- Renamed several assistant packages for clarity, including "Entity Extraction" to "Entity Extractor" and "Keyword Extraction" to "Keyword Extractor."
- Revised descriptions for various assistants to enhance understanding of their functionalities, such as changing "Extract keywords from text content" to "Extract search keywords."
- Added a "uses" field with "search" set to "disabled" in the configuration of each assistant, standardizing their setup.
- Updated the "Prompt Optimizer" description to "Optimize prompts for better results" and modified the "QueryDSL Generator" to "Query Builder" for improved clarity.
- Ensured consistent naming conventions and descriptions across all assistant packages to enhance user experience and documentation clarity.
- Updated the `shouldAutoSearch` method to include additional parameters for improved intent detection, allowing for better decision-making on whether to execute auto search.
- Introduced a new `checkSearchIntent` method to utilize the `__yao.needsearch` agent for determining the necessity of a search based on user input.
- Implemented a `ClearExcept` method in the cache to selectively clear non-system agents while preserving essential system agents during cache management.
- Updated the `LoadBuiltIn` function to maintain system agents in the cache, ensuring they remain available for use.
- Enhanced test coverage for loading system agents and validating search intent detection, ensuring robustness in the assistant's search capabilities.
- Revised localization files to include new messages for search intent feedback, improving user experience during search operations.
- Added configuration support for system agents in the assistant initialization process, allowing for custom connectors for agents like __yao.keyword and __yao.querydsl.
- Implemented the loading mechanism for system agents from bindata, ensuring that essential agents are available during runtime.
- Updated the LoadBuiltIn function to exclude system agents from being removed, enhancing the management of built-in and system agents.
- Enhanced test coverage by introducing tests for loading system agents, verifying their presence and correctness in the cache.
- Updated documentation to reflect the new system agents configuration and loading processes.
- 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.
- Introduced a new search configuration structure, allowing for detailed settings for web, knowledge base, database, citation, and weights.
- Updated the `Assistant` model to include a `Search` field, enabling assistant-specific search configurations.
- Enhanced the loading and merging logic for search configurations, ensuring global defaults can be overridden by assistant-specific settings.
- Added comprehensive tests for loading, saving, and updating assistants with search configurations, verifying the integrity of search settings.
- Updated documentation in DESIGN.md to reflect the new search configuration hierarchy and usage, clarifying the interaction between global and assistant-level settings.
- Introduced `GetInfo` method in the Assistant struct to return basic assistant information with optional locale support for internationalization.
- Implemented `GetInfoByIDs` function to retrieve information for multiple assistants based on their IDs, enhancing batch processing capabilities.
- Updated chat buffer management to include a mode parameter, allowing for dynamic switching between chat and task modes.
- Enhanced message handling to store and retrieve the mode associated with each message, improving context tracking during chat sessions.
- Revised tests to validate the new functionalities, ensuring accurate retrieval of assistant information and proper mode management in chat operations.
- Updated the `ChatBuffer` to support streaming messages, allowing for content to be appended and finalized with `SendStream` and `End` methods.
- Modified the `AddAssistantMessage` method to include a message ID, improving message tracking and retrieval.
- Implemented new methods for appending content to streaming messages and completing them, ensuring accurate message storage and event handling.
- Revised tests to validate the new streaming functionality and ensure proper integration with existing message handling processes.
- Updated `CHAT_STORAGE_DESIGN.md` to reflect changes in message storage and indexing, including unique constraints for message IDs within requests.
- Enhanced chat buffer and message handling to support dynamic connector switching, allowing users to change the connector during a chat session.
- Updated the `ChatBuffer` and `BufferedMessage` structures to include a `connector` field, enabling tracking of the connector used for each message.
- Modified the `EnsureChat` method to skip chat creation when history is disabled, improving chat session management.
- Revised tests to validate the new connector functionality, ensuring accurate message retrieval and connector state management.
- Updated `CHAT_STORAGE_DESIGN.md` to reflect the addition of the `last_connector` field in chat metadata and message structures.
- Added CreateChat, GetChat, UpdateChat, and DeleteChat methods to manage chat sessions effectively.
- Implemented validation for required fields and handling of nullable fields during chat creation and updates.
- Enhanced chat retrieval with pagination and filtering options, including time-based grouping.
