Oxygen AI Positron for Web Author
- AI Edits Now Merge Directly into Your Document - Positron merges AI-generated changes directly into your document instead of overwriting and reloading the file. If Track Changes is enabled, Positron records the merge as a tracked change in your name. You can instruct Positron to force change tracking and use its own name as the change author, so you can review AI edits like those of any other contributor.
- Easily Review AI-Modified Files - Files created or modified by the AI now appear directly in the chat area, where you can review the changes. You can compare the original content with the AI-updated version or directly open a changed file to make corrections.
- Extend AI Capabilities Using Skills - Define and use skills (based on the Anthropic Agent Skills) to extend the AI agent's capabilities by creating reusable, specialized modules for specific tasks. You can use them for automating repetitive workflows, integrating with external tools and APIs, standardizing best practices, and enabling the AI assistant to handle domain-specific or proprietary processes. From simple utilities to complex integrations, skills let you customize the AI agent to match your unique business needs and accelerate productivity.
- Built-in AI Skills - Several built-in skills are now available to help when you want the AI to:
- Add review comments to your document.
- Translate XML content into another language while preserving markup and technical elements.
- Apply structured persona-based analysis to evaluate a task through multiple audience perspectives.
- Load Skills from Zip Archives - You can reference an archive that contains custom AI actions, agents, and skills in the Web Author admin pages. These skill folders can now be packed as zip archives (with the .skill file extension), and AI Positron will dynamically load the skills from the archives.
- Personas Chat Mode - You can now use the Personas AI chat mode to review a task from multiple audience perspectives and get a more balanced recommendation. If you do not specify personas, the agent automatically defines several relevant personas, analyzes the content from their perspectives, identifies conflicting viewpoints, and tries to reach a compromise before providing a final recommendation.
- Ask AI to Explain File Differences - When you compare files, the Differences view contains buttons to have the AI assistant explain the differences for an entire document or block of content. You can also ask the AI to explain differences or how to resolve conflicts directly in the chat input box in the AI Positron view.
- AI Can Ask Clarifying Questions - AI Positron can ask for clarification when a request needs more details, helping you guide the conversation toward the intended result. You can choose from suggested answers or provide your own response.
- Connect to MCP Servers - Administrators can now configure remote Streamable HTTP MCP (Model Context Protocol) servers in the new MCP tab of the plugin configuration dialog box, making externally provided tools available to the AI alongside Positron's built-in capabilities. In the chat, the new MCP servers and tools button gives each user a clear view of all the available tools, along with the ability to enable or disable them and sign in individually to the servers that use OAuth authentication.
- Intercept AI Events via Hooks - AI Positron now includes a hook system for intercepting AI events to help monitor, govern, and shape AI behavior, giving you greater visibility and control over AI-driven workflows. This lets you audit AI actions, enforce organizational policies, collect usage metrics, and block risky operations before they execute.
- Manage Available Models for Configured AI Connections - Administrators can now control which models are available to users for configured AI connections, including OpenAI, Claude, and Gemini connectors. You can add or remove models from the connection-specific list, define a recommended default model, and include custom models.
- Select the AI Model in Chat View - You can now choose the AI model used for chat conversations and AI actions directly from the Chat view, thus enabling you to switch to the model that best fits your current task.
- New and Updated AI Models - New AI models are now available, giving you more options for balancing quality, reasoning, speed, and cost:
- OpenAI: GPT-5.6 Sol, Terra, Luna, and their Thinking variants are now available. GPT-5.6 Terra with adaptive thinking is now the default for the OpenAI Responses connector, while the non-reasoning variant is the default for the OpenAI Chat Completions connector.
- Anthropic: Claude Sonnet 5 and Claude Opus 5 are now available.
- Google: Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash Lite are available through the VertexAI connection.
- xAI: Grok 4.6, 4.5, and 4.3 are now available.
- Claude Models with Adaptive Thinking - Two new Claude models are available: Claude Sonnet 4.6 Thinking and Claude Opus 4.6 Thinking. These models use adaptive thinking to automatically determine how much reasoning is needed for each request, spending more time thinking through complex problems while responding quickly to simpler queries. When using these models, the chat interface displays a collapsible summary of the model's thinking process in real time. The thinking summary is also preserved and restored when you load conversations from history.
- Reasoning Displayed in Chat for OpenAI Thinking Models - When you use OpenAI thinking models (such as GPT-5.5 Thinking) through the Positron Service or an OpenAI Responses enterprise connector, the model's reasoning is now displayed in a collapsible section in the chat.
