- Updated `tsconfig.web.json` to support wildcard imports for `@cherrystudio/ai-core`.
- Enhanced `package.json` to include type definitions and imports for built-in plugins.
- Introduced recursive call functionality in `PluginManager` and `PluginEngine`, allowing for improved handling of tool interactions.
- Added `MCPPromptPlugin` to facilitate tool calls within prompts, enabling recursive processing of tool results.
- Refactored `transformStream` methods across plugins to accommodate new parameters and improve type safety.
- Changed `pluginClient` to `pluginEngine` in `RuntimeExecutor` for clarity and consistency.
- Updated method calls in `RuntimeExecutor` to use the new `pluginEngine`.
- Enhanced `AiSdkMiddlewareBuilder` to include `mcpTools` in the middleware configuration.
- Added `MCPPromptPlugin` to support tool calls within prompts, enabling recursive processing and improved handling of tool interactions.
- Updated `ApiService` to pass `mcpTools` during chat completion requests, enhancing integration with the new plugin system.
- Introduced `reasonPlugin` and `textPlugin` to improve chunk processing and handling of reasoning content.
- Updated `transformStream` method signatures for better type safety and usability.
- Enhanced `ThinkingTimeMiddleware` to accurately track thinking time using `performance.now()`.
- Refactored `ThinkingBlock` component to utilize block thinking time directly, improving performance and clarity.
- Added logging for middleware builder to assist in debugging and monitoring middleware configurations.
- Introduced new high-level APIs for model creation and configuration, improving usability for advanced users.
- Enhanced the RuntimeExecutor to support both direct model usage and model ID resolution, allowing for more flexible execution options.
- Updated existing methods to accept middleware configurations, streamlining the integration of custom processing logic.
- Refactored the plugin system to better accommodate middleware, enhancing the overall extensibility of the AI Core.
- Improved documentation to reflect the new capabilities and usage patterns for the runtime APIs.
- Restructured the AI Core documentation to reflect a simplified two-layer architecture, focusing on clear responsibilities between models and runtime layers.
- Removed the orchestration layer and consolidated its functionality into the runtime layer, streamlining the API for users.
- Introduced a new runtime executor for managing plugin-enhanced AI calls, improving the handling of execution and middleware.
- Updated the core modules to enhance type safety and usability, including comprehensive type definitions for model creation and execution configurations.
- Removed obsolete files and refactored existing code to improve organization and maintainability across the SDK.
- Updated the AI Core documentation to reflect the new architecture and design principles, emphasizing modularity and type safety.
- Refactored the client structure by removing obsolete files and consolidating client creation logic into a more streamlined format.
- Introduced a new core module for managing execution and middleware, improving the overall organization of the codebase.
- Enhanced the orchestration layer to provide a clearer API for users, integrating the creation and execution processes more effectively.
- Added comprehensive type definitions and utility functions for better type safety and usability across the SDK.
- Updated getAiSdkProviderId function to include mapping for provider types, improving compatibility with third-party SDKs.
- Refined return logic to ensure correct provider ID resolution, enhancing overall functionality and support for various providers.
- Introduced ToolCallChunkHandler for managing tool call events and results, improving the handling of tool interactions.
- Updated AiSdkToChunkAdapter to utilize the new handler, streamlining the processing of tool call chunks.
- Refactored transformParameters to support dynamic tool integration and improved parameter handling.
- Adjusted provider mapping in factory.ts to include new provider types, enhancing compatibility with various AI services.
- Removed obsolete cherryStudioTransformPlugin to clean up the codebase and focus on more relevant functionality.
- Updated providerToAiSdkConfig to support both OpenAI and Anthropic providers, improving flexibility in API host formatting.
- Refactored thinkingTimeMiddleware to ensure all chunks are correctly enqueued, enhancing middleware functionality.
- Corrected parameter naming in getAnthropicReasoningParams for consistency and clarity in configuration.
- Introduced a new OpenAI Compatible provider to the AiProviderRegistry, allowing for integration with the @ai-sdk/openai-compatible package.
- Updated provider configuration logic to support the new provider, including adjustments to API host formatting and options management.
- Refactored middleware to streamline handling of OpenAI-specific configurations.
- Introduced a patch for the @ai-sdk/google-vertex package to improve URL handling based on region.
- Added a new utility function to format private keys, ensuring correct PEM structure and validation.
- Updated the ProviderConfigBuilder to utilize the new private key formatting function for Google credentials.
- Created a pnpm workspace configuration to manage patched dependencies effectively.
- Introduced new utility functions for creating and merging provider options, improving type safety and usability.
- Added comprehensive examples for OpenAI, Anthropic, Google, and generic provider options to demonstrate usage.
- Refactored existing code to streamline provider configuration and enhance clarity in the options management.
- Updated the PluginEnabledAiClient to simplify the handling of model parameters and improve overall functionality.
