Oxygen AI Positron Enterprise Releases

Oxygen AI Positron for Desktop

• Open the AI Assistant in a Separate Window with Complete Chat History - You can now open the AI Positron assistant in a separate window, which starts maximized. You can resize it or move it to a second monitor, giving you more space in your editing environment. In this window, a Chat History panel appears next to the chat, so you can quickly find and reopen past conversations from the current project. You can search conversations by title, date, or content, pin the ones you use most, or rename them.
• Search, Organize, and Manage Your Chat History - Use the new Chat History dialog box to find and manage conversations saved for the current project. Open it with the Show all history action from the History menu in the AI Positron view. Conversations are grouped by day, and you can search by title, description, date, or message content. Pin important chats to keep them at the top of the list, or rename them to make them easier to recognize. AI Positron can also automatically delete unmodified chats after 365 days, while always keeping pinned chats. You can change the retention period or disable the automatic deletion feature from the Chat History preferences page.
• AI-Generated Chat Titles and Descriptions - The AI now generates a title and description for each conversation in the chat history, helping you identify and find past chats more easily. You can choose the AI model used to generate the titles and descriptions in the Chat History preferences page.
• Export and Import the Chat History of a Project - You can now export the complete chat history for a project to back it up, transfer it to another computer, or share it with a colleague. In the History menu of the AI Positron view, choose Export project history to save all conversations from the current project in a ZIP archive. Choose Import project history to add conversations from an archive to the currently open project. The Chat History dialog box provides the same actions through the Export all and Import buttons. Imported conversations are added to your existing history, and you can continue them as you would any other conversation.
• Control AI Providers and Models Available to Your Team - As a team owner, you can now choose which AI providers and models your team members can use through the Positron service and choose the default model they use. On the Positron service website (in the new Models tab of the Teams page), you can block an entire provider to prevent access to it current and future models, or block individual models while keeping some of the models for that provider available. Your own access remains unrestricted, so you can evaluate models before making them available to your team. If team members try to use a blocked model, or voice input (while OpenAI is blocked), Positron informs them that the team owner set this restriction.
• Positron Service Now Supports xAI Models - You can now use xAI's Grok models through the Positron service, giving you another family of AI models to choose from in the assistant.
• New and Updated AI Models - New AI models are now available, giving you more options for balancing quality, reasoning, speed, and cost:
  • OpenAI: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, and GPT-6 Luna are now available. GPT-6.1 Terra Thinking is now the default model for AI Positron Service subscriptions and the OpenAI Responses connector.
  • xAI: Grok 4.7 is now available.
  • Anthropic (Claude): Sonnet 5.5, Sonnet 5.5 Thinking, Haiku 5.5, and Haiku 5.5 Thinking are now available.
• Chat Agents Delegate Investigations to Sub-Agents - The Agent, DITA Agent, and Dev Agent chat modes can now delegate focused investigations or well-defined parts of larger tasks to sub-agents. Sub-agents work independently on their assigned task and return their results to the conversation, helping you break complex work into manageable parts.
• Follow Sub-Agent Activity in Live Conversation Tabs - You can now follow sub-agent activity in live conversation tabs. When an agent delegates work through the invoke_ai_agent tool, an Open agent conversation link appears in the tool call. Click it to open a read-only tab alongside the main chat, where you can follow the sub-agent's progress, tool calls, and final response as they are generated. If the sub-agent requires approval before running an unsafe tool, its tab blinks to get your attention, and you can approve or skip the request directly in that tab.
• Define Sub-Agents in a Single Markdown File - You can now define a sub-agent in a single Markdown file instead of maintaining separate JSON action and prompt files. Store the file in an AI agent folder configured in the Actions, Agents, and Skills preferences page. The file uses YAML front matter to define the sub-agent and when it should be used, followed by its instruction prompt.
• Ask the AI About the Differences Between Documents - The new compare_documents tool lets the AI compare two documents so that you can ask it to summarize the differences between two versions of a document, explain a specific change, or answer questions about the comparison. If a files comparison is open in the editing area, the AI uses that comparison, including unsaved modifications. Otherwise, name two documents in your message and the AI compares them without opening them, using the options from the Files Comparison preferences page, and can optionally use a common ancestor for a three-way comparison. This tool is available in all chat modes and requires Oxygen XML 29 or newer.
• AI Can Reply to Review Comments - The review-comments skill now allows an AI agent to reply to existing review comments, in addition to adding and resolving comments. When you ask the AI to answer a comment, it reads the entire discussion thread and adds its reply to that thread without changing the commented content. The AI ignores comments marked as done, and resolving a comment also removes any AI replies.
• Profiling Conditions Tool - The new get_profiling_conditions tool gives the AI chat modes access to your profiling attributes and allowed values (from the Profiling/Conditional Text preferences or from a DITA subject scheme map), the defined profiling condition sets, the currently applied condition set, and the way profiled content is displayed in the editor. This helps the AI use valid attributes and values and explain why conditional content is excluded or missing from the output. This tool requires Oxygen XML 29 or newer.
• Change or Forget Individual Rules in the AI Memory - The AI memory stores the rules and preferences you give the AI so they apply across conversations. Now, when you state a preference that contradicts or refines a stored rule, the AI replaces the existing rule instead of storing a second, conflicting rule. The new update_memory tool replaces clear_memory, and chat modes and agents that still refer to clear_memory automatically use the new tool.
• Review Plugin Tools Before the AI Runs Them - The AI chat now asks for your confirmation before it runs a tool contributed by a plugin. The confirmation shows what the tool does and the arguments of the call, so you stay in control of what third-party tools do on your behalf. You can choose to always allow the tools you trust.
• Hooks Apply to Tools Invoked by External AI Agents - Tools invoked by external AI agents through the Oxygen MCP server (such as Claude Code or GitHub Copilot), now trigger the same hook events as tools used in the AI chat. This allows hooks that restrict tool use or file edits to apply consistently to MCP requests. Hook events identify these requests with mcp_server in the new invocation_source field and include AI agent's name and version in the new mcp_client_name and mcp_client_version fields. Each MCP client connection of an AI agent is also reported as a mcp_server session, with a sessionStart event when it connects and a sessionEnd event when it ends.
• Restore the Oxygen MCP Server State at Application Start - A new Remember the server state (running or stopped) and restore it at application start option in the Oxygen MCP Server preferences page automatically restarts the Oxygen MCP server when the application starts if you left it running in the previous session.
• View Oxygen MCP Server Status in the AI Positron View - The Oxygen MCP Server toolbar button in the AI Positron view now indicates whether the server is running and how many documents updated by external AI agents are awaiting your review. Click the button to view server details and review the pending changes.
• Reuse Previous Messages - Use the Up arrow button in the chat input area to retrieve a message you previously sent, including its attachments. You can then edit and resend the message without retyping it, making it easy to repeat a request from an earlier session. Keep pressing Up to move backward through your message history, or Down to move forward. When a conversation is open in the chat area, Positron retrieves messages from that particular conversation. When the chat area is empty, it retrieves messages from your most recent conversations.
• Use Editor Variables When Defining Skills - Create AI skills that adapt to the environment where the application runs. Editor variables used in SKILL.md files are expanded when a skill is loaded and when its description is provided to the AI, allowing you to include values such as environment variables (${env(VARIABLE_NAME)}) and system properties (${system(PROPERTY_NAME)}) in skill instructions.
• Batch Convert Documents - When version 6.2.0 or later of the Oxygen Batch Documents Converter add-on is installed, it contributes a convert_documents tool for AI Positron that batch converts documents to the specified output format. For example, you could ask AI Positron to convert a specified file (or folder that contains multiple files) to a particular file format and AI Positron uses the integrated batch document converter tool to process the conversion.

