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_thinking parameter 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_search and reasoning_effort fields
• 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

🆕 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

🆕 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

🆕 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_effort parameter

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 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