Permission Settings
A runtime permission mechanism in AI Agent tools that declares the allowed, confirmation-required, or forbidden status of commands, paths, or tools, enforced by the runtime rather than relying on the model's voluntary compliance.
Timeline (last 90 days)
Hooks are scripts automatically executed at specific lifecycle events that can intercept, modify or reject an operation; permission settings declare which commands, paths or tools can run without asking, which must be manually confirmed, and which are completely forbidden; both are enforced by the runtime and do not rely on the model voluntarily complying.
For things that absolutely must not happen (such as pushing to the main branch), writing them in Markdown is merely a request; a hook or permission setting should be used to enforce it.
All Facts (2)
Hooks are scripts automatically executed at specific lifecycle events that can intercept, modify or reject an operation; permission settings declare which commands, paths or tools can run without asking, which must be manually confirmed, and which are completely forbidden; both are enforced by the runtime and do not rely on the model voluntarily complying.
50%UnverifiedFor things that absolutely must not happen (such as pushing to the main branch), writing them in Markdown is merely a request; a hook or permission setting should be used to enforce it.
50%