Oxygen AI Positron for Eclipse

• New and Updated AI Models - New AI models are now available, giving you more options for balancing quality, reasoning, speed, and cost:
  • OpenAI: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, and GPT-6 Luna are now available. GPT-6.1 Terra Thinking is now the default model for the OpenAI Responses connector.
  • xAI: Grok 4.7 is now available.
  • Anthropic (Claude): Sonnet 5.5, Sonnet 5.5 Thinking, Haiku 5.5, and Haiku 5.5 Thinking are now available.
• Chat Agents Delegate Investigations to Sub-Agents - The Agent, DITA Agent, and Dev Agent chat modes can now delegate focused investigations or well-defined parts of larger tasks to sub-agents. Sub-agents work independently on their assigned task and return their results to the conversation, helping you break complex work into manageable parts.
• Define Sub-Agents in a Single Markdown File - You can now define a sub-agent in a single Markdown file instead of maintaining separate JSON action and prompt files. Store the file in an AI agent folder configured in the Actions, Agents, and Skills preferences page. The file uses YAML front matter to define the sub-agent and when it should be used, followed by its instruction prompt.
• AI Can Reply to Review Comments - The review-comments skill now allows an AI agent to reply to existing review comments, in addition to adding and resolving comments. When you ask the AI to answer a comment, it reads the entire discussion thread and adds its reply to that thread without changing the commented content. The AI ignores comments marked as done, and resolving a comment also removes any AI replies.

