feat(google-gemini/lyria-3.5): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for google-gemini/lyria-3.5.

---

Note

Low Risk
Adds a static model metadata file only; no runtime, auth, or billing logic changes.

Overview
Registers Lyria 3.5 under google-gemini via a new lyria-3.5.yaml provider definition (auto-generated by model-addition-agent).

The entry marks the model active and serverless, with text and image inputs and audio output, default sampling params (temperature, top_p, top_k), and a link to Google’s music-generation API docs. mode and supportedModes are set to unknown pending clearer routing semantics.

^{Reviewed by Cursor Bugbot for commit 7132cd6. Bugbot is set up for automated code reviews on this repo. Configure here.}

[cursor]

Cursor Bugbot has reviewed your changes using default effort and found 2 potential issues.

^{❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}

^{Reviewed by Cursor Bugbot for commit 6ad05e5. Configure here.}

[cursor]

Chat params inherited for music model

Medium Severity

params overrides sampling knobs but does not set removeParams. Provider default.yaml still supplies max_tokens, stop, tool_choice, and reasoning_effort. Same-provider Lyria music models strip those chat parameters, so they would stay exposed on this entry.

 

^{Triggered by learned rule: Don't flag model-addition-agent stubs as incomplete}

^{Reviewed by Cursor Bugbot for commit 6ad05e5. Configure here.}

[github-actions]

/test-models