Browser Automation

from marsys.agents import BrowserAgent, BrowserAgentMode
from marsys.models import ModelConfig

# PRIMITIVE Mode - Fast content extraction
browser_agent = await BrowserAgent.create_safe(
    model_config=ModelConfig(
        type="api",
        provider="openrouter",
        name="anthropic/claude-haiku-4.5",
        temperature=0.3
    ),
    name="web_scraper",
    mode="primitive",  # or BrowserAgentMode.PRIMITIVE
    goal="Fast web scraping agent for content extraction",
    headless=True,
    tmp_dir="./tmp/browser"
)

# ADVANCED Mode - Visual interaction
browser_agent = await BrowserAgent.create_safe(
    model_config=ModelConfig(
        type="api",
        provider="openrouter",
        name="anthropic/claude-haiku-4.5",
        temperature=0.3
    ),
    name="web_navigator",
    mode="advanced",  # or BrowserAgentMode.ADVANCED
    goal="Expert web automation for complex interactions",
    auto_screenshot=True,  # Enable visual feedback
    vision_model_config=ModelConfig(
        type="api",
        provider="openrouter",
        name="google/gemini-2.5-flash",  # Fast and cost-effective
        temperature=0,
        thinking_budget=0
    ),
    headless=False,
    tmp_dir="./tmp/screenshots"
)

from marsys.coordination import Orchestra

# Create browser agent
browser_agent = await BrowserAgent.create_safe(
    model_config=config,
    name="scraper",
    mode="primitive",
    goal="Extract data from websites"
)

try:
    # Use with Orchestra
    topology = {
        "agents": ["scraper"],
        "flows": []
    }

    result = await Orchestra.run(
        task="Go to example.com and extract all headings",
        topology=topology
    )
finally:
    await browser_agent.cleanup()

# Search for text on the current page
result = await browser_tool.search_page("quantum computing")
# Returns: "Match 1/5 found and highlighted"
# All matches highlighted in YELLOW, current match in ORANGE

# Navigate to next match - call again with SAME term
result = await browser_tool.search_page("quantum computing")
# Returns: "Match 2/5"
# Scrolls to and highlights next occurrence

# Continue navigating (wraps around after last match)
result = await browser_tool.search_page("quantum computing")
# Returns: "Match 3/5"

# Clicking a download link automatically detects the download
result = await browser_tool.mouse_click(x=450, y=300)
# Returns: "Action 'mouse_click' triggered a file download.
#          File 'report.pdf' has been downloaded to: /path/to/tmp/downloads/report.pdf"

# Navigating to a PDF URL triggers automatic download
result = await browser_tool.goto("https://example.com/paper.pdf")
# Returns: "Action 'goto' triggered a file download.
#          File 'paper.pdf' has been downloaded to: /path/to/tmp/downloads/paper.pdf"

# Pressing Enter on a download button
await browser_tool.mouse_click(x=500, y=400)  # Focus download button
await browser_tool.keyboard_press("Enter")
# Returns: "Action 'keyboard_press' triggered a file download.
#          File 'data.xlsx' has been downloaded to: /path/to/tmp/downloads/data.xlsx"

from marsys.agents import BrowserAgent

# Create agent with existing session state
agent = await BrowserAgent.create_safe(
    model_config=config,
    name="AuthenticatedBrowser",
    mode="advanced",
    session_path="./sessions/linkedin_session.json",  # Load existing session
    headless=True
)

# Browser is now initialized with saved cookies and localStorage
# Already logged in to LinkedIn, Google, etc.
await agent.run("Go to linkedin.com/feed and extract posts")

# After logging in manually or programmatically, save the session
result = await agent.browser_tool.save_session("./sessions/my_session.json")
# Returns: "Session saved successfully to ./sessions/my_session.json. Saved 15 cookies and 3 origin storage entries."

# The agent can also save sessions via tool calls
result = await agent.run("Save the current session to ./sessions/backup.json")