Struct ExitPlanModeTool 

pub struct ExitPlanModeTool { /* private fields */ }

Tool that exits plan mode and presents the agent’s plan for human review.

Execution blocks until the human reviewer calls PlanApprovalGate::approve or PlanApprovalGate::reject. The tool returns {"approved": true} or {"approved": false, "reason": "…"} so the agent can branch on the outcome.

Implementations

impl ExitPlanModeTool

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

Create a new ExitPlanModeTool.

• gate — shared with EnterPlanModeTool and AgentRuntime.
• event_sink — emits AgentEvent::PlanProposed to TUI / HTTP.

pub fn with_permissions(self, permissions: Arc<PermissionsConfig>) -> Self

Attach a permissions config so the tool can validate that the plan covers tools in Plan mode.

Trait Implementations

impl Tool for ExitPlanModeTool

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.