- Introduced a new `Search` type to store intermediate processing results, including extracted keywords, entities, relations, and generated QueryDSL for improved debugging and citation support.
- Updated the `executeAutoSearch` method to populate the new `Search` structure, ensuring all relevant data is captured during search execution.
- Implemented methods for saving and retrieving search records in MongoDB and Redis, enhancing data persistence across sessions.
- Revised localization files to include new keys for search-related messages, improving user experience.
- Updated DESIGN.md to reflect changes in the search result structure and data flow, ensuring comprehensive documentation of the new features.
- Removed the `history` model and replaced it with a new `message` model to streamline chat message storage and retrieval.
- Introduced a `resume` model to enhance the chat's ability to recover from interruptions, capturing essential execution state data.
- Updated the `CHAT_STORAGE_DESIGN.md` to reflect these changes, including new fields and relationships for the message and resume models.
- Revised related functions and tests to support the new data structures, ensuring improved integrity and performance in chat interactions.
- Added a check to verify if the 'mcps' directory exists before attempting to load MCP files, improving error handling and preventing unnecessary operations.
- Updated the error handling in the MCP loading function to ensure robustness in the application flow.
- Deleted agent_test.go to streamline testing structure.
- Removed mcp package and its related fetch and search files to simplify the codebase.
- Enhanced context handling in jsapi_test.go and jsapi.go for better integration with JavaScript.
- Introduced no-op objects for Trace and Node to handle uninitialized states gracefully.
- Updated i18n translations to include new MCP-related labels and descriptions.
- Refactored the Makefile to include new benchmark and memory leak detection tests, improving test coverage.
- Introduced context adjustments in the Create method, allowing hooks to modify context fields such as AssistantID, Connector, Locale, Theme, Route, and Metadata.
- Added a new test scenario to validate context field adjustments, ensuring proper updates during assistant operations.
- Updated test preparation to support optional V8 mode configuration for improved performance during benchmarks.
- Deleted obsolete agent API files (agent.go, api.go, api_test.go, types.go) to streamline the codebase.
- Refactored the agent loading logic to initialize the API instance correctly, ensuring proper integration with the new structure.
- Updated context handling to improve clarity and maintainability across the agent's functionality.
- Enhanced error handling and cache management in the agent's initialization process.
- Introduced ObtainAccessTokenWithRootPermission function to streamline the creation of test users with root permissions, ensuring consistent access token generation for tests.
- Updated various test cases to utilize the new function, improving clarity and reducing redundancy in access token acquisition.
- Enhanced team configuration retrieval to expose public settings while hiding sensitive information, improving security in API responses.
- Introduced the invitation model in bindata.go, including the new invitation.mod.yao file.
- Updated system models to include the invitation model for better integration.
- Added invitation code related error handling in default.go, enhancing user experience during invitation processes.
- Implemented invitation code management methods in the user provider interface, allowing for creation, usage, and deletion of invitation codes.
- Enhanced entry configuration to support invitation code verification, improving the user registration flow.
- Added a new endpoint for verifying invitation codes in user routing, streamlining the invitation redemption process.
- Modified test data in template tests to include 'invitation_link' and 'expires_at' fields, ensuring alignment with the actual template structure.
- Changed message type verification from "mail" to "email" for clarity and accuracy.
- Enhanced comments for better understanding of test data relevance.
- 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.
- Reorganized models by replacing the assistant and chat models with a new agent structure, including assistant, chat, and history models.
- Updated user model relationships to reflect changes in role and type references, ensuring consistency with the new model structure.
- Removed obsolete organization and user role models, streamlining the overall architecture.
- Adjusted system model mappings to incorporate new member and role models, enhancing clarity in user management.
- Introduced the organization_user model to manage relationships between organizations and users.
- Updated organization and user models to include new relationships for managing memberships and ownerships.
- Refactored system and test model mappings to incorporate the new organization_user model, ensuring consistency across the application.
- Introduced the organization model with associated data structure and methods for asset management.
- Updated user model to include new indexing on locale and zoneinfo for improved internationalization queries.
- Refactored system and test model mappings to include the new organization model, ensuring consistency across the application.
- Added new models for job management: category, execution, job, and log.
- Updated bindata.go to include paths for the new job models.
- Modified model.go and utils.go to register the new job models in system and test mappings, ensuring they are accessible in the application.
- Replaced the existing kb.mod.yao file with two new files: collection.mod.yao and document.mod.yao, enhancing the organization of knowledge base models.
- Updated references in system and test models to reflect the new structure, ensuring compatibility with the updated model paths.
- Adjusted asset loading functions to accommodate the new model files, improving the overall asset management system.
- Introduced user_role and user_type models to enhance user management capabilities.
- Updated user model fields to reference role and type identifiers, improving clarity and compliance with relational standards.
- Adjusted asset metadata timestamps and system/test model mappings to include new models, ensuring consistency across the application.
- Introduced the user_oauth_account model to enhance user authentication capabilities.
- Updated asset metadata timestamps for various files to reflect recent changes.
- Ensured consistency in the system and test models by including the new user_oauth_account model in both configurations.
- 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.
- Added support for a new OAuth data store in the system store management, allowing for better organization and retrieval of OAuth-related data.
- Updated the OAuth cache store configuration to increase the cache size from 4096 to 8192, improving performance and storage capacity.
- Enhanced test utilities to include the new OAuth store, ensuring comprehensive testing coverage for the updated store management features.
- Introduced a new system store management feature, allowing for the loading of predefined system stores such as cache and OAuth client stores.
- Added a `loadSystemStores` function to handle the loading of system stores with variable replacement for configuration paths.
- Enhanced the `Load` function to include the loading of system stores, improving the overall store management process.
- Updated test utilities to support loading system stores for testing, ensuring comprehensive coverage and functionality.
- Refactored the `replaceVars` function to facilitate variable replacement in JSON strings, enhancing flexibility in store configurations.
- Introduced a new user model `yao/models/user.mod.yao` to support user management functionalities.
- Updated the OAuth service to utilize the new `DefaultUser` provider, enhancing user authentication and management capabilities.
- Refactored user retrieval methods to align with the new user model structure, ensuring compatibility and improved functionality.
- Added token management methods to the user provider interface, streamlining token handling processes.
- Enhanced test utilities to include the new user model for comprehensive testing coverage.
- Introduced a new function `loadSystemModels` to load predefined system models for testing purposes, enhancing the test environment setup.
- Implemented error handling for model loading and migration, ensuring robust integration of system models.
- Updated the `Prepare` function to call `loadSystemModels`, streamlining the test preparation process.
- Updated the assistant management functions to utilize a unified response structure, replacing the previous 'Items' field with 'Data' for consistency across the API.
- Refactored the handling of assistant mentions and details to streamline data processing, improving code readability and maintainability.
- Enhanced the AssistantResponse type to include pagination fields directly, facilitating better management of assistant data retrieval.
- Implemented new methods for adding, saving, deleting, and searching assistants, ensuring robust functionality across different storage backends.
- Updated tests to reflect changes in the assistant management logic and response structure, ensuring comprehensive coverage and reliability.
