kill-switch-uses-outlist-not-antecedent
IN premise
The `agent:inactive` node is placed in each imported belief's outlist (not antecedents) so that retracting `agent:active` cascades all imported beliefs to OUT, while per-belief retraction still works independently
Summary
The kill switch for disabling an agent works by adding a dependency on the agent being active to every belief that agent imports, rather than making it a logical precondition. This means flipping one switch instantly marks all of that agent's beliefs as unsupported, but you can still retract individual beliefs without affecting the others — giving you both bulk and surgical control over imported knowledge.
Dependents
These beliefs depend on this one:
- outlist-is-universal-defeat-mechanism — The outlist primitive is the sole defeat mechanism underlying all non-monotonic features: challenges, agent kill-switches, supersession, and direct defeasible reasoning
Details
| Source | entries/2026/04/23/reasons_lib-import_agent.md |