Releases: xiaoY233/Chat2API
Releases · xiaoY233/Chat2API
Chat2API v1.4.0
🎉 Major Features
Managed Tool Calling Redesign
- OpenAI-compatible tool calling: Added a shared tool-calling engine for OpenAI-style tools, Cherry Studio MCP payloads, and managed tool prompts.
- Multiple protocol parsers: Added support for managed XML, managed bracket syntax, Anthropic-style tool use, and Codex Responses-style payloads.
- Streaming tool-call parsing: Added stream parsing for tool-call chunks so compatible clients can receive tool-call deltas more reliably.
- Runtime planning and diagnostics: Added provider profiles, tool-choice policy handling, runtime plan generation, and management API diagnostics for tool-calling behavior.
In-app Update Flow
- Updater manager integration: Update checks now go through the updater manager instead of ad hoc renderer logic.
- Renderer update status: Exposed updater status through preload and renderer APIs.
- Update UI states: The About page now reflects update checking, download, progress, install, and error states from updater events.
- Runtime app version display: The About page now reads the packaged app version instead of showing a hard-coded fallback.
Provider Model Refresh
- Website-aligned model catalogs: Refreshed default provider model lists from current web/API behavior.
- qwen-ai curated defaults: qwen-ai now keeps a curated default set while documenting the remaining website-supported models for manual addition.
- Provider documentation: Added per-provider docs to make future provider feature adaptation and user model-management workflows easier.
🚀 Enhancements
Provider Improvements
- GLM: Default model updated to GLM-5.1 with actual model id
glm-5.1. - Kimi: Removed stale Kimi-2.5 default and kept Kimi-2.6 aligned with the website.
- MiniMax: Removed stale MiniMax-M2.5 default and kept MiniMax-M2.7 aligned with the website.
- Qwen: Updated website-model defaults, including the Qwen3.6 display-name cleanup.
- qwen-ai: Updated default supported models from captured website/API behavior and documented additional official models for manual configuration.
- Z.ai: Refreshed default supported models from the latest captured web model list.
- DeepSeek: Improved web-mode support, search text handling, persisted model migration, and model mapping behavior.
- Perplexity: Updated documentation to list only the Free-user Auto model in the supported provider table.
Session and Proxy Behavior
- Kimi chat cleanup: Added provider-side session deletion support for Kimi.
- Qwen chat cleanup: Added provider-side session deletion support for Qwen.
- Provider dispatch cleanup: Simplified provider dispatch and adapter loading paths.
- Model mapping workflow: Improved model mapping form controls and synchronized provider selection when choosing mapped models.
- Proxy address display: Fixed the header proxy badge so it reflects the configured bind address instead of always showing
127.0.0.1.
Runtime and Maintenance
- Standalone app logs: Added standalone application log storage with dedicated manager/types and renderer store integration.
- Source artifact checks: Added build-time checks to prevent unwanted source artifacts from leaking into packaged output.
- Dashboard/log updates: Updated dashboard chart and log-store behavior to work with the new logging surface.
🐛 Bug Fixes
- Fixed DeepSeek web-mode compatibility and preserved search text behavior.
- Fixed persisted DeepSeek model migration for existing installations.
- Fixed built-in model mapping defaults and provider synchronization after selecting mapped models.
- Fixed update UI state wiring and repaired update page state syntax.
- Fixed About page version display so packaged builds show the actual application version.
- Fixed proxy header address display after changing the bind address.
📚 Documentation
- Added provider guides under
docs/providers/for DeepSeek, GLM, Kimi, Mimo, MiniMax, Perplexity, Qwen, qwen-ai, and Z.ai. - Updated README and README_CN Supported Providers model tables.
- Added design and implementation notes for the in-app update flow.
- Added design and implementation notes for Chat2API tool-testing workflows.
- Documented tool configuration restore usage for local testing.
🧪 Testing and Tooling
- Added Chat2API testing skills for:
- HAR tool fixture extraction
- Management API checks
- Provider model matrix runs
- OpenAI-compatible client replay
- Proxy behavior validation
- Added regression tests for:
- Tool-calling engine, parser, stream parser, runtime plan, provider profiles, and tool-choice policy
- Tool-calling management API and settings UI
- DeepSeek stream handling and provider flow behavior
- Header proxy address display
- App log manager behavior
- Source artifact checks
- In-app update flow wiring
📦 Technical Details
Files Changed
- 124 files changed
- 10,617 lines added
- 1,649 lines removed
Release Artifacts
- macOS arm64/x64 DMG packages
- macOS x64 ZIP package
- Windows x64 installer and portable package
- Linux x64/arm64 AppImage packages
- Linux x64 tarball
- Debian amd64 package
- Auto-update metadata files for macOS, Windows, and Linux
🔄 Migration Notes
- Existing users should restart the app after upgrading so refreshed built-in provider model defaults can be synchronized into persisted provider settings.
