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.

v1.97.0

🚀 What's New in GenAIScript 1.97.0

• ✨ Enhanced Output Formats: Added support for YAML and JSON outputs, alongside improved schema-based validation for structured responses.
• 🛠️ "Make it Better" Feature: Introduced a utility to iteratively improve code or content with customizable instructions.
• 🧠 Smarter Parsing: Upgraded JSON and YAML parsing with robust repair mechanisms for better handling of malformed data.
• 🔍 Advanced Casting: New cast function enables seamless transformation of unstructured data into schema-compliant formats.
• 🔒 Security Enhancements: Implemented stricter Content Security Policy (CSP) for web components.
• 🖼️ File Handling Improvements: Enhanced support for image-based data extraction and markdown file updates.
• 📚 Sample Scripts: Added new examples like makeitbetter and keyworder for easier adoption of advanced features.

Enjoy the latest tools and features for building smarter, more structured AI workflows!

v1.96.1

✨ Enhanced WebSocket payload validation improves server reliability with clearer error messages for oversized payloads.
🚀 Optimized chunking logic for better handling of large traces and outputs.
🌐 Introduced a new browserUrl for seamless API key integration in the browser.
🖼️ Added a sample script for generating alt-text descriptions for images.
🔧 Fixed inconsistent behavior in hiding the server terminal based on diagnostics.
🔒 Improved API authentication handling by ensuring consistent key usage.
🛠️ Disabled proactive view opening in non-chat modes for a smoother user experience.

v1.96.0

• ✨ Enhanced system prompt configuration with a new UI for customizing parameters, streamlining workflows.
• 🔍 Improved logging for model resolution, offering better debugging and insights.
• 📜 Introduced unthink function to clean up <think> tags, simplifying content processing.
• 🖼️ Added image rendering in views and improved image encoding with enhanced options.
• 🚀 Optimized handling of large payloads and WebSocket message limits for better performance.
• 🛠️ Refactored and modularized utilities like normalizeInt and trimTrailingSlash into a dedicated cleaners module.
• 📂 Expanded system prompt capabilities with additional parameters for agents like Python interpreters and documentation agents.
• 🧹 Removed unused environment variables for a cleaner configuration.
• 🧪 Enhanced testing and validation for various modules, ensuring robustness.

v1.95.3

🚀 Enhancements

• Model Encoding Support: Introduced modelEncodings in configuration, enabling custom model-to-encoding mappings for greater flexibility and compatibility.
• Dynamic Encoder Loading: Improved token encoder resolution by dynamically selecting encodings based on the modelEncodings configuration.

🛠️ Improvements

• Config Management: Enhanced configuration handling with a new config getter, ensuring reliable access to loaded configurations.
• Test Host Updates: Added a stubbed config getter to TestHost for consistency across host implementations.

📁 Sample Config Update

• Added example modelEncodings entries in genaiscript.config.json to demonstrate usage.

v1.95.2

• 🚀 Enhanced Development Experience: Added new devcontainer configurations, improving local development setups with pre-installed tools and features like common-utils, git, and ffmpeg.
• 🗂️ File Caching: Introduced a robust file caching mechanism, enabling efficient storage and reuse of processed files across runs.
• 🛠️ Schema Validation Upgrade: Integrated JSON schema validation using external schemas, enhancing configuration reliability and error handling.
• 🎥 AI Kitchen Script: Added a new ai-kitchen script showcasing video analysis with transcript generation, frame extraction, and YouTube-ready content creation.
• 📜 JSON Schema Inference: Leveraged @stoplight/json-schema-generator for dynamic schema generation from objects, simplifying workflows.
• 🖼️ Improved Image Handling: Enhanced MarkdownTrace to support embedded images with better file and URL handling.
• 🔍 Web Scraping Support: Expanded browser locator capabilities with new methods for handling multiple elements.

v1.95.1

🎉 Enhanced GitHub Copilot Chat Integration

• Replaced "client" language model with github_copilot_chat for seamless integration.
• Improved error messages for better clarity when models are unavailable.

🛠️ Schema Improvements

• Added advanced JSON Schema validation and inference capabilities.
• Enhanced tooling for stricter schema generation and validation.

📋 Copy Code Button

• Introduced a "Copy" button for code snippets in the web UI, making it easier to share and reuse code.

📹 GitHub Copilot Chat Demo

• Added a sample video for showcasing GitHub Copilot Chat capabilities.

🔧 Bug Fixes and UI Tweaks

• Addressed minor UI inconsistencies in Markdown rendering and trace panels.
• Improved error handling and logging for GitHub-related operations.

v1.95.0

What's New in 1.95.0 🎉

• Enhanced Security 🔒: Introduced a robust Content Security Policy (CSP) for webviews, ensuring stricter control over resources like scripts, styles, and frames.
• Improved Webview Experience 🖥️: Added a persistent webview panel with seamless reveal functionality, providing a smoother user interface for error handling and output display.
• Streamlined Codebase 🛠️: Replaced custom nonce generation with a secure randomHex utility, enhancing maintainability and reliability.

v1.94.2

🚀 Enhanced Model Management: Improved error handling and added support for listing models across multiple providers, ensuring a smoother user experience when managing language models.

🔧 Client Language Model Refactor: Transitioned the client language model to runtimeHost for better modularity and maintainability.

🌐 Web Compatibility: Introduced support for web-browser scenarios, including enhanced CSP handling and iframe-based views for seamless integration.

📹 Video Blogifier Update: Enhanced video transcription and processing with improved prompt handling and dynamic topic resolution for better YouTube optimization.

🛠️ Dependency Updates: Refreshed dependencies across packages to maintain stability and compatibility.

🐛 Bug Fixes: Addressed issues with client builds, environment configurations, and context menu visibility to enhance overall reliability.