Oxygen AI Positron for Content Fusion

• New and Updated AI Models - New AI models are now available for the enterprise connectors, giving you more options for balancing quality, reasoning, speed, and cost:
  • OpenAI: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, and GPT-6 Luna are now available. GPT-6.1 Terra Thinking is now the default model for the OpenAI Responses connector.
  • xAI: Grok 4.7 is now available.
  • Anthropic (Claude): Sonnet 5.5, Sonnet 5.5 Thinking, Haiku 5.5, and Haiku 5.5 Thinking are now available.
• Chat Agents Delegate Investigations to Sub-Agents - The Agent, DITA Agent, and Dev Agent chat modes can now delegate focused investigations or well-defined parts of larger tasks to sub-agents. Sub-agents work independently on their assigned task and return their results to the conversation, helping you break complex work into manageable parts.
• Ask AI Positron About Document Differences - When comparing or merging documents in Content Fusion, you can ask AI Positron to explain all differences or only a selected block of differences. You can also ask it to suggest ways to resolve conflicts. This helps you understand what changed and decide which changes to keep.
• Define Sub-Agents in a Single Markdown File - You can now define a sub-agent in a single Markdown file instead of maintaining separate JSON action and prompt files. Store the file in an AI agent folder configured in the Actions, Agents, and Skills preferences page. The file uses YAML front matter to define the sub-agent and when it should be used, followed by its instruction prompt.
• AI Can Reply to Review Comments - The review-comments skill now allows an AI agent to reply to existing review comments, in addition to adding and resolving comments. When you ask the AI to answer a comment, it reads the entire discussion thread and adds its reply to that thread without changing the commented content. The AI ignores comments marked as done, and resolving a comment also removes any AI replies.
• Change or Forget Individual Rules in the AI Memory - The AI memory stores the rules and preferences you give the AI so they apply across conversations. Now, when you state a preference that contradicts or refines a stored rule, the AI replaces the existing rule instead of storing a second, conflicting rule. The new update_memory tool replaces clear_memory, and chat modes and agents that still refer to clear_memory automatically use the new tool.
• Use Editor Variables When Defining Skills - Create AI skills that adapt to the environment where the application runs. Editor variables used in SKILL.md files are expanded when a skill is loaded and when its description is provided to the AI, allowing you to include values such as environment variables (${env(VARIABLE_NAME)}) and system properties (${system(PROPERTY_NAME)}) in skill instructions.

Oxygen AI Positron for Web Author

• New and Updated AI Models - New AI models are now available, giving you more options for balancing quality, reasoning, speed, and cost:
  • OpenAI: GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Sol, and GPT-6 Luna are now available. GPT-6.1 Terra Thinking is now the default model for the OpenAI Responses connector.
  • xAI: Grok 4.7 is now available.
  • Anthropic (Claude): Sonnet 5.5, Sonnet 5.5 Thinking, Haiku 5.5, and Haiku 5.5 Thinking are now available.
• Chat Agents Delegate Investigations to Sub-Agents - The Agent, DITA Agent, and Dev Agent chat modes can now delegate focused investigations or well-defined parts of larger tasks to sub-agents. Sub-agents work independently on their assigned task and return their results to the conversation, helping you break complex work into manageable parts.
• Ask AI Positron About Document Differences - When comparing or merging documents in Web Author, you can ask AI Positron to explain all differences or only a selected block of differences. You can also ask it to suggest ways to resolve conflicts. This helps you understand what changed and decide which changes to keep.
• Define Sub-Agents in a Single Markdown File - You can now define a sub-agent in a single Markdown file instead of maintaining separate JSON action and prompt files. Store the file in an AI agent folder configured in the Actions, Agents, and Skills preferences page. The file uses YAML front matter to define the sub-agent and when it should be used, followed by its instruction prompt.
• AI Can Reply to Review Comments - The review-comments skill now allows an AI agent to reply to existing review comments, in addition to adding and resolving comments. When you ask the AI to answer a comment, it reads the entire discussion thread and adds its reply to that thread without changing the commented content. The AI ignores comments marked as done, and resolving a comment also removes any AI replies.

