Oxygen AI Positron for Web Author
- 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 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.
- 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, current date, and caret or selection data. Having richer contextual information leads to higher-quality AI responses.
- 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.
- 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 control whether a custom-defined AI action sends both content and referenced images to the LLM by using the "input-type": "markup-with-images" JSON property.
- 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 context of the document.
General Editing/Reviewing
- Apply Colors and Styles for Profiled Content using DITAVAL Flagging - 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.
- Work with Large DITA Tables Using Sticky Headers - You can now keep table headers visible while you scroll large DITA tables. Tables with many rows use an internal scrollbar so you can navigate long tables without losing context.
- Insert Multiple Rows or Columns in Tables - You can now insert multiple empty rows or columns at once in tables from DITA, DocBook, XHTML, and TEI documents. New Insert Rows and Insert Columns actions are available in the table contextual menu, allowing you to choose how many rows or columns to insert and whether to place them before or after the current selection.
- Context-Based File Browsing Filter - The file browser now filters available files based on your current task. When you insert images, maps, DITAVAL files, or other assets, you see only file types that are valid for that action. This helps you find the right files faster and avoid selecting incompatible resources during authoring.
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 visual editing mode 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 or publication modules for issues 4.0, 4.1, and 4.2 using the provided new file templates.
- 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 the structure and formatting.
Customization and Integration
- Custom Mention Suggestions and Notifications - You can now provide custom user suggestions for @ mentions in review comments using the sync.api.author.UserMentionProposalsProvider API. This helps reviewers quickly find and mention the right collaborators. You can combine this with the sync.api.author.ReviewCommentHook API to detect when comments containing mentions are added and notify the mentioned users. When you mention a collaborator in a review comment, a drop-down list displays the available users to make it very easy to select the particular collaborator. By default, the list shows all authors from the current document.
- Intercept and Validate Review Comments - You can now intercept and validate review comments, added or edited, by using the sync.api.author.ReviewCommentHook API. This lets you enforce rules such as allowing @ mentions only for users who are part of the review team.
- Customize File Browser Filters - You can use the File Browser Descriptor API to customize which file types appear in the Web Author file browser and upload dialog boxes. For example, you can define a filter that only shows SVG files when selecting images.
- Control UI Font Family via API - You can use the new workspace.setBaseFontFamily(fontFamily) API to set a custom font family for all views and dialog boxes in Web Author, so you can align the interface with your branding or readability requirements.