Struct MockExtensionsProbeTool 

pub struct MockExtensionsProbeTool { /* private fields */ }

Available on crate feature test-utils only.

A mock tool that records whatever it observed in its per-call ToolCallExtensions, so tests can assert the context reached tool execution.

call_with_extensions records session:<id> (or no-session when no SessionId is present). The plain call body records call-no-context as a sentinel: because an overridden call_with_extensions is the single dispatch entry point, that sentinel must never surface from a dispatched run — observing it would mean dispatch wrongly bypassed the context-aware path.

Implementations

impl MockExtensionsProbeTool

pub fn observed(&self) -> Option<String>

What the tool observed on its most recent call, if it has been called.

pub fn observations(&self) -> Vec<String>

Everything the tool observed, one entry per call in call order.

Trait Implementations

impl Clone for MockExtensionsProbeTool

fn clone(&self) -> MockExtensionsProbeTool

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for MockExtensionsProbeTool

fn default() -> MockExtensionsProbeTool

Returns the “default value” for a type.

impl Tool for MockExtensionsProbeTool

const NAME: &'static str = "context_probe"

The name of the tool. This name should be unique within a single ToolSet or other registration scope that dispatches tools by name.

type Error = MockToolError

The error type of the tool.

type Args = Value

The arguments type of the tool.

type Output = String

The output type of the tool.

fn description(&self) -> String

Model-facing description of what the tool does.

fn parameters(&self) -> Value

JSON Schema for the tool arguments.

async fn call(&self, _args: Self::Args) -> Result<Self::Output, Self::Error>

The tool execution method. Both the arguments and return value are a String since these values are meant to be the output and input of LLM models (respectively)

async fn call_with_extensions( &self, _args: Self::Args, extensions: &ToolCallExtensions, ) -> Result<Self::Output, Self::Error>

Tool execution with per-call runtime extensions.

fn name(&self) -> String

A method returning the name of the tool.

fn classify_error(&self, error: &Self::Error) -> ToolFailure

Classify an error returned by this tool into a structured ToolFailure.

fn call_structured( &self, args: Self::Args, extensions: &ToolCallExtensions, ) -> impl Future<Output = Result<ToolReturn<Self::Output>, Self::Error>> + WasmCompatSend

Execute the tool, returning a structured ToolReturn instead of a bare output.