🛠 ii-agent v0.2 Release Notes

We’re excited to announce the v0.2 release of the ii-agent! This update brings major feature upgrades, critical bug fixes, improved tooling, and support for more powerful LLM backends such as Gemini-2.5-pro. Here's what’s new:

🚀 What's Changed

✨ New Features

• Prompt Enhancements & User Controls
• Improved prompt generation logic and message handling.
• Users can now cancel or edit prompts during interactions.
• Tooling Enhancements
• Introduced Message Tool and Return Control Tool for better user-agent interaction.
• Added new Slide Deck Completion Tool with enhanced image usage.
• Support for long video generation and Google Drive integration.
• Added settings tool for easier runtime control.
• Model & Backend Support
• Default model updated to Claude Sonnet 4.
• Added support for:
  • Gemini 2.5 Pro
  • Anthropic interleaved thinking
  • OpenAI Azure endpoints
  • Local LLMs via LMStudio (OpenAI-compatible API)

🐛 Fixes & Refinements

• Resolved prompt looping in history runs.
• Improved error handling in tools like BrowserPressKeyTool.
• Addressed frontend bugs in message state and Docker persistence.
• Simplified the Slide Deck Tool and removed redundant logic in history initialization.
• Reduced token usage in message output to optimize performance.

🧹 Code Cleanup & Refactors

• Refactored global styles and frontend logic for better maintainability.
• Replaced context managers and enhanced internal messaging workflows.

📦 DevOps & Infrastructure

• Dockerized the entire project for seamless deployment.
• Fixed Docker-related issues with yarn and event DB persistence.

👥 New Contributors

• 🎉 @GokuDoku made their first contribution with local LLM support: #72

📈 Full Changelog

Compare the full diff here: v0.1...v0.2