v1.88.1

✨ Enhanced Caching and Performance

• Improved cache handling to reduce duplicates and boost efficiency.
• Added support for concurrent cache operations, ensuring smoother task execution.

🌐 Expanded Model and Playground Support

• Introduced OpenAI's o1 and DeepSeek models for advanced use cases.
• Enhanced playground capabilities to leverage new model features.

🌍 CORS and Network Improvements

• Added a configurable CORS origin option for better security and flexibility.
• Improved server logging with network interface details for easier debugging.

🧪 New Samples and Usability Enhancements

• Added new sample scripts: repomap-test for file processing and triangle-sum for mathematical proofs.
• Optimized JSONL parsing for cleaner, faster operations.

v1.88.0

✨ New Features & Enhancements

• Introduced network flag for server accessibility and enhanced CORS support for both local and HTTP servers.
• Added LogProbs and TopLogProbs tab panels for deeper insights into model outputs.
• Improved file drag-and-drop UX with active state feedback.
• Enabled support for binary file handling, expanding file compatibility.
• Integrated rehype-highlight for better Markdown syntax highlighting.

🛠️ Refinements & Fixes

• Major refactor of run cache, optimizing cached response handling.
• Streamlined model handling for O1 variants and fixed related tools support.
• Improved chat rendering and pricing tab visibility in the UI.

📄 Documentation

• Reorganized and cleaned up the README for better clarity and usability.

This release empowers developers with better server configurations, enhanced file handling, and deeper insights into model interactions! 🚀

v1.87.0

🎉 Enhanced Readability and Structure!
This release focuses on improving the clarity and organization of our README.

• ✏️ A cleaner, streamlined README structure for easier navigation.
• 📄 Quick access to online documentation and resources.
• 📺 Highlighted links to a YouTube interview for deeper insights.

Get started faster and stay focused with a more polished introduction! 🚀

v1.86.4

🚀 Improved Azure Connection Handling

• Resolved token expiration issues with enhanced logging for better debugging.
• Simplified Azure token management by removing unused clear() method.

🔧 Configuration Enhancements

• Streamlined configuration headers for Azure Serverless Models, improving clarity and maintainability.

These updates enhance stability and simplify the Azure integration experience! 🌟

v1.86.3

✨ Enhanced Token Logging
Token expiration times are now logged in UTC for improved clarity and consistency.

🐛 Fixed Array Handling in Message Functions
Message appending functions now support both string and array content seamlessly, ensuring robust and flexible message handling.

♻️ Streamlined Configuration Reads
Unnecessary token clearing during configuration reads has been removed, improving efficiency and simplifying the codebase.

🔍 Improved Script Metadata Parsing
Script metadata parsing has been integrated directly into the runtime, enhancing script management and

v1.86.2

What's New in 1.86.2

• ✨ Enhanced CLI flexibility with updated options: the --rewrite flag now overrides the --suffix option for seamless file handling.
• 🐛 Improved stability by handling undefined responses in tracing and refining temperature settings for better output quality.

v1.86.0

🚀 New Features and Enhancements

• Convert Command for GenAIScript: Introducing a powerful new convert command to streamline file processing through GenAIScript. This command enables you to convert files individually, with various options for handling output, concurrency, and exclusions. Perfect for automating and enhancing your workflow! 📂

• Enhanced Token Logging: The token logging system now includes detailed type and scope information. This enhancement provides greater transparency and insight into token usage, helping you manage and optimize your resources more effectively. 🔍

🔧 Improvements

• Reasoning Model Update: The reasoning model has been renamed for consistency and clarity, aligning with best practices and improving code readability. 🧠

🛠️ Fixes and Optimizations

• Ollama Model Handling: Improved error handling when pulling models from Ollama, ensuring smoother operations and better user feedback in case of failures. 🛡️

• Code Clean-Up: Various code refinements, including more precise file handling and error logging, contribute to a more robust and efficient system. 🧹

Enjoy the new features and improvements in GenAIScript 1.86.0! 🎉

v1.85.1

🎉 New Features and Enhancements in GenAIScript 1.85.1

• YAML Export and Filename Resolution: We've added support for YAML export, enhancing the flexibility of file handling and configuration management. 📝

• Custom Weights and Pre-Encoded Tokens: You can now leverage custom weights and pre-encoded tokens for more precise model interactions, allowing for tailored AI responses. 🎯

• Content Safety Checks: Introducing a new content safety feature to detect and prevent prompt injections, ensuring safer and more reliable AI outputs. 🔒

• Improved Model Handling: The model alias handling logic has been refactored for greater efficiency. This includes the addition of candidate models for large, small, vision, and reasoning tasks, providing a broader range of model options. 🚀

• Enhanced Logging and Debugging: We've simplified model logging and pulling processes, making it easier to track and debug model-related actions. 🛠️

• Max Retry for Server Management: Implemented a maximum retry mechanism for server start attempts, improving the robustness of server operations. 🔄

This release focuses on improving the flexibility, safety, and efficiency of GenAIScript, empowering developers with better tools and features for AI-driven projects. Enjoy exploring the new capabilities! 🌟

v1.85.0

In this release, GenAIScript introduces significant enhancements and support for new features:

🚀 Anthropic Bedrock Support: We are excited to announce support for Anthropic Bedrock models, enabling more robust and diverse language model interactions. This includes the addition of new model types, enhancing the versatility of GenAIScript's AI capabilities.

🔄 Refined Message Handling: The message conversion logic has been refactored to improve efficiency and accuracy. This update ensures better handling of chat messages, particularly when converting and collapsing message content, leading to a smoother user experience.

🔧 Tool Parsing Improvements: We've addressed issues related to tool parsing, especially when dealing with empty strings. This fix enhances the robustness of the script's parsing capabilities.

🖼️ Updated Image Path and Keywords: The file path and keywords for the robots image have been updated, ensuring that the correct assets are used and improving the relevance of image-based operations.

These updates collectively enhance the functionality, performance, and user experience of GenAIScript. Enjoy exploring the new capabilities!

v1.84.8

In this release of GenAIScript, we've introduced several exciting new features and enhancements to improve your experience:

• ✨ Enhanced Model Management: We've updated model identifiers and pricing tiers, providing more flexibility and transparency in model usage. This includes the addition of reasoning model support in NodeHost, enhancing the capabilities for complex computations.

• 🚀 New Model Aliases: We've added and updated model aliases for Agent and Memory, allowing for more intuitive management of these components.

• 🛠️ Improved Model Pull Logic: The model pull logic now includes a tag check, ensuring that the correct models are pulled more efficiently.

• 📝 Refined Logging: Logging for script finding has been improved, providing clearer insights and easier debugging.

• 🌟 Workspace Folder Utilization: The VSCode extension now leverages workspace folders, streamlining project management and improving integration with your development environment.

These updates aim to enhance your workflow, providing more robust tools and clearer insights into your projects. Enjoy the new features and improvements!