import-agent-inactive-always-in-outlist

IN premise

Every imported belief unconditionally has `agent:inactive` in its outlist, enforced in `_build_justifications()` with no code path that omits it — this is the mechanism behind the per-agent kill switch.

Summary

When beliefs are imported into the system, they are always tagged with a dependency on their source agent being active. This means any agent can be fully "switched off" at any time — retracting the agent's active status will automatically cascade and pull out every belief that agent contributed, without needing to track or retract them individually.

Details

Sourceentries/2026/05/11/reasons_lib-import_agent.md