshots, and
        // send results back using responsesClient.createAzureResponse()
        // with the previousResponseId and computer call output.

        // Clean up
        agentsClient.deleteAgentVersion(agent.getName(), agent.getVersion());
    }
}

Para el bucle simulado completo, use el ejemplo de ComputerUseSync.java mantenido con su asistente de ComputerUseUtil.java. El asistente asigna las acciones solicitadas a capturas de pantalla capturadas previamente. Reemplace esa simulación por el ejecutor de acciones de la aplicación, captura de pantalla y flujo de aprobación de seguridad.

Usar el uso del ordenador con la API REST

Obtención de un token de acceso:

export AGENT_TOKEN=$(az account get-access-token --scope "https://ai.azure.com/.default" --query accessToken -o tsv)

Creación de un agente con uso de equipo

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/agents?api-version=v1" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "name": "computer-use-agent",
    "definition": {
      "kind": "prompt",
      "model": "computer-use-preview",
      "instructions": "You are a computer automation assistant.",
      "tools": [
        {
          "type": "computer_use_preview",
          "environment": "windows",
          "display_width": 1024,
          "display_height": 768
        }
      ]
    }
  }'

Generar una respuesta

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "agent_reference": {"type": "agent_reference", "name": "computer-use-agent"},
    "input": "Open the browser and navigate to microsoft.com"
  }'

La respuesta incluye computer_call elementos de salida con acciones que se van a ejecutar. Antes de ejecutar una acción, inspeccione pending_safety_checks. Si la matriz no está vacía, detén el proceso y muestra la acción y las comprobaciones de seguridad al usuario final. Continúe solo después de que el usuario apruebe explícitamente la acción.

Enviar resultados de la acción con captura de pantalla

Después de que el usuario apruebe las comprobaciones de seguridad pendientes y la aplicación ejecute la acción del equipo, capture una captura de pantalla y la envíe de vuelta. Incluya cada comprobación aprobada en acknowledged_safety_checks. Si no se devolvió ninguna verificación, use un array vacío.

curl -X POST "$FOUNDRY_PROJECT_ENDPOINT/openai/v1/responses" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AGENT_TOKEN" \
  -d '{
    "agent_reference": {"type": "agent_reference", "name": "computer-use-agent"},
    "previous_response_id": "<RESPONSE_ID>",
    "input": [
      {
        "type": "computer_call_output",
        "call_id": "<CALL_ID>",
        "acknowledged_safety_checks": [],
        "output": {
          "type": "computer_screenshot",
          "image_url": "data:image/png;base64,<BASE64_SCREENSHOT>"
        }
      }
    ]
  }'

Reemplace <RESPONSE_ID>, <CALL_ID>y por <BASE64_SCREENSHOT> los valores de la respuesta anterior. Repita este ciclo hasta que el modelo devuelva una respuesta de texto en lugar de .computer_call

Limpieza

curl -X DELETE "$FOUNDRY_PROJECT_ENDPOINT/agents/computer-use-agent?api-version=v1" \
  -H "Authorization: Bearer $AGENT_TOKEN"