Struct FollowupTool 

pub struct FollowupTool { /* private fields */ }

The schedule_followup tool: the agent books its own next wake-up.

The follow-up runs as a delayed agent_run job in the same session, with delivery on. Turn it on with AgentPlugin::followups.

Implementations

impl FollowupTool

pub const MAX_PROMPT_CHARS: usize = 2_000

Longest prompt a follow-up may carry, in characters.

pub const MAX_CHAIN: u32 = 10

Longest chain of follow-ups (a follow-up that schedules a follow-up that …). Stops an agent from waking itself forever.

pub const fn new(max_delay: Duration) -> Self

Allow follow-ups up to max_delay from now.

pub const fn depth(self, depth: u32) -> Self

The run this tool serves is depth follow-ups deep.

pub fn memory_scope(self, scope: MemoryScope) -> Self

Run follow-ups with memory bound to this scope.

Trait Implementations

impl Clone for FollowupTool

fn clone(&self) -> Self

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for FollowupTool

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Tool for FollowupTool

fn name(&self) -> &'static str

Tool name as the model calls it. Keep it snake_case.

fn description(&self) -> &'static str

What the tool does, shown to the model.

fn input_schema(&self) -> Value

JSON Schema for the tool’s input object.

fn effect(&self) -> ToolEffect

What the tool can change. Defaults to ToolEffect::Write: a tool is trusted with less only when it says so.

fn execute<'a>( &'a self, input: Value, ctx: &'a ToolContext, ) -> Pin<Box<dyn Future<Output = Result<Value, AgentError>> + Send + 'a>>

Run the tool against decoded JSON arguments.

fn definition(&self) -> ToolDefinition

Bundle the metadata the model sees into a ToolDefinition.