Struct BoundaryGuide 

pub struct BoundaryGuide;

Tells the agent to lead with the limitation and stop there.

Deliberately phrased as a test the model applies — “would this act on the world?” — rather than a list of forbidden verbs. A list is a thing to be outside of; the question generalises to whatever the app’s tool belt does not cover.

Trait Implementations

impl Guide for BoundaryGuide

fn id(&self) -> &GuideId

fn kind(&self) -> Execution

fn scope(&self) -> &GuideScope

fn apply<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, ctx: &'life1 mut Context, _w: &'life2 World, ) -> Pin<Box<dyn Future<Output = Result<(), GuideError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Called ONCE per session, at the start, before the first model call. Use for content that doesn’t change across iterations (profile, skills catalogue, static instructions).

fn apply_before_iter<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, _ctx: &'life1 mut Context, _world: &'life2 World, ) -> Pin<Box<dyn Future<Output = Result<(), GuideError>> + Send + 'async_trait>>

where 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, Self: 'async_trait,

Called BEFORE every model.complete() call within a session (default: no-op). Override to inject content that should adapt to the current conversation state — most useful for recall-style guides that want to re-query an external store based on the last user message.