Add Playwright assistant regression coverage

.env.example

@@ -23,4 +23,4 @@ VAPID_PUBLIC_KEY=
 
 # ── AI agent (optional in dev; Asistente won't work without it) ──────────────
 OPENAI_API_KEY=
-AGENT_MODEL=gpt-5.4-mini
+AGENT_MODEL=gpt-5.6-luna

.github/workflows/deploy.yml

@@ -51,7 +51,7 @@ jobs:
           VAPID_PRIVATE_KEY=${{ secrets.VAPID_PRIVATE_KEY }}
           VAPID_PUBLIC_KEY=${{ secrets.VAPID_PUBLIC_KEY }}
           OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}
-          AGENT_MODEL=gpt-5.4-mini
+          AGENT_MODEL=gpt-5.6-luna
           ENVEOF
           sed -i 's/^[[:space:]]*//' .env.prod
 

.gitignore

@@ -16,3 +16,8 @@ tech_docs/
 .claude/
 .venv/
 frontend/openapi.json
+
+# playwright (demo artifacts are generated, not committed)
+frontend/test-results/
+frontend/playwright-report/
+frontend/e2e-docs/

backend/app/agent/agent.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from agent_framework import Agent
-from agent_framework.openai import OpenAIChatCompletionClient
+from agent_framework.openai import OpenAIChatClient
 
 from app.config import settings
 from app.agent.tools import TOOLS
@@ -83,7 +83,9 @@ Generative UI — render tools:
 
 
 def build_agent() -> Agent:
-    client = OpenAIChatCompletionClient(
+    # Use the Responses API for every configured model. It preserves one tool
+    # transport across model changes and supports Luna's tool-result turns.
+    client = OpenAIChatClient(
         api_key=settings.OPENAI_API_KEY,
         model=settings.AGENT_MODEL,
     )

backend/app/config.py

@@ -20,7 +20,7 @@ class Settings(BaseSettings):
     VAPID_PUBLIC_KEY: str = ""
     VAPID_CLAIM_EMAIL: str = "mailto:admin@wealth.cescalante.dev"
     OPENAI_API_KEY: str = ""
-    AGENT_MODEL: str = "gpt-5.4-mini"
+    AGENT_MODEL: str = "gpt-5.6-luna"
 
     @property
     def cors_origins_list(self) -> list[str]:

backend/constraints.txt

@@ -1,8 +1,8 @@
 a2a-sdk==0.3.23
 ag-ui-protocol==0.1.19
-agent-framework==1.10.0
+agent-framework==1.11.0
 agent-framework-a2a==1.0.0b260428
-agent-framework-ag-ui==1.0.0rc7
+agent-framework-ag-ui==1.0.0rc8
 agent-framework-anthropic==1.0.0b260428
 agent-framework-azure-ai-search==1.0.0b260428
 agent-framework-azure-cosmos==1.0.0b260428
@@ -11,7 +11,7 @@ agent-framework-bedrock==1.0.0b260428
 agent-framework-chatkit==1.0.0b260428
 agent-framework-claude==1.0.0b260428
 agent-framework-copilotstudio==1.0.0b260428
-agent-framework-core==1.10.0
+agent-framework-core==1.11.0
 agent-framework-declarative==1.0.0b260428
 agent-framework-devui==1.0.0b260428
 agent-framework-durabletask==1.0.0b260428
@@ -21,7 +21,7 @@ agent-framework-github-copilot==1.0.0b260402
 agent-framework-lab==1.0.0b251024
 agent-framework-mem0==1.0.0b260428
 agent-framework-ollama==1.0.0b260428
-agent-framework-openai==1.10.0
+agent-framework-openai==1.10.1
 agent-framework-orchestrations==1.0.0b260428
 agent-framework-purview==1.0.0b260428
 agent-framework-redis==1.0.0b260428
@@ -165,7 +165,7 @@ six==1.17.0
 sniffio==1.3.1
 SQLAlchemy==2.0.50
 sqlmodel==0.0.38
-sse-starlette==3.4.4
+sse-starlette==3.4.5
 starlette==1.2.1
 tenacity==9.1.4
 tqdm==4.68.2

