Description
The problem
Since 2025.4 I noticed that my voice pipeline with "prefer local" option enabled does not prefer the local assist in almost any cases which leads LLM is used all the time.
This makes it quite hard to use standard sentences which should be predictable.
I used custom sentences and built-in ones
Built-in
Via GGA
Custom-Sentence
Sentence Wie ist die Temperatur im Garten?
Local Assist
Via GGA
What version of Home Assistant Core has the issue?
core-2025.4.1
What was the last working version of Home Assistant Core?
core-2025.3.0
What type of installation are you running?
Home Assistant OS
Integration causing the issue
Google Generative AI
Link to integration documentation on our website
No response
Diagnostics information
No response
Example YAML snippet
Anything in the logs that might be useful for us?
Additional information
I use the defaults.
