v1.101.2

🚀 Enhanced Performance & Features

• Improved Image Handling: Optimized load times for large images and added support for concurrent image processing with p-limit.
• Text Splitting Revamp: Introduced a new TextSplitter for advanced text chunking with overlap and custom separators, boosting text-processing efficiency.

🛠️ Simplified APIs & Tools

• Streamlined Teams Integration: Simplified Microsoft Teams APIs with auto-detection for team and channel IDs, plus enhanced markdown-to-HTML conversion for descriptions.
• Enhanced File Metadata: Added file size tracking for better workspace file management.

🧪 Testing Made Easy

• Expanded Test Coverage: Integrated tests across multiple scripts and modules, including textsplitter and sample configurations, ensuring robust reliability.

🌟 Visual Updates

• New Sample Images: Added high-quality images to the sample directory for improved testing and demonstrations.

Enjoy the enhanced GenAIScript experience! 🎉

v1.101.1

Improved File Handling 🗂️: Resolved an issue in the copyFile method where directories were not being correctly created. This ensures smoother file operations and better reliability when copying files.

v1.101.0

What's New in 1.101.0

🚀 Microsoft Teams Integration
Introducing the ability to post messages directly to Microsoft Teams channels! Share updates, attach files, and enhance collaboration with the new --teams-message CLI option.

📂 File Handling Enhancements

• Implemented a 2MB file size limit for safer and more efficient file processing.
• Improved buffer handling for better performance and reliability.

🛠️ Developer Experience

• Added support for Microsoft Graph API tokens.
• Enhanced markdown-to-HTML conversion for Teams messages, ensuring rich formatting compatibility.

📸 Image Processing Updates
Fine-tuned image transformations with options like greyscale, rotation, and cropping for better customization.

🎥 Sample Updates
New Teams integration and vision-related samples to showcase advanced capabilities.

v1.100.0

What's New in GenAIScript 1.100.0 🎉

• Enhanced DOCX Parsing: Added support for converting DOCX files into Markdown, HTML, or plain text with improved error logging and input validation.
• Python Runtime Integration: Introduced Pyodide-powered Python runtime for seamless Python script execution.
• Video Clip Extraction: Easily extract video clips with precise start, duration, or end parameters.
• Improved File Handling: Ensured destination directories exist before file copying and blocked .env file copying for added security.
• LLM Pricing Updates: Adjusted pricing and configurations for better cost efficiency, including updates for o1-mini and o3-mini models.
• GitHub Enhancements: Added a new wrapper to list repository releases effortlessly.
• Refinements: Removed schema inference tools and added stricter input validation for JSON schemas.

Upgrade now to explore these exciting features! 🚀

v1.99.0

✨ Introducing GenAIScript 1.99.0!

• New Features

  • Added refresh command for connection info tree.
  • Extract video clips with the new extractClip function.
  • Enhanced GitHub integration with release listing support.

• Enhancements

  • Updated pricing and configurations for LLM models, including support for new models like o3-mini.
  • Improved JSON schema handling with better parameter conversion and support for NaN and empty strings.
  • Refined video processing with added salt options for hashing and clip extraction.

• Fixes & Improvements

  • Adjusted WebSocket frame limits for better reliability.
  • Removed deprecated schema inference tool, simplifying workflows.
  • Added .env file copy restrictions for enhanced security.

• Documentation Updates

  • Expanded parameter and video tool documentation for easier usage.

Enjoy the latest improvements! 🚀

v1.98.1

• 🚀 New Feature: Introduced markdownifyPdf to convert PDFs into Markdown with text and image analysis for enhanced document processing.
• ✨ Improved Usability: Added an emojify example script for creative text summarization and expansion.
• 📚 Model Enhancements: Simplified model alias resolution and added support for vision_small models, improving OCR capabilities.
• 🛠 Refinements:
  • Enhanced logging in PDF extraction for better debugging.
  • Simplified log probability checks in web panels for cleaner UI behavior.
  • Improved metadata handling and finalized variable resolution for prompt templates.
• 🔧 System Updates: Enabled conditional Markdown formatting based on model type for consistent output.
• 🐛 Bug Fixes: Addressed circular alias resolution issues and refined trace heading formatting.

v1.98.0

Release Notes for 1.98.0

🚀 New Features

• Added support for reasoning effort flag, enabling fine-grained control over reasoning models.
• Introduced basic support for O3-mini models.
• Enhanced web view with Codicon support for improved UI consistency.
• Automatically selects GitHub Copilot Chat model for better developer experience.

🛠️ Improvements

• Updated configuration tree view for better organization and usability.
• Improved error handling and logging, including rendering of log probabilities and choices.
• Enhanced markdown rendering with React 19 and integrated VSCode design system.

🐛 Bug Fixes

• Resolved issues with provider selection and script name display.
• Fixed rendering glitches in trace and choices.
• Corrected tab renaming errors and hot reload limitations.

📄 Documentation

• Updated documentation to reflect new features and configuration options.

🧹 Miscellaneous

• Ignored profiler and snapshot files in .gitignore for cleaner repository management.

v1.97.3

What's New in GenAIScript 1.97.3

🚀 Enhanced Reasoning Capabilities

• Introduced a new "Reasoning" feature to improve assistant responses. Reasoning content is now captured, displayed, and structured for better insights.
• Added reasoning tabs to the UI for easier exploration of model thought processes.

📄 Improved PDF Rendering

• Boosted reliability of PDF parsing and rendering with enhanced canvas support and error handling.

🌑 Dark Mode Update

• Refined dark theme visuals for a more polished user experience.

🛠️ Code Quality Improvements

• Fixed issues with escape type definitions.
• Optimized handling of buffer-like objects, including support for Uint8Array.
• Enhanced logging and error tracing for better debugging.

✨ UI Enhancements

• Added badges for perplexity, uncertainty, and reasoning in the interface.
• Improved tabbed previews for Markdown outputs, including annotations and reasoning.

🐛 Bug Fixes

• Resolved missing closing tags in XML rendering.
• Fixed newline handling in various outputs.

v1.97.2

🚀 New Features & Enhancements

• 🔒 Pluggable Secret Scanning: Detect and redact secrets like API keys in your files and chats with customizable patterns.
• 🖥️ VS Code Server Controls: Added the ability to show the GenAIScript server terminal directly from VS Code.

⚡ Performance Improvements

• 🛠️ Optimized Imports: Delayed loading of inquirer prompts to reduce startup overhead.

🛡️ Security Enhancements

• 🧹 Secret Scanning in LLM Communication: Automatically scans and redacts sensitive information during interactions with language models.

📚 Documentation

• ✍️ Updated README with details on secret scanning configuration.

v1.97.1

✨ Enhanced Transcription and Parsing

• Added timestamp parsing for transcription, improving handling of time-based data.

🖼️ Image Tiling and Rendering

• Introduced image tiling support, enabling seamless composition of multiple images into a single tiled output.
• Enhanced image rendering logic for better system integration.

♻️ Refactored and Optimized Code

• Extracted core logic into reusable functions for improved maintainability.

🐛 Bug Fixes and Improvements

• Fixed token rendering issues to ensure accurate outputs.
• Resolved extra curly brace issue in schema validation prompts.

🔍 Developer Experience

• Improved markdown rendering logic for better code previews.
• Enhanced diagnostics and structured output visibility in the web interface.

🚀 UI Updates

• Auto-hide feature tabs for a cleaner user experience.
• Adjusted webview behavior for better usability in VSCode.