feat: add Gemini 3.7 Flash

[opencode-agent]

Summary

• add complete provider-agnostic metadata for Gemini 3.7 Flash, including multimodal limits, March 2026 knowledge cutoff, and selected first-party benchmarks
• add gemini-3.7-flash to the Google Gemini API and Vertex AI providers
• record the model's narrower thinking controls: low, medium, and high; unlike Gemini 3.6 Flash, Gemini 3.7 Flash rejects minimal
• use the currently charged introductory pricing through December 31, 2026

Validation

• bun validate

Evidence

• https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/ establishes the model ID, release date, launch surfaces, and standard versus introductory pricing.
• https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash establishes GA status, supported modalities and capabilities, context/output limits, and the explicit rejection of MINIMAL thinking.
• https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/thinking establishes that Gemini 3.7 Flash supports only LOW, MEDIUM, and HIGH, with MEDIUM as the default.
• https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing establishes the current introductory input, output, cached-input, and audio-input pricing through December 31, 2026.
• https://deepmind.google/models/model-cards/gemini-3-7-flash/ establishes the March 2026 knowledge cutoff and benchmark results.

Requested by: @rekram1-node (Aiden Cline via Slack)

[github-actions]

Action items

• [high] [possible mistake] providers/google/models/gemini-3.7-flash.toml:12 - Check: Provider cost must reflect currently charged USD/MTok rates. Why: The PR body says these figures are standard pricing effective 2027-01-01, while introductory pricing runs through 2026-12-31; with today at 2026-08-13, publishing only the future band makes the catalog report wrong prices for both Google and Vertex until 2027. Action: Set cost on providers/google/models/gemini-3.7-flash.toml and providers/google-vertex/models/gemini-3.7-flash.toml to the current introductory rates (cite the pricing page for those numbers); switch to standard rates when they actually apply.

[github-actions]

No actionable findings.