Struct RequestPlanModeTool 

pub struct RequestPlanModeTool { /* private fields */ }

Tool that asks the user for permission before entering plan mode.

The agent should call this tool before enter_plan_mode whenever it considers a planning phase beneficial. If the user approves, the agent proceeds with enter_plan_mode as usual. If the user rejects, the agent should execute directly without entering plan mode.

This two-step flow avoids wasting tokens generating a plan that the user never wanted.

Implementations

impl RequestPlanModeTool

pub fn new( gate: Arc<PlanModeRequestGate>, event_sink: Arc<dyn EventSink>, ) -> Self

Create a new RequestPlanModeTool.

Trait Implementations

impl Tool for RequestPlanModeTool

fn spec(&self) -> ToolSpec

fn execute<'life0, 'async_trait>( &'life0 self, arguments: Value, ) -> Pin<Box<dyn Future<Output = Result<String>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

fn side_effect_class(&self) -> ToolSideEffect

Classify this tool’s observable side-effects. Default is the most conservative value (External) so any unannotated tool is treated as risky on resume. Override to ReadOnly or Mutating for built-in tools; MCP tools derive this from their annotations.

fn is_readonly(&self) -> bool

Convenience: a tool is read-only iff it classifies as ReadOnly. Used by the parallel-dispatch path in agent.rs. Override only if you have an unusual reason (you almost never should — override side_effect_class instead and let this default through).

fn is_readonly_for_args(&self, _arguments: &Value) -> bool

Like is_readonly but can inspect the call-time arguments.