feat: support Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

[ImBIOS]

Summary

Add support for Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber models.

Context

Google recently released the Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber models on July 21, 2026. This PR adds support for these models to Forge, enabling users to run fast, cost-efficient, and highly capable agentic workflows.

Changes

• Added gemini-3.6-flash, gemini-3.5-flash-lite, and gemini-3.5-flash-cyber to the vertex_ai provider list in crates/forge_repo/src/provider/provider.json.
• Added gemini-3.6-flash, gemini-3.5-flash-lite, and gemini-3.5-flash-cyber to the google_ai_studio provider list in crates/forge_repo/src/provider/provider.json.
• Added google/gemini-3.6-flash, google/gemini-3.5-flash-lite, and google/gemini-3.5-flash-cyber to the root vertex.json file.

Use Cases

• Run multi-step agentic workflows with 1M context window at extremely low latency and cost.
• Select these models interactively via the :model command.

Testing

• Verified compilation and ran tests in the forge_repo and forge_app crates:

cargo check
cargo test -p forge_repo
cargo test -p forge_app

Links

Fix #3779