Struct TodoWriteTool 

pub struct TodoWriteTool { /* private fields */ }

Tool that lets the agent create and update a structured task checklist.

Holds a shared reference to the task list so the runtime can read it back via [AgentRuntime::current_todos]. Emits AgentEvent::TodoUpdated via the supplied event_sink on every successful write so downstream consumers (TUI, HTTP API, …) can react without polling.

Implementations

impl TodoWriteTool

pub fn new( todo_list: Arc<RwLock<Vec<TodoItem>>>, event_sink: Arc<dyn EventSink>, ) -> Self

Create a new TodoWriteTool.

• todo_list — shared state; pass the same Arc to [AgentRuntime] so current_todos() returns up-to-date data.
• event_sink — receives AgentEvent::TodoUpdated on every successful write. Pass crate::event::NullSink to suppress.

Trait Implementations

impl Tool for TodoWriteTool

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.