Restructure test connection to discover models first, handle rate limits gracefully

Dikirim

17 Maret 2026 pukul 01.12 UTC

Penulis

Kamo

Commit

7dbc52c

- Model discovery (lightweight GET) runs before chat test (POST) - Rate limit (429) errors show user-friendly warning instead of failing - Auth errors (401/403) show clear "invalid API key" message - Test reports success if models were discovered even if chat test was rate-limited