Oxygen AI Positron for Desktop

• Oxygen as a Local MCP HTTP Server - The AI Positron add-on can now run as a local MCP (Model Context Protocol) HTTP server, allowing third-party AI assistants such as Claude Desktop, Claude Code, Open Code, or Cursor to connect and use the tools contributed by AI Positron.
  • A new Oxygen MCP Server preferences page is available in Preferences / Plugins / Oxygen AI Positron.
  • You can configure the port, start or stop the server, and copy the MCP configuration's JSON content to paste into your AI assistant.
  • When the MCP server is started and changes are made to files using the tools provided by the Oxygen MCP Server, a new status button appears in the chat view that allows you to accept, modify, or reject the changes made by the external AI assistants.
  • The server provides a special tool that allows the AI assistant to retrieve context information obtained from the open application, including the project context prompt configured by the user, information about the documents open in the editor and DITA Maps Manager, information about the currently selected document (including the content selected inside it), and the list of skills available to be loaded.
• AI Edits Now Merge Directly into Your Document - Positron merges AI-generated changes directly into your document instead of overwriting and reloading the file. This works whether the document is already open in the Author editing mode or not open at all. 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 the ones of any other contributor. This feature requires the latest Oxygen XML 28.1 build.
• 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 the AI's suggested answers or provide your own response.
• 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 AI Positron Service subscriptions and 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 available with AI Positron Service subscriptions.
  • Google: Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash Lite are available with AI Positron Service subscriptions or through the VertexAI connection.
  • xAI: Grok 4.6, 4.5, and 4.3 are now available for Enterprise users.
  • Voice transcription: The speech-to-text model used to turn voice recordings into text prompts has been updated from GPT-4o Transcribe to GPT Transcribe for the AI Positron Service and OpenAI external connections.
• Validate and Check for Completeness - Ensure your deliverables are publishing-ready by instantly catching critical document errors and broken references directly during your chat session. The new validate_and_check_for_completeness tool invokes a validation check on a DITA map or DITA-OT project file with the settings configuration provided by the LLM, available by default for the DITA Agent chat mode. This tool requires Oxygen XML 29 or newer. Contact us to get early access.
• Validate With Schematron Function - Automate compliance with custom business rules by validating documents against existing Schematron files or tailored rules generated on the fly by AI. The new validate_with_schematron tool, available by default to all AI agents, applies existing Schematron rules or generates new ones based on user-provided requirements to validate documents. This tool requires Oxygen XML 29 or newer.
• Transformation Scenario Tools - Enable autonomous Agent and DevAgent workflows by allowing the AI to automatically publish documentation and verify script-based changes. The new transformation scenario tools let the AI run specific transformation scenarios via invoke_transformation_scenario, discover available options using list_transformation_scenarios, and extract output logs or validation errors directly from the Results view using get_results_messages. These tools require Oxygen XML 29 or newer.
• Configure Maximum Context Window Usage for Microsoft Azure and AWS Bedrock - For Microsoft Azure and AWS Bedrock connectors, model deployments and IDs are custom-defined, so Oxygen cannot automatically determine the available context window size. The new Maximum context window option lets you set it manually, ensuring that the chat's context usage indicator accurately shows the portion of the available context window used by each request and that the automatic context compaction works correctly.
• 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.
• 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). For Oxygen AI Positron Service connections, it now shows the percentage of your plan's credits used, the exact credit count, and the date your credits reset.
• Faster Rewrite and Translation Actions - The built-in Rewrite and Translate to... actions now apply targeted edits instead of regenerating the entire document. This delivers faster results and reduces token usage, especially for large files, while preserving your markup and formatting. You can review, accept, or reject the changes through document change tracking.
• Attach Folders in Chat - You can now attach a folder to a chat message via drag-and-drop or copy and paste. The AI will automatically explore the folder's contents on demand, reading individual files as needed.
• Keep Secrets Out of AI-Generated Commands - When the AI assistant runs command-line commands on your behalf, you no longer need to expose sensitive tokens or credentials to it. Store secrets in Oxygen editor variables or, starting with Oxygen 29, in the dedicated Secrets manager - the values are resolved at runtime, so the AI only sees the variable name, never the secret itself.
• Define Sub-categories for AI Actions - When configuring an AI action, multiple values (separated by / ) can be defined for the categoryId property in the JSON configuration files, and those values are shown visually as subcategories.
• Human-Readable Names Shown for MCP Tools - When an MCP server provides human-readable tool names, you see those names when the tools are called in the Chat view or when they are presented in the Tools dialog box.
• Updated the MCP SDK to Version 2.0.0 - The Model Context Protocol MCP SDK that is used by AI Positron was updated to version 2.0.0 to support the latest standard changes.
• URLs of Opened Files Included in Metadata Information - The URLs of files that are opened during AI conversations are now included in the metadata, giving LLMs more context for investigations.
• User-Edited Sandbox Files Identified in Metadata - When you edit a file that has pending AI Positron changes, the AI recognizes your edits and can re-read the affected sections before proposing further changes. This keeps suggestions aligned with your latest edits before you accept or reject them.
• Large Images Optimized Before Being Sent to the AI - Large images (bigger than 2000 pixels) are now automatically resized before being sent to the AI model, preserving their aspect ratio while keeping them within vision-model limits. This helps reduce token usage, improves reliability, and makes it easier to work with image-rich content.
• Development Actions Consolidated - The Chat About Code, Explain Code, Suggest Refactoring, and Autocomplete AI actions were removed because better results for their intended use can now be achieved by chatting with the AI.
• Wildcards Allowed in Unsafe Tool Auto-Approval Preferences - The Unsafe tool auto-approval preferences page now supports the * wildcard character in tool names. This makes it possible to allow all tools from an MCP server (for example, brave-search_*) without approving each tool individually.

