feat(stream-test): drive the whole browse scenario with real input

Make every action real keyboard/mouse via xdotool, not just the visible
browsing: address-bar navigation (Ctrl+L + char-by-char typing), the YouTube
settings gear -> 화질 -> 1080p menu (real clicks, verified hd1080), the autoplay
toggle, the play button, and fullscreen via the real 'f' key (F11 isn't honored
by this WM; 'f' yields true 1080p fullscreen without pausing). CDP/DOM API is
now used only to read state for verification.

bot/scripts/stream-test/README.md

@@ -9,9 +9,12 @@ real browsing session captured from the X display.
   `DISCORD_GUILD_ID`, `DISCORD_VOICE_CHANNEL_ID`, `VNC_RESOLUTION`,
   `VNC_FRAMERATE`, `VNC_BITRATE_KBPS`, `STREAM_HW`, `VNC_DISPLAY`).
 - `human.mjs` - human-like interaction helpers. Real mouse/keyboard via
-  `xdotool` (so the cursor is visible in the stream); Playwright locates
+  `xdotool` (so the cursor is visible in the stream); Playwright only locates
-  elements. Behind-the-scenes control (fullscreen, play, quality, autoplay,
+  elements. Every action is real input: address-bar navigation (Ctrl+L +
-  navigation) uses the CDP/DOM API.
+  typing), search typing, clicking the video / settings menu / autoplay toggle /
+  play button, fullscreen via the `f` key, scrolling, and entering links. The
+  CDP/DOM API is used only to read state for verification, and as a rare click
+  fallback when an element has no on-screen box.
 - `scenario.mjs` - the browse scenario (YouTube -> IU live -> 1080p ->
   fullscreen -> Naver -> 나무위키), driven with the human helpers. Connects to a
   Chrome already running with `--remote-debugging-port` (`CDP_PORT`, default

bot/scripts/stream-test/human.mjs

@@ -100,4 +100,26 @@ export async function humanScroll(page, dir, notches, overLocator) {
   await sleep(rand(250, 600));
 }
 
+// Press a single key (real keyboard).
+export async function humanKey(key) { await xdo(['key', '--clearmodifiers', key]); await sleep(rand(120, 300)); }
+
+// Navigate like a person: focus the address bar (Ctrl+L), type the URL one char
+// at a time, press Enter.
+export async function navigateOmnibox(text) {
+  await xdo(['key', '--clearmodifiers', 'ctrl+l']); await sleep(rand(300, 600));
+  await humanType(text); await sleep(rand(150, 320));
+  await xdo(['key', '--clearmodifiers', 'Return']);
+}
+
+// Move the real cursor over an element (hover, no click) - e.g. to reveal a
+// video player's controls or to focus it for a keyboard shortcut.
+export async function humanHover(page, locator) {
+  const box = await locator.boundingBox().catch(() => null);
+  if (!box) return;
+  const g = await page.evaluate(() => ({ sx: window.screenX, sy: window.screenY, ow: window.outerWidth, oh: window.outerHeight, iw: window.innerWidth, ih: window.innerHeight }));
+  const bx = Math.max(0, Math.round((g.ow - g.iw) / 2));
+  const oy = g.sy + Math.max(0, g.oh - g.ih - bx);
+  await humanMove(Math.round(g.sx + bx + box.x + box.width * 0.5), Math.round(oy + box.y + box.height * 0.4));
+}
+
 export { sleep, rand };