- Users with custom qwen-ai models can keep using Provider Management / Model Management to add models that are supported by the website but not included in the curated default list.
- Provider-side chat cleanup is now available for Kimi and Qwen when Chat2API sessions are cleared.
✅ Verification
npm run prebuild:checknpm run buildnode --test tests/updater/in-app-update-flow.test.ts tests/providers/provider-flow.test.ts tests/tool-calling/*.test.ts- Release workflow completed successfully for macOS arm64/x64, Windows x64, and Linux x64/arm64.
📝 Full Changelog
See v1.3.0...v1.4.0
Installation: Download the appropriate package for your platform from the assets below.
macOS Users: If you encounter "App is damaged and can't be opened", run:
sudo xattr -rd com.apple.quarantine "/Applications/Chat2API.app"Chat2API v1.3.0
Highlights
- Redesigned request log persistence to use standalone NDJSON storage with migration, retention limits, buffered writes, and sanitization controls.
- Reduced request log I/O and fixed session cleanup behavior.
- Added and validated provider model flow updates, including DeepSeek V4 Pro / V4 Flash compatibility and Kimi K2.6 request payload behavior.
- Added DeepSeek Expert model mapping support.
- Fixed language preference persistence across app restarts.
- Added GitHub issue templates and repository guidance for future maintenance.
Verification
npm run buildnode --test tests/request-logs/request-log-manager.test.ts tests/request-logs/request-log-sanitizer.test.ts tests/providers/provider-flow.test.ts
Chat2API v1.2.0
🎉 Major Features
Automatic Application Update System
- One-click update: Check, download, and install updates seamlessly within the app
- Real-time progress tracking: Monitor download progress with speed, size, and percentage
- Automatic installation: Restart and install updates with a single click
- Comprehensive error handling: Graceful error recovery with retry functionality
- Multi-language support: Update UI available in both Chinese and English
Custom Model Management
- Add custom models: Define and add custom models for any provider
- Remove models: Easily remove unwanted models from the list
- Reset to defaults: Restore default model configurations with one click
- Dynamic updates: Models are updated dynamically without app restart
New Provider: Mimo
- Full support: Complete integration with Mimo AI provider
- Thinking mode: Enhanced thinking mode parsing for Mimo models
- Stream handling: Optimized stream response handling
🚀 Enhancements
Provider Improvements
- Multi-provider chat deletion: Delete chats across multiple providers simultaneously
- Kimi thinking mode: Enhanced thinking mode support for Kimi provider
- MiniMax stream handling: Fixed stream handling issues for MiniMax provider
- Dynamic model updates: Providers can now update their model lists dynamically
Architecture Optimization
- Major refactoring: Significant architecture improvements for better maintainability
- Stateless session management: Refactored to stateless single-turn mode
- Tool calls handling: Improved and refactored tool calls forwarding logic
Documentation
- Code Wiki: Generated comprehensive project Code Wiki documentation
- README updates: Updated screenshots and feature descriptions
- Better formatting: Fixed image links and table formatting in documentation
🐛 Bug Fixes
- Fixed Mimo thinking mode parsing issues
- Resolved MiniMax stream handling problems
- Corrected image link syntax in documentation
- Fixed screenshots table formatting
📦 Technical Details
Dependencies
- Added
electron-updaterv6.3.9 for automatic updates
Files Changed
- 15 files modified
- 626 lines added
- 22 lines removed
- 2 new files created
🔄 Migration Notes
This version includes significant architectural changes:
- Session management is now stateless
- Model configurations are more flexible
- Update system requires no manual intervention
📝 Full Changelog
See v1.1.4...v1.2.0
Installation: Download the appropriate package for your platform from the assets below.
