QTom
72e5876c64
feat(gateway): Cache-Driven RPM Buffer
- buffer 公式从 baseRPM/5 改为 concurrency + maxSessions
保留 baseRPM/5 作为 floor 向后兼容
- 粘性路径 fallback 新增 [StickyCacheMiss] 结构化日志
reason: rpm_red / gate_check / session_limit / wait_queue_full / account_cleared
- session_limit 路径跳过 wait queue 重试(RegisterSession 拒绝无副作用)
- 典型配置 buffer 从 3 提升至 13,大幅减少高峰期 Prompt Cache Miss
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-31 13:24:22 +08:00
..
2026-03-30 15:36:53 +08:00
2026-03-18 15:03:24 +08:00
2026-03-30 15:44:34 +08:00
2026-02-08 12:05:39 +08:00
2026-02-08 12:05:39 +08:00
2026-03-27 14:33:05 +08:00
2026-03-28 00:55:55 +08:00
2026-03-30 15:54:04 +08:00
2026-03-27 14:33:05 +08:00
2026-03-31 13:24:22 +08:00
2026-03-17 15:38:18 +08:00
2026-03-09 19:55:18 +08:00
2026-02-28 15:01:20 +08:00
2026-03-18 14:13:52 +08:00