Oxygen Content Fusion Releases

• Updated Apache Tomcat to a newer version.

• Fixed autosave when closing the editor (or when navigating away) in browsers that stopped supporting "unload" event, such as Google Chrome.
• Concurrent Editing in review tasks: Fixed inconsistent rendering of document content across concurrent users.

• Component Update: Apache Tomcat has been updated to versions 9.0.118 and 10.1.55.
• S1000D framework: Updated the 'Insert Image' action to handle image insertion more smoothly and prevent unexpected errors. Smart Paste support has also been restored, allowing content pasted from external sources to be handled correctly again.

Core Updates

• Streamlined Collaboration with mentions - Communication within the review process is now more direct and responsive. You can now pull specific teammates into a conversation exactly where they are needed using mentions. Key improvements
  • Mentioned User Selection - Simply type the @ symbol in any comment or reply to trigger a searchable list of collaborators, then select the desired user to mention.
  • Instant Email Notifications - Once mentioned, the collaborator receives an automated email notification containing your message, ensuring they never miss a critical update.
  • Direct link to comments - Each notification includes a direct link that takes the user straight to the specific message within the review task, eliminating the need to hunt through documents for context.
• New Review Task Dashboard - Navigating complex review cycles just got easier. A dedicated Dashboard view for review tasks was introduced, providing a centralized hub for tracking progress and context at a glance. Key improvements
  • Detailed Task Descriptions - Move beyond simple titles. You can now provide a full description for each task, ensuring all reviewers understand the specific goals and context of the proposed changes.
  • Consolidated Task Metadata - Instantly view task information such as, Status information, Due Date (with a countdown), task Owners, and, in case of tasks created within a project, the task Source consisting of project and branch information.
  • File Management - Access and manage all associated files directly from the dashboard, with action buttons to access various actions, including adding new files to the task.
  • Real-time Review Status - A new sidebar provides a live status of reviewers activity, showing the reviewer status information, so you can easily see who Finalized their review, who is still In Progress, and who did not yet access the task and their status is Pending.
• Better Onboarding Experience with New Project Templates - When creating a sample project, you can use the new carousel to choose from a variety of project templates to help you get started:
  • Empty project to start from scratch.
  • DITA Software Documentation starter project.
  • Circle Chat Demo - A sample software documentation project showcasing reuse and profiling.
  • Hydraulic Gear Pump - A sample hardware documentation project showcasing the use of an image map.
  • Sunny Sky Demo - A sample API documentation project showcasing the inclusion of an OpenAPI JSON file in a DITA XML project.

Updated Visual Editor

• Content Fusion's visual editor was updated to integrate the latest changes implemented in Oxygen XML Web Author 28.1.0.
• Improved Table & Content Flagging Support - Table support was updated to support large DITA tables, by implementing "sticky" headers, keeping table headers visible while you scroll. Tables with many rows use an internal scrollbar so you can navigate long tables without losing context. You can now insert multiple empty rows or columns at once in tables from DITA, DocBook, XHTML, and TEI documents. You can now easily distinguish profiled content by applying colors and text styles using DITAVAL flagging. These styles are rendered directly in the visual editor and DITA Map pane according to your active DITAVAL file.
• Built-in S1000D Support - You can now work with S1000D issue 4.x content using built-in support for editing and visual authoring, including templates, and Smart Paste. Key functionality
  • Editing and Validation - Edit S1000D documents with schema-guided editing, validation, and content completion support.
  • Visual Editing with Dedicated Styles and Actions - Visually edit S1000D documents and switch between full-width, print preview, or large-font styles. Use dedicated actions to insert and edit tables, lists, and text styling.
  • Smart Paste - Paste content from web browsers or Word documents into S1000D documents while preserving the structure and formatting.

Enhanced AI-Assisted Authoring

• You can access AI features via the optional Oxygen AI Positron for Content Fusion plugin. It streamlines content creation and enhances productivity with the ability to use AI Agents and the various built-in AI actions. This release integrates all the latest updates from AI Positron, including the following features:
  • Planner AI Agent - You can select the newly-introduced Planner agent as your current chat mode to handle complex, token-intensive operations (for example, you could ask the AI to translate all files in the current folder, find all conrefs and replace them with conkeyrefs in userguide.ditamap, or update the short descriptions in all topics). The Planner AI agent explores your project, proposes a multi-step plan, and after your approval, delegates each step to the most suitable AI agent for that specific task, such as:
    • Agent - A general-purpose project assistant. You can chat with it about your project, set goals, or give instructions. It proposes changes, and you decide what to keep.
    • DITA Agent - A specialized agent for DITA XML projects. It can explore the project, help with complex DITA tasks, propose a plan, and make project-wide changes on your behalf.
    • Your custom agent - You can now define new agents by creating new AI actions that contain the "output-action": "agentic" property.
  • Smarter Context & Vision - More context information is available when you interact with the AI. The chat now automatically includes additional information about your environment and editing context, such as the application version, current date, and caret or selection data. Having richer contextual information leads to higher-quality AI responses. The structure and styles for attached Word and PDF documents are preserved when attaching them in the chat. Their internal structure (headings, lists, tables, code blocks) and styling (bold, italic) are sent to the AI so that it better understands the content of the document. You can create AI actions with vision support, allowing a custom-defined AI action to send both content and referenced images to the LLM, by using the "input-type": "markup-with-images" JSON property.

