evOo-local/apps/web/e2e/media-pipeline.spec.ts
cynarAI 42eb420545
Agent replies without thinking aloud or tool names; chart-links E2E names its failure (#199)
A run of the real prompt against the local model showed reasoning written as chat text, internal tool names in a capabilities answer, and only a data fetch when asked to build a tool. The working principles now say that everything written is shown, to describe abilities in plain words, and that a request for a tool means building one.

The chart-links spec now waits for the chart or its error and reports browser errors, so the recurring 90-second timeout names its cause. The ZIP upload spec matches the file chip exactly, since the agent reply can quote the name.
2026-10-10 17:24:34 +02:00

113 lines
4.8 KiB
TypeScript

import path from "node:path";
import { fileURLToPath } from "node:url";
import { expect, test } from "@playwright/test";
import { captureScreenshot, completeOnboarding, signup } from "./helpers";
test.describe.configure({ mode: "serial" });
// VP9 in MP4: Playwright's Chromium has no H.264 decoder, real browsers play both.
const clip = path.join(path.dirname(fileURLToPath(import.meta.url)), "fixtures", "media-clip.mp4");
const pixel = Buffer.from(
"iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mP8z8BQDwAEhQGAhKmMIQAAAABJRU5ErkJggg==",
"base64",
);
test("an uploaded video streams from the artifact route and plays inline", async ({
page,
}, testInfo) => {
const stamp = Date.now();
await signup(page, `media-video-${stamp}@rakazo.test`, "password12", "Media Video");
await completeOnboarding(page);
const upload = page.waitForResponse(
(response) =>
response.request().method() === "POST" && /\/api\/artifacts\?/.test(response.url()),
);
await page.locator('input[type="file"]').setInputFiles(clip);
await expect(page.getByRole("button", { name: "Remove media-clip.mp4" })).toBeVisible();
await page.getByRole("combobox", { name: /Message/ }).fill("here is the clip");
await page.keyboard.press("Enter");
expect((await upload).status()).toBe(201);
const video = page.getByTestId("media-video").locator("video");
await expect(video).toBeVisible({ timeout: 30_000 });
await expect(video).toHaveAttribute("src", /^\/api\/artifacts\/[^/?]+$/);
await expect
.poll(() => video.evaluate((element: HTMLVideoElement) => element.readyState), {
timeout: 15_000,
})
.toBeGreaterThanOrEqual(1);
expect(await video.evaluate((element: HTMLVideoElement) => element.duration)).toBeCloseTo(1, 0);
await video.evaluate(async (element: HTMLVideoElement) => {
element.muted = true;
await element.play();
});
await expect
.poll(() => video.evaluate((element: HTMLVideoElement) => element.currentTime))
.toBeGreaterThan(0);
await video.evaluate((element: HTMLVideoElement) => {
element.pause();
element.currentTime = 0.5;
element.scrollIntoView({ block: "center" });
});
await captureScreenshot(page, testInfo, "media-video-block");
});
test("an image in the main conversation opens and downloads from the artifact route", async ({
page,
}) => {
const stamp = Date.now();
await signup(page, `media-image-${stamp}@rakazo.test`, "password12", "Media Image");
// The main conversation is a group thread, so this covers group uploads and reads.
await completeOnboarding(page, undefined, { mainConversation: true });
await page
.locator('input[type="file"]')
.setInputFiles({ name: "pixel.png", mimeType: "image/png", buffer: pixel });
await page.getByRole("combobox", { name: /Message/ }).fill("a pixel");
await page.keyboard.press("Enter");
const thumbnail = page.getByTestId("transcript").getByRole("img", { name: "pixel.png" });
await expect(thumbnail).toBeVisible({ timeout: 30_000 });
await expect(thumbnail).toHaveAttribute("src", /^\/api\/artifacts\/[^/?]+$/);
await thumbnail.click();
const dialog = page.getByRole("dialog", { name: "pixel.png" });
const download = dialog.getByRole("link", { name: "Download pixel.png" });
await expect(download).toHaveAttribute("href", /\/api\/artifacts\/[^/?]+\?download=1$/);
const saved = page.waitForEvent("download");
await download.click();
expect((await saved).suggestedFilename()).toBe("pixel.png");
});
test("a repository ZIP above the inline cap streams up as a file", async ({ page }, testInfo) => {
const stamp = Date.now();
await signup(page, `zip-upload-${stamp}@rakazo.test`, "password12", "Zip Upload");
await completeOnboarding(page);
const input = page.locator('input[type="file"]');
await expect(input).toHaveAttribute("accept", /application\/zip/);
const upload = page.waitForResponse(
(response) =>
response.request().method() === "POST" && /\/api\/artifacts\?/.test(response.url()),
);
// Windows reports ZIPs under the legacy type; 12 MiB is above the 10 MiB inline cap.
await input.setInputFiles({
name: "repo.zip",
mimeType: "application/x-zip-compressed",
buffer: Buffer.alloc(12 * 1024 * 1024, 1),
});
await expect(page.getByRole("button", { name: "Remove repo.zip" })).toBeVisible();
await page.getByRole("combobox", { name: /Message/ }).fill("here is the repo");
await page.keyboard.press("Enter");
const response = await upload;
expect(response.status()).toBe(201);
expect(response.request().headers()["content-type"]).toBe("application/zip");
// Exact: the agent's reply can quote the file name too.
await expect(page.getByTestId("transcript").getByText("repo.zip", { exact: true })).toBeVisible({
timeout: 30_000,
});
await captureScreenshot(page, testInfo, "zip-upload");
});