mirror of
https://github.com/zyycn/codex-proxy-rs.git
synced 2026-11-06 08:06:19 +00:00
Scheduled account warmup sent reasoning.effort=none, but the Codex model catalog lists low as the lowest supported level for every model an account can see. Upstream answers HTTP 200 with an SSE error event (unsupported_value on reasoning.effort), which the warmup terminal check records as response_failed, so the cycle ends with warmed_up=0 and never starts the 5h window. Send low instead and cover the upstream payload with a regression test.