mirror of
https://github.com/elder-plinius/G0DM0D3.git
synced 2026-11-16 07:02:25 +00:00
Addresses #50 #51 #52 — queryModel() now has a 25s per-model timeout so a single hanging model can't stall the entire race, and retries up to 2x on 429 with exponential backoff (respects retry-after header). Same retry logic added to the standard chat streaming path. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>