- Added support for Google Vertex AI credentials in the provider configuration.
- Refactored the VertexAPIClient to handle both standard and VertexProvider types.
- Implemented utility functions to check Vertex AI configuration completeness and create VertexProvider instances.
- Updated provider mapping in index_new.ts to ensure proper handling of Vertex AI settings.
- Introduced the @ai-sdk/openai-compatible package to support compatibility with OpenAI.
- Added a new ProviderConfigFactory and ProviderConfigBuilder for streamlined provider configuration.
- Updated the provider registry to include the new Google Vertex AI import path.
- Enhanced the index.ts to export new provider configuration utilities for better type safety and usability.
- Refactored ApiService and middleware to integrate the new provider configurations effectively.
- Added detailed usage examples for the native provider registry in the README.md, demonstrating how to create and utilize custom provider registries.
- Updated ApiClientFactory to enforce type safety for model instances.
- Refactored PluginEnabledAiClient methods to support both built-in logic and custom registry usage for text and object generation, improving flexibility and usability.
- Changed the type of options in ClientConfig to 'any' for flexibility.
- Overloaded createImageClient method to support different provider settings.
- Added vertexai mapping to the provider type mapping in index_new.ts for enhanced compatibility.
- Updated PluginEnabledAiClient to streamline the handling of experimental_transform parameters.
- Adjusted ModernAiProvider's smoothStream configuration for better chunking of text, enhancing processing efficiency.
- Re-enabled block updates in messageThunk for improved state management.
- Introduced cherryStudioTransformPlugin for converting Cherry Studio messages to AI SDK format, enhancing compatibility.
- Added cherryStudioSettingsPlugin to manage Assistant settings like temperature and TopP.
- Implemented createCherryStudioContext function for preparing context metadata for Cherry Studio calls.
- Modified convertAndEmitChunk method to handle new chunk types and streamline processing.
- Adjusted thinkingTimeMiddleware to remove unnecessary parameters and enhance clarity.
- Updated middleware integration in AiSdkMiddlewareBuilder for better middleware management.
- Added detailed usage examples for the native provider registry in the README.md, demonstrating how to create and utilize custom provider registries.
- Updated ApiClientFactory to enforce type safety for model instances.
- Refactored PluginEnabledAiClient methods to support both built-in logic and custom registry usage for text and object generation, improving flexibility and usability.
- Added smoothStream to the middleware exports in index.ts for improved streaming capabilities.
- Updated PluginEnabledAiClient to conditionally apply middlewares, removing the default simulateStreamingMiddleware.
- Modified ModernAiProvider to utilize smoothStream in streamText, enhancing text processing with configurable chunking and delay options.
- Added AiSdkMiddlewareBuilder for dynamic middleware construction based on various conditions.
- Updated ModernAiProvider to utilize new middleware configuration, improving flexibility in handling completions.
- Refactored ApiService to pass middleware configuration during AI completions, enabling better control over processing.
- Introduced new README documentation for the middleware builder, outlining usage and supported conditions.
feat: 为插件系统实现中间件
feat: 实现自定义的思考中间件
- Updated package.json and related files to reflect the correct naming convention for the @cherrystudio/ai-core package.
- Adjusted import paths in various files to ensure consistency with the new package name.
- Enhanced type resolution in tsconfig.web.json to align with the updated package structure.
- Added @cherry-studio/ai-core as a workspace dependency in package.json for improved modularity.
- Updated tsconfig to include paths for the new AI core package, enhancing type resolution.
- Refactored aiCore package to use source files directly, improving build efficiency.
- Introduced a new AiSdkToChunkAdapter for converting AI SDK streams to Cherry Studio chunk format.
- Implemented a modernized AI provider interface in index_new.ts, allowing fallback to legacy implementations.
- Enhanced parameter transformation logic for better integration with AI SDK features.
- Updated ApiService to utilize the new AI provider, streamlining chat completion requests.
- Introduced `PluginEnabledAiClient` for a more flexible client interface with integrated plugin support.
- Updated `ApiClientFactory` and `UniversalAiSdkClient` to utilize new provider settings for improved type safety.
- Added a comprehensive plugin management system, allowing for dynamic plugin registration and execution.
- Enhanced the provider registry to include new AI providers and updated existing provider settings.
- Removed deprecated files and streamlined the codebase for better maintainability and clarity.
- Updated documentation to reflect new features and usage examples for the plugin system.
- Introduced `createImageClient` method in `ApiClientFactory` to support image generation for various providers.
- Updated `UniversalAiSdkClient` to include `generateImage` method, allowing image generation through the unified client interface.
- Refactored client creation functions to utilize the new `ProviderOptions` type for improved type safety.
- Enhanced the provider registry to indicate which providers support image generation, streamlining client creation and usage.
- Updated type definitions in `types.ts` to reflect changes in client options and middleware support.
