feat(mistral-ai/voxtral-mini-transcribe-2602): add new models [bot]#1331
feat(mistral-ai/voxtral-mini-transcribe-2602): add new models [bot]#1331models-bot[bot] wants to merge 2 commits into
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
| key: temperature | ||
| status: active | ||
| supportedModes: | ||
| - audio_transcription |
There was a problem hiding this comment.
Wrong primary transcription mode
Medium Severity
mode is set to unknown while supportedModes lists audio_transcription. For this transcription model, the primary mode should be audio_transcription, matching voxtral-mini-transcribe-2507 and the schema’s intent for canonical capability.
Reviewed by Cursor Bugbot for commit 09b0594. Configure here.
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
There are 2 total unresolved issues (including 1 from previous review).
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 82b4736. Configure here.
| params: | ||
| - defaultValue: 0.0 | ||
| key: temperature | ||
| status: retired |
There was a problem hiding this comment.
New model marked retired
High Severity
This PR adds voxtral-mini-transcribe-2602, but the entry sets isDeprecated: true and status: retired, which in this repo means the model is no longer accessible. That contradicts a “add new models” change and Mistral’s current batch transcription offering for this API id, so consumers may hide or block a live model.
Reviewed by Cursor Bugbot for commit 82b4736. Configure here.
Gateway test results
|
1 participant
Auto-generated by model-addition-agent for
mistral-ai/voxtral-mini-transcribe-2602.Note
Low Risk
Static provider metadata only; no runtime or auth changes.
Overview
Adds a new Mistral provider catalog file for
voxtral-mini-transcribe-2602, auto-generated by the model-addition agent.The entry is minimal: 16k context,
audio_transcriptioninsupportedModes, default temperature 0.0, and it is flaggedisDeprecated: truewithstatus: retiredandmode: unknown(unlike active Voxtral transcribe models such asvoxtral-mini-2602, which use full metadata andstatus: active).Reviewed by Cursor Bugbot for commit 82b4736. Bugbot is set up for automated code reviews on this repo. Configure here.