- Introduced `index_google_drive_selected_files` function to enable indexing of multiple user-selected files in parallel, improving efficiency.
- Refactored existing indexing logic to handle batch processing, including error handling for individual file failures.
- Added unit tests for the new batch indexing functionality, ensuring robustness and proper error collection during the indexing process.
- Added `_download_files_parallel` function to enable concurrent downloading of files from Google Drive, improving efficiency in document processing.
- Introduced `_download_and_index` function to handle the parallel downloading and indexing phases, streamlining the overall workflow.
- Updated `_index_full_scan` and `_index_with_delta_sync` methods to utilize the new parallel downloading functionality, enhancing performance.
- Added unit tests to validate the new parallel downloading and indexing logic, ensuring robustness and error handling during document processing.
- Refactored Google Calendar and Gmail indexers to utilize the new `index_batch_parallel` method for concurrent document indexing, enhancing performance.
- Updated the indexing logic to replace serial processing with parallel execution, allowing for improved efficiency in handling multiple documents.
- Adjusted logging and error handling to accommodate the new parallel processing approach, ensuring robust operation during indexing.
- Enhanced unit tests to validate the functionality of the parallel indexing method and its integration with existing workflows.
- Modified the `_should_skip_file` function to prevent skipping of documents with a FAILED status, ensuring they are reprocessed even if their content remains unchanged.
- Added a new integration test to verify that FAILED documents are not skipped during the indexing process.
- Added `download_and_extract_content` function to extract content from Google Drive files as markdown.
- Updated Google Drive indexer to utilize the new content extraction method.
- Implemented document migration logic to update legacy Composio document types to their native Google types.
- Introduced identifier hashing for stable document identification.
- Improved file pre-filtering to handle unchanged and rename-only files efficiently.
Resolve 8 conflicts:
- Accept upstream deletion of 3 composio_*_connector.py (unified Google connectors)
- Accept our deletion of ElectricProvider.tsx, use-connectors-electric.ts,
use-messages-electric.ts (replaced by Zero equivalents)
- Keep both new deps in package.json (@rocicorp/zero + @slate-serializers/html)
- Regenerate pnpm-lock.yaml
- Fix timestamp conversion: String(epochMs) → new Date(epochMs).toISOString()
in use-messages-sync, use-comments-sync, use-documents, use-inbox.
Without this, date comparisons (isEdited, cutoff filters) would fail.
- Fix updated_at: undefined → null in use-inbox to match InboxItem type
- Fix ZeroProvider: skip Zero connection for unauthenticated users
- Clean 30+ stale "Electric SQL" comments in backend Python code
- Refactored token refresh logic in ConfluenceHistoryConnector and JiraHistoryConnector to use lazy imports, avoiding circular dependencies.
- Enhanced the ComposerAction component to manage tool availability based on connected types, adding support for Jira and Confluence tools.
- Updated tool icon management to include Jira and Confluence, improving the user interface for tool interactions.
- Updated the GmailAccount class to extract email from the connector name when formatted with " - ".
- Added new tool actions for Gmail and Google Calendar, including creating drafts, sending emails, and managing calendar events, improving integration and user functionality.
- Introduced a mapping of native Google document types to their legacy Composio equivalents, ensuring seamless search and indexing for both types.
- Updated relevant components to utilize the new mapping, enhancing the consistency of document type handling across the application.
- Improved search functionality to transparently include legacy types, maintaining accessibility for older documents until re-indexed.
- Implemented fallback logic in Google Calendar, Drive, and Gmail indexers to handle legacy Composio document types, ensuring smooth migration to native types.
- Updated document indexing functions to check for existing documents using both primary and legacy hashes, improving data integrity during indexing.
- Modified the indexing functions for Google Calendar and Gmail to return the count of skipped messages alongside indexed messages, enhancing performance tracking.
- Updated related tests to accommodate the new return values, ensuring comprehensive coverage of the indexing process.