Oxygen AI Positron for Eclipse

• 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 now available through the Gemini connector.
  • xAI - Grok 4.6, 4.5, and 4.3 are now available.
• Validate and Check for Completeness - The new validate_and_check_for_completeness tool invokes a validation and completeness check 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 Oxygen XML 29 or newer.
• Validate With Schematron Function - The new validate_with_schematron tool generates Schematron rules based on user-provided requirements and uses them to validate documents. This tool requires Oxygen XML 29 or newer.
• Faster Rewrite and Translation Actions - The built-in Rewrite and Translate to... actions now apply targeted edits instead of regenerating the entire document. This delivers faster results and reduces token usage, especially for large files, while preserving your markup and formatting. You can review, accept, or reject the changes through document change tracking.
• Large Images Optimized Before Being Sent to the AI - Large images (bigger than 2000 pixels) are now automatically resized before being sent to the AI model, preserving their aspect ratio while keeping them within vision-model limits. This helps reduce token usage, improves reliability, and makes it easier to work with image-rich content.
• Development Actions Consolidated - The Chat About Code, Explain Code, Suggest Refactoring, and Autocomplete AI actions were removed since better results for their intended use can now be achieved through chatting with the AI.

Oxygen AI Positron for Content Fusion

• 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.
• 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 the ones of any other contributor.
• 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.
• 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 AI Positron Service subscriptions and 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 available with AI Positron Service subscriptions.
  • Google - Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, and Gemini 3.5 Flash Lite are now available through the VertexAI connection.
  • xAI - Grok 4.6, 4.5, and 4.3 are now available for Enterprise users.
• Validate and Check for Completeness - The new validate_and_check_for_completeness tool invokes a validate and check for completeness check 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.
• Evaluate XPath Expressions - The new evaluate_xpath tool enables the LLM to retrieve nodes against a document resource 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.
• 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.
• 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.
• 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). For Oxygen AI Positron Service connections, it now shows the percentage of your plan's credits used, the exact credit count, and the date your credits reset.
• Faster Rewrite and Translation Actions - The built-in Rewrite and Translate to... actions now apply targeted edits instead of regenerating the entire document. This delivers faster results and reduces token usage, especially for large files, while preserving your markup and formatting. You can review, accept, or reject the changes through document change tracking.
• Define Sub-categories for AI Actions - When configuring an AI action, multiple values (separated by / ) can be defined for the categoryId property in the JSON configuration files and those values are shown visually as sub-categories.
• URLs of Opened Files Included in Metadata Information - The URLs of files that are opened during AI conversations are now included in the metadata, giving LLMs more context for investigations.
• User-Edited Sandbox Files Identified in Metadata - When you edit a file that has pending AI Positron changes, the AI recognizes your edits and can re-read the affected sections before proposing further changes. This keeps suggestions aligned with your latest edits before you accept or reject them.
• Large Images Optimized Before Being Sent to the AI - Large images (bigger than 2000 pixels) are now automatically resized before being sent to the AI model, preserving their aspect ratio while keeping them within vision-model limits. This helps reduce token usage, improves reliability, and makes it easier to work with image-rich content.

Oxygen AI Positron for Web Author

• 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.
• 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 the ones of any other contributor. This feature requires the latest build of Oxygen XML Web Author 28.1.
• 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.
• 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.
• Validate and Check for Completeness - The new validate_and_check_for_completeness tool invokes a validate and check for completeness check 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 against a document resource 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.
• 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.
• 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.
• 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).
• Define Sub-categories for AI Actions - When configuring an AI action, multiple values (separated by / ) can be defined for the categoryId property in the JSON configuration files and those values are shown visually as sub-categories.
• User-Edited Sandbox Files Identified in Metadata - When you edit a file that has pending AI Positron changes, the AI recognizes your edits and can re-read the affected sections before proposing further changes. This keeps suggestions aligned with your latest edits before you accept or reject them.
• Large Images Optimized Before Being Sent to the AI - Large images (bigger than 2000 pixels) are now automatically resized before being sent to the AI model, preserving their aspect ratio while keeping them within vision-model limits. This helps reduce token usage, improves reliability, and makes it easier to work with image-rich content.