backend/requirements.txt

@@ -11,6 +11,6 @@ httpx
 pywebpush
 py-vapid
 python-dateutil
-agent-framework==1.10.0
-agent-framework-ag-ui==1.0.0rc7
-agent-framework-openai==1.10.0
+agent-framework==1.11.0
+agent-framework-ag-ui==1.0.0rc8
+agent-framework-openai==1.10.1

backend/tests/test_agent_config.py

@@ -0,0 +1,14 @@
+"""Assistant transport configuration."""
+
+from agent_framework.openai import OpenAIChatClient
+
+from app.agent import agent as agent_module
+
+
+def test_agent_uses_responses_client_for_the_configured_model(monkeypatch):
+    monkeypatch.setattr(agent_module.settings, "AGENT_MODEL", "gpt-5.6-luna")
+
+    agent = agent_module.build_agent()
+
+    assert isinstance(agent.client, OpenAIChatClient)
+    assert agent.client.model == "gpt-5.6-luna"

docker-compose.prod.yml

@@ -31,7 +31,7 @@ services:
       VAPID_PRIVATE_KEY: ${VAPID_PRIVATE_KEY}
       VAPID_PUBLIC_KEY: ${VAPID_PUBLIC_KEY}
       OPENAI_API_KEY: ${OPENAI_API_KEY}
-      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.4-mini}
+      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.6-luna}
       # MAF 1.6+ enables OTel instrumentation by default; keep it off explicitly.
       ENABLE_INSTRUMENTATION: "false"
     expose:

docker-compose.yml

@@ -30,7 +30,7 @@ services:
       VAPID_PRIVATE_KEY: ${VAPID_PRIVATE_KEY:-}
       VAPID_PUBLIC_KEY: ${VAPID_PUBLIC_KEY:-}
       OPENAI_API_KEY: ${OPENAI_API_KEY:-}
-      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.4-mini}
+      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.6-luna}
       # MAF 1.6+ enables OTel instrumentation by default; keep it off explicitly.
       ENABLE_INSTRUMENTATION: "false"
     ports:

frontend/e2e/asistente.spec.ts

@@ -0,0 +1,113 @@
+import { expect, test, type Page } from "@playwright/test";
+
+test.setTimeout(150_000);
+
+async function startFreshAssistant(page: Page) {
+  await page.goto("/login");
+  await page.getByLabel("Username").fill(process.env.ADMIN_USERNAME!);
+  await page.getByLabel("Password").fill(process.env.ADMIN_PASSWORD!);
+  await page.getByRole("button", { name: /sign in/i }).click();
+  await page.waitForURL("/");
+
+  const initialConnect = page.waitForResponse((response) => {
+    if (!response.url().includes("/api/copilotkit") || response.request().method() !== "POST") {
+      return false;
+    }
+    try {
+      return JSON.parse(response.request().postData() ?? "{}").method === "agent/connect";
+    } catch {
+      return false;
+    }
+  });
+  await page.goto("/asistente");
+  await expect(page.getByRole("heading", { name: "Asistente" })).toBeVisible();
+  await (await initialConnect).finished();
+
+  const newConversation = page.getByRole("button", { name: "Nueva conversación" });
+  if (await newConversation.isEnabled()) {
+    await newConversation.click();
+    const reconnect = page.waitForResponse((response) => {
+      if (!response.url().includes("/api/copilotkit") || response.request().method() !== "POST") {
+        return false;
+      }
+      try {
+        return JSON.parse(response.request().postData() ?? "{}").method === "agent/connect";
+      } catch {
+        return false;
+      }
+    });
+    await page.getByRole("button", { name: "Borrar historial" }).click();
+    await (await reconnect).finished();
+    await expect(
+      page.getByRole("textbox", { name: "Escribe tu pregunta…" }),
+    ).toBeEnabled({ timeout: 30_000 });
+  }
+}
+
+async function ask(page: Page, question: string, expectedTool: string) {
+  // The BFF response is the exact CopilotKit stream consumed by the browser.
+  // Checking it catches server-side RUN_ERROR events even if the UI changes.
+  const stream = page.waitForResponse(
+    (response) => {
+      if (
+        !response.url().includes("/api/copilotkit") ||
+        response.request().method() !== "POST"
+      ) {
+        return false;
+      }
+      try {
+        return JSON.parse(response.request().postData() ?? "{}").method === "agent/run";
+      } catch {
+        return false;
+      }
+    },
+  );
+  const composer = page.getByRole("textbox", { name: "Escribe tu pregunta…" });
+  await expect(composer).toBeEnabled({ timeout: 30_000 });
+  await composer.fill(question);
+  const sendButton = page.getByTestId("copilot-send-button");
+  await expect(sendButton).toBeEnabled({ timeout: 30_000 });
+  await sendButton.click();
+  await expect(page.getByText(question, { exact: true }).last()).toBeVisible();
+
+  const response = await stream;
+  await response.finished();
+  const events = await response.text();
+  expect(events).not.toContain("RUN_ERROR");
+  expect(events).toContain(expectedTool);
+
+  // The HTTP stream may finish before CopilotKit has committed the tool run
+  // and released its client-side running state. Waiting for the page action
+  // avoids losing the next Enter keypress during that short interval.
+  await expect(page.getByRole("button", { name: "Nueva conversación" })).toBeEnabled({
+    timeout: 30_000,
+  });
+}
+
+test("Asistente completes Luna's read-only tool flows", async ({ page }) => {
+  const consoleErrors: string[] = [];
+  page.on("console", (message) => {
+    if (message.type() === "error") consoleErrors.push(message.text());
+  });
+
+  await startFreshAssistant(page);
+
+  await ask(page, "What date is it today?", "get_current_date");
+  await ask(page, "List my last 10 transactions.", "get_recent_transactions");
+  await ask(page, "What is my net worth?", "get_net_worth");
+  await ask(page, "How much did I spend today?", "get_daily_spending");
+  await ask(page, "Show my spending by category this month.", "render_spending_summary");
+
+  const spendingCard = page.getByTestId("spending-summary-card");
+  await expect(spendingCard).toBeVisible({ timeout: 30_000 });
+  await expect(page.getByRole("textbox", { name: "Escribe tu pregunta…" })).toBeEnabled({
+    timeout: 30_000,
+  });
+
+  await page.reload();
+  await expect(page.getByRole("heading", { name: "Asistente" })).toBeVisible();
+  await expect(page.getByText("Show my spending by category this month.", { exact: true })).toBeVisible();
+  await expect(page.getByTestId("spending-summary-card")).toBeVisible();
+
+  expect(consoleErrors.join("\n")).not.toContain("ChatClientException");
+});