bot/scripts/stream-test/scenario.mjs

@@ -1,68 +1,97 @@
-// Browse scenario driven with human-like real mouse/keyboard (see human.mjs).
+// Browse scenario driven ENTIRELY with real mouse/keyboard input via xdotool
-// Connects to a Chrome already running with --remote-debugging-port (default
+// (see human.mjs). Connects to a Chrome already running with
-// 9222) on the streamed X display, and performs:
+// --remote-debugging-port (default 9222) on the streamed X display.
-//   YouTube search -> open IU live concert -> 1080p -> watch 20s -> fullscreen
-//   20s -> Naver search 아이유 -> scroll -> 나무위키 -> scroll.
 //
-// Real input (visible on the stream): search/Naver typing, clicking the video,
+// All ACTIONS are real input: address-bar navigation (Ctrl+L + typing),
-// the fullscreen button, scrolling, entering 나무위키.
+// search typing, clicking the video, the settings gear -> 화질 -> 1080p menu,
-// API-driven (behind the scenes): window fullscreen, play, quality, autoplay
+// the autoplay toggle, the play button, fullscreen via the 'f' key, scrolling,
-// toggle, page navigation, and click fallbacks.
+// and entering 나무위키. The CDP/DOM API is used ONLY to read state for
+// verification (paused/quality/fullscreen) and as a rare click fallback when an
+// element has no on-screen box.
 import { chromium } from 'playwright';
-import { humanClick, humanType, pressKey, humanScroll, sleep } from './human.mjs';
+import { humanClick, humanType, humanKey, humanHover, navigateOmnibox, humanScroll, sleep } from './human.mjs';
 
 const CDP = process.env.CDP_PORT || '9222';
-const VID = process.env.TEST_VIDEO_ID || 'X_am71G6Vy4'; // IU HEREH WORLD TOUR (live, 1080p+)
+const VID = process.env.TEST_VIDEO_ID || 'X_am71G6Vy4';
 const SEARCH = process.env.TEST_YT_QUERY || '내손을잡아';
 const NAVER_Q = process.env.TEST_NAVER_QUERY || '아이유';
 
 const b = await chromium.connectOverCDP(`http://localhost:${CDP}`);
 const ctx = b.contexts()[0];
 const page = ctx.pages()[0];
-const s = await ctx.newCDPSession(page);
 page.setDefaultTimeout(25000);
-const winState = async (st) => { const { windowId } = await s.send('Browser.getWindowForTarget'); await s.send('Browser.setWindowBounds', { windowId, bounds: { windowState: st } }); };
+const read = (fn) => page.evaluate(fn);
-const ensurePlaying = () => page.evaluate(() => { const v = document.querySelector('video'); const p = document.getElementById('movie_player'); try { p && p.playVideo && p.playVideo(); } catch {} if (v && v.paused) v.play().catch(() => {}); });
+const playerLoc = () => page.locator('#movie_player');
-const autoplayOff = () => page.evaluate(() => { const btn = document.querySelector('.ytp-autonav-toggle-button'); if (btn && btn.getAttribute('aria-checked') === 'true') btn.click(); });
 
-await page.evaluate(() => { if (document.fullscreenElement) document.exitFullscreen?.(); });
+// 1) open YouTube by typing the URL in the address bar
-await winState('normal');
+await navigateOmnibox('https://www.youtube.com'); await sleep(3000);
-await page.goto('https://www.youtube.com', { waitUntil: 'domcontentloaded' }); await sleep(2500);
 
+// 2) really type the search and submit
 await humanClick(page, page.locator('input#search, input[name=search_query]').first());
 await humanType(SEARCH);
-await pressKey('Return');
+await humanKey('Return');
 await sleep(3800);
 
+// 3) click the IU concert result with the real mouse
 let link = page.locator(`a#video-title[href*="${VID}"], a[href*="${VID}"]`).first();
 if (!(await link.count().catch(() => 0))) link = page.locator('ytd-video-renderer a#video-title, ytd-rich-item-renderer a#video-title').first();
 await humanClick(page, link);
-await sleep(3000);
+await sleep(3500);
-if (!/watch/.test(page.url())) await page.goto('https://www.youtube.com/watch?v=' + VID, { waitUntil: 'domcontentloaded' });
+await page.waitForSelector('#movie_player', { timeout: 25000 }); await sleep(2000);
-await page.waitForSelector('#movie_player', { timeout: 25000 }); await sleep(2500);
+for (let i = 0; i < 8; i++) { const ad = page.locator('.ytp-ad-skip-button, .ytp-ad-skip-button-modern, .ytp-skip-ad-button'); if (await ad.count().catch(() => 0)) { await humanClick(page, ad.first()); await sleep(1200); } else break; }
-for (let i = 0; i < 8; i++) { const ad = page.locator('.ytp-ad-skip-button, .ytp-ad-skip-button-modern, .ytp-skip-ad-button'); if (await ad.count().catch(() => 0)) { await ad.first().click({ timeout: 1500 }).catch(() => {}); await sleep(1200); } else break; }
 
