ToolCallJudgeOptions
Matcher context accepted by ToolCallJudge().
Example
Section titled “Example”await expect(result).toSatisfyJudge(ToolCallJudge(), { expectedTools: ["lookupInvoice", "createRefund"],});Extends
Section titled “Extends”JudgeContext<any,any,HarnessMetadata,any>.Omit<ToolCallScorerOptions,"input"|"output"|"toolCalls"|"expectedTools">
Properties
Section titled “Properties”expectedTools?
Section titled “expectedTools?”
optionalexpectedTools?:ToolCallJudgeExpectedTool[]
harness
Section titled “harness”harness:
any
Harness associated with this judge context.
Inherited from
Section titled “Inherited from”input:
any
Original eval input passed to the harness.
Inherited from
Section titled “Inherited from”metadata
Section titled “metadata”metadata:
Readonly<TMetadata>
Per-run expectations or configuration passed to run(input, { metadata }).
Inherited from
Section titled “Inherited from”output
Section titled “output”output:
any
App-facing output returned by the harness.
Inherited from
Section titled “Inherited from”run:
HarnessRun<any>
Complete normalized harness run being judged.
Inherited from
Section titled “Inherited from”runJudge?
Section titled “runJudge?”
optionalrunJudge?:RunJudge
Runs the configured matcher, judge, or suite judge harness with run-scoped context.
Inherited from
Section titled “Inherited from”session
Section titled “session”session:
NormalizedSession
Normalized transcript associated with the harness run.
Inherited from
Section titled “Inherited from”toolCalls
Section titled “toolCalls”toolCalls:
ToolCallRecord[]
Flattened tool calls observed in the normalized session.