Root cause: Google's fetchAvailableModels API returns different model
catalogs depending on the endpoint. The daily endpoint returns 33
models including Gemini 3.8 Flash series, while the production
endpoint only returns 28 models without 3.8.
Additionally, the User-Agent header was using a stale Electron-style
format (Antigravity/4.3.0) that does not match the real Antigravity
client's UA (antigravity/hub/2.12.2), and unnecessary x-client-name /
x-client-version headers were being sent.
Changes:
- Reorder ANTIGRAVITY_ENDPOINTS to try daily endpoint first (matching
real Antigravity client behavior)
- Update ANTIGRAVITY_USER_AGENT to match the real Antigravity hub UA
- Remove unnecessary x-client-name/x-client-version headers
- Add Gemini 3.8 Flash (high/medium/low/tiered) to static model list
- Add gemini-3.8-flash passthrough in resolveAntigravityModel
vLLM and some OpenAI-compatible APIs reject requests containing an
empty `tools: []` array with a 400 Bad Request. This affects the
model connectivity test which sends no tools. Instead of always
including the tools field, conditionally add it only when tools are
present.
nanoha