Files
G0DM0D3/api
faber 64170bf9a2 fix: add per-model timeout (25s) and 429 retry with backoff
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>
2026-07-10 15:50:43 -04:00
..
2026-03-25 10:44:35 -07:00
2026-03-25 10:44:35 -07:00
2026-03-25 10:44:35 -07:00
2026-03-25 10:44:35 -07:00