AI垃圾邮件机器人声称不是垃圾邮件，但扫描日志显示它是垃圾邮件

[Roman (Roman Rizzi)]

This will fix both the test and the post not getting flagged:

FIX: Default prompts have to be explicit about the expected format.

The Spam detector Persona system prompt was confusing Claude models. The change makes the expected response format instructions more explicit.