stop-hook-fires-on-agent-wait-state-not-just-stop

The Stop hook fires repeatedly even when the agent is merely waiting for user input (not actually initiating a stop). Every assistant message that yields control back to the user triggers the hook, flooding the conversation with dozens of false-positive evaluations. The hook condition logic needs to gate on an actual stop() call or agent-initiated termination, not on the hook_event_name=‘Stop’ alone. Fix: add a guard that checks whether the agent explicitly requested session termination before evaluating completion criteria.

Related

• stop-hook-false-positive-during-waiting-state
• stop-hook-false-positive-during-active-wait-state
• stop-hook-fires-on-idle-wait-state-false-positive-loop
• stop-hook-false-positive-during-agent-wait-states
• stop-hook-fires-false-positives-on-agent-waiting-state
• stop-hook-fires-on-agent-idle-state-not-just-termination