- Introduced helper functions for converting database rows to Chat structs and grouping chats by time.
- Updated message and resume models to support soft deletes, improving data management and integrity.
- 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.
- Updated `GetText` and `SaveText` methods to support both full content and a preview (first 2000 characters) for improved performance and usability.
- Added comprehensive tests in `manager_test.go` to validate the new functionality, including UTF-8 character handling and content retrieval scenarios.
- Modified the attachment model to include a `content_preview` field alongside the existing `content` field, ensuring efficient data management.
- Enhanced the README.md to document the new dual storage feature, providing clear examples for users on how to utilize the updated methods.
- Implemented `GetText` and `SaveText` methods in the attachment manager to handle storing and retrieving parsed text content from files.
- Enhanced the `manager_test.go` with comprehensive tests for various scenarios, including saving, updating, and retrieving text, as well as handling non-existent file IDs.
- Updated the README.md to document the new text content storage features, providing examples for saving and retrieving parsed text.
- Modified the attachment model to include a new `content` field for storing text content, improving the overall functionality of the attachment management system.
- Introduced `modes` field to support multiple operational modes for the assistant, allowing for flexible functionality (e.g., chat, task).
- Added `default_mode` field to specify the primary mode of operation for the assistant.
- Updated the `Map`, `Clone`, and `Update` methods to handle the new fields appropriately.
- Enhanced the `ToAssistantModel` conversion function to include the new fields.
- Added tests to validate the integration and functionality of modes and default mode within the assistant model.
- Introduced a new `Database` type to encapsulate database models and options.
- Updated the `Assistant` model to include a `DB` field for database configuration.
- Enhanced the `Map`, `Clone`, and `Update` methods to handle the new `DB` field appropriately.
- Implemented the `ToDatabase` conversion function to support various input types for database initialization.
- Added comprehensive tests to validate the integration of the database functionality within the assistant model.
- Updated relevant fields and methods to ensure consistent handling of the new database configuration.
- Introduced the `disable_global_prompts` field in the Assistant model to control the usage of global prompts.
- Updated the Load and Get methods to initialize and retrieve global prompts from the configuration.
- Refactored tests to validate the new global prompts functionality and ensure proper loading and context handling.
- Improved the overall structure and clarity of the assistant's capabilities and configurations.
- 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.
- Added global uses configuration to the assistant, allowing for centralized management of vision, audio, search, and fetch settings.
- Updated the Assistant struct and related methods to support the new Uses configuration, improving flexibility in assistant operations.
- Refactored the Stream method to utilize the new CompletionResponse type, enhancing response handling.
- Introduced new methods for building requests and managing capabilities, streamlining the assistant's interaction with various connectors.
- 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.
- Deleted session-related functions (UserID, GuestID, UserRoles, UserOrGuestID) from the agent package to streamline the codebase.
- Removed RAG-related code and references, simplifying the agent's architecture.
- Updated API and load functions to reflect these changes, ensuring consistency across the agent module.
- Enhanced test coverage by cleaning up deprecated test cases related to removed functionalities.
- Introduced new fields in the attachment model for public access control and sharing options, allowing attachments to be marked as public or shared with specific teams.
- Updated the upload process to handle new permission fields, ensuring proper handling of public and share options during file uploads.
- Implemented permission checks in the file retrieval and deletion processes to enforce access control based on user roles and attachment settings.
- Added comprehensive tests for the new permission fields to validate functionality and ensure correct behavior in various scenarios.
- Updated the modification times for various assets in `bindata.go` to reflect recent changes.
- Refactored import statements in `team_invitation.go` to maintain consistency and improve code organization by moving the `utils` import to the correct position.
- Updated the modification times for various assets in `bindata.go` to reflect recent changes.
- Enhanced the collection management in the API by adding new fields for `preset`, `public`, and `share` in the collection and document models, allowing for better control over collection visibility and sharing options.
- Updated the `CreateCollection` function to incorporate the new `share` field, improving the handling of collection data based on user permissions.
- Refactored utility functions to streamline type conversions, ensuring consistent data handling across the user and team management functionalities.
- Added `Parse` function to handle attachment wrapper strings, extracting uploader name and file ID.
