计算机使用

from google import genai
from google.genai import types
from google.genai.types import Content, Part

client = genai.Client()

# Specify predefined functions to exclude (optional)
excluded_functions = ["drag_and_drop"]

generate_content_config = genai.types.GenerateContentConfig(
    tools=[
        # 1. Computer Use tool with browser environment
        types.Tool(
            computer_use=types.ComputerUse(
                environment=types.Environment.ENVIRONMENT_BROWSER,
                # Optional: Exclude specific predefined functions
                excluded_predefined_functions=excluded_functions
                )
              ),
        # 2. Optional: Custom user-defined functions
        #types.Tool(
          # function_declarations=custom_functions
          #   )
          ],
  )

# Create the content with user message
contents=[
    Content(
        role="user",
        parts=[
            Part(text="Search for highly rated smart fridges with touchscreen, 2 doors, around 25 cu ft, priced below 4000 dollars on Google Shopping. Create a bulleted list of the 3 cheapest options in the format of name, description, price in an easy-to-read layout."),
            # Optional: include a screenshot of the initial state
            #Part.from_bytes(
                #data=screenshot_image_bytes,
                #mime_type='image/png',
            #),
        ],
    )
]

# Generate content with the configured settings
response = client.models.generate_content(
    model='gemini-2.5-computer-use-preview-10-2025',
    contents=contents,
    config=generate_content_config,
)

# Print the response output
print(response)

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(candidate, page, screen_width, screen_height):
    results = []
    function_calls = []
    for part in candidate.content.parts:
        if part.function_call:
            function_calls.append(part.function_call)

    for function_call in function_calls:
        action_result = {}
        fname = function_call.name
        args = function_call.args
        print(f"  -> Executing: {fname}")

        try:
            if fname == "open_web_browser":
                pass # Already open
            elif fname == "click_at":
                actual_x = denormalize_x(args["x"], screen_width)
                actual_y = denormalize_y(args["y"], screen_height)
                page.mouse.click(actual_x, actual_y)
            elif fname == "type_text_at":
                actual_x = denormalize_x(args["x"], screen_width)
                actual_y = denormalize_y(args["y"], screen_height)
                text = args["text"]
                press_enter = args.get("press_enter", False)

                page.mouse.click(actual_x, actual_y)
                # Simple clear (Command+A, Backspace for Mac)
                page.keyboard.press("Meta+A")
                page.keyboard.press("Backspace")
                page.keyboard.type(text)
                if press_enter:
                    page.keyboard.press("Enter")
            else:
                print(f"Warning: Unimplemented or custom function {fname}")

            # Wait for potential navigations/renders
            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, action_result))

    return results

# Execute function calls
candidate = response.candidates[0]
results = execute_function_calls(response.candidates[0], page, SCREEN_WIDTH, SCREEN_HEIGHT)

def get_function_responses(page, results):
    screenshot_bytes = page.screenshot(type="png")
    current_url = page.url
    function_responses = []
    for name, result in results:
        response_data = {"url": current_url}
        response_data.update(result)
        function_responses.append(
            types.FunctionResponse(
                name=name,
                response=response_data,
                parts=[types.FunctionResponsePart(
                        inline_data=types.FunctionResponseBlob(
                            mime_type="image/png",
                            data=screenshot_bytes))
                ]
            )
        )
    return function_responses

# Capture state and return to model
function_responses = get_function_responses(page, results)
user_feedback_content = Content(
    role="user",
    parts=[Part(function_response=fr) for fr in function_responses])

# Append this feedback to the 'contents' history list for the next API call.
contents.append(user_feedback_content)

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

from google import genai
from google.genai import types
from google.genai.types import Content, Part

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")

    # Configure the model (From Step 1)
    config = types.GenerateContentConfig(
        tools=[types.Tool(computer_use=types.ComputerUse(
            environment=types.Environment.ENVIRONMENT_BROWSER
        ))],
        thinking_config=types.ThinkingConfig(include_thoughts=True),
    )

    # Initialize history
    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}")

    contents = [
        Content(role="user", parts=[
            Part(text=USER_PROMPT),
            Part.from_bytes(data=initial_screenshot, mime_type='image/png')
        ])
    ]

    # Agent Loop
    turn_limit = 5
    for i in range(turn_limit):
        print(f"\n--- Turn {i+1} ---")
        print("Thinking...")
        response = client.models.generate_content(
            model='gemini-2.5-computer-use-preview-10-2025',
            contents=contents,
            config=config,
        )

        candidate = response.candidates[0]
        contents.append(candidate.content)

        has_function_calls = any(part.function_call for part in candidate.content.parts)
        if not has_function_calls:
            text_response = " ".join([part.text for part in candidate.content.parts if part.text])
            print("Agent finished:", text_response)
            break

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

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

        contents.append(
            Content(role="user", parts=[Part(function_response=fr) for fr in function_responses])
        )

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

from typing import Optional, Dict, Any

from google import genai
from google.genai import types
from google.genai.types import Content, Part

client = genai.Client()