- Improved error handling to maintain consistency in returned values across different indexing functions.
- Updated the indexing function to return the count of skipped files alongside indexed files, improving tracking of indexing performance.
- Added logic to accumulate skipped file counts during the indexing process, providing better insights into potential issues.
- Enhanced notification updates to include skipped file counts, ensuring comprehensive progress reporting for users.
- Improved error handling for Google Drive indexing and listing operations to manage authentication failures more effectively.
- Added logic to mark connectors as 'auth_expired' when a 401 error or invalid credentials are detected, prompting users to re-authenticate.
- Updated error messages to provide clearer guidance on authentication issues, ensuring a better user experience.
- Added endpoint to list agent tools with metadata, excluding hidden tools.
- Updated NewChatRequest and RegenerateRequest schemas to include disabled tools.
- Integrated disabled tools management in the NewChatPage and Composer components.
- Improved tool instructions and visibility in the system prompt.
- Refactored tool registration to support hidden tools and default enabled states.
- Enhanced document chunk creation to handle strict zip behavior.
- Cleaned up imports and formatting across various files for consistency.
- Introduced a shielded async session context manager to ensure safe session closure during cancellations.
- Updated various database operations to utilize the new shielded session, preventing orphaned connections.
- Added environment variables to optimize glibc memory management, improving overall application performance.
- Implemented a function to trim the native heap, allowing for better memory reclamation on Linux systems.
- Added proper session closure to prevent connection leaks during streaming.
- Implemented a fresh session for cleanup tasks to ensure data integrity.
- Enhanced error handling during session operations to improve robustness.
- Removed unnecessary session parameters from function signatures for clarity.
- Increased maximum file upload limit from 10 to 50 to improve user experience.
- Implemented batch processing for document uploads to avoid proxy timeouts, splitting files into manageable chunks.
- Enhanced garbage collection in chat streaming functions to prevent memory leaks and improve performance.
- Added memory delta tracking in system snapshots for better monitoring of resource usage.
- Updated LLM router and service configurations to prevent unbounded internal accumulation and improve efficiency.
- Improved in-memory rate limiting by evicting timestamps outside the current window and cleaning up empty keys.
- Updated LLM router service to cache context profiles and avoid redundant computations.
- Introduced cache eviction logic for MCP tools and sandbox instances to manage memory usage effectively.
- Added garbage collection triggers in chat streaming functions to reclaim resources promptly.
- Introduced RequestPerfMiddleware to log request performance metrics, including slow request thresholds.
- Updated various services and retrievers to utilize the new performance logging utility for better tracking of execution times.
- Enhanced existing methods with detailed performance logs for operations such as embedding, searching, and indexing.
- Removed deprecated logging setup in stream_new_chat and replaced it with the new performance logger.
- Replaced direct embedding calls with a utility function across various components to streamline embedding logic.
- Added enable_summary flag to several models and routes to control summary generation behavior.
- Introduced slow callback logging in FastAPI to identify blocking calls.
- Added performance logging for agent creation and tool loading processes.
- Implemented caching for MCP tools to reduce redundant server calls.
- Enhanced sandbox management with in-process caching for improved efficiency.
- Refactored several functions for better readability and performance tracking.
- Updated tests to ensure proper functionality of new features and optimizations.
- Added functionality to persist sandbox files locally before deletion.
- Introduced methods for retrieving and deleting locally stored sandbox files.
- Updated routes to handle local file downloads and background deletion of sandboxes.
- Enhanced streaming tasks to support sandbox file management.
- Added _TimeoutAwareSandbox class to handle per-command timeouts in DaytonaSandbox.
- Updated _find_or_create function to manage sandbox states and restart stopped/archived sandboxes.
- Enhanced get_or_create_sandbox to return the new sandbox class.
- Introduced file download functionality in the frontend, allowing users to download generated files from the sandbox.
- Updated system prompt to include guidelines for sharing generated files.
