# Changelog

All notable changes to Claude Vision Auto will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [1.0.0] - 2025-10-29

### Added
- Initial release of Claude Vision Auto
- Vision-based auto-approval using MiniCPM-V
- Support for multiple screenshot tools (scrot, gnome-screenshot, ImageMagick, maim)
- Configurable timing and behavior via environment variables
- Debug mode for troubleshooting
- Comprehensive documentation (README, INSTALLATION, USAGE)
- MIT License
- Example usage scripts
- Basic test suite

### Features
- Automatic detection of approval prompts
- Screenshot capture of terminal window
- Vision analysis via Ollama API
- Intelligent response submission (1, y, WAIT)
- Configurable idle threshold and response delay
- Support for multiple vision models (MiniCPM-V, Llama 3.2 Vision, LLaVA)
- Automatic screenshot cleanup
- Connection testing and validation

### Supported Platforms
- Linux (Debian/Ubuntu tested)
- X11 display server
- Python 3.8+

## [Unreleased]

### Planned
- Wayland support
- macOS support
- Headless mode (API-only)
- Configurable response patterns
- Multi-terminal support
- Session recording and replay
- Windows support (WSL)