Tags: aws/nova-act
Tags
release: v2.1.319.0 **Features** * Add state guardrail to control which URLs Nova Act can visit **Fixes & Improvements** * Improve support for select and input elements * Allow about:blank navigation * Fall back to scroll by moving mouse if page does not scroll * Improve type definitions * Reorder operations in browser initialization to improve starting page transition time * Safely terminate Chrome before copying user data to prevent resource conflicts when using default Chrome browser * Refactor backend interface to support multiple authentication strategies and endpoints and improve observability * Add Content Security Policy (CSP) and improved HTML escaping to mitigate XSS risks * Additional minor fixes, improvements, and cleanup Co-authored-by: Rajan Agarwal <[email protected]> Co-authored-by: Sushil Bajracharya <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Matt Potok <[email protected]> Co-authored-by: Ulas Kirazci <[email protected]> Co-authored-by: Yilin Zhu <[email protected]> Co-authored-by: Bhaumik Mistry <[email protected]> Co-authored-by: Rick Liu <[email protected]> Co-authored-by: Animesh Pandey <[email protected]> Co-authored-by: Aaron Challenner <[email protected]>
release: v2.1.124.0 **Features** * Enable CDP connection to existing browser session via the cdp_connect_to_existing parameter of the NovaAct constructor **Fixes & Improvements** * Remove deprecated parameters that throw ValidationFailed exceptions * Fix exception raising for get_session_logs_directory() function * Remove mypy overrides for cleaner type checking * Improve definition of JSONType for better type safety * Group actuator and browser related files under a tools directory for better organization * Fix clearing input when agent types across different operating systems * Fix scroll and click functionality on PDFs * Update JSONType and replace all JSONSerializable references * Style improvements for action viewer * Refactor Interpreter to return a Program to unify response formats across different backends and enable structured tool execution Co-authored-by: Matt Potok <[email protected]> Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Animesh Pandey <[email protected]> Co-authored-by: Rick Liu <[email protected]> Co-authored-by: Ulas Kirazci <[email protected]> Co-authored-by: Luciana Corteggiano <[email protected]>
release: v2.1.36.0 **Features** * Integration with theNova 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 Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Eric Zhou <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Matthew Potok <[email protected]> Co-authored-by: Sushil Bajracharya <[email protected]> Co-authored-by: Ulas Kirazci <[email protected]> Co-authored-by: Yilin Zhu <[email protected]>
release: v2.0.357.0 **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 Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Matthew Potok <[email protected]> Co-authored-by: Yilin Zhu <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Sushil Bajracharya <[email protected]> Co-authored-by: Christopher Whitten <[email protected]> Co-authored-by: Eric Zhou <[email protected]> Co-authored-by: Aaron Challenner <[email protected]>
release: v2.0.177.0 This version includes minor fixes and documentation improvements Co-authored-by: Christopher Whitten <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Yilin Zhu <[email protected]> Co-authored-by: Animesh Pandey <[email protected]> Co-authored-by: Eric Zhou <[email protected]>
release: Playwright browser actuation
**Features**
* Playwright Browser Actuation
* Overhauled the browser actuation stack to use Playwright for improved accuracy, client-side latency, and customization
* Extend the DefaultNovaLocalBrowserActuator class to override methods like agent_click to customize behavior
* Implement the BrowserActuatorBase interface to provide your own browser implementation
**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
Co-authored-by: Christopher Whitten <[email protected]>
Co-authored-by: Kevin Kao <[email protected]>
Co-authored-by: Andrew Werchniak <[email protected]>
Co-authored-by: Yilin Zhu <[email protected]>
Co-authored-by: Matthew Potok <[email protected]>
Co-authored-by: Ulas Kirazci <[email protected]>
Co-authored-by: Kadhir Manickam <[email protected]>
Co-authored-by: Animesh Pandey <[email protected]>
feat: path to production (preview) - Authenticate with AWS IAM - Write Action Viewer logs to Amazon S3 - Integrate with the Amazon Bedrock AgentCore Browser Note: Access to the preview is limited to select customers Co-authored-by: Christopher Whitten <[email protected]> Co-authored-by: Shruti Arora <[email protected]>
feat: add proxy support and quality of life improvements **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 * Various fixes and improvements to the extension and actuation preview Co-authored-by: Andrew Werchniak <[email protected]> Co-authored-by: Animesh Pandey <[email protected]> Co-authored-by: Gary Lim <[email protected]> Co-authored-by: Christopher Whitten <[email protected]> Co-authored-by: Matthew Potok <[email protected]> Co-authored-by: Kevin Kao <[email protected]> Co-authored-by: Billy Wang <[email protected]> Co-authored-by: Yilin Zhu <[email protected]>
refactor: improve Nova Act client code organization and maintainability - Created abstract ActDispatcher interface to standardize dispatcher implementations - Moved common logging utilities to shared location - Simplified client initialization by introducing dispatcher factory pattern - Removed direct dependency on extension version in core client code
PreviousNext