Selora AI v0.14.0: Required for Home Assistant 2026.8, Plus Group Management from Chat

Selora AI v0.14.0 is out, and this one is not optional if you are on a recent Home Assistant. The Selora AI panel does not render correctly on Home Assistant 2026.8.0 and later without this release. Alongside that fix, Selora AI can now create and maintain Home Assistant groups from chat, automation and scene creation is animated, and chat no longer stalls with cloud gateway models.

Required for Home Assistant 2026.8.0 and later

Home Assistant 2026.8.0 no longer always gives the panel container a definite height. The Selora AI panel shell resolved to auto and became content-sized: the session list laid out every row at full length, the page grew to several screens tall, and the header scrolled off the top. Installs with a long chat history saw the worst of it.

The panel shell is now clamped to the viewport, and the clamp only applies in the failure case. When Home Assistant does size the container, the existing sizing already resolves smaller and nothing changes, so panels HA deliberately constrains are unaffected.

If you are running Home Assistant 2026.8.0 or newer, upgrade to v0.14.0.

Manage Home Assistant groups from chat

Ask Selora AI to group your living-room lights and it creates a real Home Assistant group helper, the same kind you would create yourself in Settings, Devices & Services, Helpers. You can edit it afterwards without touching a single automation.

That is the point. Automations stop repeating long entity lists. They target one stable entity_id, and you change what is in the group whenever you like.

• Four new chat tools. List, create, update, and delete groups without leaving the conversation.
• Per-domain by construction. Numeric sensor groups combine with a statistic, using the mean by default.
• Deletion shows the blast radius. A confirmation card names everything referencing the group, including automations, scripts, scenes, and parent groups, and covers legacy YAML groups too.
• YAML groups stay yours. Groups you defined in YAML are surfaced read-only with an explanation rather than silently duplicated.

Automation and scene creation is now animated

New automations and scenes reveal themselves in the panel as they are created, instead of appearing abruptly. The unused draft subsystem was removed along the way, so the Automations tab shows live automations only, and pending proposals stay in chat where they belong.

Chat no longer stalls with cloud gateway models

If you run DeepSeek or another model served through a gateway, three separate annoyances shared one root cause. Those models sometimes write the tool call they want to make as ordinary text instead of issuing it properly, and Selora AI could not see it.

• No more stalling mid-investigation. With no tool call visible, the turn looked finished, so multi-step investigations stopped and you had to type “continue”. Selora AI now recognises what happened and asks the model to re-issue the call, so the turn carries on by itself.
• No more raw markup in replies. Text like <｜DSML｜tool_calls> reached the chat bubble because the filter only understood the plain ASCII form, and these models use a lookalike character that renders identically. Both forms are now filtered.
• No more repetition. While streaming, the assistant lost track of what it had already said between steps and re-introduced the same sentence each round. Its own wording is now carried forward.

A restart banner instead of a cryptic error

When the integration is updated without restarting Home Assistant, the panel and the backend can fall out of step. That used to surface as extra keys not allowed @ data['…']. The panel now detects the mismatch and tells you to restart or reload, with a matching warning in the log. Translated into all 13 supported locales.

Compatibility

The minimum Home Assistant version is unchanged at 2025.1.0. The 2026.8.0 issue is a rendering regression this release fixes, not a new requirement.

See the full changelog for the complete list.

What’s Next

We are continuing work on Selora AI Local, the private model that runs entirely on your own hardware, so more of what you do stays in your home.

Update via HACS, or if you already have Selora AI installed, the update will appear in your Home Assistant settings.