frontend/e2e/feature-doc.ts

@@ -0,0 +1,127 @@
+import fs from "node:fs";
+import path from "node:path";
+import { test, type Page, type TestInfo } from "@playwright/test";
+import * as narration from "./narration";
+import { renderFinalVideo } from "./video-render";
+import type { Clip } from "./subtitles";
+
+const DEMO = !!process.env.PW_DEMO;
+
+/**
+ * Wraps test.step() so every step of a demo spec produces a captioned
+ * screenshot, and — in PW_DEMO mode — a native Playwright screencast
+ * recording with cursor annotations, chapter-title cards, burned-in
+ * subtitles and (when `say` is available) spoken Spanish narration.
+ * Screenshots/video/subtitles land in e2e-docs/<slug>/ and are also
+ * attached to the Playwright HTML report; save() stitches everything into
+ * a Markdown walkthrough that can be published as-is.
+ */
+export class FeatureDoc {
+  private steps: { title: string; caption: string; file: string }[] = [];
+  private clips: Clip[] = [];
+  private readonly dir: string;
+  private recordingStartedAt = 0;
+
+  constructor(
+    private page: Page,
+    private testInfo: TestInfo,
+    private slug: string,
+    private title: string,
+    private intro: string,
+  ) {
+    this.dir = path.resolve("e2e-docs", slug);
+    fs.rmSync(this.dir, { recursive: true, force: true });
+    fs.mkdirSync(this.dir, { recursive: true });
+  }
+
+  /** Starts the native screencast recording. Call before the first step(). */
+  async start() {
+    if (!DEMO) return;
+    this.recordingStartedAt = Date.now();
+    await this.page.screencast.start({
+      path: path.join(this.dir, "raw.webm"),
+      size: { width: 1920, height: 1080 },
+    });
+    await this.page.screencast.showActions({ cursor: "pointer" });
+  }
+
+  async step(title: string, caption: string, fn: () => Promise<void>) {
+    const narrationPromise = DEMO
+      ? narration.synthesize(caption, this.testInfo.outputDir, this.clips.length)
+      : Promise.resolve(null);
+
+    const stepStart = Date.now();
+    if (DEMO) {
+      await this.page.screencast.showChapter(title, { description: caption, duration: 1500 });
+    }
+
+    await test.step(title, fn);
+
+    const narrationResult = await narrationPromise;
+    if (DEMO) {
+      const elapsed = Date.now() - stepStart;
+      const target = (narrationResult?.durationMs ?? 0) + 300;
+      if (target > elapsed) await this.page.waitForTimeout(target - elapsed);
+    }
+
+    const file = `${String(this.steps.length + 1).padStart(2, "0")}-${title
+      .toLowerCase()
+      .normalize("NFD")
+      .replace(/[̀-ͯ]+/g, "")
+      .replace(/[^a-z0-9]+/g, "-")
+      .replace(/^-|-$/g, "")}.png`;
+    const body = await this.page.screenshot({
+      path: path.join(this.dir, file),
+      animations: "disabled",
+    });
+    await this.testInfo.attach(title, { body, contentType: "image/png" });
+    this.steps.push({ title, caption, file });
+
+    if (DEMO) {
+      this.clips.push({
+        title,
+        caption,
+        file,
+        startMs: stepStart - this.recordingStartedAt,
+        endMs: Date.now() - this.recordingStartedAt,
+        narration: narrationResult,
+      });
+    }
+  }
+
+  async save() {
+    let videoName = "video.mp4";
+    if (DEMO) {
+      await this.page.screencast.stop();
+      const { videoFile, degraded } = await renderFinalVideo({
+        rawWebmPath: path.join(this.dir, "raw.webm"),
+        clips: this.clips,
+        outDir: this.dir,
+      });
+      for (const warning of degraded) console.warn(`[${this.slug}] ${warning}`);
+      videoName = path.basename(videoFile);
+      await this.testInfo.attach("video", {
+        path: videoFile,
+        contentType: videoName.endsWith(".mp4") ? "video/mp4" : "video/webm",
+      });
+    }
+
+    const md = [
+      `# ${this.title}`,
+      "",
+      this.intro,
+      "",
+      `> Generado automáticamente por \`${path.basename(this.testInfo.file)}\` — ${this.steps.length} pasos. El video completo del recorrido está en [${videoName}](${videoName}).`,
+      "",
+      ...this.steps.flatMap((s, i) => [
+        `## ${i + 1}. ${s.title}`,
+        "",
+        s.caption,
+        "",
+        `![${s.title}](${s.file})`,
+        "",
+      ]),
+    ].join("\n");
+    fs.writeFileSync(path.join(this.dir, "index.md"), md);
+  }
+}