Oxygen AI Positron for Desktop

• 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.
• Configure Scripts for AI Hook Events - A new Oxygen AI Positron Hooks add-on lets you configure external scripts to run when specific AI hook events occur. Using a JSON configuration file, you can connect AI lifecycle events to your own tooling for auditing, policy enforcement, analytics, and workflow automation.
• Automatic Conversation Compaction - A new automatic conversation compaction feature allows the AI Positron to summarize older portions of long conversations (when the allowed context usage reaches 70%) and replace it 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 Preferences page. You can also manually trigger a compaction by using the Context Consumption button in the footer of the AI Positron view.
• Dev Agent Chat Mode - You can use the new Dev Agent chat mode to chat with the AI about your XML development project, set goals, or give instructions. The AI can help with XSL/XSLT, Schematron, DTDs, XML Schemas, XPath, validation, and transformations. It explores your project to complete even the most complex tasks efficiently, proposes a plan, and can make project-wide changes on your behalf, while you decide what to keep.
• New Development Skills - New specialized skills are available to enhance AI assistance for various development vocabularies, including XSLT, XSD, Schematron, and XSpec. These skills help the AI generate more accurate, error-free code suggestions, making development faster and more efficient.
• 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.
• 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.
• Connect to MCP Servers that Use OAuth Authentication - Connections to Model Context Protocol (MCP) HTTP servers that use OAuth are now supported. You can also see a summary of the servers that are running or have failed in the Connection status section and it includes log in/out buttons.
• Load Skills from Zip Archives - You can now pack skill folders as zip archives (with the .skill file extension) to distribute and share custom skills as single files. Once placed in the configured skill folders, these packages are automatically recognized and loaded by AI Positron.
• Fix Multiple Validation Problems at Once - You can now use the AI Positron Fix action on multiple selected validation problems in the Results pane, so you can resolve them in a single operation.
• AWS Bedrock: Connect Using AWS CLI Credentials (Profile/SSO) - The AWS Bedrock connector now supports AWS Credentials (Profile/SSO) as a more secure method than API key authentication. This option requires AWS CLI v2 to be installed on your machine and supports SSO and any other credential type that the AWS CLI supports.
• New AI Models Available - You can now choose from more AI models for AI-assisted tasks:
  • GPT-5.4 Thinking, GPT-5.5, and GPT-5.5 Thinking through the Positron Service or an OpenAI Responses enterprise connection.
  • Claude Opus 4.8 Thinking and Claude Opus 4.8, well-suited for agentic workflows and complex multi-step tasks.
  • Gemini 3.5 Flash through the Positron Service or the VertexAI enterprise connection.
• 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 additional models that are not part of the predefined list.
• Editor Variables Supported in Prompt Reference When Creating Custom AI Actions - When creating custom AI actions, you can now use Oxygen editor variables when defining the prompt_ref property (for example, to reference content from the user's home folder) and the content will be expanded automatically.
• New AI Tool Function for Evaluating XPath Expressions - AI Positron now provides the evaluate_xpath tool function to the LLM, enabling it to retrieve nodes against a document resource using XPath 2.0 expressions. The result includes the matched element and its location within the document, giving you a faster and simpler way to access structured content.
• New XPath AI Functions - ai:chat() and ai:resolve-action() - Two new AI extension functions can be called from XPath, and any XPath-enabled language (XSLT, XQuery, XProc, XSpec, Schematron, Schematron Quick Fix, etc.). The ai:chat function runs a full chat completion. It takes a conversation (and optional tool definitions and model settings) and returns the complete message history, allowing multi-turn exchanges to be continued. The ai:resolve-action function turns a saved AI Positron action into the messages and options that are passed to the ai:chat function, letting you separate an action's definition from its execution. Like the other AI functions, they can be enabled or disabled from the XPath Functions preferences page.

