Changelog

Follow up on the latest improvements and updates.

RSS

new

improved

fixed

v0.14.0

What’s New
  • You can now set approval rules for tools
  • MCP Server now supports prompt templates
Improvements
  • MCP Prompts and Tool outputs are automatically converted into model-friendly formats.
  • Better compatibility when working with non-text content across providers like Ollama, Google, Anthropic, and Mistral.
Fixes
  • Fixed mismatches between model form inputs and their configuration.
  • Resolved an issue where MCP Tools and Prompts couldn’t be used if the MCP Key included a hyphen (“-”).
  • Security Patch
    : Fixed an XSS vulnerability caused by ECharts rendering.
⚠️ Since this update includes a critical security fix, we strongly recommend upgrading to the latest version as soon as possible.

new

improved

fixed

v0.13.2

New
  • Added built-in provider: Perplexity (citation links not yet shown in UI)
  • Added Grok-4 as a built-in model
  • Added optional API Key setting for Ollama
Improved
  • Improved UI on macOS for a more native experience
  • Enhanced KaTeX rendering for array formulas
  • Improved performance when handling large text outputs
Fixed
  • Fixed a white screen issue when creating a new chat right after deletion
  • Fixed inability to clear Proxy settings in provider configuration
  • Fixed missing name validation when saving models

new

improved

fixed

v0.13.0

New Features
  • Added support for setting proxies for providers
  • Added built-in provider: 302AI
  • Added right-click menu to folder and chat navigation in the sidebar
Improvements
  • Window styling adapted for both Windows and Linux systems
Bug Fixes
  • Fixed issue where switching conversations mid-reply could cause errors
  • Attempted fix for MCP Server not accepting self-signed certificates (requires setting `NODE_EXTRA_CA_CERTS on app launch)

fixed

v0.12.1

hotfix
Fix the issue with the incorrect temperature value during initial loading.

improved

fixed

v0.12.0

🚀 Optimizations
  1. Added more built-in models for 5ire Provider
  2. Aligned 5ire model capabilities with official standards, supporting vision and tools
  3. Enhanced error handling mechanisms for tool invocation
  4. Upgraded Baidu services to new API version (using API Key authentication)
🐞 Bug Fixes
  1. Fixed failure in switching new chat models
  2. Resolved application crash caused by bulk knowledge imports

fixed

v0.11.3

🚨 Hotfix: Fixed Model Switching Failure
This emergency release resolves a critical issue where users encountered errors when attempting to switch between models.

fixed

v0.11.2

What's New
  1. Fixed model list retrieval issues from LM Studio
  2. Resolved missing custom headers in remote tool calls
  3. Addressed model switching failures in chat

fixed

v0.11.1

What's New
  • ⚠️ Critical fixes for high-risk XSS and RCE vulnerabilities
  • 🐛 Resolved errors caused by incompatible system role name between custom providers and OpenAI API standards

new

improved

fixed

v0.11.0

🎉 New Features
  • Added support for remote tools (SSE & StreamableHttp)
  • Integrated Ollama Vision capabilities
✨ Enhancements
  • Optimized the mcp.json tool configuration file format to align with Claude's schema
  • Optimized boot speed on Linux
🐛 Bug Fixes
  • Fixed tool invocation failures in Ollama integration
  • Resolved conversation breakdowns caused by empty chat history

fixed

v0.10.1

What's New
  • Resolved critical compatibility issue with OpenAI service integrations
  • Implemented dynamic font size synchronization with system settings
  • Fixed enum type-related errors in Gemini model function call declarations
  • Addressed table layout distortion caused by excessively long environment variables in tool configuration interface
Load More