- Introduced a plugin system in the AI Core package, allowing for flexible request handling and middleware integration.
- Added support for various hook types: First, Sequential, Parallel, and Stream, enabling developers to customize request processing.
- Implemented a PluginManager for managing and executing plugins, enhancing extensibility and modularity.
- Updated architecture documentation to reflect new plugin capabilities and usage examples.
- Included new middleware types and examples to demonstrate the plugin system's functionality.
This update aims to improve the developer experience by providing a robust framework for extending AI Core's capabilities.
- Added a new package `@cherry-studio/ai-core` that provides a unified interface for various AI providers based on the Vercel AI SDK.
- Implemented core components including `ApiClientFactory`, `UniversalAiSdkClient`, and a provider registry for dynamic imports.
- Included TypeScript support and a lightweight design for improved developer experience.
- Documented architecture and usage examples in `AI_SDK_ARCHITECTURE.md` and `README.md`.
- Updated `package.json` to include dependencies for supported AI providers.
This package aims to streamline the integration of multiple AI providers while ensuring type safety and modularity.
- Removed unused MCP server handling from Inputbar and MessagesService.
- Updated ApiService to fetch active MCP servers directly from the store.
- Deprecated knowledgeBaseIds and enabledMCPs in Message types and related functions.
- Cleaned up related utility functions to enhance code clarity and maintainability.
* fix: openai response tool use
- Added OpenAIResponseStreamListener interface for handling OpenAI response streams.
- Implemented attachRawStreamListener method in OpenAIResponseAPIClient to manage raw output.
- Updated RawStreamListenerMiddleware to integrate OpenAI response handling.
- Refactored BaseApiClient to remove unused attachRawStreamListener method.
- Improved buildSdkMessages to handle OpenAI response formats.
* fix: remove logging from StreamAdapterMiddleware
- Removed Logger.info call from StreamAdapterMiddleware to streamline output and reduce unnecessary logging.
* fix: update attachRawStreamListener to return a Promise
- Changed attachRawStreamListener method in OpenAIResponseAPIClient to be asynchronous, returning a Promise for better handling of raw output.
- Updated RawStreamListenerMiddleware to await the result of attachRawStreamListener, ensuring proper flow of data handling.
* refactor: enhance attachRawStreamListener to return a ReadableStream
- Updated the attachRawStreamListener method in OpenAIResponseAPIClient to return a ReadableStream, allowing for more efficient handling of streamed responses.
- Modified RawStreamListenerMiddleware to accommodate the new return type, ensuring proper integration of the transformed stream into the middleware flow.
* refactor: update getResponseChunkTransformer to accept CompletionsContext
- Modified the getResponseChunkTransformer method in BaseApiClient and its implementations to accept a CompletionsContext parameter, enhancing the flexibility of response handling.
- Adjusted related middleware and client classes to ensure compatibility with the new method signature, improving the overall integration of response transformations.
* refactor: update getResponseChunkTransformer to accept CompletionsContext
- Modified the getResponseChunkTransformer method in AihubmixAPIClient to accept a CompletionsContext parameter, enhancing the flexibility of response handling.
- Ensured compatibility with the updated method signature across related client classes.
- Added error handling for tool fetching to log errors and return an empty array if a server fails to respond.
- Changed from Promise.all to Promise.allSettled to ensure all tool fetching attempts are accounted for, filtering out any rejected promises.
- Added debug logging in buildSdkMessages for better traceability.
- Improved handling of tool calls in the transform method to correctly index multiple tool uses.
- Enqueued additional response types to enhance the output structure for better integration with the streaming API.
- Refactored event listener attachment for clarity and maintainability.
* fix: series bugs of quick assistant
* fix: update quick assistant ID handling and improve error management in HomeWindow
* refactor(HomeWindow, Messages): streamline clipboard handling and improve component structure
- Removed unused imports and hotkey functionality from Messages component.
- Refactored clipboard management in HomeWindow to use refs for better performance.
- Enhanced user input handling and state management in HomeWindow.
- Updated InputBar to accept assistant prop instead of model for better clarity.
- Improved Footer component to handle copy functionality and pin state more effectively.
* Enhance Footer component: add rotation animation to pin icon and adjust margin
- Updated the Pin icon in the Footer component to include a rotation animation based on the pin state.
- Adjusted the margin of the PinButtonArea for improved layout consistency.
* refactor(HomeWindow): improve clipboard handling and input placeholder logic
- Updated clipboard reading logic to check for document focus in addition to startup settings.
- Consolidated key event handling to streamline input processing.
- Enhanced placeholder logic in InputBar to reflect the current assistant's name or model more accurately.
* fix: initialize messageContents and improve message handling in GeminiAPIClient; add new Gemini model to configuration
* refactor: streamline message handling in GeminiAPIClient; enhance message extraction from SDK payload