- Validate and Check for Completeness - The new validate_and_check_for_completeness tool performs validation and checks for completeness on a DITA map or DITA-OT project file with the settings configuration provided by the LLM. The tool is available by default for the DITA Agent chat mode. This tool requires Web Author 29 or newer.
- Evaluate XPath Expressions - The new evaluate_xpath tool enables the LLM to retrieve nodes from a document using XPath expressions. It returns both the matching node and its location within the document, making access to structured content faster, simpler, and more precise.
- 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. This makes it easier to generate content based on files in a folder or validate whether referenced images fit the surrounding context.
- Image References Expanded in Selected Content - When you select content that includes image references in the visual editor, the referenced images are included along with the text. This allows you to ask the AI agent to review the text and images together, for example, to check whether the image and its accompanying text work well together.
- Analyze Referenced SVG Images - When you use AI actions such as "Generate image alternate text" or interact with the AI in the chat, the assistant is now given access to the referenced SVG images (in addition to JPEG and PNG images). This allows the AI to provide feedback based on the SVG image content.
- Attach Excel Documents - You can now attach Excel (xlsx) documents in the AI Positron chat view to provide additional context for your conversation with the AI.
- 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. This helps reduce confusion in ongoing conversations and makes follow-up requests feel more accurate and natural.
- Edit Markdown Documents While Vibe Authoring - When vibe writing, AI Positron can now retrieve content from and modify the current document, whether it is an XML or Markdown document.
- Markdown Response Rendered Visually - AI Positron now makes Markdown-based AI responses easier to read and use by automatically rendering them in a rich, browser-like preview. Instead of viewing raw Markdown, you get a polished display with support for headings, lists, tables, links, code blocks, and inline styling (bold, italic, underline, code phrases). You can easily copy the contents of a code block by clicking the Copy button in the top-right corner. A new Switch how the response is rendered drop-down button also lets you instantly choose the visualization mode that best matches your workflow.
- Automatic Conversation Compaction:
- A new automatic conversation compaction feature allows AI Positron to summarize older portions of long conversations (when the allowed context usage reaches 70%) and replace them with a concise recap, allowing your conversation with the AI to continue without losing context. The automatic system can be disabled via an option in the Administration page.
- You can also manually trigger a compaction by using the Context Consumption button in the footer of the AI Positron view.
- Context Window Size Indicator - A new indicator in the AI Positron footer gives you visibility into the model's context window size so you can understand how much context is available for your conversation. The indicator includes a breakdown of the total context window and how much of that context is currently in use.
- View Token Usage Information - Hovering over the context usage indicator shows how much of the model's context window the current conversation is using. For external AI connections, it also now shows the token count for the last response and a running total for the whole conversation (including any responses regenerated or replaced by edits).
- New OpenAI Responses Enterprise Connector - A new OpenAI Responses enterprise connector is now available. It uses the OpenAI Responses API, which is required for newer reasoning models such as GPT-5.5 Thinking.
- Support for Claude Deployments in Microsoft Azure Connections - Claude (Anthropic) models hosted on Azure AI Foundry can now be used directly from your Microsoft Azure AI connections.
- Configure Reasoning Effort Level for Microsoft Azure Connections - For Microsoft Azure connections, you can now choose the default reasoning effort level (low, medium, or high) to use when executing actions or chat requests via the new Reasoning Effort parameter.
- Configure Maximum Context Window Usage for Microsoft Azure and AWS Bedrock - Microsoft Azure and AWS Bedrock connections use custom deployments and model IDs rather than fixed model names, so Oxygen cannot automatically determine their context window size. Set it yourself with the new Maximum context window option when configuring the connector. This lets the chat's context usage indicator accurately show the portion of the available context window used by each request and enables automatic context compaction to work correctly.
S1000D
- Issues 5.0, 6, and 7 Schemas Now Bundled - Schema sets are now bundled for S1000D issues 5.0, 6, and 7, alongside issues 4.0, 4.1, 4.2, thus enabling local validation of data modules without fetching schemas from the internet.
- Automatic Data Module Validation Against BREX - Web Author now automatically validates S1000D data modules against the business rules in their referenced BREX file. To enable this validation, make sure that the referenced BREX file (brexDmRef) includes both the issue information (inWork) and the language, and that the BREX file is in the same directory as the data module.
- Quick Access to S1000D Editing Actions - A floating toolbar gives you access to context-specific actions when editing S1000D documents. It appears automatically when you select content in supported locations and offers actions tailored to the current editing context.
- AI Skills for S1000D Authoring - The built-in S1000D framework includes AI skills to help AI agents work with S1000D documents. The skills provide guidance for data modules, publication modules, BREX modules, Common Information Repositories, and management files.
