Agents propose, humans dispose
An agent integration can suggest work; it cannot accept it. That is human in the loop at the point where a proposal becomes a change. magus records authorship from the transport that performed the write, so a change carries the origin the channel delivered (the OS account, the entry point, the credential or host) no matter what the writer reports about itself. Interrupting a person costs attention, and the suggestion operation reflects that: it requires a stated reason before the proposal reaches anyone.
The job store is ordinarily written by agents, unlike the attention events
notify raises, because an attention event is addressed to a person while a
job is an agent-to-agent declaration read back by the guard and the console. A
person still has a full door onto it: magus job forks, takes and returns a
job, and magus ls jobs reads the plan back.
Automated review is wrong at a steady rate, and wrong in a characteristic way: the confident finding that "fixes" behavior somebody chose on purpose. The person deciding whether a proposal lands is the one who catches those findings. If magus applied them itself, they would ship unexamined.
Enforced by
- Authorship is stamped from the transport a write arrived on.
- The suggestion operation refuses a proposal with no stated reason.
- One author per job row, enforced by the store rather than by a closed CLI.
Good
The worker returns its result; a person or the root verifies it before anything lands:
magus job exit design-index --stdin
magus job wait design-index
Bad
review-bot --apply-suggestions --push
The bot's confident findings land with nobody reading them, including the one that "fixes" behavior somebody chose on purpose.