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 v2.1.237 Home All releases olderv2.1.236 v2.1.238newer
Claude Code v2.1.237

Auto-mode classifier reads poll events by sender

Not switched on
Useful2 Signal4
Sessions

The turn-handling classifier now splits queued events into separate turns depending on whether a human or another agent sent them.

Per-sender expansion of queued harness events feeds the auto-mode classifier, reachable only under the poll-events gate.

What

The context handed to the classifier that decides how to handle a turn now expands queued harness events into individual user turns according to who sent them. World events and entries with no sender text are dropped, human-principal text is rendered as a verified human turn, peer-agent text is wrapped as coming from another agent, and anything else is prefixed as a non-user source. Previously the whole attachment contributed no per-sender turns at all.

Details
  • Part of the poll-events path, so it is inert unless that gate is on.
  • The verified-human marker it can emit is itself only produced under the Slack entrypoint.
Evidence

y.authority === "world-event"

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

See this entry in the whole of v2.1.237 →