Released: Mar 18, 2026

V28.1 での更新項目

機能

AI Enhancements Powered by Oxygen AI Positron

• Sensitive Data Masking for AI Requests - Personal or private information (such as email addresses, phone numbers, IDs, or API keys) is now automatically identified and masked in AI requests to help protect sensitive data. You can extend this protection by adding custom patterns to cover additional data types. The masked information is automatically restored in the AI response, ensuring that users see the correct content and that any generated or updated files remain accurate.
• Improved Review Experience for AI-Modified Files - All files created or modified by AI now appear directly in the chat area, so you can review the proposed changes and accept or discard them without leaving the conversation. You can also open each file individually and accept only a subset of the proposed changes while rejecting the rest.
• Optimized Token Consumption for AI Prompts and Tools - The prompts and tools that the AI uses to generate answers have been improved to consume fewer tokens/credits.
• New Planner Chat Mode for Resource-Consuming Tasks - The newly introduced Planner chat mode is now available for complex, token-intensive operations (e.g., "Translate all files in the current folder" or "Find all conrefs and replace them with conkeyrefs in userguide.ditamap"). After being given the prompt, the AI explores your project, proposes a multi-step plan, and, after your approval, delegates each step to the most suitable AI agent. This means large, project-wide changes can be coordinated without hitting LLM context limits, while still showing you the tool calls and results for review.
• Smarter PDF/Word Attachment Expansion in Planner Mode - When using the Planner chat mode with PDF or Word (.docx) attachments, the document is now automatically split into multiple Markdown files, with embedded images extracted into a temporary folder. This allows the Planner to invoke sub-agents that can process, transform, or convert the extracted files and assets as needed (for example, converting them to other formats or generating new project structures).
• More Context Information Available in Chat - The AI chat now automatically includes additional information about your environment and editing context, such as the Oxygen application version, operating system details, current date, main file information, and caret or selection data (Oxygen 28.1 or newer). Having richer contextual information leads to higher-quality AI responses. For example, when the AI needs to run a command-line tool, knowing whether you are using Windows or macOS is essential to generate correct and relevant commands.
• Tools Selector - You can now customize the AI's capabilities for each chat mode. The new Tools selector allows you to disable or enable specific tools (either added via Model Context Protocol or provided in the chat mode definition), giving you more control to fine-tune the AI's responses and behavior for your specific tasks.
• Chat Selection Includes Images - When you use the AI chat with content selected in your document, any images within that selection are now also included for the LLM to analyze along with the text.
• Create New AI Chat Modes - You can now extend the AI chat by creating your own custom chat modes. This allows you to build specialized assistants tailored to your specific needs and workflows.
• AI Positron Fix Action Turns Agentic - The AI Positron Fix action now automatically applies proposed fixes directly in your document and continues to explore additional sections when more context is needed.
• Documentation and APIs to Create New Chat Modes - You can now officially define new chat modes by creating new AI actions that contain the "output-action": "agentic" property.
• Tools to List and Invoke AI Agents - Newly added tools make it possible to create powerful new chat modes to plan complex changes and then use separate agents for each part of the plan.
• Tool to Run Command Line - A newly added tool is available in all chat modes and can be used to invoke a command-line process. Note that the tool needs explicit user approval when it is invoked.
• Tool to Copy/Move/Rename Local Resources - A new tool is available in all chat modes and can be used to copy, move, or rename a local file or folder path. When used in Oxygen 28.1 and newer, if the Main Files feature is enabled in Oxygen, references to the moved or renamed resource are also automatically updated.
• Control AI Action Visibility - You can now choose whether a defined AI action is visible in the UI or only available to other AI actions as a sub-agent by using the new visibility property.
• Create AI Actions with Vision Support - You can now decide whether a custom AI action sends both content and referenced images to the LLM by using the "input-type": "markup-with-images" JSON property. This helps you include images only when they are relevant for the AI response.
• Generate Image Alternate Text Improvements - The Generate Image Alternate Text action can now be used on all images that are referenced within a document at once, while you can still use the action on individual selections as well.
• Preserve Structure and Styles for Attached Word and PDF Documents - When attaching Word (.docx) or PDF documents in the chat, their internal structure (headings, lists, tables, code blocks) and styling (bold, italic) are now preserved when being sent to the AI so that it better understands the document.
• Updated Model Context Protocol Library - The Model Context Protocol SDK that is bundled with AI Positron 8.1 has been updated to contain the latest fixes in the 0.16.0 SDK.
• Removed Support for Older Models - Support for older models (such as GPT-4, GPT-4 Turbo, GPT-4o, Sonnet 3.7, and more) has been removed. Alternatives with improved characteristics are available, such as models with higher intelligence, lower prices, or larger context windows.

