8.2.0 26.0+ plugin Syncro Soft Oxygen AI Positron Oxygen AI Positron

Oxygen AI Positron

Oxygen AI Positron for Desktop is an advanced AI-powered solution designed to assist content creators, technical writers, and developers throughout every stage of the writing process. By leveraging the capabilities of AI platforms, AI Positron streamlines content creation and enhances productivity, thus empowering users to craft high-quality documentation and content with greater speed and confidence.

Release Notes 8.2.0

  1. Extend AI Capabilities Using Skills - Define and use skills based on the Anthropic standard to extend the AI assistant with reusable, specialized modules for specific tasks. Use them to automate repetitive workflows, integrate with external tools and APIs, standardize best practices, and support domain-specific processes.
  2. Built-in Skills - Several built-in skills are now available to help when you want the LLM to:
    • Add review comments to your document.
    • Translate XML content into another language while preserving markup and technical elements.
    • Get help with AI Positron features by using the user guide documentation.
    • Apply structured persona-based analysis to evaluate a task through multiple audience perspectives.
  3. Configure Multiple Action, Agent, and Skill Folders - You can now configure a comma-separated list of folders that AI Positron uses to load actions, agents, and skills.
  4. Context Window Size Indicator - A new indicator in the AI Positron footer shows the model's context window size so you can see how much context is available for the conversation and how much is currently in use.
  5. Personas Chat Mode - You can now use the Personas chat mode to review a task from multiple audience perspectives and get a more balanced recommendation.
  6. Claude Models with Adaptive Thinking - Added support for Claude Sonnet 4.6 Thinking and Claude Opus 4.6 Thinking. These models use adaptive thinking to determine how much reasoning is needed for each request. The chat interface displays a collapsible summary of the model's thinking process in real time.
  7. Latest OpenAI Models Available - The GPT-5.5 Thinking, GPT-5.4, GPT-5.4 Mini, and GPT-5.4 Nano models are now available in the list of OpenAI models.
  8. New Gemini Models Available - The Gemini 3 Flash, 3.1 Pro, and 3.1 Flash Lite models are now available in the list of models to choose from.
  9. New Default Model - OpenAI GPT-5.4 is now the default model for the Positron Service and the OpenAI connector.
  10. Smarter AI Awareness of Changes in Your Working Context - When you continue a chat after changing the selected content or switching to a different file, the AI can now follow those context changes better and respond based on what you are currently working on.
  11. Binary Resource Insights - You can now ask the AI to analyze binary resources such as images, PDF, Word, Excel, and PowerPoint files without first attaching them in the chat.
  12. Review Changes Support for Copy/Move/Rename AI Operations - The Review Changes sandbox now tracks copy, move, and rename operations on files and folders performed by the AI.
  13. Attach Excel Documents - You can now attach Excel (xlsx) documents in the AI Positron chat view.
  14. Analyze Referenced SVG Images - When using AI actions such as "Generate alternate text" or interacting with the AI in the chat, the LLM now has access to the contents of referenced SVG images, in addition to JPEG and PNG images.
  15. Configure Reasoning Effort Level for Microsoft Azure Connections - For Microsoft Azure connections, you can now choose the default reasoning effort level to use when executing actions or chat requests by using the new Reasoning Effort parameter.
  16. Support for Claude Deployments in Microsoft Azure Connections - Claude (Anthropic) models hosted on Azure AI Foundry can now be used directly from Microsoft Azure AI connections.
  17. Define Multiple AI Connections in JSON Configuration Files - If you configure AI services by using a JSON configuration file, you can now define an array of multiple connections.
  18. Improved Unsafe Tools Approval - When prompted to run unsafe tools, such as tools provided by Model Context Protocol integrations, you can now choose to always approve specific tools. The confirmation prompt no longer times out, and the UI was redesigned to be easier to read.
  19. Improved Proofread AI Action and Skill - Various improvements and fixes were made to the Proofread AI action and its corresponding skill.
  20. Model Context Protocol (MCP) Improvements - The Model Context Protocol (MCP) SDK was updated to version 1.1.1. You can now use Oxygen editor variables for all parameter values in an AI Positron MCP configuration file. The cwd property is also now supported for local MCP connections.
  21. Expand Oxygen Editor Variables in AI Actions and Agents Prompts - Oxygen editor variables used in AI actions and agents prompts are now expanded automatically.
  22. Ask for Website Access - You are now asked directly in the chat view for permission if the LLM attempts to read content from a website. You can choose to always allow access to a specific website host.
  23. Fixed an issue where certain chat history entries could fail to load due to invalid characters.