Targets & regrading

async def run_agent(ctx: EvalContext):
    result = await support_agent(ctx.input)
    ctx.store(output=result.text, metadata={"tools": result.tools})

@eval(input="I want a refund", target=run_agent)
async def test_refund(ctx: EvalContext):
    assert "refund" in ctx.output.lower(), "Should acknowledge the refund"

@eval(input="Cancel my order", target=run_agent)
async def test_cancel(ctx: EvalContext):
    assert "cancel_order" in ctx.metadata["tools"], "Should call cancel_order"

import { evaluate, type EvalContext } from "ezvals";

async function runAgent(ctx: EvalContext) {
  const result = await supportAgent(String(ctx.input));
  ctx.store({ output: result.text, metadata: { tools: result.tools } });
}

evaluate("test_refund", { input: "I want a refund", target: runAgent }, (ctx) => {
  assert(String(ctx.output).toLowerCase().includes("refund"), "Should acknowledge the refund");
});

evaluate("test_cancel", { input: "Cancel my order", target: runAgent }, (ctx) => {
  assert((ctx.metadata.tools as string[]).includes("cancel_order"), "Should call cancel_order");
});