DITA Editing

• Edit DITA Change History using Form Controls - You can now use inline actions and form controls in the DITA prolog section to quickly add, edit, or delete change history entries, including setting completion dates and updating revision details, so you can keep audit trails accurate.

DITA Publishing

• Character-Level Fallback Fonts - For DITA to PDF publishing, you can now use the new enable.character.level.font.fallback parameter to enable character-level font fallbacks so that mixed-language content (for example, Latin and non-Latin) is rendered correctly in the same document.

S1000D

• Editing and Validation - You can now edit S1000D documents with schema-guided editing, content completion, and validation support: XML Schema-based validation, and currently BREX-based validation through conversion to Schematron.
• Visual Editing and Actions - You can now visually edit S1000D documents in the Author page and switch between full-width, print preview, or large-font styles. Use dedicated actions to insert and edit tables, lists, and text styling.
• New File Templates - You can now create new S1000D data modules or publication modules for issues 4.0, 4.1, and 4.2 using the provided file templates.
• BREX Editing and Transformation - You can now edit BREX modules in the Text or Author page with content completion and validation support. You can also convert BREX modules to Schematron using the provided transformation scenario.
• Documentation for S1000D Elements and Attributes - You can now view documentation for S1000D elements and attributes directly in the content completion window and in the Attributes view.
• Smart Paste for S1000D Documents - You can now paste content from web browsers or Word documents into S1000D documents while preserving structure and formatting.
• CGM Add-on Update - The CGM add-on that adds support for rendering CGM images in the Author visual editor has been updated to use the latest jcgm version 2.0.5 library.

File/Directory Comparison

• Control Comment Callout Width and Visibility - You can now choose the width used for rendering comment callouts using the new Comment callout width option in the File Comparison Appearance preferences page, so you can better control how much space they take in the comparison view. You can also toggle displaying comment callouts when comparing files in Author mode using the Show comment callouts toolbar button.
• Timestamps and User Information in Comparison Reports - Your comparison reports now include metadata about who ran the comparison, when it was run, and how long it took. This helps you track and audit comparison activity over time. For HTML reports, this information is also displayed in the browser in a collapsible section.

