The assistant now answers questions about the tunnel, its live status and its log on the shared page of a remote-access share. It sees only that share and never any key material.
A chat opened from the remote-access dialogs or from the metric editor of a report now stays focused on that topic for its whole life. A badge above the message box shows the topic, and the chat offers matching starter questions.
The assistant now answers where a setting or page is with a link to it, and explains what a type of event means or how a measurement is worked out. It also lists what a plant measures, draws the curve for a component or a whole plant, and points out stretches with no data.
An organization's own Anthropic, OpenAI or self-hosted account can now be added by an administrator or moderator under "AI providers" in the organization's AI settings. The models members may use are picked from it and one marked as the default, after which members choose a model per conversation.
A model can no longer be chosen for the assistant, which always answers on the model Mirox provides. A model an organization had chosen earlier is cleared the next time the AI settings open.
A dropdown beside the chat's input bar sets how much reasoning the assistant does before it answers: "Deep", "Medium", "Low" or "Off". Every conversation opened or switched to starts on "Medium".
The assistant now opens, updates, closes or reopens a ticket, comments on it, and links the components and events it concerns, after asking first. It can also read notifications and activity, look things up in the documentation, and change the signed-in user's own settings.