- Updated the report generation tool to include error handling for failed report generation, persisting error messages in the database.
- Modified metadata extraction to count section headings and return a status indicating readiness or failure.
- Adjusted frontend components to handle and display error states based on report generation outcomes, improving user feedback and experience.
Enables users to edit tool call arguments before execution in human-in-the-loop
workflows. Adds edit mode UI with form fields, grayscale styling, and subtle
pulse animations for pending approvals. Backend stub enhanced to verify edited
arguments are correctly passed through.
- Added a new ReportPanel component to display report details inline within the chat interface.
- Updated NewChatPage and PublicChatView to include the ReportPanel, enhancing user experience by allowing report viewing alongside chat interactions.
- Introduced report panel state management with Jotai atoms to control visibility and data handling.
- Refactored existing components to accommodate the new report panel layout and functionality.
- Added a new tool for generating structured Markdown reports based on user input.
- Implemented routes for creating, reading, exporting, and deleting reports.
- Integrated report generation into the chat flow, allowing users to generate reports inline.
- Updated schemas to support report data structures and responses.
- Enhanced frontend components to handle report generation and display results.
- Create CreateNotionPageToolUI component with approval card (approve/reject)
- Handle data-interrupt-request SSE event in page.tsx
- Add handleResume callback to POST decisions and stream continuation
- Skip message persistence for interrupted messages (handleResume persists)
- Stamp __decided__ on tool results for immutable post-decision state
- Sync pendingInterrupt ID after message persistence rename
- Removed the write_todos tool as it is now included by default through TodoListMiddleware in the deep agent.
- Updated the system prompt and documentation to reflect the integration of TodoListMiddleware, clarifying its capabilities for managing planning and todo lists.
- Enhanced the chat handling logic to extract todos directly from the deep agent's command output, ensuring seamless user experience.
- Refactored UI components to align with the new data structure and improve rendering of todo items, including updates to the Plan and TodoItem components.
- Cleaned up code for better maintainability and readability, following recent refactoring efforts.
- Updated the write_todos tool to include an optional description field for todo items, improving task detail management.
- Enhanced the system prompt with clearer guidelines on using the write_todos tool, including refined usage patterns and examples for various user scenarios.
- Improved UI components to support the new description feature, ensuring better visibility of task details during planning and execution.
- Streamlined the code for better readability and maintainability, aligning with recent refactoring efforts.
- Refactored the write_todos tool to enhance argument and result schemas using Zod for better validation and type safety.
- Updated the WriteTodosToolUI to streamline the rendering logic and improve loading states, ensuring a smoother user experience.
- Enhanced the Plan and TodoItem components to better handle streaming states and display progress, providing clearer feedback during task management.
- Cleaned up code formatting and structure for improved readability and maintainability.
- Introduced a new TextShimmerLoader component to provide a shimmer effect for loading text, improving user experience during in-progress states.
- Updated the TodoItem component to utilize the TextShimmerLoader for displaying labels of in-progress tasks, replacing the previous pulse animation.
- Updated NewChatPage to persist partial responses when requests are cancelled by the user.
- Enhanced WriteTodosToolUI to check if the thread is running, improving the display of loading states and error handling.
- Modified Plan and TodoItem components to conditionally animate in-progress items based on streaming status, providing a clearer user experience during task management.
- Added a new write_todos tool to facilitate the creation and management of planning lists within the chat interface.
- Updated system prompt with detailed instructions on using the write_todos tool, including usage patterns and restrictions.
- Enhanced the chat message handling to support the new tool, ensuring proper integration and user experience.
- Implemented UI components for displaying and interacting with the planning lists, including progress tracking and status indicators.
- Introduced Zod schemas for type-safe parsing of mentioned document information in chat messages.
- Updated the extractMentionedDocuments function to utilize the new schemas for better validation.
- Made the 'alt' property optional in image-related components for improved flexibility and fallback handling.
- Added a fallback mechanism using headless Chromium to fetch page content when standard HTTP requests fail.
- Introduced utility functions for unescaping HTML entities and converting relative URLs to absolute.
- Updated HTTP request headers to mimic a browser for better compatibility with web servers.
- Improved error handling and logging for better debugging and user feedback.
- Made various properties in Zod schemas nullable for better type safety and flexibility in handling optional data.
- Removed the play overlay button from the artwork section for a cleaner design.
- Replaced the existing volume slider with a custom volume bar for better visual distinction.
- Enhanced the volume control layout for improved user experience and accessibility.
- Removed unnecessary calculations for in-progress and last completed step states in ThinkingStepsDisplay.
- Simplified the getStepOpenState function to focus on current step status.
- Introduced constants for animation timing and file extension categories in ChainOfThought for better maintainability.
- Enhanced icon retrieval logic based on file types and step statuses, improving clarity and performance.
- Updated component props to use TypeScript interfaces for better type safety and readability.
