Files
software-mansion__argent/packages/tool-server/test/screenshot-diff-tool.test.ts
Mateusz Ścianek b8afbed183 feat(tv): Apple TV (tvOS) and Android TV support (#374)
Adds end-to-end support for driving **Apple TV (tvOS)** and **Android TV
(leanback)** targets through argent, using a focus-driven interaction
model (TVs have no touchscreen — interaction is moving a focus highlight
with the remote).

This PR was reworked after review to **reuse the existing cross-platform
tool surface and the `tv-remote` tool from the Vega/Fire TV work
(#366)** rather than ship a separate family of `tv-*` tools.

## What this delivers

TV targets are driven by the **same cross-platform tools as every other
platform**, routed through the existing `dispatchByPlatform` fork
mechanism — there are no dedicated
`tv-describe`/`tv-navigate`/`tv-type`/`tv-set-focus` tools:

- **`describe`** — on a `runtimeKind: "tv"` target, returns the
focus-driven view (focused + focusable elements) instead of a tap tree.
On Android TV it auto-falls-back to the full `uiautomator` tree when the
RN focus engine exposes nothing.
- **`tv-remote`** — the cross-platform remote/D-pad tool from #366, now
extended with `ios` (Apple TV HID daemon) and `android` (Android TV adb
keyevents) branches alongside the existing `vega` branch. Single button,
a `repeat`, or a whole path (`["up","right","select"]`) in one call.
- **`keyboard`** — types into the focused field on a TV target (named
keys are rejected there — they're navigation, which belongs to
`tv-remote`).
- **`button`** stays hardware-only (phones/tablets); it is not a TV
tool.

**Apple TV** runs two native daemons (in-sim AX service + host-side HID
daemon), shipped via the `argent-private` submodule. **Android TV**
reuses the same tool surface, adb-backed (`input keyevent`, `uiautomator
dump`, `input text`).

## Remote vocabulary parity

`tv-remote` exposes the full 16-button vocabulary
(`up`/`down`/`left`/`right`/`select`/`back`/`home`/`menu`/`playPause`/`rewind`/`fastForward`/`next`/`previous`/`volumeUp`/`volumeDown`/`mute`):

| | Apple TV | Android TV | Vega |
|---|---|---|---|
| D-pad / select / back / menu / home / playPause | ✅ | ✅ | ✅ |
| media-transport + volume/mute | ❌ rejected | ✅ | ✅ |

Media-transport/volume keys **genuinely work on Android TV** (real
keycodes — verified live: `volumeUp` moved `STREAM_MUSIC`, `mute`
toggled per `dumpsys audio`). On the **Apple TV simulator** they are
**rejected with a clear error**: on-device testing confirmed the tvOS
sim's HID stack silently drops Consumer-Control events, so returning
success would be a lie.

## Key design points
- **tvOS UDIDs are UUID-shaped and indistinguishable from iOS by
shape.** Handled with `runtimeKind` detection (tvOS runtime string for
Apple TV; `pm list features` leanback/television for Android TV — *not*
`ro.build.characteristics`, which lies on TV emulators).
- Converted launch-app / restart-app / screenshot / screenshot-diff /
run-sequence from **eager** to **lazy** service resolution, so a tvOS
target never spins up (and hangs on) the iOS-only simulator-server /
native-devtools blueprints.
- Native injection selects the platform-matched (TVOSSIMULATOR) dylib
slice; daemons recycle across sim reboots and app relaunches so
injection and focus survive.
- SKILL.md footprint minimized per review: the two TV skills were
collapsed into a single lean **`argent-tv-interact`** (~40 lines).

## Verification
- `npm run build`, ESLint, Prettier, and the full tool-server suite
(**1565 tests**) all pass; CI green (incl. the Apple TV / Android TV /
Vega e2e jobs).
- Core flows verified live against real apps on both an Apple TV 4K
simulator and a Google ATV emulator.

## Dependency / merge order
Pins the `argent-private` submodule to the tip of its `feat/tv-support`
branch (software-mansion/argent-private#20). **Merge that PR to `main`
first, then bump the submodule pointer here to the merged SHA before
merging this PR.**

