- Deleted the old ReasoningCache class and its instance.
- Introduced CacheService for managing reasoning caches.
- Updated unified-messages service to utilize new googleReasoningCache and openRouterReasoningCache.
- Added AiSdkToAnthropicSSE adapter to handle streaming events and integrate with new cache service.
- Reorganized shared adapters to include the new AiSdkToAnthropicSSE adapter.
- Created openrouter adapter with detailed reasoning schemas for better type safety and validation.
- Updated reasoning cache to use tool-specific keys for better organization.
- Added methods to list cache keys and entries.
- Improved API version regex patterns for more accurate matching.
- Refactored API host formatting to handle leading/trailing whitespace and slashes.
- Added functions to extract and remove trailing API version segments from URLs.
- Fix tool result content bug: return `values` array instead of empty array
- Fix empty message bug: skip pushing user/assistant messages when content is empty
- Expand provider support: remove type restrictions to support all AI SDK providers
- Add missing alias for @cherrystudio/ai-sdk-provider in main process config
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Added provider API host formatting utilities to handle differences between Cherry Studio and AI SDK.
- Introduced functions for formatting provider API hosts, including support for Azure OpenAI and Vertex AI.
- Created a simple API key rotator for managing API key rotation.
- Developed shared provider initialization and mapping utilities for resolving provider IDs.
- Implemented AI SDK configuration utilities for converting Cherry Studio providers to AI SDK configurations.
- Added support for various providers including OpenRouter, Google Vertex AI, and Amazon Bedrock.
- Enhanced error handling and logging in the unified messages service for better debugging.
- Introduced functions for streaming and generating unified messages using AI SDK.
* build: replace openai package with @cherrystudio/openai
Update all imports from 'openai' to '@cherrystudio/openai' and remove the yarn patch
* refactor(OpenAIResponseAPIClient): simplify token estimation logic for function call output
Consolidate token estimation by first concatenating all output parts into a single string before counting tokens. This improves maintainability and handles additional output types consistently.
* Revert "fix: make anthropic model provided by cherryin visible to agent (#10695)"
This reverts commit 7b3b73d390.
* fix: agent supported model filter
- Unify buildClaudeCodeSystemMessage implementation in shared package
- Refactor MessagesService to provide comprehensive message processing API
- Extract streaming logic, error handling, and header preparation into service methods
- Remove duplicate anthropic config from renderer, use shared implementation
- Update ClaudeCodeService to use append mode for custom instructions
- Improve type safety and request validation in message processing
- Add support for anthropicApiHost configuration in providers
- Improve model filtering for Anthropic-compatible providers
- Add isAnthropicModel function to validate Anthropic models
- Update ClaudeCode service to support compatible providers
- Enhance logging and error handling in API routes
- Fix model transformation and validation logic
- Updated logging statements across various modules to provide more structured and detailed information.
- Changed log levels from info to debug for less critical messages to reduce log clutter.
- Enhanced error logging to include relevant context such as agentId, sessionId, and model details.
- Standardized log messages to follow a consistent format, improving readability and maintainability.
- Add MCP server configuration UI for agent settings
- Update agent and session forms to include MCP server selection
- Fix MCP API service logging and tools handling
- Add Chinese localization for MCP settings
- Update type definitions to support MCP server arrays
This enables agents to use MCP (Model Control Protocol) servers
as additional tools and capabilities in their execution context.
- Rename built_in_tools field to tools for consistency
- Add type field to Tool schema (builtin/mcp/custom)
- Consolidate tool handling in BaseService with listMcpTools method
- Remove unused CreateSessionResponse and related schemas
- Clean up unused imports and dead code in session handlers
- Unify agent and session tool resolution logic
- Add shared Anthropic utilities package with OAuth and API key client creation
- Implement provider-specific message routing alongside existing v1 API
- Enhance authentication middleware with priority handling (API key > Bearer token)
- Add comprehensive auth middleware test suite with timing attack protection
- Update session handling and message transformation for Claude Code integration
- Improve error handling and validation across message processing pipeline
- Standardize import formatting and code structure across affected modules
This establishes the foundation for Claude Code OAuth authentication while maintaining
backward compatibility with existing API key authentication methods.
- Extract getServersFromRedux to shared utility getMCPServersFromRedux
- Implement 5-minute TTL cache for MCP servers and providers
- Reduce redundant Redux store queries in API server
- Improve response times for frequently accessed data
* feat: add api server
This reverts commit c76aa03566.
* update yarn.lock
* fix: correct import paths in ToolSettings component
Update import paths for PreprocessSettings and WebSearchSettings to reference correct locations in DocProcessSettings and WebSearchSettings directories.
* feat(settings): add API server settings link and route
* fix(auth): improve authorization handling and error responses
* feat(chat): enhance model validation and logging for chat completions
feat(models): improve logging for model retrieval and filtering
feat(utils): add model ID validation and support for OpenAI providers
* feat(api-server): refactor config loading and remove unused ToolSettings component
* refactor(ApiServerService): simplify config retrieval and improve error handling in ApiServerSettings
* fix(mcp): remove unnecessary await in listTools return statement
* refactor(ApiServerSettings): replace window.message with window.toast for notifications
---------
Co-authored-by: kangfenmao <kangfenmao@qq.com>
