guard.enabled (unset is on) makes every policy check nothing while false, live: llmgw ctl guard off/on set it in the cluster's settings, and ctl status, ctl guard list and the guardrails page say when they are off. A refusal by a judge names the hazard it saw - judge: S6,Specialized Advice - and the verdict is kept with the request in a new usage column, guard_rule, shown by ctl request, the request log and the guardrails page. llmgw ctl guard judge ask has a judge read a text, past the cache, and shows its raw answer and how it is read; the endpoint is kept out of the audit so no text is recorded. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
6 lines
354 B
SQL
6 lines
354 B
SQL
-- What in a guard policy decided a request, beside its category: the
|
|
-- pattern's name, or the judge's verdict — "S6,Specialized Advice" — so a
|
|
-- request a judge refused says which hazard it saw, and a judge that
|
|
-- refuses ordinary questions can be told from one that is right to.
|
|
ALTER TABLE usage ADD COLUMN guard_rule TEXT NOT NULL DEFAULT '';
|