Oxygen AI Positron for Eclipse

• OpenAI Responses Connector for Reasoning Models - You can now configure an OpenAI Responses enterprise connector to use the OpenAI Responses API. This connector is required for newer OpenAI reasoning models (such as GPT-5.5 Thinking) and keeps requests from being stored on OpenAI's servers.
• New Development Skills - New specialized skills are available to enhance AI assistance for various development vocabularies, including XSLT, XSD, Schematron, and XSpec. These skills help the AI generate more accurate, error-free code suggestions, making development faster and more efficient.
• Load Skills from Zip Archives - You can now pack skill folders as zip archives (with the .skill file extension) to distribute and share custom skills as single files. Once placed in the configured skill folders, these packages are automatically recognized and loaded by AI Positron.
• New AI Models Available - You can now choose from more AI models for AI-assisted tasks:
  • GPT-5.4 Thinking, GPT-5.5, and GPT-5.5 Thinking through the OpenAI Responses connector.
  • Claude Opus 4.8 Thinking and Claude Opus 4.8, well-suited for agentic workflows and complex multi-step tasks.
  • Gemini 3.5 Flash through the Gemini connector.
• Editor Variables Supported in Prompt Reference When Creating Custom AI Actions - When creating custom AI actions, you can now use Oxygen editor variables when defining the prompt_ref property (for example, to reference content from the user's home folder) and the content will be expanded automatically.
• New AI Tool Function for Evaluating XPath Expressions - AI Positron now provides the evaluate_xpath tool function to the LLM, enabling it to retrieve nodes against a document resource using XPath 2.0 expressions. The result includes the matched element and its location within the document, giving you a faster and simpler way to access structured content.

Oxygen AI Positron for Content Fusion

• 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.
• Automatic Conversation Compaction - A new automatic conversation compaction feature allows the AI Positron to summarize older portions of long conversations (when the allowed context usage reaches 70%) and replace it 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.
• AI Automatically Saves Custom Actions, Skills, and Prompts in the Current Project - When you ask the AI to create a custom AI action, skill, or context prompt, it now automatically determines the correct location to save it within your current project. This removes the need to manually specify or organize where these customizations are stored.
• 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.
• 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.
• Load Skills from Zip Archives - You can reference an archive that contains custom AI actions, agents, and skills in the Web Author admin pages. Or you can place the custom AI actions, agents and skills in a special folder located in the Content Fusion project (.contentfusion/positron-ai-actions). These skill folders can now be packed as zip archives (with the .skill file extension) and the AI Positron will dynamically load the skills from the archives.
• New AI Models Available - You can now choose from more AI models for AI-assisted tasks:
  • GPT-5.4 Thinking, GPT-5.5, and GPT-5.5 Thinking through the OpenAI Responses enterprise connection.
  • Claude Opus 4.8 Thinking and Claude Opus 4.8, well-suited for agentic workflows and complex multi-step tasks.
  • Gemini 3.5 Flash through the VertexAI enterprise connection.
• 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 additional models that are not part of the predefined list.

Oxygen AI Positron for Web Author

• 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.
• Automatic Conversation Compaction - A new automatic conversation compaction feature allows the AI Positron to summarize older portions of long conversations (when the allowed context usage reaches 70%) and replace it 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.
• 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.
• 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.
• 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 the AI Positron will dynamically load the skills from the archives.
• New AI Models Available - You can now choose from more AI models for AI-assisted tasks:
  • GPT-5.4 Thinking, GPT-5.5, and GPT-5.5 Thinking through the OpenAI Responses enterprise connection.
  • Claude Opus 4.8 Thinking and Claude Opus 4.8, well-suited for agentic workflows and complex multi-step tasks.
  • Gemini 3.5 Flash through the VertexAI enterprise connection.
• 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.

Oxygen AI Positron for Desktop

• Extend AI Capabilities Using Skills - Added the ability to 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 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 LLM 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.
  • Get help with AI Positron features by automatically reading the user guide documentation.
• 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.
• 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 2-4 relevant personas, analyzes the content from their perspectives, identifies conflicting viewpoints, and tries to reach a compromise before providing a final recommendation.
• 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.
• 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.
• 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.
• 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.
• Analyze Referenced SVG Images - When using AI actions such as "Generate image alternate text" or interacting with the AI in the chat, the LLM 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.
• 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. Each affected resource appears as a single entry in the Waiting for Review panel (even if the file was both modified and moved or renamed during the conversation), so you can clearly see what happened and accept or reject the changes. Rejected operations restore files and folders to their original state.
• 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.
• 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.
• New Gemini Models Available for Oxygen AI Positron Service - The Gemini 3 Flash, 3.1 Pro, and 3.1 Flash Lite models are now available in the list of models to choose from when using the Oxygen AI Positron Service.
• Define Multiple AI Connections in JSON Configuration Files - If you configure your AI services using a JSON configuration file, you can now define an array of multiple connections. This provides your users with the flexibility to choose their preferred AI service connection directly from the interface.
• Improved Tools Approval - When prompted to run potentially unsafe tools (for example, tools provided by Model Context Protocol integrations), you can now choose to always approve specific tools. The confirmation prompt no longer times out, preventing automatic cancellations. Additionally, the entire UI of the confirmation request has been redesigned to be more intuitive and easier to read.
• Model Context Protocol (MCP) Improvements - The Model Context Protocol (MCP) SDK has been updated to version 1.1.1. You can now use Oxygen editor variables for all parameter values in an AI Positron MCP configuration file to easily create dynamic and portable configurations. Additionally, you can specify the cwd (current working directory) property for local MCP connections to ensure your commands execute in the correct local context.
• Ask for Website Access - You are now asked directly in the chat view for permission if the LLM attempts to read content from any website. You can choose to always allow connections to a certain website host.

