A late interrupting advisor note delivered after the primary ended with a
terminal text answer (no queued work) was routed to `preserve` for every
severity, so a `blocker` flagging a mistake in the final output became a
passive card that the model ignored until the next user turn.
Scope the terminal-answer preserve rule to non-blocker severities: a
`blocker` now steers a triggered turn so the primary acknowledges and
continues before the turn is considered done, while a late `concern` still
preserves as a visible card (keeps the #4840 no-duplicate-completion path).
Fixes#5628
roboomp
54df76be81