SYSTEM_PROMPT = """You are operating an Android phone. Today's date is October 15, 2023, so ignore any other date provided.
* To provide an answer to the user, *do not use any tools* and output your answer on a separate line. IMPORTANT: Do not add any formatting or additional punctuation/text, just output the answer by itself after two empty lines.
* Make sure you scroll down to see everything before deciding something isn't available.
* You can open an app from anywhere. The icon doesn't have to currently be on screen.
* Unless explicitly told otherwise, make sure to save any changes you make.
* If text is cut off or incomplete, scroll or click into the element to get the full text before providing an answer.
* IMPORTANT: Complete the given task EXACTLY as stated. DO NOT make any assumptions that completing a similar task is correct.  If you can't find what you're looking for, SCROLL to find it.
* If you want to edit some text, ONLY USE THE `type` tool. Do not use the onscreen keyboard.
* Quick settings shouldn't be used to change settings. Use the Settings app instead.
* The given task may already be completed. If so, there is no need to do anything.
"""

def open_app(app_name: str, intent: Optional[str] = None) -> Dict[str, Any]:
    """Opens an app by name.

    Args:
        app_name: Name of the app to open (any string).
        intent: Optional deep-link or action to pass when launching, if the app supports it.

    Returns:
        JSON payload acknowledging the request (app name and optional intent).
    """
    return {"status": "requested_open", "app_name": app_name, "intent": intent}

def long_press_at(x: int, y: int) -> Dict[str, int]:
    """Long-press at a specific screen coordinate.

    Args:
        x: X coordinate (absolute), scaled to the device screen width (pixels).
        y: Y coordinate (absolute), scaled to the device screen height (pixels).

    Returns:
        Object with the coordinates pressed and the duration used.
    """
    return {"x": x, "y": y}

def go_home() -> Dict[str, str]:
    """Navigates to the device home screen.

    Returns:
        A small acknowledgment payload.
    """
    return {"status": "home_requested"}

#  Build function declarations
CUSTOM_FUNCTION_DECLARATIONS = [
    types.FunctionDeclaration.from_callable(client=client, callable=open_app),
    types.FunctionDeclaration.from_callable(client=client, callable=long_press_at),
    types.FunctionDeclaration.from_callable(client=client, callable=go_home),
]

#Exclude browser functions
EXCLUDED_PREDEFINED_FUNCTIONS = [
    "open_web_browser",
    "search",
    "navigate",
    "hover_at",
    "scroll_document",
    "go_forward",
    "key_combination",
    "drag_and_drop",
]

#Utility function to construct a GenerateContentConfig
def make_generate_content_config() -> genai.types.GenerateContentConfig:
    """Return a fixed GenerateContentConfig with Computer Use + custom functions."""
    return genai.types.GenerateContentConfig(
        system_instruction=SYSTEM_PROMPT,
        tools=[
            types.Tool(
                computer_use=types.ComputerUse(
                    environment=types.Environment.ENVIRONMENT_BROWSER,
                    excluded_predefined_functions=EXCLUDED_PREDEFINED_FUNCTIONS,
                )
            ),
            types.Tool(function_declarations=CUSTOM_FUNCTION_DECLARATIONS),
        ],
    )

# Create the content with user message
contents: list[Content] = [
    Content(
        role="user",
        parts=[
            # text instruction
            Part(text="Open Chrome, then long-press at 200,400."),
            # optional screenshot attachment
            Part.from_bytes(
                data=screenshot_image_bytes,
                mime_type="image/png",
            ),
        ],
    )
]

# Build your fixed config (from helper)
config = make_generate_content_config()

# Generate content with the configured settings
response = client.models.generate_content(
        model='gemini-2.5-computer-use-preview-10-2025',
        contents=contents,
        config=config,
    )

print(response)

import termcolor

def get_safety_confirmation(safety_decision):
    """Prompt user for confirmation when safety check is triggered."""
    termcolor.cprint("Safety service requires explicit confirmation!", color="red")
    print(safety_decision["explanation"])

    decision = ""
    while decision.lower() not in ("y", "n", "ye", "yes", "no"):
        decision = input("Do you wish to proceed? [Y]es/[N]o\n")

    if decision.lower() in ("n", "no"):
        return "TERMINATE"
    return "CONTINUE"

def execute_function_calls(candidate, page, screen_width, screen_height):

    # ... Extract function calls from response ...

    for function_call in function_calls:
        extra_fr_fields = {}

        # Check for safety decision
        if 'safety_decision' in function_call.args:
            decision = get_safety_confirmation(function_call.args['safety_decision'])
            if decision == "TERMINATE":
                print("Terminating agent loop")
                break
            extra_fr_fields["safety_acknowledgement"] = "true" # Safety acknowledgement

        # ... Execute function call and append to results ...

function_response_parts.append(
    FunctionResponse(
        name=name,
        response={"url": current_url,
                  **extra_fr_fields},  # Include safety acknowledgement
        parts=[
            types.FunctionResponsePart(
                inline_data=types.FunctionResponseBlob(
                    mime_type="image/png", data=screenshot
                )
             )
           ]
         )
       )