Guardrails turn off and on; a judge's refusal says which hazard; ctl guard judge ask

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>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-06 12:41:08 +02:00
1 parent 3f5a809373
commit 249a91aeec
34 files changed
+505 -33

No files matched your search

+6
View File
@@ -44,6 +44,9 @@ type Summary struct {
ControlPlanes ControlPlanes `json:"control_planes,omitzero"`
// Judges are the guardrails' judge models with something wrong.
Judges []JudgeView `json:"judges,omitempty"`
// GuardOff says the guardrails are turned off (guard.enabled: false):
// no request is checked, whatever the policies say.
GuardOff bool `json:"guard_off,omitempty"`
}
// StoreMember is one member of a replicated store, as its Patroni reports it.
@@ -151,6 +154,9 @@ const idleThreshold = 10 * time.Minute
// Summary builds the fleet summary.
func (a *API) Summary() Summary {
s := Summary{Version: version.Version}
if a.guard != nil && a.guard.Library != nil && !a.guard.Library().On() {
s.GuardOff = true
}
for _, j := range a.Judges() {
if j.Problem != "" {
s.Judges = append(s.Judges, j)