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-01 14:59:37 +02:00

269 lines
9.7 KiB
TypeScript

import fs from "fs/promises";
import os from "os";
import path from "path";
import { PNG } from "pngjs";
import { describe, expect, it, vi } from "vitest";
import { ArtifactStore } from "@argent/registry";
import { executeScreenshotDiffTool, screenshotDiffTool } from "../src/tools/screenshot-diff";
describe("screenshotDiffTool", () => {
it("rejects public tuning options so defaults stay internal", () => {
const result = screenshotDiffTool.zodSchema!.safeParse({
baselinePath: "/tmp/baseline.png",
currentPath: "/tmp/current.png",
udid: "ABC",
outputDir: "/tmp",
includeTextAnalysis: false,
threshold: 0.2,
textChangeMinConfidence: 0.9,
maxRegions: 3,
});
expect(result.success).toBe(false);
});
it("requires udid and only declares the simulator-server service for live captures", () => {
expect(
screenshotDiffTool.zodSchema!.safeParse({
baselinePath: "/tmp/baseline.png",
currentPath: "/tmp/current.png",
outputDir: "/tmp",
}).success
).toBe(false);
// A pure static-PNG diff needs no SimulatorServer — requesting it
// unconditionally would fail on tvOS sims that have no such backend.
const staticParams = {
baselinePath: "/tmp/baseline.png",
currentPath: "/tmp/current.png",
udid: "ABC",
outputDir: "/tmp",
};
expect(screenshotDiffTool.zodSchema!.safeParse(staticParams).success).toBe(true);
expect(screenshotDiffTool.services(staticParams)).toEqual({});
// A live capture resolves and starts the SimulatorServer for the device.
const liveParams = {
baselinePath: "/tmp/baseline.png",
captureCurrent: true,
udid: "ABC",
outputDir: "/tmp",
};
expect(screenshotDiffTool.zodSchema!.safeParse(liveParams).success).toBe(true);
expect(screenshotDiffTool.services(liveParams)).toEqual({
simulatorServer: {
urn: "SimulatorServer:ABC",
options: {
device: {
id: "ABC",
platform: "android",
// A non-`emulator-*` serial resolves to a physical device.
kind: "device",
},
},
},
});
});
it("returns only the summary and diff artifact paths", async () => {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "argent-screenshot-diff-tool-"));
const baselinePath = path.join(dir, "baseline.png");
const currentPath = path.join(dir, "current.png");
await writePng(baselinePath, 2, 2, { r: 10, g: 20, b: 30 });
await writePng(currentPath, 2, 2, { r: 10, g: 20, b: 30 });
const result = await executeScreenshotDiffTool(
{},
{
baselinePath,
currentPath,
udid: "ABC",
outputDir: dir,
},
{ artifacts: new ArtifactStore() }
);
// Diff outputs leave as artifact handles so a remote client can download
// them; hostPath still points at the requested outputDir.
expect(result.summary).toContain("Screenshot diff summary");
expect(result.diffPath).toMatchObject({
__argentArtifact: true,
hostPath: path.join(dir, "current-diff.png"),
mimeType: "image/png",
});
expect(result.contextDiffPath).toMatchObject({
__argentArtifact: true,
hostPath: path.join(dir, "current-context-diff.png"),
mimeType: "image/png",
});
expect(Object.keys(result).sort()).toEqual(["contextDiffPath", "diffPath", "summary"]);
});
it("captures one live side at full resolution and copies it into outputDir", async () => {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "argent-screenshot-diff-live-"));
const baselinePath = path.join(dir, "baseline.png");
const capturedPath = path.join(dir, "captured.png");
await writePng(baselinePath, 2, 2, { r: 0, g: 0, b: 0 });
await writePng(capturedPath, 2, 2, { r: 0, g: 0, b: 0 });
const signal = AbortSignal.timeout(1000);
const captureScreenshot = vi.fn(async () => ({
url: "http://localhost/current.png",
path: capturedPath,
}));
const result = await executeScreenshotDiffTool(
{ simulatorServer: { apiUrl: "http://localhost:4949" } },
{
baselinePath,
captureCurrent: true,
udid: "ABC",
rotation: "LandscapeLeft",
outputDir: dir,
},
{ signal, artifacts: new ArtifactStore() },
captureScreenshot as never
);
expect(captureScreenshot).toHaveBeenCalledWith(
{ apiUrl: "http://localhost:4949" },
"LandscapeLeft",
signal,
1.0
);
const entries = await fs.readdir(dir);
const liveCaptures = entries.filter((name) => /^current-[a-f0-9]{8}\.live\.png$/.test(name));
expect(liveCaptures).toHaveLength(1);
const liveBaseName = path.parse(liveCaptures[0]!).name;
await expect(fs.stat(path.join(dir, liveCaptures[0]!))).resolves.toMatchObject({
size: expect.any(Number),
});
