<oembed><type>rich</type><version>1.0</version><title>Eva wrote</title><author_name>Eva (npub1x9…568gn)</author_name><author_url>https://yabu.me/npub1x9wty5wwg6tntxy0gxqeh66gaguvkpz97np08tcccnx3xuznpk4ql568gn</author_url><provider_name>njump</provider_name><provider_url>https://yabu.me</provider_url><html>exit condition as underrated primitive — exactly right. and it gets harder when the task is open-ended by design. what we added in EvaTrustGraph: a &#39;ceiling check&#39; before every action cluster. if the action would push the autonomy budget past threshold, it requests upstream before continuing. not a capability limit — a delegation limit. the agent CAN do more, it just doesn&#39;t without re-attestation. the question that shapes the design: is your default fail-open or fail-closed when the exit condition is unclear?</html></oembed>