- Introduced `Base64` function to convert attachment wrappers to Base64 format, with optional data URI support.
- Enhanced `readFilePathAsBase64` to read files from the filesystem and return Base64 encoded content.
- Updated `teamInvitationGetPublic` to process team logos and inviter pictures as Base64 for direct display in the response.
- Introduced the `robot_email`, `authorized_senders`, and `email_filter_rules` fields to the robot member model, enhancing the configuration options for robot members.
- Updated the member creation and existence check logic to ensure the uniqueness of `robot_email` globally, improving data integrity.
- Refactored API endpoints and request/response structures to accommodate the new fields, ensuring consistency across the member management system.
- Enhanced test cases to validate the new robot member features, including scenarios for email uniqueness and configuration updates, improving overall test coverage and reliability.
- Added the is_owner field to the member model to indicate if a member is the team owner, improving clarity and performance for queries related to team ownership.
- Updated the team creation process to automatically set the is_owner field for the creator of the team, ensuring accurate member status upon creation.
- Refactored related tests to verify the correct assignment of the is_owner field, enhancing test coverage and reliability in team membership scenarios.
- Removed redundant permission and restriction fields from the member model to streamline the data structure and improve maintainability.
- Introduced member_id as a unique identifier for members, improving data integrity and consistency across member operations.
- Updated member-related functions to utilize member_id instead of internal IDs, enhancing API usability and clarity.
- Implemented email existence checks for team members, allowing for better validation during member creation and updates.
- Refactored existing tests to accommodate changes in member identification and email validation, ensuring comprehensive coverage and reliability.
- Added new API endpoint for checking if an email exists within a team, improving user experience during member management.
- Enhanced the member model by adding 'avatar' and updating 'display_name' and 'bio' fields for improved identity representation.
- Refactored robot member creation and validation to utilize the new fields, ensuring consistency across user and robot profiles.
- Updated test cases to reflect changes in member data structure, improving coverage and accuracy in robot member operations.
- Adjusted database indices and constraints to accommodate new fields and ensure efficient querying.
- Added display_name, bio, and email fields to the member model for improved team-specific identity.
- Updated team invitation creation and acceptance logic to handle new profile fields, ensuring proper data management and user experience.
- Implemented logic to copy user profile fields when creating or updating members, enhancing data consistency.
- Added role_id field to the team model for specifying team owner roles.
- Enhanced team creation logic to set default role_id based on team configuration if not provided.
- Updated tests to reflect changes in team type and role handling, ensuring accurate assertions.
- Improved documentation for team configuration to clarify default role settings for team creators.
- 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.
- Updated modification times for various asset files in bindata.go to reflect recent changes.
- Enhanced user authentication by adding support for custom claims in the context during authorization, improving flexibility in handling user data.
- Refactored entry verification logic to generate and send OTPs for user registration, streamlining the registration process and improving user experience.
- Introduced new status handling for user accounts, ensuring proper feedback for pending, unverified, and disabled accounts during login attempts.
- Added 'locale' field to user type structure for language localization.
- Updated API methods to include locale in pricing and published types retrieval.
- Enhanced tests to validate locale handling in user type operations, ensuring robust support for multiple languages.
- Updated user type structure to include new fields for pricing: price_daily, price_monthly, price_yearly, and credits_monthly.
- Added status field to manage publishing states (draft, published, archived) for user types.
- Enhanced the user type API to support pricing operations, including retrieval and updates for pricing information.
- Refactored tests to cover new pricing functionalities and ensure robust handling of user type statuses.
- Updated the UpdateUserLastLogin method to accept a LoginContext, allowing for tracking of last login IP, user agent, device, and platform.
- Modified the LoginThirdParty and LoginByUserID functions to utilize the new LoginContext, improving the accuracy of login tracking.
- Enhanced the user model to include fields for last login details, ensuring comprehensive user activity logging.
- Refactored tests to validate the new login context handling, ensuring robust coverage of the updated functionality.
- Introduced invitation_id handling for member management, allowing for unique identification of pending invitations.
- Added methods to create, update, and remove members by invitation_id, improving the invitation workflow.
- Updated member data structures and API responses to include invitation-related fields, enhancing clarity and usability.
- Implemented tests for invitation ID operations, ensuring robust validation and error handling.
