OpenAI/Composite groups can now reject requests that exceed the max reasoning effort instead of always rewriting them down to the ceiling. Existing groups keep the previous auto-downgrade behavior.
用量行新增 requested_reasoning_effort,记录分组策略与模型族改写前的客户端请求值;推理强度列与模型列一致,主行显示请求值,有映射时用 ↳ 展示实际转发值。