macOS Users: If you encounter "App is damaged and can't be opened", run:
sudo xattr -rd com.apple.quarantine "/Applications/Chat2API.app"Chat2API v1.1.4
Chat2API Manager v1.1.4 Release Notes
🎉 Major Features
🆕 New Provider: Perplexity
- Added Perplexity AI provider support
- Seamless integration with existing provider management
- Full support for Perplexity's web search capabilities
Clear Chat History
- Qwen AI: Delete all conversation history from Qwen AI website
- MiniMax: Batch delete all conversations
- Confirmation dialog with warning to prevent accidental deletion
Enhanced Thinking Mode Control (Qwen AI)
- Model name suffixes for fine-grained control:
-thinking: Force enable thinking mode-fast: Force disable thinking mode (fast responses)
- Default to disable thinking mode and auto-search
- Explicit
enable_thinkingparameter support
Improved Credit Display (MiniMax)
- Updated to use new membership API endpoint
- Added credit expiration timestamp display
- Shows remaining daily login gift credits
🚀 Improvements
Management API
- Remote administration API for server management
- Secure API key-based authentication
- Programmatic control of proxy settings
Request Logging Enhancement
- Response body logging for streaming and non-streaming requests
- Added
web_searchandreasoning_effortfields - Enhanced log detail view with new "Response" tab
Model Mapping Configuration
- Unsaved changes protection to prevent accidental data loss
Multi-Provider Adapter Improvements
- Kimi: Improved thinking mode detection with phase tracking
- Qwen/Qwen-AI: Enhanced parent_id handling for multi-turn conversations
- Minimax: Optimized tool call support
- DeepSeek: Improved fold/search models streaming
- Perplexity: Enhanced error handling
Multi-Turn Conversation Support
- Fixed parent message ID updates for non-stream responses
- Improved conversation context retention
🐛 Bug Fixes
- Fixed DeepSeek web search model streaming issues
- Fixed Qwen AI non-stream empty content handling
- Fixed Perplexity error handling and response parsing
- Fixed duplicate resolve in Qwen AI handleNonStream
- Fixed Z.ai non-stream response handling
- Corrected handleNonStream parameter handling in multiple adapters
📦 Technical Updates
- Improved TypeScript type definitions
- Enhanced error handling and logging
- Added backward compatible model name mappings
Chat2API v1.1.3
🆕 New Features
Improved Log Detail Modal
- Redesigned log detail modal with improved user experience
- Better layout and information organization
🐛 Bug Fixes
Data Loss Prevention
- Fixed encryption key instability that caused data loss on app restart
- Now uses stable encryption key derived from machine-specific identifiers
- Fixed Windows restart configuration loss issue
UI Improvements
- Fixed text overflow issues in log detail dialogs
- Improved text wrapping and scroll handling for long content
Chat2API v1.1.2-fix
🆕 New Features
Improved Log Detail Modal
- Redesigned log detail modal with improved user experience
- Better layout and information organization
🐛 Bug Fixes
Data Loss Prevention
- Fixed encryption key instability that caused data loss on app restart
- Now uses stable encryption key derived from machine-specific identifiers
- Fixed Windows restart configuration loss issue
UI Improvements
- Fixed text overflow issues in log detail dialogs
- Improved text wrapping and scroll handling for long content
Chat2API v1.1.0
🆕 New Features
Session Management for Multi-turn Conversations
- Added session management system supporting both single-turn and multi-turn modes
- Configurable session timeout, max messages per session, and max sessions per account
- Unified session context handling across all adapters (DeepSeek, GLM, Kimi, MiniMax, Qwen, Z.ai)
Function Calling Simulation
- Implemented function calling simulation for non-native models via prompt engineering
- Supports bracket format
[function_calls][call:name]{args}[/call][/function_calls] - Compatible with Cherry Studio, Kilo Code, and other OpenAI-compatible clients
- Unified tool call handling across all providers
Tool Prompt Injection System
- Client detection for automatic prompt adaptation (Cherry Studio, Kilo Code, etc.)
- Configurable tool prompt injection with skip option for specific clients
- Multiple prompt variants optimized for different models (DeepSeek, GLM, Qwen)
DeepSeek Enhancements
- Added web search capability support
- Added reasoning/thinking mode support with
reasoning_effortparameter
UI & UX Improvements
- Improved UI responsiveness
- Persisted proxy bind address configuration
- Updated macOS icons
🐛 Bug Fixes
- Fixed duplicate stream termination issues in Qwen and Z.ai adapters
- Fixed stream handling with explicit boolean checks
- Persisted proxy bind address configuration
Chat2API v1.0.0
Chat2API v1.0.0
Chat2API is a native desktop application that provides an OpenAI-compatible API for multiple AI service providers. It allows you to use any OpenAI-compatible client with DeepSeek, GLM, Kimi, MiniMax, Qwen, Z.ai and more across macOS, Windows, and Linux.
Downloads
| Platform | Architecture | Download |
|---|---|---|
| macOS | Apple Silicon (M1/M2) | Chat2API-1.0.0-mac-arm64.dmg |
| macOS | Intel | Chat2API-1.0.0-mac-x64.dmg |
| Windows | x64 | Chat2API-1.0.0-x64-setup.exe |
| Linux | x64 | Chat2API-1.0.0-x64.AppImage |
| Linux | ARM64 | Chat2API-1.0.0-arm64.AppImage |