test: E2E tests para agente test-personality y pipeline de creacion

Tests funcionales (test-personality.spec.ts): - Saludo con personalidad pirata espacial (keywords flexibles) - Personalidad consistente en respuestas serias (fotosintesis + pirata) - !help y !ping funcionan (assertions estrictas) - Sin errores E2EE Tests de pipeline (create-agent-pipeline.spec.ts): - Valida agent.go con Rules() y ActionKindLLM - Config sin type: robot (es agent por defecto) - System prompt con personalidad + seccion de seguridad - LLM configurado (openai/gpt-4o) - Encryption habilitada, import en launcher Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 20:52:34 +00:00
parent 1089d0e765
commit aea0f74d4a
2 changed files with 162 additions and 0 deletions
@@ -0,0 +1,99 @@
+import { test, expect, handleElementDialogs } from "../fixtures/persistent-context";
+import {
+  goToRoom,
+  sendMessage,
+  waitForBotReply,
+  assertNoDecryptionErrors,
+} from "../fixtures/matrix-room";
+
+// Keywords that indicate pirate-space personality.
+// The LLM is non-deterministic, so we check for presence of ANY keyword from the set.
+const PIRATE_SPACE_KEYWORDS = [
+  "arrr",
+  "cosmonauta",
+  "estelar",
+  "marea",
+  "nave",
+  "galaxia",
+  "estrella",
+  "pirata",
+  "capitan",
+  "nebulosa",
+  "intergal",
+  "asteroide",
+  "meteorito",
+  "agujero negro",
+  "tripulacion",
+  "🏴‍☠️",
+  "🚀",
+  "⭐",
+  "🌌",
+  "☄️",
+  "💀",
+];
+
+function containsPirateKeyword(text: string): boolean {
+  const lower = text.toLowerCase();
+  return PIRATE_SPACE_KEYWORDS.some((kw) => lower.includes(kw.toLowerCase()));
+}
+
+test.describe("test-personality (pirata espacial)", () => {
+  test.beforeEach(async ({ page }) => {
+    await page.goto("/");
+    await handleElementDialogs(page);
+    await goToRoom(page, "Test Personality");
+  });
+
+  test("responde a saludo con personalidad pirata espacial", async ({ page }) => {
+    await sendMessage(page, "Hola, como estas?");
+
+    const reply = await waitForBotReply(page, {
+      timeout: 60_000,
+      sender: "Test Personality",
+    });
+    expect(reply).toBeTruthy();
+    expect(reply.length).toBeGreaterThan(20);
+    expect(containsPirateKeyword(reply)).toBe(true);
+  });
+
+  test("personalidad consistente en respuestas serias", async ({ page }) => {
+    await sendMessage(page, "Que es la fotosintesis? Responde en una frase.");
+
+    const reply = await waitForBotReply(page, {
+      timeout: 60_000,
+      sender: "Test Personality",
+    });
+    expect(reply).toBeTruthy();
+    expect(reply.length).toBeGreaterThan(20);
+    // Should contain real content about photosynthesis
+    expect(reply.toLowerCase()).toMatch(/luz|sol|planta|energia|clorofila|carbon/i);
+    // And still maintain pirate personality
+    expect(containsPirateKeyword(reply)).toBe(true);
+  });
+
+  test("!help muestra lista de comandos", async ({ page }) => {
+    await sendMessage(page, "!help");
+
+    const reply = await waitForBotReply(page, {
+      timeout: 10_000,
+      sender: "Test Personality",
+    });
+    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: "Test Personality",
+    });
+    expect(reply).toBeTruthy();
+  });
+
+  test("no hay errores de E2EE en el timeline", async ({ page }) => {
+    await assertNoDecryptionErrors(page);
+  });
+});