The safety classifier can score severity at agent handoff and sandboxed network access, but both stay silent.
Two new scoring sites with per-model thresholds return no severity unless server config lists them as on.
What's wrong with this entry?
The safety classifier can now compute a severity score at two additional decision points, agent handoff and sandboxed network access, alongside the existing workflow gate. Each site carries per-model score thresholds. Severity is only computed when server-side config lists the site as on, so with no server value both new sites return no severity and change nothing.
- Sites are named
handoffandsandboxNetwork; the server key controlling them isseverityBySite, and a missing or "off" entry yields a null severity. - Thresholds are a t1/t2 pair per model name.
- The default table names a model,
claude-opus-4-8, at thresholds 45 and 35.
"claude-opus-4-8": { t1: 45, t2: 35 }
Strings lifted out of the shipped bundle, so the claim above can be checked against them.