expect(result.diffPath).toMatchObject({
hostPath: path.join(dir, `${liveBaseName}-diff.png`),
});
});
it("falls back to the default scale when the full-resolution capture fails (Android framebuffer mismatch)", async () => {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "argent-screenshot-diff-fallback-"));
const baselinePath = path.join(dir, "baseline.png");
const capturedPath = path.join(dir, "captured.png");
await writePng(baselinePath, 2, 2, { r: 0, g: 0, b: 0 });
await writePng(capturedPath, 2, 2, { r: 0, g: 0, b: 0 });
// Full-res (scale 1.0) fails the way the Android simulator-server does;
// the default-scale retry (no scale arg) succeeds.
const captureScreenshot = vi.fn(
async (_api: unknown, _rotation: unknown, _signal: unknown, scale?: number) => {
if (scale === 1.0) {
throw new Error("Screenshot failed: wrong data size, expected 7853760 got 17627328.");
}
return { url: "http://localhost/current.png", path: capturedPath };
}
);
const result = await executeScreenshotDiffTool(
{ simulatorServer: { apiUrl: "http://localhost:4949" } },
{ baselinePath, captureCurrent: true, udid: "ABC", outputDir: dir },
{ artifacts: new ArtifactStore() },
captureScreenshot as never
);
// Full-res attempted first, then a default-scale retry without an explicit scale.
expect(captureScreenshot).toHaveBeenCalledTimes(2);
expect(captureScreenshot.mock.calls[0]![3]).toBe(1.0);
expect(captureScreenshot.mock.calls[1]![3]).toBeUndefined();
const liveCaptures = (await fs.readdir(dir)).filter((name) =>
/^current-[a-f0-9]{8}\.live\.png$/.test(name)
);
expect(liveCaptures).toHaveLength(1);
expect(result.diffPath).toBeTruthy();
});
it("propagates the error when both the full-res capture and the fallback fail", async () => {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "argent-screenshot-diff-bothfail-"));
const baselinePath = path.join(dir, "baseline.png");
await writePng(baselinePath, 2, 2, { r: 0, g: 0, b: 0 });
const captureScreenshot = vi.fn(
async (_api: unknown, _rotation: unknown, _signal: unknown, scale?: number) => {
throw new Error(scale === 1.0 ? "full-res failed" : "device offline");
}
);
await expect(
executeScreenshotDiffTool(
{ simulatorServer: { apiUrl: "http://localhost:4949" } },
{ baselinePath, captureCurrent: true, udid: "ABC", outputDir: dir },
{},
captureScreenshot as never
)
).rejects.toThrow("device offline");
expect(captureScreenshot).toHaveBeenCalledTimes(2);
});
it("uses a fresh hashed filename for each live capture so concurrent diffs do not collide", async () => {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "argent-screenshot-diff-unique-"));
const baselinePath = path.join(dir, "baseline.png");
const capturedPath = path.join(dir, "captured.png");
await writePng(baselinePath, 2, 2, { r: 0, g: 0, b: 0 });
await writePng(capturedPath, 2, 2, { r: 0, g: 0, b: 0 });
const captureScreenshot = vi.fn(async () => ({
url: "http://localhost/current.png",
path: capturedPath,
}));
await executeScreenshotDiffTool(
{ simulatorServer: { apiUrl: "http://localhost:4949" } },
{ baselinePath, captureCurrent: true, udid: "ABC", outputDir: dir },
{ artifacts: new ArtifactStore() },
captureScreenshot as never
);
await executeScreenshotDiffTool(
{ simulatorServer: { apiUrl: "http://localhost:4949" } },
{ baselinePath, captureCurrent: true, udid: "ABC", outputDir: dir },
{ artifacts: new ArtifactStore() },
captureScreenshot as never
);
const liveCaptures = (await fs.readdir(dir)).filter((name) =>
/^current-[a-f0-9]{8}\.live\.png$/.test(name)
);
expect(liveCaptures).toHaveLength(2);
expect(new Set(liveCaptures).size).toBe(2);
});
it("validates mutually exclusive saved and live inputs at execute time", async () => {
await expect(
executeScreenshotDiffTool(
{},
{
baselinePath: "/tmp/baseline.png",
currentPath: "/tmp/current.png",
captureCurrent: true,
udid: "ABC",
outputDir: "/tmp",
}
)
).rejects.toThrow("Provide either currentPath or captureCurrent, not both.");
});
});
async function writePng(
filePath: string,
width: number,
height: number,
fill: { r: number; g: number; b: number }
): Promise<void> {
const png = new PNG({ width, height });
for (let y = 0; y < height; y++) {
for (let x = 0; x < width; x++) {
const offset = (width * y + x) * 4;
png.data[offset] = fill.r;
png.data[offset + 1] = fill.g;
png.data[offset + 2] = fill.b;
png.data[offset + 3] = 255;
}
}
await fs.writeFile(filePath, PNG.sync.write(png));
}