feat(google-gemini/gemini-3.7-flash-video-understanding-eap): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for google-gemini/gemini-3.7-flash-video-understanding-eap.

---

Note

Low Risk
Single new model metadata file with no runtime or auth changes; low blast radius.

Overview
Registers Gemini 3.7 Flash Video Understanding EAP for the google-gemini provider via a new YAML model definition (auto-generated by the model-addition agent).

The config sets 1M max input tokens and 65536 max output tokens, enables thinking, and exposes standard sampling params (temperature, top_p, top_k) with mode: unknown.

^{Reviewed by Cursor Bugbot for commit 337a714. 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 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 337a714. Configure here.}

[cursor]

Incorrect model mode set

Medium Severity

mode is set to unknown, but this entry is a Gemini Flash video-understanding model with chat sampling params (temperature, top_p, top_k) and thinking: true. Sibling Gemini Flash configs use mode: chat, so registry consumers that filter or route by mode will not treat this model as a chat model.

 

^{Reviewed by Cursor Bugbot for commit 337a714. Configure here.}