Features

• Integration with the Nova Act extension for enhanced development experience with automated environment setup, chat-based script generation, real-time debugging, and step-by-step testing capabilities

Fixes & Improvements

• Expand file upload coverage
• Fix scroll behavior when bounding box is the entire page before scrolling
• Fix model parameters not being passed to product server start-plan call
• Fix emoji decoding issues
• Improve scroll and click functionality on PDFs
• Fix scroll behavior when bounding box is the entire page (viewport dimensions)
• Improve setting of session and act ids
• Major error handling refactor with comprehensive improvements across multiple modules
• Minor logging improvements
• Relax Playwright dependency version constraints
• Add allow-origins for Chrome devtools frontend
• Interpret double and right clicks
• Additional minor fixes, improvements, and cleanup

Documentation Updates

• Add README note about cross-OS keyboard shortcuts with AgentCore Browser
• Improve documentation following error refactor
• Add README section for Nova Act extension

Fixes & Improvements

• Strengthen type checking
• Minor refactor of telemetry module for reusability
• Remove legacy extension-related code
• Improve stop hook and S3Writer logging
• Factor browser profile and user data directory management out of default_chrome_browser feature to standardize user_data_dir behavior
• Improve scrollable element check logic
• Fix go_to_url_timeout
• Correct inaccurate ModelError raises
• Update agent_type() to insert the text if string length is > 10
• Allow scrollbars in Playwright headless mode
• Measure step server time
• Fix wait_for_page_to_settle bug that resulted in wait logic being bypassed
• Additional minor fixes, improvements, and cleanup

Documentation Updates

• Add README note about unencrypted password storage in browsers on some operating systems
• Update sample workflows

Features

• Playwright Browser Actuation
  • Overhauled the browser actuation stack to use Playwright for improved accuracy, client-side latency, and customization

Fixes & Improvements

• Allow specifying user agent when cdp_endpoint_url is set
• Add observation_delay_ms argument to act() for customizable delays before observations, e.g., waiting for UI animations
• Improve Action Viewer log output
• Improve error messages
• Handle Chrome v138 breaking changes to extension loading
• Additional minor fixes and improvements

Documentation Updates

• README
  • Minor reorganization of Common Building Blocks section
  • Add section on integration with Amazon Bedrock AgentCore Browser Tool
  • Add notes about Playwright downloads

Features

• Nova Act path to production (preview)
  • Authenticate with AWS IAM
  • Write Action Viewer logs to S3
  • Integrate with the Amazon Bedrock AgentCore Browser
  • Learn more about the path to production preview in our blog post. Once you’re ready to bring your prototype to production, join our waitlist. Access to the preview is limited to select customers.

Features

• Pass proxy configurations to Playwright via proxy option in the NovaAct constructor to route traffic through a specific proxy server

Fixes & Improvements

• Refactor PlaywrightInstanceManager to improve code organization and make the actuation system more modular and maintainable
• Improve session logs directory management
• Fix page access logic for different actuator types (default vs custom)
• Enhance error message clarity
• Improve custom actuator functionality by providing access to the starting page URL during initialization
• Improve unicode string decoding
• Simplify DOM and idToBboxMap actuation logic
• Improve observability
• Bump Playwright version to 1.52.0
• Various fixes and improvements to the extension and actuation preview

Features

• Pass CDP header to Playwright via cdp_headers option in the NovaAct constructor
• Try upcoming features via preview option in NovaAct constructor
  • Note: preview features may be unstable and the API may change in the future
• Use Playwright for actuation via playwright_actuation preview feature
• Customize actuation via custom_actuator preview feature

Fixes & Improvements

• Refactor local log file writing
• Improve act telemetry
• Support --profile-directory flag when launching default Chrome
• Support headless mode when launching default Chrome
• Various extension fixes and improvements

Features

• Use the use_default_chrome_browser option of the NovaAct constructor to run workflows with your locally installed Chrome to access sites requiring specific extensions or security features (macOS only)

Fixes & Improvements

• Add enum for common JavaScript expressions
• Scaffolding for option to disable extension
• Improve Nova Act client code organization and maintainability

Features

• Allow custom page load timeout via go_to_url_timeout
• Enable remote debugging with Chrome DevTools frontend
• Add sample code for finding apartments and calculating walking distance to the train station

Fixes & Improvements

• Implement safe copy of Chrome user data directory using rsync
• Scaffolding for automated default chrome use
• Improve actuation error handling
• Improve error handling for version mismatches between SDK and extension
• Move RunInfoCompiler creation to nova_act.py
• Cleanup backend authentication code
• Lock numpy version to fix build error

Documentation

• README updates:
  • Remove password field workaround
  • Add note to use ignore_https_errors=True with file URLs
  • Standardize prerequisites list format
  • Add note about English language support
  • Add table of contents
  • Add steps for headless browsing
• FAQ updates:
  • Simplify region support information