Browser Automation

browser_navigate_to(url="https://example.com")

browser_act(action="click the login button")
browser_act(action="fill in email with [email protected]")
browser_act(action="scroll down")
browser_act(action="select 'Premium' from the dropdown")

browser_extract_content(instruction="get all product names and prices")
browser_extract_content(instruction="extract the main article text")

browser_screenshot(name="homepage")

# Navigate to login page
browser_navigate_to(url="https://app.example.com/login")

# Fill in credentials
browser_act(action="click the email field")
browser_act(action="type [email protected]")
browser_act(action="click the password field")
browser_act(
    action="type %password%",
    variables={"password": "secure_pass"}
)

# Submit form
browser_act(action="click the Sign In button")

# Navigate to product page
browser_navigate_to(url="https://shop.example.com/products")

# Scroll to load all products
browser_act(action="scroll to bottom")

# Extract product data
result = browser_extract_content(
    instruction="extract all products with name, price, and rating"
)

# Research a company website
browser_navigate_to(url="https://example.io")

# Browse key pages
browser_act(action="click the Features link")
features = browser_extract_content(instruction="extract feature descriptions")

browser_act(action="click Pricing")
pricing = browser_extract_content(instruction="get pricing tiers and costs")

browser_act(action="click About Us")
company_info = browser_extract_content(instruction="extract company mission and team size")

@tool_metadata(
    display_name="Browser",
    description="Interact with web pages using mouse and keyboard, take screenshots, and extract content",
    icon="Globe",
    color="bg-cyan-100 dark:bg-cyan-800/50"
)
class BrowserTool(SandboxToolsBase):
    """
    Browser Tool for browser automation using local Stagehand API.
    
    Only 4 core functions that can handle everything:
    - browser_navigate_to: Navigate to URLs
    - browser_act: Perform any action (click, type, scroll, dropdowns etc.)
    - browser_extract_content: Extract content from pages
    - browser_screenshot: Take screenshots
    """

def _validate_base64_image(self, base64_string: str, max_size_mb: int = 10) -> tuple[bool, str]:
    """
    Comprehensive validation of base64 image data.
    
    - Checks string length and format
    - Validates base64 characters
    - Decodes and verifies image data
    - Checks file size limits
    - Validates image format using PIL
    """

browser_act(
    action="fill in password with %pass%",
    variables={"pass": "actual_password"}
)

browser_act(
    action="click the upload button",
    filePath="/workspace/documents/resume.pdf"
)

# ✅ GOOD: Direct navigation
browser_navigate_to(url="https://example.io")
browser_extract_content(instruction="get product features")

# ❌ BAD: Generic web search
web_search(query="example.io features")

# Action returns screenshot automatically
result = browser_act(action="click the Submit button")
# Check the screenshot to confirm button was clicked

# Extract content once
product_data = browser_extract_content(
    instruction="get product information"
)

# ✅ Use extracted data for deliverables
# ❌ Don't override with web search results

GEMINI_API_KEY=your_api_key_here