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's wrong with this entry?
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.
- 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.
y.authority === "world-event"
Strings lifted out of the shipped bundle, so the claim above can be checked against them.