Quickstart

export ANPORD_API_KEY="anp_..."
export EVAL_MODEL="gpt-5.6-sol"

import { Anpord } from "anpord";

const anpord = new Anpord();
const model = process.env.EVAL_MODEL;

if (!model) throw new Error("Set EVAL_MODEL");

const { id } = await anpord.evals.start({
  cases: [
    {
      name: "writes the requested file",
      goal: "Create hello.txt containing exactly hello",
      verify: "test \"$(cat hello.txt)\" = hello",
    },
  ],
  prompt: "Work in the current repository. {{goal}}",
  tasks: [{ harness: "codex", model, provider: "daytona" }],
  trials: 3,
});

let run = await anpord.evals.get({ id });

while (run.status === "running") {
  await new Promise((resolve) => setTimeout(resolve, 2_000));
  run = await anpord.evals.get({ id });
}

if (run.status === "failed") {
  throw new Error(run.failure ?? "Eval run failed");
}

const result = run.cells[0]?.distribution;
if (!result) throw new Error("Run produced no result");

console.log({ id, passRate: result.passRate, scored: result.scored });
await anpord.dispose();

bun eval.ts