stop-hook-fires-on-every-agent-turn-not-just-session-end

The Stop hook triggers after every agent message turn (including mid-conversation waiting states), not only when the agent genuinely terminates the session. This caused 30+ false-positive hook evaluations in a single brainstorming session where the agent was simply waiting for user input between clarifying questions. The hook’s condition ‘Before allowing the agent to stop’ is evaluated on every tool-use completion, not only on explicit session termination.

Related

• stop-hook-false-positive-loop-on-agent-waiting-state
• stop-hook-needs-agent-stop-intent-guard
• stop-hook-false-positive-on-waiting-state
• stop-hook-deadlock-on-awaiting-user-input-sessions
• stop-hook-infinite-loop-when-brainstorming-awaits-user-input
• stop-hook-must-check-for-actual-stop-event-not-message-conte
• stop-hook-fires-on-agent-waiting-state-not-only-stop