AI Translator Add-on

• AI-Powered Translation Engine - The translation engine delivers high-quality XLIFF translations powered by a built-in quality control mechanism. It validates results through quality checks, detects structural and formatting issues, and escalates retries through alternative models when needed. The engine reuses approved content via TMX-based translation memory, follows your custom instructions (terminology, style, context) for consistent output, and caches AI responses to reduce costs and accelerate repeat translations. Key features include:
  • Translation Quality Checks & Retries - The translation engine detects low-quality translations, structural errors, or formatting problems, and retries failed translations using alternative AI models to meet quality standards.
  • Translation Memory Integration - The built-in translation memory system provides intelligent reuse of existing translations. You can provide TMX 1.4b files to leverage previously translated content, improving consistency across your translation projects.
  • Custom User Translation Instructions - Provide custom instructions to guide the AI translation process. Upload files with specific terminology, style guidelines, or contextual information to ensure translations meet your exact requirements and maintain consistency with your organization's standards.
  • Caching System - The translation engine implements a caching mechanism that stores AI API responses locally to avoid redundant calls. Cached translations are retrieved instantly from local storage, significantly reducing translation costs and improving performance for repeated translations.
• AI Translator View - An intuitive graphical interface is integrated into Oxygen for creating and managing translation tasks. Create translation tasks by specifying an XLIFF file, optional TMX memory files, and custom user instructions. The view includes inline validation for XLIFF and TMX inputs and provides quick access to preferences. Key features include:
  • Real-Time Progress Tracking - Visual progress monitoring provides detailed status updates, including task states, translation unit counts and completion percentages, time estimates, and elapsed time. Track multiple translation jobs simultaneously with individual progress indicators and play/stop controls for each task.
  • Job Persistence - Translation jobs automatically survive JVM restarts and can be resumed from where they left off, ensuring no translation work is lost even in case of unexpected interruptions.
  • XLIFF/TMX Validation Utilities - Built-in validators for XLIFF 1.2 structure and TMX 1.4b inputs catch format issues before processing begins, preventing wasted API calls and ensuring clean translation workflows.
  • Translation Logging and Statistics - Each translation task generates a detailed log file that tracks the entire translation process. The log includes a comprehensive report with translation metrics to help you identify optimization opportunities and manage your translation budget effectively.
• Custom Translation Configurations - You can now define multiple AI translation configurations from a dedicated preferences page. For each configuration, you choose the AI model used for the initial translation, a model used for quality validation (which can differ from the primary model), and alternative models that are used if quality checks fail, creating a fallback chain. You can also adjust performance-related options such as the maximum number of parallel translation jobs and caching behavior. This helps you tailor translation workflows to different projects and balance quality, cost, and speed.

Add-on Updates

• Git Client - Version 5.6.0 of the Git Client has been released with the following updates:
  • Multiple worktrees are now supported, allowing you to manage several branches simultaneously without the hassle of stashing changes or performing a fresh clone.
  • A new Explain commit action is available (when right-clicking commits in the Git History view) that utilizes AI Positron to explain the changes from the selected commits.
  • Actions have been added to quickly open the working copy folder in your system's file manager or terminal.
  • New actions are now available in the Git Branch Manager to show the head of a selected branch in the Git History or to track a remote branch from a local one.
  • The performance of the Git Client has been significantly improved when working without access to the remote repository.
  • Various other improvements, component updates, and bug fixes have been implemented.
  • The minimum required version of Oxygen has been updated to 27.1.

API Additions

• Retrieve Line/Column for Offset in Author Mode - The new WSTextBasedEditorPage.getColumnOfOffset and WSTextBasedEditorPage.getLineOfOffset APIs allow you to retrieve the corresponding line and column information for a caret offset location in the Author visual editor mode.

Accessibility

• Support for VPAT 2.5 - Oxygen has been evaluated against the latest VPAT 2.5 accessibility guidelines.

Component Updates

• The version of OpenJDK that is bundled with the installation kits for providing the Java Runtime Environment has been updated to version 21.0.10 from Eclipse Adoptium.
• Updated the Jackson JSON libraries that are used by the Oxygen core to version 2.20.1.
• The publishing engine has been updated to integrate DITA-OT 4.4.
• The Oxygen plugins for Eclipse have been updated to fully support Eclipse versions 4.38 and 4.39.
• XML Calabash 3.0.38 has been integrated into Oxygen to offer support for validating and transforming XProc scripts.
• The TEI XML schemas have been updated to version 4.11.
• The TEI XSLT Stylesheets have been updated to version 7.60.0.

Scripting

• Provide Options for Directory/File Comparison Scripts via a Configuration File - The directory/file comparison scripts can now read arguments from an XML, JSON, or YAML configuration file.
• Timestamps and User Information in Comparison Reports - Your comparison reports now include metadata about who ran the comparison, when it was run, and how long it took. This helps you track and audit comparison activity over time. For HTML reports, this information is also displayed in the browser in a collapsible section.