- Replaced the deprecated getConnectorCapabilities method with a unified capability getter in the Assistant model, improving capability retrieval logic.
- Added a new API endpoint to retrieve essential assistant information, including fields like id, name, avatar, and connector options, enhancing the assistant's data accessibility.
- Updated the LLM management to support filtering by capabilities, allowing for more flexible provider listings based on user-defined models.
- Improved overall structure and clarity in the assistant's capabilities and API responses, ensuring better maintainability and usability.
- Enhanced the getConnectorCapabilities method to prioritize model capabilities and connector settings, improving capability retrieval logic.
- Deprecated the tools field in the Assistant model, transitioning to MCP for tool management, and updated related methods accordingly.
- Introduced new fields for connector options and prompt presets in the Assistant model, allowing for more flexible configurations.
- Updated the GetAssistant method to support field selection, improving data retrieval efficiency and flexibility.
- Refactored tests and documentation to reflect changes in the assistant structure and capabilities, ensuring clarity and maintainability.
- Renamed and restructured the TestNewOpenAPI function to TestGetCompletionRequest for clarity.
- Updated test cases to validate completion requests using a structured request body instead of query parameters.
- Enhanced error handling and assertions to ensure comprehensive coverage of various scenarios, including metadata handling and expected outputs.
- Removed the obsolete openapi_chat_test.go file to streamline the test suite.
- 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.
- Updated the CreateAssistant and UpdateAssistant functions to simplify the success response by returning only the assistant_id instead of the full assistant data.
- Removed unnecessary JSON marshaling and unmarshaling, improving performance and clarity in response handling.
- Implemented UpdateAssistant method in Mongo, Redis, and Xun stores to allow partial updates of assistant fields.
- Updated Store interface to include the new UpdateAssistant method, enhancing the flexibility of assistant management.
- Added comprehensive tests for UpdateAssistant functionality, covering various scenarios including single and multiple field updates, JSON field handling, and error cases.
- Updated API routes to support PUT requests for updating assistants, ensuring proper permission checks and response handling.
- Simplified the response structure by directly returning the assistant and tags objects instead of wrapping them in a "data" field.
- Updated corresponding tests to reflect the new response format, ensuring accurate assertions and improved readability.
- Added a new GetAssistant function to retrieve assistant details by ID, incorporating permission checks to ensure authorized access.
- Updated the assistant route to use the new GetAssistant handler, enhancing security by verifying user permissions before returning assistant data.
- Introduced a FilterBuiltInAssistant function to clear sensitive fields for built-in assistants, ensuring compliance with data protection standards.
- Enhanced test coverage for the GetAssistant functionality, including tests for successful retrieval, permission filtering, and error handling scenarios.
- Moved the OAuth guard application from a specific assistants group to the main router group, simplifying route management.
- Updated assistant CRUD and action endpoints to directly use the main group, ensuring consistent access control across all assistant-related routes.
- Enhanced the HandleAssistantTags function to support multiple filtering options including type, connector, built-in status, mentionable status, automated status, and keywords.
- Updated the GetAssistantTags method in the store interfaces to accept a filter parameter, allowing for more granular tag retrieval.
- Refactored the Xun, Mongo, and Redis implementations of GetAssistantTags to utilize the new filtering capabilities.
- Added comprehensive tests for the new filtering functionality, ensuring correct behavior across various scenarios.
- Updated API endpoint documentation to reflect the new filtering options for assistant tags.
- Added permission fields (YaoCreatedBy, YaoUpdatedBy, YaoTeamID, YaoTenantID) to the AssistantModel for better tracking of ownership and access control.
- Introduced a custom QueryFilter in the AssistantFilter struct to allow for flexible permission-based filtering of assistants.
- Updated the GetAssistants method to apply the custom query filter, improving the retrieval logic based on user permissions.
- Enhanced test coverage for the new QueryFilter functionality, ensuring accurate filtering of assistants based on various criteria.
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.
- Updated the assistant-related API handler functions in neo/api.go to follow Go naming conventions by capitalizing the function names, making them exported for use in openapi/agent.
- This change enhances code readability and consistency across the API implementation.
- Added new LLM and MCP server management handlers in their respective packages, improving the overall structure and organization of the OpenAPI module.
- Removed the obsolete agent.go file, streamlining the codebase.
- 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.
- Replaced the Agent API with the Chat API, focusing on AI chat completions with full OpenAI client compatibility and real-time streaming capabilities.
- Updated routing to attach chat handlers instead of agent handlers, ensuring OAuth protection for all endpoints.
- Revised README documentation to reflect the new Chat API structure, including detailed descriptions of endpoints, features, and usage examples.
- Removed the deprecated agent files and their associated documentation to streamline the codebase.
- Introduced the Agent API to facilitate AI agent interactions, including chat completions with real-time streaming capabilities.
- Implemented endpoints for GET and POST requests to handle chat completions, supporting features like context management and assistant selection.
- Updated the README to include comprehensive documentation for the Agent API, detailing its functionalities, key endpoints, and usage examples.
- Enhanced the OpenAPI structure to integrate the new agent handlers into the existing routing system, ensuring OAuth protection for all endpoints.
