Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All of v2.1.238 Home All releases olderv2.1.237 v2.1.239newer
Claude Code v2.1.238

Safety-classifier severity scoring extended to two more sites, both inert here

Not switched on
Useful2 Signal4
Permissions

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

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.

Details
  • Sites are named handoff and sandboxNetwork; the server key controlling them is severityBySite, 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.
Evidence

"claude-opus-4-8": { t1: 45, t2: 35 }

Strings lifted out of the shipped bundle, so the claim above can be checked against them.

See this entry in the whole of v2.1.238 →