Guardrails in the console: attach and detach on a branch, where each applies from, and a column

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Ilker ManapandClaude Opus 5.5 committed 2026-10-04 15:18:42 +02:00
1 parent 02aac84ca5
commit d55472c00a
5 files changed
+159 -3

No files matched your search

+13
View File
@@ -64,6 +64,19 @@ APIs change between minors without a deprecation period.
streamed answer is read every 600 characters.
- **Isolation:** a judge model is hidden from clients and refused to them.
It is critical by default, and cannot be loaded on demand.
- **Seeing what the guardrails do.**
- **Metrics:** `llmgw_guard_checks_total` (stage, policy, action,
category, mode), latency for checks and for the judge, judge errors,
fail-open, redactions by kind, stopped streams, and blocks per tenant.
- **Alerts:** judged traffic served unjudged, a slow or unreachable
judge, a tenant's blocks spiking, a secret in an answer.
- **Pages and commands:** `/admin/guard` shows counts by place, policy
and category and the recent requests by id; `ctl request` shows the
verdict; the profile page lists the policies in force where the person
works; the console's organization rows have **Guardrails…** and a
column.
- **The chat page** says when a request was refused or an answer stopped
by policy, instead of showing an error.
### Security