- Refactored team access checks to streamline member management processes.
- Updated the member model to include a new member_type field, allowing differentiation between human and robot members.
- Added fields specific to robot members, including robot_name, robot_description, and robot_avatar, to capture essential information.
- Introduced robot configuration fields such as robot_config, agents, tools, and data_access_permissions for enhanced functionality.
- Implemented scheduling and automation features for robots, including is_active_robot, schedule_config, and activity_frequency.
- Enhanced indexing to support efficient queries for robot members and their activities, improving overall system performance.
- 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.
- Introduced field lists for job, category, execution, and log queries to streamline data retrieval.
- Updated ListJobs, GetJob, GetCategories, and ListLogs functions to utilize new field lists for improved query efficiency.
- Enhanced job creation logic to set default values for enabled status, ensuring new jobs are active by default.
- Added category name resolution in job retrieval, enriching job data with associated category names.
- Improved error handling and logging throughout job and category management processes for better traceability.
- Introduced unique ID generation for jobs, categories, and executions using gonanoid, improving ID handling and reducing collisions.
- Updated SaveJob and SaveCategory functions to utilize new ID generation methods, ensuring consistent and unique identifiers.
- Enhanced job creation logic to allow for category name handling, enabling automatic category ID assignment based on provided names.
- Refactored ensureCategoryExists to check for existing categories by name, streamlining category management during job operations.
- Improved error handling and logging for ID generation and category retrieval processes, ensuring better traceability and reliability.
- Implemented execution options to allow priority settings and shared data for job executions.
- Introduced new execution types for processes and commands, improving flexibility in job handling.
- Updated job and execution models to include new fields for execution options and priority.
- Refactored job submission logic to support context-aware execution, enhancing error handling and process management.
- Improved test coverage for job execution scenarios, ensuring robust validation of new features.
- Added new job management functions: Once, Cron, and Daemon for creating jobs with different scheduling types.
- Introduced methods for job manipulation, including Start, Cancel, and various setters for job properties.
- Updated job model to reflect changes in the job execution process type, renaming "process_type" to "mode" and adjusting enum values to uppercase.
- Removed obsolete interfaces and types related to job management, streamlining the codebase.
- 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.
- Introduced readonly field for collections and documents to indicate if they are read-only.
- Updated ListCollections endpoint to support pagination and filtering by various parameters, including keywords, status, and system flags.
- Enhanced query capabilities with dynamic field selection and sorting options for collections.
- Refactored GetCollections to ListCollections for improved clarity in functionality.
- Updated API response structures to reflect new filtering and sorting features, ensuring better data access and management.
- Added GetCollection endpoint to retrieve collections by ID, including error handling for missing IDs and uninitialized knowledge base.
- Updated CreateCollectionConfig to use more descriptive field names for embedding provider and option IDs.
- Refactored UpdateSegments function to improve validation and error handling, ensuring document IDs and segment texts are properly checked.
- Introduced new request structures for updating votes, scores, and weights for segments, enhancing the API's capabilities.
- Removed the outdated vote handling file to streamline the codebase.
- Introduced `file_id` field in the document model to link documents with their corresponding files in the attachment system.
- Updated `AddFileProcess` to include `file_id` in the response, improving document tracking.
- Modified `GetDocument` function to support the new `file_id` field in document retrieval.
- Removed the unused `ScrollDocuments` endpoint to streamline the API.
- Improved error handling and response structure for document-related operations.
- Updated modification timestamps for various asset files to reflect recent changes.
- Modified chunking options to include new parameters: Separator and EnableDebug, with default values set.
- Enhanced the Options method in Structured and Semantic providers to handle additional properties from the option map, improving flexibility in configuration.
- Added new fields in the document model for converter and fetcher option IDs, allowing for better integration with provider configurations.
- Renamed extractor provider to extraction provider across the codebase for consistency and clarity.
- Updated references in configuration files, provider factories, and asset management to reflect the new terminology.
- Removed the extractor provider implementation and associated test files, streamlining the provider structure.
- Adjusted test cases and documentation to align with the new extraction provider framework.
- Updated modification timestamps for various asset files to reflect recent changes.
- Added support for "application/octet-stream" MIME type in the attachment.local.yao file to enhance file upload capabilities.
