- Added support for Jira OAuth with new environment variables for client ID, client secret, and redirect URI.
- Implemented Jira connector routes for OAuth flow, including authorization and callback handling.
- Enhanced Jira connector to support both OAuth 2.0 and legacy API token authentication methods.
- Updated Jira indexing logic to utilize OAuth credentials with auto-refresh capabilities.
- Removed outdated Jira UI components and adjusted frontend logic to reflect the new integration.
- Added support for Jira OAuth with new environment variables for client ID, client secret, and redirect URI.
- Implemented Jira connector routes for OAuth flow, including authorization and callback handling.
- Enhanced Jira connector to support both OAuth 2.0 and legacy API token authentication.
- Updated Jira indexing logic to utilize OAuth credentials with auto-refresh capabilities.
- Removed outdated Jira UI components and adjusted frontend logic to reflect the new integration.
- Introduced Discord OAuth support with new environment variables for client ID, client secret, and redirect URI.
- Implemented Discord connector routes for OAuth flow, including authorization and callback handling.
- Enhanced Discord connector to support both OAuth-based authentication and legacy bot token usage.
- Updated Discord indexing logic to utilize OAuth credentials with auto-refresh capabilities.
- Removed outdated Discord UI components and adjusted frontend logic to reflect the new integration.
- Updated SlackHistory class to enforce the use of session and connector_id for token refresh, raising a ValueError for legacy token usage.
- Simplified conditional checks for client initialization in SlackHistory.
- Cleaned up unnecessary comments and whitespace in the codebase.
- Introduced Slack OAuth support with new environment variables for client ID, client secret, and redirect URI.
- Implemented Slack connector routes for OAuth flow, including authorization and callback handling.
- Updated configuration to support both new OAuth format and legacy token handling.
- Enhanced the Slack indexer to decrypt tokens when necessary, ensuring compatibility with existing encrypted credentials.
- Removed outdated Slack connector UI components and adjusted frontend logic to reflect the new integration.
- Enhanced LinearConnector and NotionHistoryConnector classes to support automatic token refresh, improving reliability in accessing APIs.
- Updated initialization to require session and connector ID, allowing for dynamic credential management.
- Introduced new credential schemas for Linear and Notion, encapsulating access and refresh tokens with expiration handling.
- Refactored indexers to utilize the new connector structure, ensuring seamless integration with the updated authentication flow.
- Improved error handling and logging during token refresh processes for better debugging and user feedback.
- Enhanced token decryption logic in Airtable, Google Drive, Linear, and Notion indexers to only attempt decryption when tokens are explicitly marked as encrypted.
- Added error handling for missing SECRET_KEY when tokens are marked as encrypted, improving robustness and clarity in error reporting.
- Updated comments to clarify the handling of plaintext tokens when encryption is not indicated.
- Added encryption for sensitive tokens (access token, refresh token, client secret) in Google Calendar, Google Drive, Gmail, Linear, and Notion connectors to enhance security.
- Introduced OAuthStateManager for secure state parameter generation and validation, improving the integrity of OAuth flows.
- Updated callback routes to handle state validation and error management, ensuring robust handling of authorization processes.
- Enhanced indexers to support decryption of tokens for backward compatibility, maintaining functionality with existing encrypted credentials.
- Improved validation for date parameters in connector routes to ensure proper input handling.
- Introduced Linear OAuth support with new environment variables for client ID, client secret, and redirect URI.
- Implemented Linear connector routes for OAuth flow, including authorization and callback handling.
- Updated existing components to accommodate Linear integration, including validation changes and connector configuration.
- Enhanced the Linear indexer to utilize OAuth access tokens instead of API keys.
- Adjusted UI components to reflect the new Linear connector without requiring special configuration.
- Introduced Notion OAuth support with new environment variables for client ID, client secret, and redirect URI.
- Implemented Notion connector routes for OAuth flow, including authorization and callback handling.
- Updated existing components to accommodate Notion integration, including validation changes and connector configuration.
- Enhanced the Notion indexer to utilize OAuth access tokens instead of integration tokens.
- Adjusted UI components to reflect the new Notion connector without requiring special configuration.
- Commented out the write_todos tracking and messaging logic in the stream_new_chat.py file.
- Disabled the import and usage of WriteTodosToolUI in the new-chat page component.
- Updated related logic in the active connectors tab to remove indexing state handling for write_todos.
- These changes are part of a temporary disablement of the write_todos feature for further evaluation.
- Add structured request body with folders and files arrays
- Support individual file indexing alongside folder indexing
- Remove deprecated folder_ids/folder_names query params
- Update UI to allow selecting both folders and files
- Simplify module docstrings (remove meta-commentary about 'small focused modules')
- Remove redundant inline comments (e.g., 'Log task start', 'Get connector from database')
- Trim verbose function docstrings to essential information only
- Remove over-explanatory comments that restate what code does
- Keep necessary documentation, remove noise for better readability
- Store tokens in folder_tokens dict instead of single global token
- Each folder now tracks its own sync state independently
- Fixes issue where indexing folder 2 incorrectly used delta sync after folder 1 was indexed
- First-time indexing now correctly uses full scan for each new folder
- Add optional 'connector' parameter with 'type' and 'metadata' fields
- Create helper function _update_document_from_connector
- Use document_metadata column (not metadata) for JSON field
- Merge metadata with existing using dict spread operator
- Google Drive documents now marked as GOOGLE_DRIVE_CONNECTOR
- Backward compatible - no changes to existing logic
- Simple and clean implementation
- Query document from database to ensure it's attached to session
- Prevents detached instance errors after process_file_in_background commits
- Properly updates document_type and metadata with session management
- Return file metadata from content_extractor for indexer to use
- Update document type and metadata in indexer after processing
- Explicitly commit changes to database
- Ensures documents are properly marked as GOOGLE_DRIVE_CONNECTOR type
- Full folder scan on first index
- Delta sync using change tracking for subsequent indexes
- Process files in parallel batches
- Handle file additions, modifications, and deletions
- Store change tracking token for efficient re-indexing
- 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.
- 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.
- Updated WebCrawlerConnector to prioritize Firecrawl API for crawling if an API key is provided, falling back to Chromium if Firecrawl fails.
- Improved error handling to log failures from both Firecrawl and Chromium.
- Enhanced link preview tool to use a random User-Agent for better compatibility with web servers.
- Passed Firecrawl API key to the stream_new_chat function for improved configuration management.
- Updated system prompt to clarify usage of the display_image tool, emphasizing URL requirements and restrictions on user-uploaded images.
- Enhanced the streaming chat process to provide more context about user attachments and documents during analysis.
- Implemented state resets when switching between chats to prevent stale data and race conditions.
- Added new components for displaying image previews and document attachments in the chat interface.
- Improved attachment processing to support image data URLs for persistent display after uploads.
- Updated the new chat routes to include handling for mentioned document IDs, allowing users to reference specific documents in their chat.
- Modified the NewChatRequest schema to accommodate optional document IDs.
- Implemented document mention formatting in the chat streaming service for improved context.
- Enhanced the frontend to manage document mentions, including a new atom for state management and UI updates for document selection.
- Refactored the DocumentsDataTable component for better integration with the new mention functionality.
- Enhanced the new chat agent module to allow for configurable tools, enabling users to customize their experience with various functionalities.
- Removed outdated tools including display image, knowledge base search, link preview, podcast generation, and web scraping, streamlining the codebase.
- Updated the system prompt and agent factory to reflect these changes, ensuring a more cohesive and efficient architecture.
