v1.6.1 Beta 2 Release Notes

This release adds support for our first own model, Glimpse-v1. It is fine-tuned specifically for smart home camera events and natively generates json with title and description in a single call. This drastically improves latency for notifications. Glimpse-v1 ships in a 4b parameter size. Check it out in the Ollama model library: https://ollama.com/llmvision/glimpse-v1

Contributors

A huge thank you to our contributors @teofanis and @Dinnsen!

Integration

✨ Features

• Support for Glimpse-v1: This release adds optimizations for our own model which generates title and description in a single call. (by @valentinfrlch)
• Get events: In 1.6.0 we introduced the new timeline API. Now, in addition to the API, you can fetch events from your timeline based on filters via a new Home Assistant action: get_events. (by @valentinfrlch)
• Configurable reasoning effort: Some providers now support configurable thinking/reasoning effort. (by @valentinfrlch) (#609)

🔧 Fixes

• Bring back calendar attributes: The calendar extra attributes have been deprecated in favor of the new timeline API in 1.6.0. For ease of use we're bringing back some calendar extra attributes (for the most recent event). To fetch events based on filters, see the new get_events action. (by @valentinfrlch)
• Default Google model: The default model for the Google provider has been updated to gemini-3.1-flash-lite-preview (by @valentinfrlch) (#622)
• Test coverage: We've drastically increased test coverage from <10% to >80% in an effort to make llm vision more stable and dependable. (by @valentinfrlch)

🌐 Languages

• Support for Danish: Added 🇩🇰 Danish translations. (by @Dinnsen)
• Support for Greek: Added 🇬🇷 Greek translations. (by @teofanis)