frontend/e2e/financiamientos-demo.spec.ts

@@ -0,0 +1,102 @@
+import { test, expect } from "@playwright/test";
+import { FeatureDoc } from "./feature-doc";
+
+/**
+ * Demo walkthrough of the Financiamientos (Tasa Cero) feature. Doubles as an
+ * e2e smoke test and as the generator for e2e-docs/financiamientos/ — a
+ * captioned, screenshot-per-step Markdown doc plus the full video (native
+ * cursor/chapters, burned-in subtitles, spoken narration) in the Playwright
+ * HTML report.
+ */
+// NOTE: do not `test.use({ video: "off" })` here — disabling the fixture
+// video breaks page.screencast's internal sizing (verified: it then records
+// a shrunken frame letterboxed inside the requested canvas). The fixture's
+// own video ends up redundant/unused but harmless.
+
+test("@demo Financiamientos — compras Tasa Cero en cuotas", async ({ page }, testInfo) => {
+  const doc = new FeatureDoc(
+    page,
+    testInfo,
+    "financiamientos",
+    "Financiamientos — Tasa Cero",
+    "WealthySmart trackea las compras BAC Tasa Cero como planes de cuotas mensuales: cada cuota futura ya cuenta en el presupuesto del mes que le toca, en lugar de registrar la compra como un solo pago.",
+  );
+  await doc.start();
+
+  await doc.step(
+    "Iniciar sesión",
+    "El acceso está protegido con usuario y contraseña; la sesión vive en una cookie HTTP-only.",
+    async () => {
+      await page.goto("/login");
+      // CopilotKit mounts its dev web-inspector in dev builds; keep it out of
+      // the recording — it isn't part of the product.
+      await page.addStyleTag({ content: "cpk-web-inspector { display: none !important; }" });
+      await page.getByLabel("Username").fill(process.env.ADMIN_USERNAME!);
+      await page.getByLabel("Password").fill(process.env.ADMIN_PASSWORD!);
+      await expect(page.getByRole("button", { name: /sign in/i })).toBeEnabled();
+    },
+  );
+
+  await doc.step(
+    "Panel de inicio",
+    "Después del login se llega al dashboard Inicio, con el resumen del mes y la navegación lateral por módulos.",
+    async () => {
+      await page.getByRole("button", { name: /sign in/i }).click();
+      await page.waitForURL("/");
+      await expect(page.getByRole("link", { name: "Financiamientos", exact: true })).toBeVisible();
+      await page.waitForLoadState("networkidle");
+    },
+  );
+
+  await doc.step(
+    "Modo privacidad",
+    "El botón de privacidad difumina todos los montos sensibles — útil para compartir pantalla (y para este demo).",
+    async () => {
+      await page.getByRole("button", { name: "Toggle privacy mode" }).click();
+      await expect(page.locator("html")).toHaveClass(/privacy/);
+    },
+  );
+
+  await doc.step(
+    "Página de Financiamientos",
+    "El módulo resume todos los planes Tasa Cero: saldo faltante total, cuánto suman las cuotas de los planes activos cada mes, y cuántos planes siguen vivos.",
+    async () => {
+      await page.getByRole("link", { name: "Financiamientos", exact: true }).click();
+      await page.waitForURL("/financiamientos");
+      await expect(page.getByText("Saldo faltante total")).toBeVisible();
+      await expect(page.getByText("Cuotas por mes (activos)")).toBeVisible();
+      await page.waitForLoadState("networkidle");
+    },
+  );
+
+  await doc.step(
+    "Tabla de planes",
+    "Cada plan muestra el comercio, el avance de cuotas (facturadas vs. totales), el monto de la cuota, el saldo que falta y cuándo cae la próxima cuota.",
+    async () => {
+      const rows = page.getByRole("button", { name: /editar plan de/i });
+      await expect(rows.first()).toBeVisible();
+      expect(await rows.count()).toBeGreaterThan(0);
+      await expect(page.getByRole("columnheader", { name: "Próxima cuota" })).toBeVisible();
+    },
+  );
+
+  await doc.step(
+    "Detalle de un plan",
+    "Al hacer clic en un plan se abre su detalle editable: fecha ancla, número de cuotas y monto. Desde aquí también se puede deshacer la conversión a Tasa Cero.",
+    async () => {
+      await page.getByRole("button", { name: /editar plan de/i }).first().click();
+      await expect(page.getByRole("heading", { name: "Editar plan Tasa Cero" })).toBeVisible();
+    },
+  );
+
+  await doc.step(
+    "Cerrar el detalle",
+    "El plan queda igual que estaba — el recorrido es de solo lectura.",
+    async () => {
+      await page.keyboard.press("Escape");
+      await expect(page.getByRole("heading", { name: "Editar plan Tasa Cero" })).toBeHidden();
+    },
+  );
+
+  await doc.save();
+});

