Files
agents_and_robots/e2e/tests/assistant-bot.spec.ts
T
egutierrez 1fd836368f feat: tests E2E para assistant-bot y asistente-2
Tests de cada agente via Element Web + Playwright:
- assistant-bot: saludo DM, pregunta, !help, !ping, E2EE check
- asistente-2: saludo, !tools, tool use (que hora es?), !help, E2EE check

Assertions flexibles para respuestas LLM (no-deterministicas),
estrictas para commands deterministicos (!help, !ping).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-08 14:34:57 +00:00

69 lines
1.8 KiB
TypeScript

import { test, expect } from "@playwright/test";
import {
goToRoom,
sendMessage,
waitForBotReply,
assertNoDecryptionErrors,
} from "../fixtures/matrix-room";
test.describe("assistant-bot", () => {
test.beforeEach(async ({ page }) => {
await page.goto("/");
// Esperar a que la sesion este lista
await expect(
page.locator('[role="tree"][aria-label="Rooms"]')
).toBeVisible({ timeout: 30_000 });
await goToRoom(page, "Assistant");
});
test("responde a un saludo en DM", async ({ page }) => {
await sendMessage(page, "Hola, como estas?");
const reply = await waitForBotReply(page, {
timeout: 60_000,
sender: "Assistant",
});
expect(reply).toBeTruthy();
expect(reply.length).toBeGreaterThan(10);
});
test("responde a una pregunta con contenido coherente", async ({ page }) => {
await sendMessage(page, "Que es la fotosintesis? Responde en una frase.");
const reply = await waitForBotReply(page, {
timeout: 60_000,
sender: "Assistant",
});
expect(reply).toBeTruthy();
expect(reply.length).toBeGreaterThan(10);
});
test("!help muestra lista de comandos", async ({ page }) => {
await sendMessage(page, "!help");
const reply = await waitForBotReply(page, {
timeout: 10_000,
sender: "Assistant",
});
expect(reply).toBeTruthy();
expect(reply.toLowerCase()).toContain("help");
expect(reply.toLowerCase()).toContain("ping");
});
test("!ping responde", async ({ page }) => {
await sendMessage(page, "!ping");
const reply = await waitForBotReply(page, {
timeout: 10_000,
sender: "Assistant",
});
expect(reply).toBeTruthy();
});
test("no hay errores de E2EE en el timeline", async ({ page }) => {
await assertNoDecryptionErrors(page);
});
});