Ilker Manap and Claude Opus 5.5
c553f2041a
The baseline fails closed with two judges, and a judge not answering is a notification
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 19:19:49 +02:00
Ilker Manap and Claude Opus 5.5
dbcecd1e85
Judge an answer with Llama Guard 3's own prompt, as a completion, not a conversation ending on the answer
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:35:57 +02:00
Ilker Manap and Claude Opus 5.5
742d6633e2
Read a judge's verdict after the answer llama.cpp goes on from, and log a verdict that cannot be read
...
Found on the PoC: llama.cpp takes a conversation ending on the assistant's
turn as a reply to continue, so Llama Guard answered "Rome.safe" and every
answer judged was served unjudged.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:33:23 +02:00
Ilker Manap and Claude Opus 5.5
62038484d6
Never lose a word held back at one release when the next has nothing to rewrite
...
Found on the PoC: a streamed list came out as "1. 2. 3." — each item cut at
one release and dropped at the next, which sent the engine's own events.
A property test now cuts an answer every way and checks it arrives whole.
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:24:22 +02:00
Ilker Manap and Claude Opus 5.5
2cc52fd1a7
Read an unwritten guard mode as enforce when merging, not as the weakest
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:22:07 +02:00
Ilker Manap and Claude Opus 5.5
47e847423d
Guardrail metrics and alerts: checks, latency, judge failures, fail-open, redactions, stopped streams, tenant blocks
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:11:50 +02:00
Ilker Manap and Claude Opus 5.5
43f6a585a6
A judge model on the cluster: role guard in the catalog, judge in a guard policy
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 15:09:31 +02:00
Ilker Manap and Claude Opus 5.5
dc788e5cda
Opt-in capability checks and structured-answer validation in guard policies
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:39:40 +02:00
Ilker Manap and Claude Opus 5.5
ec737cffb5
no_store: refuse conversations, notes and models outside the cluster under a policy that keeps nothing
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:36:02 +02:00
Ilker Manap and Claude Opus 5.5
13e6f19301
Attach guard policies to scopes: store, admin API and ctl guard; run the gate when server.yaml defines policies
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:34:47 +02:00
Ilker Manap and Claude Opus 5.5
b4bdd250af
The gate: judge requests and answers by the policies in force, buffered or a sentence at a time
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:31:55 +02:00
Ilker Manap and Claude Opus 5.5
ccdc07fe0c
Guard policies: a library in server.yaml, merged so nothing below loosens what is above
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:27:23 +02:00
Ilker Manap and Claude Opus 5.5
e3ef5b18c1
Test national phone numbers and bare digit runs
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:25:32 +02:00
Ilker Manap and Claude Opus 5.5
ee33524599
Find personal data and secrets by validated pattern, and prompt injection through disguises
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:25:20 +02:00
Ilker Manap and Claude Opus 5.5
e701f92806
Add the guard interface, and filter hooks in the proxy for buffered and streamed answers
...
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com >
2026-10-04 12:16:00 +02:00
