用的newapi接的Nvidia 的deepseek v4pro，关闭了远程压缩，用的ccswitch 。无法自动压缩压缩上下文
但是一旦上下文快满了就会报错
stream disconnected before completion: Requested token count exceeds the model’s maximum context length of 262144 tokens. You requested a total of 262167 tokens: 196631 tokens from the input messages and 65536 tokens for the completion. Please reduce the number of tokens in the input messages or the completion to fit within the limit.
但是可以手动压缩这是什么原因呢