Other Improvements

• Project & Task Management
  • Granular Access Control - Introduced Owner and Member roles for Projects (now, only Owners can modify project-level settings).
  • Publication Context - The publication context is now automatically preserved when creating review tasks directly from a project.
  • Streamlined Reviewer Invitations - A new Add Reviewers button in the Review Status drop-down provides instant access to the Share settings.
• User Interface
  • Refined Headers - The application and context headers have been redesigned to reduce clutter and maximize workspace.
  • Focused Editing - Support for collapsing the left side-view allows you to focus entirely on the editor.
  • Optimized Search - A redesigned search side-view now includes a dedicated pop-over for advanced search syntax.
• Review & Activity Side-Views
  • Rich Email Notifications - Review task emails now include the full text of review comments directly in the notification.
  • Dedicated Review View - Review items have moved from a sub-tab in the Search page to their own Review side-view, featuring improved filtering with a Mentioning Me filter for comments.
  • Continuous Feedback - The Task Activity side-view now keeps the message input visible at all times, with automated notifications sent to all task collaborators when a new message is added.
  • Activity Filtering - New filters in the Task Activity view allow you to quickly isolate the entries that are most relevant to you.

Projects

• Control Whether Project Files are Included as Context in a New Review Task - When creating a review task from the project's workspace, a new 'Include all project files as context' option is available to control the set of files to be included in the task's context. When the option is enabled, project files are included to provide context for the reviewers and to avoid missing images or broken links. If disabled, only the selected files are included, allowing you to share specific files.
• Multi-Branch Publishing Pipelines - You can now run deliverables from any branch defined in the project, allowing you to manage and publish multiple versions of your content.
• Easily Create New Review Tasks from the Publications Tree - You can now add topics to a new review task from the Publications tree by using the contextual menu, making it easier to create review tasks that include relevant context.

Review Tasks

• Reactivate Integrated Tasks - For non-project originating review tasks that have been Marked as Integrated, it is now possible to reopen them and send the tasks back into the review flow.

Visual Editor Powered by Oxygen XML Web Author

• Easily Resize Table Columns - You can now adjust column widths for tables simply by dragging the column separator.
• Toggle Full Width Mode on DITA Tables - Tables in DITA documents now have a Toggle Full Width button that appears above the table. This is especially helpful for large tables that are wider than the displayed screen, since it removes the scroll bar and displays the table in full width mode.
• Add Comment from the Floating Toolbar - You can now add comments in a document directly from the floating toolbar that appears when you select content. This helps you give faster feedback in precise locations.
• Display Whitespace Markers in the Editor - You can now display whitespace markers in the editor. This is useful for distinguishing between layout spacing and the whitespace characters that appear in the content.
• View Referenced Markdown Content in Expanded DITA Maps - Content from referenced Markdown files is now displayed when you expand all topics in a DITA map using the View Topic Content action. The Markdown content is automatically converted to DITA and displayed as it will appear in your published output, so you can review all your content together. In Edit Topic Content mode, the Markdown document is read-only.
• Copy Visual Editor Content as Markdown - You can now use the Copy as Markdown option in the visual editor's contextual menu to copy selected content as Markdown. When you paste it into another application (for example, in the prompts given to an AI Agent), formatting such as headings, styling, code blocks, tables, and lists is preserved in Markdown format.
• Preview Video and Audio Controls in DITA 2.0 Documents - When editing DITA 2.0 documents, you can now see video and audio controls (<video>, <audio> elements) rendered directly in the visual editor, so you can easily review embedded media content.
• Search for Specific Attribute Values - You can now search for values that appear in attributes using the Find/Replace side view. After running a search, you can filter the results to show only matches found in attribute values, only in content, or both, helping you quickly locate and update the information you need.

Oxygen AI Positron for Content Fusion

• Uncluttered Chat Input Area - Attachments that you add to your conversation to provide additional context are now presented above the chat input area, ensuring that they do not clutter your instructions. You can still reference specific attachments inline within your instructions by using the @ symbol followed by the file name.
• New AI Models Available - Various new models are now available in the list of AI models to choose from, including:
  • OpenAI - GPT-5.1 and GPT-5.1 Thinking.
  • xAI Grok - Grok 4 Fast and Grok 4 Fast (Non Reasoning).
  • Claude - Claude Sonnet 4.5 and Claude Haiku 4.5.
• Inspect Chat Context - You can now see the main context information that is sent to the AI for the current chat by hovering over the Context chip that is displayed above the chat input area. This adds clarity about the information the AI has available when processing a request. That information includes the editor selection (if available), edited document location, the DITA map location, and the project location (applicable when editing in the Personal Workspace).
• Invoke AI Actions with Keyboard Shortcut - You can now quickly invoke AI actions by using the / symbol in an empty chat, then start typing the name of the action. This displays a pop-up menu with a list of available actions that match the text you entered.
• Edit Document Tool - When using agentic chat to make changes to topics, small changes (e.g. attribute values, spelling corrections) can be made by the AI engine using the newly available edit_document tool that performs exact string replacements in a specified file.
• Easier Access to Tool Call Details - You can now troubleshoot tool calls easier by viewing detailed information about each tool call directly in the Chat view. Simply hover over the tool name to see a summary, or click it to open a dialog box where you can review, copy tool call details, and import or export chats for sharing purposes.
• Custom Actions Prioritized - Your custom actions are now displayed before the built-in actions wherever AI actions are shown, so you can access them more quickly.