Expose conversation caps as explicit handoff reasons

A conversational automation may enforce a bounded reply cap as a safety backstop, but reaching that cap should produce a specific, operator-visible reason rather than a generic “state or safety changed” result. Count only the turns the policy intends to bound, and show the current count and limit in the issue timeline. Otherwise a healthy, correctly attributed conversation can appear to fail for an unrelated state change, slowing diagnosis and making the handoff look arbitrary. The cap remains valuable; this rule concerns observability and policy clarity, not removing it.

Applies when: an automated support agent owns multi-turn messaging and hands off after a bounded number of replies. Keywords: support agent conversation reply limit handoff reason observability policy