Module spam 

The spam filter’s tools (docs/mcp.md, “The spam filter’s tools”), so that an agent can run it, watch it and judge it from outside, as sioul spam does (crate::spam::report, whose lines and data each answers with).

• Reading: spam_status (numbers), spam_eval (the table’s test, and its worst errors by sender and subject, masked), spam_dry_run (what the filter would do now with the mail in each inbox: nothing moves), spam_review (the review queue), spam_job (a job, as it stands).
• Writing: spam_label (one line in this device’s label log, as the window’s Spam and Not spam write it: never a move, nothing on a server); spam_fetch and spam_train start a job apart and answer at once with its id. The download reads your mail servers, read-only; a training is a trial unless replace is asked.

Senders and subjects are listed as search_mail lists them: masked (codes, sign-in links, account numbers), hostile mail to a shielded address by “someone at” its domain, nothing from a blocked sender. [mcp] spam = false keeps all of them from agents (protocol).

Constants

ACTIONS 🔒

TOOLS

Functions

action 🔒

An action asked by its name.

answer 🔒

A report as the agent is given it: a message kept from agents (a closed project’s, or in no project while those are closed, access) taken out of every list, its line with it, and counted, never named.

dry_run 🔒

eval 🔒

fetch 🔒

job 🔒

label 🔒

review 🔒

status 🔒

train 🔒