frontend/e2e/narration.ts

@@ -0,0 +1,59 @@
+import { execFile, execFileSync } from "node:child_process";
+import fs from "node:fs";
+import path from "node:path";
+import { promisify } from "node:util";
+
+const execFileAsync = promisify(execFile);
+
+let sayChecked = false;
+let sayAvailable = false;
+
+function hasSay() {
+  if (!sayChecked) {
+    sayChecked = true;
+    try {
+      execFileSync("say", ["-v", "?"], { stdio: "ignore" });
+      sayAvailable = true;
+    } catch {
+      console.warn("`say` not found — skipping TTS narration (subtitles still work).");
+    }
+  }
+  return sayAvailable;
+}
+
+const cache = new Map<string, Promise<{ path: string; durationMs: number } | null>>();
+
+/** Synthesizes Spanish narration for a caption via macOS `say`. Returns null (never throws) if unavailable. */
+export function synthesize(
+  text: string,
+  outDir: string,
+  index: number,
+  voice = "Paulina",
+): Promise<{ path: string; durationMs: number } | null> {
+  const key = `${voice}:${text}`;
+  const cached = cache.get(key);
+  if (cached) return cached;
+
+  const promise = (async () => {
+    if (!hasSay()) return null;
+    fs.mkdirSync(outDir, { recursive: true });
+    const file = path.join(outDir, `narration-${String(index).padStart(2, "0")}.aiff`);
+    try {
+      await execFileAsync("say", ["-v", voice, "-o", file, text]);
+      const { stdout } = await execFileAsync("ffprobe", [
+        "-v", "error",
+        "-show_entries", "format=duration",
+        "-of", "csv=p=0",
+        file,
+      ]);
+      const durationMs = Math.round(parseFloat(stdout.trim()) * 1000);
+      return { path: file, durationMs };
+    } catch (err) {
+      console.warn(`Narration synthesis failed for "${text.slice(0, 40)}…": ${err}`);
+      fs.rmSync(file, { force: true });
+      return null;
+    }
+  })();
+  cache.set(key, promise);
+  return promise;
+}

frontend/e2e/subtitles.ts

@@ -0,0 +1,33 @@
+export interface Clip {
+  title: string;
+  caption: string;
+  file: string;
+  startMs: number;
+  endMs: number;
+  narration: { path: string; durationMs: number } | null;
+}
+
+export function msToSrtTimestamp(ms: number): string {
+  const clamped = Math.max(0, Math.round(ms));
+  const hours = Math.floor(clamped / 3_600_000);
+  const minutes = Math.floor((clamped % 3_600_000) / 60_000);
+  const seconds = Math.floor((clamped % 60_000) / 1000);
+  const millis = clamped % 1000;
+  const pad = (n: number, len = 2) => String(n).padStart(len, "0");
+  return `${pad(hours)}:${pad(minutes)}:${pad(seconds)},${pad(millis, 3)}`;
+}
+
+/** One subtitle cue per step, spanning its full on-screen duration. */
+export function buildSrt(clips: Clip[]): string {
+  return clips
+    .map((clip, i) => {
+      const index = i + 1;
+      return [
+        String(index),
+        `${msToSrtTimestamp(clip.startMs)} --> ${msToSrtTimestamp(clip.endMs)}`,
+        clip.caption,
+        "",
+      ].join("\n");
+    })
+    .join("\n");
+}

