feat(google-gemini/gemini-3.5-live-translate-preview): add new models [bot]#1708
Conversation
|
/test-models |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 8cc5caa. Configure here.
| - defaultValue: 0.95 | ||
| key: top_p | ||
| - defaultValue: 64 | ||
| key: top_k |
There was a problem hiding this comment.
Missing max_tokens limit metadata
Medium Severity
The model declares max_output_tokens of 65536 but does not set limits.max_tokens or override the provider max_tokens param. Merged google-gemini defaults still expose max_tokens with maxValue 4096, so registry consumers can treat the generation cap as 4096 despite the 65536 output limit.
Reviewed by Cursor Bugbot for commit 8cc5caa. Configure here.
Gateway test results
Skipped (1)
Skip reason |
1 participant
Auto-generated by model-addition-agent for
google-gemini/gemini-3.5-live-translate-preview.Note
Low Risk
Declarative model metadata only; no runtime or routing logic changes.
Overview
Adds a new provider catalog entry for
gemini-3.5-live-translate-preview, enabling audio translation via Google’s Live Translate API.The YAML defines audio-in / audio+text-out modalities, preview status, serverless provisioning, and audio-token pricing. It exposes sampling params (
temperature,top_p,top_k) and stripsreasoning_effortandtool_choiceas unsupported for this mode. Token limits are set to a 131K context and 65K max output.Reviewed by Cursor Bugbot for commit 8cc5caa. Bugbot is set up for automated code reviews on this repo. Configure here.