Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One change · api

inference-hooks-configuration changed

manage-claude/inference-hooks-configuration

Nearest release: v2.1.271, published 2 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+3added
Lines−3removed
From line 101 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits7to this page, all time

The whole hunk

from line 101, old and new numbered
/
lines
from line 101
101101 
102102Under **Exclusions**, select roles whose members are not covered by Inference hooks: their prompts are never sent to your AI security server. Only custom roles your organization created can be excluded; the built-in roles aren't offered. Pick them in the role selector, whose placeholder reads **Select roles to exclude**, and manage who holds each role from the roles admin page (**Manage roles**); changing exclusions requires identity management permission. The list is empty by default, and with no roles excluded, every governed request is inspected.
103103 
104Exclusion applies to a user's interactive sessions; traffic authenticated by machine credentials is always inspected. If Claude can't resolve a requester's role membership, the request fails closed with a retryable error rather than proceeding uninspected. Changes to the exclusion list are recorded in the audit trail.
104Exclusion applies to a user's interactive sessions; traffic authenticated by machine credentials is always inspected. Changes to the exclusion list are recorded in the audit trail.
105105 
106106## Custom blocked prompt message
107107 
from line 127
127127 
128128To recover, fix the server, then turn **Enforce verdicts** back on to reset the breaker.
129129 
130The breaker can also reset on its own. Starting 10 minutes after the trip, Anthropic tests whether your server has recovered: at most about once per minute, one request from your organization's normal traffic is sent to your server for inspection, and that request proceeds for its user whether or not your server answers. If your server responds with a valid verdict, allow or deny, the breaker resets and enforcement resumes. Any other outcome is a webhook failure: the breaker stays tripped and testing continues.
130The breaker can also reset on its own. Starting 10 minutes after the trip, Anthropic checks whether your server has recovered by sending it a test request in the background, at most about once per minute; no user request is involved. If your server responds with a valid verdict, allow or deny, the breaker resets and enforcement resumes. Otherwise the breaker stays tripped and the checks continue.
131131 
132Automatic recovery runs only while your Inference hooks settings are unchanged since the trip. If you change any Inference hooks setting after a trip, including rotating the signing secret, testing stops and the breaker no longer resets on its own; turn **Enforce verdicts** back on when your server is fixed. Automatic recovery applies only to trips: if you turn **Enforce verdicts** off yourself, enforcement stays off until you turn it back on.
132Automatic recovery runs only while your Inference hooks settings are unchanged since the trip. If you change any Inference hooks setting after a trip, including rotating the signing secret, the checks stop and the breaker no longer resets on its own; turn **Enforce verdicts** back on when your server is fixed. Automatic recovery applies only to trips: if you turn **Enforce verdicts** off yourself, enforcement stays off until you turn it back on.
133133 
134134## Rotate your signing secret
135135