frontend/e2e/video-render.ts

@@ -0,0 +1,88 @@
+import { execFile, execFileSync } from "node:child_process";
+import fs from "node:fs";
+import path from "node:path";
+import { promisify } from "node:util";
+import { buildSrt, type Clip } from "./subtitles";
+
+const execFileAsync = promisify(execFile);
+
+function hasFfmpeg() {
+  try {
+    execFileSync("ffmpeg", ["-version"], { stdio: "ignore" });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+const SUBTITLE_STYLE =
+  "FontSize=22,PrimaryColour=&H00FFFFFF,BackColour=&H80000000,BorderStyle=3,Outline=1,Shadow=0,MarginV=40";
+
+function escapeForFilter(p: string) {
+  // ffmpeg filter arguments treat ':' and '\' specially — escape both.
+  return p.replace(/\\/g, "\\\\").replace(/:/g, "\\:");
+}
+
+export async function renderFinalVideo({
+  rawWebmPath,
+  clips,
+  outDir,
+}: {
+  rawWebmPath: string;
+  clips: Clip[];
+  outDir: string;
+}): Promise<{ videoFile: string; degraded: string[] }> {
+  const degraded: string[] = [];
+  const srtPath = path.join(outDir, "captions.srt");
+  fs.writeFileSync(srtPath, buildSrt(clips));
+
+  if (!hasFfmpeg()) {
+    const dest = path.join(outDir, "video.webm");
+    fs.renameSync(rawWebmPath, dest);
+    degraded.push("ffmpeg not found — kept raw video.webm, no subtitles burned in, no narration.");
+    return { videoFile: dest, degraded };
+  }
+
+  const narrated = clips.filter((c) => c.narration);
+  const mp4Path = path.join(outDir, "video.mp4");
+  const srtArg = `subtitles=${escapeForFilter(srtPath)}:force_style='${SUBTITLE_STYLE}'`;
+
+  if (narrated.length === 0) {
+    degraded.push("No narration available — burned-in subtitles only.");
+    await execFileAsync("ffmpeg", [
+      "-y", "-i", rawWebmPath,
+      "-vf", srtArg,
+      "-c:v", "libx264", "-crf", "20", "-pix_fmt", "yuv420p",
+      "-movflags", "+faststart",
+      "-an",
+      mp4Path,
+    ]);
+  } else {
+    const audioInputs = narrated.flatMap((c) => ["-i", c.narration!.path]);
+    const adelayParts = narrated.map(
+      (c, i) => `[${i + 1}:a]adelay=${Math.max(0, Math.round(c.startMs))}|${Math.max(0, Math.round(c.startMs))}[a${i}]`,
+    );
+    const mixInputs = narrated.map((_, i) => `[a${i}]`).join("");
+    const filterComplex = [
+      `[0:v]${srtArg}[vout]`,
+      ...adelayParts,
+      `${mixInputs}amix=inputs=${narrated.length}:normalize=0[aout]`,
+    ].join(";");
+
+    await execFileAsync("ffmpeg", [
+      "-y", "-i", rawWebmPath, ...audioInputs,
+      "-filter_complex", filterComplex,
+      "-map", "[vout]", "-map", "[aout]",
+      "-c:v", "libx264", "-crf", "20", "-pix_fmt", "yuv420p",
+      "-c:a", "aac",
+      "-shortest",
+      "-movflags", "+faststart",
+      mp4Path,
+    ]);
+  }
+
+  fs.rmSync(rawWebmPath, { force: true });
+  for (const c of narrated) fs.rmSync(c.narration!.path, { force: true });
+
+  return { videoFile: mp4Path, degraded };
+}

