- Added a new GeneralSetting struct to manage configurable docs link
- Removed hardcoded ChatLink and ChatLink2 variables across multiple files
- Updated frontend components to dynamically render docs link from status
- Simplified chat and link-related logic in various components
- Added a warning modal for quota per unit setting in operation settings
- Introduce `SelfUseModeEnabled` setting to allow flexible model ratio configuration
- Update error handling to provide more informative messages when model ratios are not set
- Modify pricing and relay logic to support self-use mode
- Add UI toggle for enabling self-use mode in operation settings
- Implement fallback mechanism for model ratios when self-use mode is enabled
- Update error message for missing model ratio to be more user-friendly
- Modify ModelRatioNotSetEditor to filter models without price or ratio
- Enhance model data initialization with fallback values
- Implement `/api/channel/models_enabled` endpoint to retrieve enabled models
- Add `EnabledListModels` handler in controller
- Create new `ModelRatioNotSetEditor` component for managing unset model ratios
- Update router to include new models_enabled route
- Add internationalization support for new model management UI
- Include GPT-4.5 preview model in OpenAI model list
- Replace ThinkingAdapterMaxTokens with a more flexible DefaultMaxTokens map
- Add support for model-specific default max tokens configuration
- Update relay and web interface to use the new configuration approach
- Implement a fallback mechanism for default max tokens
- Update Claude relay to set default MaxTokens dynamically
- Modify web interface to clarify default MaxTokens input purpose
- Improve token configuration logic for thinking adapter models
- Introduce a new configuration management approach for model-specific settings
- Update Gemini settings to use the new config system with more flexible management
- Add support for dynamic configuration updates in option handling
- Modify Claude and Vertex adaptors to use new configuration methods
- Enhance web interface to support namespaced configuration keys
- Enhance channel test to detect more embedding models
- Update Azure OpenAI default API version to 2024-12-01-preview
- Remove redundant default API version setting in channel edit
- Add user cache writing in channel test
- Introduce AutomaticDisableKeywords setting to dynamically control channel disabling
- Implement AC search for matching error messages against disable keywords
- Add frontend UI for configuring automatic disable keywords
- Update localization with new keyword-based channel disabling feature
- Refactor sensitive word and AC search logic to support multiple keyword lists
- Updated GetAllUsers function to return total user count along with paginated results, improving data handling in user retrieval.
- Modified GetAllUsers API endpoint to accept page size as a parameter, allowing for dynamic pagination.
- Enhanced UsersTable component to support customizable page sizes and improved pagination logic.
- Added error handling for empty username and password in AddUser component.
- Updated LogsTable component to display pagination information in a user-friendly format.
- Changed the structure of usableGroups in GetUserGroups to store additional information (ratio and description) for each group.
- Introduced a new renderRatio function to visually represent group ratios with color coding.
- Updated the Playground and EditToken components to utilize the new group structure and rendering options.
- Enhanced the renderGroupOption function for better UI representation of group options.
- Fixed minor comments and improved code readability.
- Added input validation to ensure that the `num` parameter in `renderQuotaNumberWithDigit` is a valid number, returning 0 for invalid inputs.
- Updated the `Detail` component to use `datum['rawQuota']` instead of `datum['Usage']` for rendering quota values, ensuring more accurate data representation.
- Enhanced data aggregation logic to handle cases where quota values may be missing or invalid, improving overall data integrity in charts and tables.
- Removed unnecessary time granularity calculations and streamlined the data processing for better performance.
- Added new translation keys for English localization in `en.json`, including "Token group, default is the your's group" and "IP whitelist (do not overly trust this function)".
- Refactored `EditToken.js` to utilize the `useTranslation` hook for improved internationalization, ensuring all user-facing strings are translatable.
- Updated error and success messages to use translation functions, enhancing user experience for non-English speakers.
- Improved UI elements to support localization, including labels, placeholders, and button texts, ensuring consistency across the token editing interface.
- Introduced a new `FetchModels` endpoint to retrieve model IDs from a specified base URL and API key, enhancing flexibility for different channel types.
- Refactored `FetchUpstreamModels` to simplify base URL handling and improve error messages during response parsing.
- Updated API routes to include the new endpoint and adjusted the frontend to utilize the new fetch mechanism for model lists.
- Removed outdated checks for channel type in the frontend, streamlining the model fetching process.
