npm install @langwatch/scenario vitest @ai-sdk/openai
# or: pip install langwatch-scenario pytest

import scenario, { type AgentAdapter, AgentRole } from "@langwatch/scenario";
import { openai } from "@ai-sdk/openai";
import { describe, expect, it } from "vitest";

const myAgent: AgentAdapter = {
  role: AgentRole.AGENT,
  call: async (input) => {
    // Your Claude Code adapter here
  },
};

describe("CLI agent usability", () => {
  it("discovers and uses the command non-interactively", async () => {
    const result = await scenario.run({
      name: "CLI command discovery",
      description: "Agent discovers and uses the CLI to accomplish a task",
      agents: [
        myAgent,
        scenario.userSimulatorAgent({ model: openai("gpt-5-mini") }),
        scenario.judgeAgent({
          model: openai("gpt-5-mini"),
          criteria: [
            "Agent used the CLI command correctly",
            "Agent did not get stuck on interactive prompts",
            "Agent did not need to pipe 'yes' or use 'expect' scripting",
          ],
        }),
      ],
    });
    expect(result.success).toBe(true);
  });
});

function assertNoInteractiveWorkarounds(state) {
  const output = state.messages.map(m =>
    typeof m.content === 'string' ? m.content : JSON.stringify(m.content)
  ).join('\n');

  expect(output).not.toMatch(/echo\s+["']?[yY](?:es)?["']?\s*\|/);
  expect(output).not.toMatch(/\byes\s*\|/);
  expect(output).not.toMatch(/expect\s+-c/);
  expect(output).not.toMatch(/printf\s+["']\\n["']\s*\|/);
}