Oxygen AI Positron for Eclipse

• Extend AI Capabilities Using Skills - Added the ability to 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 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 LLM 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.
  • Get help with AI Positron features by automatically reading the user guide documentation.
• 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.
• 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.
• 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.
• 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.
• Analyze Referenced SVG Images - When using AI actions such as "Generate image alternate text" or interacting with the AI in the chat, the LLM 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.
• 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 Multiple Action, Agent, and Skill Folders - You can now configure a comma-separated list of folders that the AI Positron will use to load actions, agents, and skills. This can be done in the Actions section of the AI Positron preferences page.

Oxygen AI Positron for Content Fusion

• Select the LLM Model Directly from the Chat View - Depending on the configured LLM connection, you can now select the LLM model to use when chatting or invoking AI actions using a drop-down control in the chat box.
• Extend AI Capabilities Using Skills - Added the ability to 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 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 LLM 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 Actions, Skills, and Project Context from Content Fusion Projects - If a Content Fusion project contains an ai-positron-actions folder in the project root (or in .contentfusion/ai-positron-actions), AI Positron automatically loads custom actions and skills from it. If the folder also contains an ai-context.md file, its contents are automatically used as the project context prompt for new chats. Updates to these resources are applied when you start a new chat.
• 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.
• 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 2-4 relevant personas, analyzes the content from their perspectives, identifies conflicting viewpoints, and tries to reach a compromise before providing a final recommendation.
• 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.
• 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.
• 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.
• 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.
• 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.
• Analyze Referenced SVG Images - When using AI actions such as "Generate image alternate text" or interacting with the AI in the chat, the LLM 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.
• 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.
• 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.
• 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.
• Edit Markdown Documents While Vibe Writing - When vibe writing, AI Positron can now retrieve content from and modify the current document, whether it is an XML or Markdown document.

Oxygen AI Positron for Web Author

• Select LLM Model in Chat View - Depending on the configured LLM connection, you can now select the LLM model to use when chatting or invoking AI actions using a drop-down control in the chat box.
• Extend AI Capabilities Using Skills - Added the ability to 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 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 LLM 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.
• 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.
• 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 2-4 relevant personas, analyzes the content from their perspectives, identifies conflicting viewpoints, and tries to reach a compromise before providing a final recommendation.
• 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.
• 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.
• 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.
• 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.
• 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.
• Analyze Referenced SVG Images - When using AI actions such as "Generate image alternate text" or interacting with the AI in the chat, the LLM 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.
• 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.
• 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.
• 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.
• Edit Markdown Documents While Vibe Writing - When vibe writing, AI Positron can now retrieve content from and modify the current document, whether it is an XML or Markdown document.

Oxygen AI Positron for Desktop

• OpenAI GPT-5.2 Models Available - The flagship GPT-5.2 and GPT-5.2 Thinking models, OpenAI's flagship models for agentic tasks, are now available in the list of OpenAI models to choose from. The Thinking variant is designed for complex tasks and multi-step decisions where accuracy matters more than speed.
• 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 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 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).
• 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.

Oxygen AI Positron for Eclipse

• OpenAI GPT-5.2 Models Available - The flagship GPT-5.2 and GPT-5.2 Thinking models are now available in the list of OpenAI models to choose from.
• 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.
• 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, and caret or selection data (Oxygen 28.1 or newer).
• 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 context of the document.

Oxygen AI Positron for Content Fusion

• OpenAI GPT-5.2 Models Available - The flagship GPT-5.2 and GPT-5.2 Thinking models are now available in the list of OpenAI models to choose from.
• 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 (Content Fusion 9.0 or newer).
• 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.
• List Directory Tool (Available with Content Fusion 9.1) - When using an agent chat mode, a new list_dir tool is available to list the contents of a directory, which helps the AI understand the structure of your project.
• 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.

Oxygen AI Positron for Web Author

• OpenAI GPT-5.2 Models Available - The flagship GPT-5.2 and GPT-5.2 Thinking models are now available in the list of OpenAI models to choose from.
• Optimized Token Consumption for AI Prompts and Tools - 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 (Web Author 28.1 or newer).
• 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.