- Added checks to ensure toolCallId exists and is a valid string before processing tool results.
- Preserves the original part if toolCallId is missing or invalid, improving robustness in message conversion.
- Updated logic to prioritize cache as the source of truth during streaming, with asynchronous database updates for persistence.
- Improved error handling for background database updates, ensuring cache validity even if DB update fails.
- Cleaned up mergeResponseMessages and mergeReasoningMessages functions by removing redundant code.
- Introduced lru-cache version 11.1.0 in package.json and pnpm-lock.yaml.
- Refactored updateMessageEntries to utilize TypeScript-based merge logic with write-through caching.
- Improved error handling for fetching existing message entries and updated database logic to merge new entries with existing ones.
- Updated GET reports endpoint to use `getReportsWithPermissions` for improved access control.
- Added support for filtering reports based on `shared_with_me` and `only_my_reports` flags.
- Introduced `getReportsWithPermissions` function to handle complex permission logic in the database layer.
- Enhanced report metadata retrieval to ensure proper access validation before fetching report details.
- Simplified the `GeneratingContent` component to display a static loading message.
- Updated `ReportPageController` to determine if a report is being generated based on the current message context.
- Adjusted report status handling in the delta creation process to maintain 'loading' status during streaming.
- Enhanced logic in the modify reports helper to ensure file status reflects loading during streaming and only updates to completed or failed when all edits are finalized.
- Modified database query to preserve input order for new messages during updates.
- Added '@buster/data-source' dependency to the server and pnpm lock files.
- Enhanced the getMetricDataHandler function to support versioning and data source integration.
- Updated the metric data query schema to include an optional version number parameter.
- Modified the API endpoint to accommodate the new versioning feature for metric data retrieval.
- Changed the wording of elapsed time in reasoning messages from "min" to "minutes" for better readability.
- Updated the final reasoning message format to specify "Reasoned for" instead of "Total workflow time," enhancing user understanding of the output.
These changes contribute to a more user-friendly experience and maintain consistency in messaging across different tools.
- Added permission checks to metric file download handler
- Added permission checks to export-metric-data trigger task
- Created comprehensive tests for access control integration
- Updated AssetType enums to include report_file
- Resolved export conflicts in server-shared package
- Fixed AI package imports for new getPermissionedDatasets API
- Introduced start time tracking for tool operations in create, modify, and report tools to improve performance monitoring.
- Updated reasoning entries to include elapsed time for completed operations, enhancing user feedback.
- Refactored tool logic to ensure consistent handling of file statuses and improved clarity in reasoning messages.
- Enhanced logging for better traceability during tool execution.
These changes improve the overall user experience and maintainability of the toolset.
- Combined asset type enums from both branches
- Merged all database query exports
- Integrated access-controls package into server-shared
- Resolved conflicts in AI package instructions
- Updated type definitions for better clarity and type safety in metric file download and export tasks.
- Enhanced error handling in the metric files API to utilize HTTPException for more consistent error responses.
- Added environment variable validation in export tasks to ensure necessary credentials are present before execution.
- Improved type assertions for content in metric export queries to ensure proper handling of JSONB data.
- Introduced new API endpoint for downloading metric files as CSV.
- Implemented export logic to handle large datasets (up to 1 million rows) and generate presigned URLs for secure downloads.
- Added cleanup task to remove exported files from R2 storage after 60 seconds.
- Updated environment configuration to include Cloudflare R2 credentials.
- Enhanced error handling for various export scenarios.
- Refactored related database queries and schemas for better integration.
- Updated documentation for new features and usage instructions.
- Introduced a new streaming mechanism for generating TODO lists, allowing for real-time updates and improved user experience.
- Added context handling for datasets in both `AnalystAgent` and `ThinkAndPrepAgent`, ensuring relevant data is included in system messages.
- Implemented new helper functions for managing TODO state and reasoning messages, improving code organization and clarity.
- Updated integration tests to validate the new streaming functionality and ensure consistent message roles.
These changes significantly enhance the functionality and maintainability of the TODO creation process within the agent workflow.
- Eliminated `responseMessages`, `reasoning`, and `rawLlmMessages` from chat creation and handling functions to streamline data processing.
- Updated the `generateJsonbArraySql` function to accept pre-stringified JSON for better performance and clarity.
These changes enhance the efficiency of chat message management and reduce unnecessary complexity in the codebase.
dal
Nate Kelley