mirror of
https://github.com/zyycn/codex-proxy-rs.git
synced 2026-11-06 08:06:19 +00:00
Exclude confirmed OpenAI prewarm requests from completed usage while preserving audit records and unknown inference pricing. Keep only the quota capacity card, trim unused Admin/API diagnostics, and use the actual quota observation time without changing forecast gates. Reduce warning noise and align capacity headings with the cards. Co-authored-by: Codex <noreply@openai.com>