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

+2 -1
View File
@@ -1545,6 +1545,7 @@ type RequestView struct {
GuardAction string `json:"guard_action,omitempty"`
GuardPolicy string `json:"guard_policy,omitempty"`
GuardCategory string `json:"guard_category,omitempty"`
GuardRule string `json:"guard_rule,omitempty"`
GuardMs int64 `json:"guard_ms,omitempty"`
// What the client said about it: OpenAI's user field, and its tags.
EndUser string `json:"end_user,omitempty"`
@@ -1573,7 +1574,7 @@ func (a *API) request(w http.ResponseWriter, r *http.Request) {
Model: u.Model, ServedModel: u.ServedModel, Replica: u.Replica, Status: u.Status,
LatencyMs: u.LatencyMs, QueueMs: u.QueueMs, TTFTMs: u.TTFTMs,
PromptTokens: u.PromptTokens, CompletionTokens: u.CompletionTokens, CostMicros: u.CostMicros,
GuardAction: u.GuardAction, GuardPolicy: u.GuardPolicy, GuardCategory: u.GuardCategory, GuardMs: u.GuardMs,
GuardAction: u.GuardAction, GuardPolicy: u.GuardPolicy, GuardCategory: u.GuardCategory, GuardRule: u.GuardRule, GuardMs: u.GuardMs,
EndUser: u.EndUser, Tags: u.Tags, CacheHit: u.CacheHit,
})
}