- Replaced 'Voice' with 'Audio' in the system configuration and related tests to better reflect functionality.
- Introduced new methods for role management in the llmprovider, allowing for dynamic retrieval of roles based on user and team context.
- Updated the OpenAPI settings to support new role management endpoints and capabilities.
- Enhanced the handling of API keys in provider management, allowing for optional plain-text retrieval.
- Implemented initialization for the Setting Registry during the Load process.
- Added reload functionality to refresh the Setting Registry as needed.
- Enhanced error handling to capture and report issues during initialization and reloading.
- Added initialization for LLM Provider and MCP Client Registries during the Load process.
- Implemented reload functionality for both registries to ensure they are properly refreshed when needed.
- Enhanced error handling to capture and report issues during initialization and reloading of the registries.
- Added panic recovery to health checker and data cleaner to prevent crashes from unexpected errors.
- Implemented graceful shutdown for both components, ensuring they complete ongoing tasks before stopping.
- Updated the job import in the load module to manage health checker and data cleaner lifecycle.
- Introduced new channels to signal completion of health checks and data cleanups.
- Introduced a new `workspace` field across various robot-related structures, including `CreateRobotRequest`, `UpdateRobotRequest`, and `RobotResponse`, allowing for better organization and management of robots within specific workspaces.
- Updated database queries and response mappings to accommodate the new workspace field, ensuring seamless integration with existing functionalities.
- Enhanced agent execution context to include workspace information, improving the contextual awareness of agents during operations.
- Added tests to validate the creation and updating of robots with workspace data, ensuring robust functionality and backward compatibility.
- Added steps in both Linux and macOS workflows to inject commercial license root certificates from GitHub Secrets during the build process.
- Updated the `inspect` and `load` packages to include license information, enhancing the application's licensing capabilities.
- Included license metadata in the OpenAPI response for better visibility of licensing status.
- Replaced the previous file extension checks with a unified parsing function for sandbox configuration, improving code clarity and maintainability.
- Introduced a new HostExecConfig structure to manage local execution settings, allowing for more granular control over command execution permissions.
- Removed deprecated Moapi API files and related functionality, simplifying the codebase and reducing maintenance overhead.
- Updated the Tai node registration process to ensure local capabilities are accurately reflected based on the environment, enhancing overall system robustness.
- Added functionality to start the monitor service during the loading process, ensuring that watchers are registered.
- Implemented the stopping of the monitor service before unloading other services to allow for event handling.
- Updated middleware to utilize access logging for improved request tracking.
Made-with: Cursor
- Added sandbox initialization in the load process to ensure proper setup of the sandbox manager.
- Implemented gRPC heartbeat handling to track container liveness, enhancing the monitoring capabilities of the sandbox.
- Updated related documentation to reflect the new integration and functionality.
Made-with: Cursor
- Add new indirect dependencies including various Charmbracelet packages for improved UI handling.
- Enhance logging in the Assistant module by adding tool completion and start logging for better traceability of tool calls.
- Modify context handling in the RequestLogger to support a stack-based assistant ID management, improving the logging structure for agent requests.
- Implement event service integration for better trace management and debugging capabilities.
- Add external tool inspection functionality in the engine, allowing detection of tools like FFmpeg, PDF converters, and Docker.
- Update the `inspect` command to include detected tools in the output.
- Remove the studio configuration from the application, simplifying the configuration structure and related code.
- Clean up unused studio-related code in various files, including login processing and configuration management.
- Updated the CreateRobot API to auto-generate the member_id if not provided, enhancing usability and ensuring unique identifiers.
- Revised CreateRobotRequest structure to make member_id optional, aligning with the new auto-generation logic.
- Added a new function for generating unique member IDs with collision detection, ensuring compliance with existing ID patterns.
- Enhanced unit tests to validate the new behavior, ensuring robust error handling and proper ID generation.
- Updated related OpenAPI documentation to reflect changes in request structure and behavior.
- Introduced a `loadStep` function to wrap loading operations, providing timing and progress callback functionality.
- Updated the `Load` function to utilize `loadStep` for various components, improving visibility into loading durations.
- Enhanced the `start` command to display loading progress and duration in development mode, improving user experience during application startup.
- Refactored model loading functions to return models without migration, streamlining the loading process and improving performance.
- Updated assistant data handling to utilize structured models, improving code clarity and maintainability.
- Enhanced the assistant save and load functions to work with the new AssistantModel structure.
- Refactored mention handling to streamline the conversion process from raw data to structured mentions.
- Improved error handling in the assistant save process, ensuring better feedback for invalid data.
- Updated API responses to use the new gin.H format for consistency across the application.
Remove deprecated studio package and refactor agent integration
- Deleted the studio package, which is no longer in use, to streamline the codebase.
- Updated references in the agent and chat modules to utilize the new agent package instead of the deprecated neo package.
- Ensured that all related middleware and routing functionalities are now aligned with the agent architecture, enhancing overall system coherence.
- Integrated MCP client loading in both Load and Reload functions, enhancing the engine's capability to manage MCP configurations.
- Added error handling for MCP loading, ensuring warnings are generated for any issues encountered during the process.
- This update improves the overall robustness of the engine's loading mechanism and provides better feedback on MCP-related errors.
- Added context support to Send and SendBatch methods across all messenger providers (Twilio, Mailgun, SMTP).
- Implemented environment variable resolution in provider configurations to enhance flexibility.
- Updated Load function in the engine to include messenger loading, ensuring all components are initialized properly.
- Refactored related tests to validate new context handling and configuration parsing, improving overall robustness.
- Introduced a new `Groups` field in the `Attachment` struct to support categorization of attachments.
- Integrated `types.MetaInfo` into `ManagerOption` for improved metadata handling.
- Added a local uploader for attachments, enabling file uploads from a specified local path.
- Updated asset management functions to reflect changes in file metadata and structure.
- Moved Knowledge Base loading logic from the Load function to ensure it is consistently handled in both Load and Reload functions.
- Improved error handling by printing errors during Knowledge Base loading in the Reload function, enhancing user feedback.
- Updated GitHub Actions workflows to use the latest Ubuntu version and added services for Neo4j, Qdrant, and FastEmbed.
- Integrated FFmpeg and additional utilities into the CI environment, ensuring they are installed and tested during the workflow.
- Implemented environment variable resolution in the Knowledge Base configuration, allowing dynamic configuration based on environment settings.
- Added tests for environment variable resolution in the Knowledge Base configuration, ensuring correct parsing and handling of variables.
- Integrated OpenAPI loading functionality into the engine's Load and Reload processes, allowing for better API management.
- Updated the OpenAPI configuration to set a default BaseURL and ensure it does not have a trailing slash.
- Implemented the Attach method to connect the OpenAPI server to the Gin router, facilitating API endpoint management.
- Removed the obsolete hello package to streamline the OpenAPI module.
- Added new system models for assistant, attachment, audit, chat, config, dsl, history, and kb with metadata including tags, built-in status, read-only attributes, and sort order.
- Refactored the model loading process to include a dedicated function for loading system models, improving organization and maintainability.
- Updated the application loading logic to set a default prefix for system tables, ensuring consistent naming conventions.
- Improved error handling during model loading and migration processes for better reliability.
- Added checks in various loading functions to ignore processing if the respective directories do not exist, improving error handling and preventing unnecessary operations.
- Updated the Load function signature to return warnings alongside errors, allowing for better feedback on loading issues across different components.