-await ensurePlaying(); await sleep(1200);
+// 4) if paused, press play with the real mouse
-await page.evaluate(() => { const p = document.getElementById('movie_player'); try { const L = p.getAvailableQualityLevels ? p.getAvailableQualityLevels() : []; const w = L.includes('hd1080') ? 'hd1080' : (L[0]); p.setPlaybackQualityRange && p.setPlaybackQualityRange(w, w); } catch {} });
+if (await read(() => document.querySelector('video')?.paused)) {
-await autoplayOff();
+  const big = page.locator('.ytp-large-play-button, .ytp-play-button').first();
+  await humanClick(page, big);
+}
+await sleep(1500);
+
+// 5) set 1080p through the real settings menu (gear -> 화질 -> 1080p), verify
+async function setQuality1080() {
+  for (let attempt = 0; attempt < 2; attempt++) {
+    await humanHover(page, playerLoc());
+    await humanClick(page, page.locator('.ytp-settings-button')); await sleep(900);
+    let qrow = page.locator('.ytp-menuitem', { hasText: /화질|Quality/ }).first();
+    if (!(await qrow.count().catch(() => 0))) qrow = page.locator('.ytp-panel-menu .ytp-menuitem').last();
+    await humanClick(page, qrow); await sleep(900);
+    const item = page.locator('.ytp-menuitem', { hasText: /1080/ }).first();
+    if (await item.count().catch(() => 0)) await humanClick(page, item);
+    await sleep(2000);
+    const q = await read(() => document.getElementById('movie_player')?.getPlaybackQuality?.());
+    if (q && /1080/.test(q)) return q;
+  }
+  return null;
+}
+console.log('QUALITY', await setQuality1080());
+
+// 6) turn off autoplay with a real click if it is on
+const auto = page.locator('.ytp-autonav-toggle-button');
+if ((await auto.count().catch(() => 0)) && (await auto.getAttribute('aria-checked').catch(() => null)) === 'true') {
+  await humanHover(page, playerLoc());
+  await humanClick(page, auto);
+}
 console.log('STEP watch-1080-windowed'); await sleep(20000);
 
-await winState('fullscreen'); await sleep(1200);
+// 7) fullscreen with the real 'f' key (hover the player to focus it), 20s
-await humanClick(page, page.locator('.ytp-fullscreen-button'));
+await humanHover(page, playerLoc());
-await sleep(800); await ensurePlaying();
+await humanKey('f'); await sleep(1500);
-console.log('STEP fullscreen'); await sleep(20000);
+if (!(await read(() => !!document.fullscreenElement))) { await humanHover(page, playerLoc()); await humanKey('f'); await sleep(1200); }
+console.log('STEP fullscreen', await read(() => ({ full: !!document.fullscreenElement, h: window.innerHeight }))); await sleep(20000);
 
-await page.evaluate(() => { if (document.fullscreenElement) document.exitFullscreen?.(); });
+// 8) exit fullscreen with real 'f'
-await winState('normal'); await sleep(1500);
+await humanKey('f'); await sleep(1500);
 
-await page.goto('https://www.naver.com', { waitUntil: 'domcontentloaded' }); await sleep(2500);
+// 9) Naver via the address bar, then really type the query
+await navigateOmnibox('https://www.naver.com'); await sleep(2800);
 await humanClick(page, page.locator('input#query').first());
 await humanType(NAVER_Q);
-await pressKey('Return');
+await humanKey('Return');
 await sleep(2800);
 await humanScroll(page, +1, 18);
 console.log('STEP naver-scrolled');
 
+// 10) enter 나무위키 with a real click, then scroll
 const namu = page.locator('a[href*="namu.wiki"]').first();
 if (await namu.count().catch(() => 0)) {
   await humanClick(page, namu);