frontend/package.json

@@ -9,14 +9,16 @@
     "build": "vite build",
     "preview": "tsx server.ts",
     "typecheck": "tsc --noEmit",
+    "e2e": "playwright test",
+    "demo": "PW_DEMO=1 playwright test --grep @demo",
     "gen:api": "openapi-typescript openapi.json -o src/lib/api-types.gen.ts"
   },
   "dependencies": {
     "@ag-ui/client": "0.0.57",
     "@base-ui/react": "^1.4.1",
-    "@copilotkit/react-core": "1.62.2",
-    "@copilotkit/react-ui": "1.62.2",
-    "@copilotkit/runtime": "1.62.2",
+    "@copilotkit/react-core": "1.62.3",
+    "@copilotkit/react-ui": "1.62.3",
+    "@copilotkit/runtime": "1.62.3",
     "@fontsource-variable/ibm-plex-sans": "^5.2.8",
     "@fontsource-variable/noto-sans": "^5.2.10",
     "@hono/node-server": "^1.14.4",
@@ -41,6 +43,7 @@
     "tw-animate-css": "^1.4.0"
   },
   "devDependencies": {
+    "@playwright/test": "^1.61.1",
     "@tailwindcss/vite": "^4",
     "@types/node": "^20",
     "@types/react": "^19",

frontend/playwright.config.ts

@@ -0,0 +1,52 @@
+import fs from "node:fs";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+import { defineConfig } from "@playwright/test";
+
+// Demo specs log in with the real dev credentials; pull them from the repo
+// .env so they never live in the test source.
+const repoEnv = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "../.env");
+if (fs.existsSync(repoEnv)) {
+  for (const line of fs.readFileSync(repoEnv, "utf8").split("\n")) {
+    const m = line.match(/^([A-Z_]+)=["']?(.*?)["']?$/);
+    if (m && !(m[1] in process.env)) process.env[m[1]] = m[2];
+  }
+}
+
+export default defineConfig({
+  testDir: "./e2e",
+  outputDir: "./test-results",
+  fullyParallel: false,
+  // Demo runs synthesize narration and run several ffmpeg passes in save();
+  // that can exceed the 30s default, especially with many steps.
+  timeout: process.env.PW_DEMO ? 120_000 : 30_000,
+  reporter: [
+    ["list"],
+    ["html", { outputFolder: "playwright-report", open: "never" }],
+  ],
+  use: {
+    baseURL: "http://localhost:3000",
+    // Demo runs (pnpm demo) pace every action so the recorded video is
+    // watchable by a human; functional e2e runs stay at full speed.
+    launchOptions: {
+      slowMo: process.env.PW_DEMO ? 500 : 0,
+    },
+    locale: "es-CR",
+    timezoneId: "America/Costa_Rica",
+    viewport: { width: 1920, height: 1080 },
+    // Retina-density rendering so doc screenshots stay crisp when zoomed.
+    deviceScaleFactor: 2,
+    // Full recordings are only useful for the paced demo. Keeping them off
+    // for regular e2e avoids making test success depend on artifact uploads.
+    video: process.env.PW_DEMO ? { mode: "on", size: { width: 1920, height: 1080 } } : "off",
+    screenshot: "only-on-failure",
+    trace: process.env.PW_DEMO ? "on" : "on-first-retry",
+  },
+  webServer: {
+    command: "pnpm dev",
+    url: "http://localhost:3000",
+    reuseExistingServer: true,
+    stdout: "ignore",
+    timeout: 60_000,
+  },
+});

frontend/src/components/chat/ChatCards.tsx

@@ -76,7 +76,10 @@ export function SpendingSummaryCard({
   ];
 
   return (
-    <div className="rounded-xl border border-border bg-card text-card-foreground p-4 space-y-4 my-2 shadow-sm">
+    <div
+      data-testid="spending-summary-card"
+      className="rounded-xl border border-border bg-card text-card-foreground p-4 space-y-4 my-2 shadow-sm"
+    >
       {/* Header */}
       <div className="flex items-start justify-between gap-4">
         <div>