Update changelog for #4401: split fix and default-model change
This commit is contained in:
@@ -1 +1 @@
|
||||
- Fixed `GrokRealtimeLLMService` ignoring the configured model. The model was stored in `Settings` but never sent to xAI, so every session silently fell back to the deprecated `grok-voice-fast-1.0`. The model is now passed via the `?model=` query parameter on the WebSocket URL as xAI's Voice Agent API requires, and the default has been updated to the recommended `grok-voice-think-fast-1.0`.
|
||||
- Fixed `GrokRealtimeLLMService` ignoring the configured model. The model was stored in `Settings` but never sent to xAI, so every session silently fell back to xAI's server-side default. The model is now passed via the `?model=` query parameter on the WebSocket URL as xAI's Voice Agent API requires.
|
||||
|
||||
Reference in New Issue
Block a user