- Improved Author Mode Experience - The rendering of S1000D modules has been improved, including full compatibility with dark mode.
- Automatic File Name Validation - Built-in validation rules check whether an S1000D file name matches the identified module and follows the required uppercase structure, displaying a warning when the file name is invalid.
- Align Data Module Codes with File Names - A default Schematron rule checks whether a data module code is consistent with its file name. If a mismatch is detected, a Quick Fix can align the code with the file name.
- Table Validation Support - You can validate the layout of tables in S1000D documents using an optional validation scenario. Apply it to the current module from the Validation menu or enable it for all modules in the S1000D framework configuration.
- Automatic ICN Insertions in Data Modules - When an ICN is referenced in S1000D, Web Author automatically inserts the unparsed entity declaration and associated notation declaration in the DOCTYPE for all S1000D data module types.
Platform and Security
- Web Author Introduces the Oxygen Security Manager - Since the Java Security Manager is deprecated and permanently disabled starting with Java 24, Web Author now comes with its own Oxygen Security Manager. It is enabled by default in the installers and the All Platforms kit, and it restricts file access to only what the application needs. To make sure you are always aware of the security status, Web Author does not start if the Security Manager cannot be installed, unless you explicitly disable it.
- Web Author Moves to Apache Tomcat 10 - Web Author now runs on Apache Tomcat 10 (version 10.1.61), upgraded from Tomcat 9. Tomcat 10 is also the minimum required version of the servlet container.
- Web Author Now Ships with Java 21 - Java 21 is now bundled by default, while Java 17 remains supported as the minimum required version.
General Editing/Reviewing
- Work with Git LFS Repositories - Web Author now supports displaying files stored with Git Large File Storage (LFS). Images and other LFS-tracked files are rendered directly in the editor, so you can view the content of repositories that keep large binary resources in LFS. This works with all Git connectors, including GitHub, GitLab, Bitbucket, Azure DevOps, and their on-premises editions. Editing or uploading LFS-tracked files is not supported yet.
- Smart Paste URLs over Selected Text - When you paste a URL over selected text, Web Author now automatically turns the selection into a link that points to that URL, keeping the selected text as the link label.
- Scale DITA Images - DITA images that specify a scale attribute are now rendered at the scaled size in the visual editor. You can easily set the scale using the Set image size action from the image's floating toolbar.
Customization and Integration
- Create Frameworks Faster with Web Author AI Skills - A new open-source set of AI skills helps you create and customize Web Author frameworks with an AI coding assistant. Describe what you need in plain language, and the assistant generates the document templates, CSS styling, form controls, custom actions, and validation rules, then tests the result directly in Web Author.
- Use the Web Author API Documentation with AI Assistants - The Web Author JavaScript API and Oxygen SDK API documentation are now also available as llms.txt files. Paste a link to any of these documentations into an AI assistant, such as AI Positron, and it can use the API reference to help you build plugins and integrations faster.
- Show Floating Toolbars While Editing Inside an Element - Floating toolbars can now be displayed while the caret is inside an element, without having to select the whole element first. In DITA documents, for example, table and image actions are now available in a toolbar displayed below the table or image whenever you edit inside it. To add such toolbars to your own framework, use the new -oxy-block-floating-toolbar property.
- Configure the Outline Pane Contextual Menu - The contextual menu of the Outline pane is now configurable through the webAuthorOutlineConfig.xml file. You can choose which actions it shows and in what order, separately for the TOC and Structure modes.
Other Improvements
- Better Handling for Lost Network Connection - If your internet connection is lost while editing, a message now tells you that you are offline and editing is paused. When the connection is restored, the message disappears and you can safely continue editing.
- Text Mode by Default for Generic XML Files - XML files that have no associated framework now open directly in Text mode, with syntax highlighting. These are usually configuration or data files, and without a framework the visual editor offers little help, so you can start editing them right away.
- Choose Whether Table Headers Stay Visible While Scrolling - When editing DITA tables in Full Width mode, you can now choose whether the table header stays visible as you scroll through the table, using a new action in the table's floating toolbar. This is useful for tables with large headers, where a header that stays visible would take up too much of the screen.
- Insert Characters from Unicode 18.0 - When you insert special characters, you can now choose characters from the recently updated dataset of the Unicode Standard, Version 18.0.
Deprecated/Removed Components
- WebSphere Liberty No Longer Supported - Web Author can no longer be deployed in WebSphere Liberty, and the WebSphere distribution is no longer provided. Customers who currently run Web Author on WebSphere should contact support before upgrading.