- Enhanced the model resolution logic to support dynamic provider IDs for chat modes.
- Updated provider registration to handle both OpenAI and Azure with a unified approach for chat variants.
- Refactored the `buildOpenAIProviderOptions` function to streamline parameter handling and removed unnecessary parameters.
- Added configuration options for Azure to manage API versions and deployment URLs effectively.
- Commented out unused parameters and code in the KnowledgeSearchTool to improve clarity and maintainability.
- Removed the tool choice assignment in searchOrchestrationPlugin to streamline the logic.
- Updated instructions handling in KnowledgeSearchTool to eliminate unnecessary fields.
- Updated `getTemperature` and `getTopP` functions to incorporate reasoning effort checks for Claude models.
- Refactored logic to ensure temperature and TopP settings are only returned when applicable.
- Improved clarity and maintainability of parameter retrieval functions.
- Simplified the OpenAI mode handling in the provider configuration.
- Added service tier settings to provider-specific options for better configuration management.
- Refactored the `buildOpenAIProviderOptions` function to remove redundant parameters and improve clarity.
- Added a new provider configuration module to handle special provider logic and formatting.
- Implemented asynchronous preparation of special provider configurations in the ModernAiProvider class.
- Refactored provider initialization logic to support dynamic registration of new AI providers.
- Updated utility functions to streamline provider option building and improve compatibility with new provider configurations.
- Bumped the version of the ai-core package to 1.0.0-alpha.11.
- Removed the `isOpenAIChatCompletionOnlyModel` utility function to simplify model resolution.
- Adjusted the `providerToAiSdkConfig` function to accept a model parameter for improved configuration handling.
- Updated the `ModernAiProvider` class to utilize the new model parameter in its configuration.
- Cleaned up deprecated code related to search keyword extraction and reasoning parameters.
- Updated the ErrorBlock component to include a centered modal for displaying error details, enhancing the user interface and accessibility of error information.
- Introduced a check for developer mode in the completions methods to enable tracing capabilities when a topic ID is provided.
- Updated the method signatures and internal calls to streamline the handling of completions with and without tracing.
- Improved code organization by making the completionsForTrace method private and renaming it for clarity.
- Updated the Inputbar component to include the `isPromptToolUse` function, allowing for better visibility of MCP tools based on the assistant's capabilities.
- This change improves user experience by expanding the conditions under which MCP tools are displayed.
- Added new translation keys for error details in multiple languages, including 'detail', 'details', 'message', 'requestBody', 'requestUrl', 'stack', and 'status'.
- Updated the ErrorBlock component to display a modal with detailed error information, allowing users to view and copy error details easily.
- Improved the user experience by providing a clear and accessible way to understand error messages and their context.
- Updated the error handling in the `onError` callback to use `AISDKError` type for better type safety.
- Introduced a new `serializeError` function to standardize error serialization.
- Modified the `ErrorBlock` component to directly access the error message.
- Removed deprecated error formatting functions to streamline the error utility module.
Updated the ModelResolver and related components to use '|' as the default separator instead of ':'. This change improves compatibility and resolves potential conflicts with model ID suffixes. Adjusted model resolution logic accordingly to ensure consistent behavior across the application.
* feat: add batch delete functionality for files page
- Add batch selection with checkboxes for individual files
- Implement batch delete operation with confirmation dialog
- Add select all/none functionality with indeterminate state
- Include safety check to prevent deleting files used in paintings
- Support multiple languages for batch operation UI text
- Exclude image files from batch operations per design requirements
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* style: make batch delete popconfirm icon color consistent
- Add red color styling to batch delete popconfirm icon to match individual delete
- Update i18n translations for batch warning message across all locales
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: improve batch delete UX and i18n translations
- Change "batch_operation" label to "Select All" across all languages
- Remove unused batch_warning translation for paintings
- Simplify delete confirmation messages to use single form
- Optimize batch delete to use Promise.all for better performance
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Integrated a new AI SDK architecture for better performance
- Added OCR functionality for image text recognition
- Introduced a code tools page with environment variable settings
- Enhanced the MCP server list with search capabilities
- Improved SVG preview and HTML content rendering
- Fixed multiple issues including document preprocessing failures and path handling on Windows
- Optimized performance and memory usage across various components
* fix: not using system default terminal on deepin
deepin-terminal is not in the `linuxTerminals` list, that will
cause xterm picked as the terminal to run code tool, which has
compatibility with Chinese charaters.
see: https://bbs.deepin.org.cn/post/290948
Signed-off-by: Hualet Wang <mr.asianwang@gmail.com>
* feat(codetool): add support for deepin-terminal
---------
Signed-off-by: Hualet Wang <mr.asianwang@gmail.com>
Co-authored-by: GeorgeDong32 <GeorgeDong32@qq.com>
Removed unused type exports from the aiCore module and consolidated type definitions for better clarity. Updated provider registration tests to reflect new configurations and improved error handling for non-existent providers. Enhanced the overall structure of the provider management system, ensuring better type safety and consistency across the codebase.
