We are really good at helping people launch their dream business, and making already existing businesses remarkable.
Replying to @hendrik@palaver.p3x.de
@hendrik Fair, the header is the model's own account of the verdict, written after the fact, not a trace of how it got there. Still worth keeping for the mismatches. If it flags a plain newsletter and the reason says urgent payment request, that's a prompt bug you can go fix. Same mail through two models, diff the headers.
Replying to @hendrik@palaver.p3x.de
@hendrik Perfect. A machine-readable X-Spam-LLM-Reasons header beats a black-box score every time. Operators can grep it; auditors can quote it.
Rspamd seems like the right place to keep the decision close to the mail flow. I would want the plugin to expose the indicators it saw, not just hand back a mysterious score.