fix: cap selfbot stream -maxrate at lib's 10 Mbps ceiling; add stream-test tooling

- selfbot.ts: the @dank074 lib advertises a hardcoded max_bitrate of 10 Mbps to Discord (BaseMediaConnection: `max_bitrate: 10000 * 1000`). Our encoder used -maxrate = 1.5x target (12 Mbps at 8 Mbps target), so high-motion bursts exceeded the negotiated ceiling and WebRTC dropped packets (viewer stutter). Cap -maxrate at 10 Mbps. - Add bot/scripts/stream-test/: env-driven stream-hold.ts (persistent Go-Live holder), human.mjs (real xdotool mouse/keyboard + char-by-char typing), and scenario.mjs (YouTube/Naver browse). Channel/guild/video are env-parametrised. - .env.example: document DISCORD_VOICE_CHANNEL_ID for the stream-test scripts.
2026-06-10 12:50:24 +09:00
parent 7a148f8caa
commit 1e30a49562
6 changed files with 274 additions and 1 deletions
--- a/.env.example
+++ b/.env.example
@@ -11,6 +11,8 @@ DISCORD_BOT_TOKEN=
 DISCORD_APP_ID=
 # The (single) server this bot serves. Guild-scoped commands appear instantly.
 DISCORD_GUILD_ID=
+# Voice channel used by the stream-test scripts (bot/scripts/stream-test).
+DISCORD_VOICE_CHANNEL_ID=

 # ---------------------------------------------------------------------------
 # Brain bridge (Python service in bridge/) — STT + reply engine + TTS
--- a/bot/scripts/stream-test/README.md
+++ b/bot/scripts/stream-test/README.md
@@ -0,0 +1,39 @@
+# stream-test
+
+Operational scripts for manually verifying the selfbot Go-Live broadcast with a
+real browsing session captured from the X display.
+
+## Files
+- `stream-hold.ts` - joins the voice channel and keeps the Go-Live stream up
+  until stopped. All params from `.env` (`DISCORD_SELFBOT_TOKEN`,
+  `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
+  elements. Behind-the-scenes control (fullscreen, play, quality, autoplay,
+  navigation) uses the CDP/DOM API.
+- `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
+  9222) on the streamed display.
+
+## Run
+```
+# keep the broadcast up (separate process / service)
+bun bot/scripts/stream-test/stream-hold.ts
+
+# Chrome on the streamed display with remote debugging, then:
+node bot/scripts/stream-test/scenario.mjs
+```
+
+## A/B framerate/resolution
+Lower settings to compare what Discord actually delivers to viewers, e.g.:
+```
+VNC_RESOLUTION=1280x720 VNC_FRAMERATE=30 bun bot/scripts/stream-test/stream-hold.ts
+```
+
+## Notes
+- Selfbot streaming violates Discord ToS; use a burner account.
+- Requires `xdotool`, an X display, and a system `ffmpeg` with `x11grab`/nvenc.
+- Prereqs (`playwright`, system Chrome) are not bot dependencies; install
+  separately where you run the scenario.
--- a/bot/scripts/stream-test/human.mjs
+++ b/bot/scripts/stream-test/human.mjs
@@ -0,0 +1,103 @@
+// Human-like interaction helpers: drive the REAL X mouse/keyboard via xdotool
+// so the cursor visibly moves and is captured by the screen stream, using
+// Playwright only to LOCATE elements and read state. This is the default
+// interaction mode for the browse scenarios.
+//
+// Note: only the user-visible browsing actions are real input (cursor move,
+// click, scroll, char-by-char typing). Behind-the-scenes control (window
+// fullscreen, play, quality, autoplay toggle, page navigation, and click
+// fallbacks) intentionally uses the CDP/DOM API for reliability.
+import { execFile } from 'node:child_process';
+
+const DISPLAY = process.env.VNC_DISPLAY || ':1';
+const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
+const rand = (a, b) => a + Math.random() * (b - a);
+const xdo = (args) =>
+  new Promise((res, rej) =>
+    execFile('xdotool', args, { env: { ...process.env, DISPLAY } }, (e, so) => (e ? rej(e) : res(so || ''))),
+  );
+
+let cur = { x: 960, y: 540 };
+const easeInOut = (t) => (t < 0.5 ? 2 * t * t : 1 - Math.pow(-2 * t + 2, 2) / 2);
+
+async function contentOrigin(page) {
+  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 topInset = Math.max(0, g.oh - g.ih - bx);
+  return { ox: g.sx + bx, oy: g.sy + topInset };
+}
+
+// Smoothly move the real cursor to a screen point with eased, slightly jittered steps.
+export async function humanMove(toX, toY) {
+  const steps = Math.max(12, Math.min(48, Math.round(Math.hypot(toX - cur.x, toY - cur.y) / 22)));
+  const cmd = [];
+  for (let i = 1; i <= steps; i++) {
+    const t = easeInOut(i / steps);
+    const jx = i < steps ? rand(-1.5, 1.5) : 0;
+    const jy = i < steps ? rand(-1.5, 1.5) : 0;
+    cmd.push('mousemove', String(Math.round(cur.x + (toX - cur.x) * t + jx)),
+                          String(Math.round(cur.y + (toY - cur.y) * t + jy)),
+             'sleep', rand(0.006, 0.018).toFixed(3));
+  }
+  await xdo(cmd);
+  cur = { x: toX, y: toY };
+  await sleep(rand(40, 130));
+}
+
+export async function humanClickXY(sx, sy) {
+  await humanMove(sx, sy);
+  await sleep(rand(60, 170));
+  await xdo(['click', '1']);
+  await sleep(rand(130, 300));
+}
+
+// Locate a Playwright element, move the real cursor into it (random offset), click.
+export async function humanClick(page, locator) {
+  await locator.scrollIntoViewIfNeeded().catch(() => {});
+  await sleep(rand(150, 380));
+  const box = await locator.boundingBox();
+  if (!box) { await locator.click({ timeout: 5000 }).catch(() => {}); return; }
+  const { ox, oy } = await contentOrigin(page);
+  const sx = Math.round(ox + box.x + box.width * rand(0.35, 0.65));
+  const sy = Math.round(oy + box.y + box.height * rand(0.35, 0.65));
+  await humanClickXY(sx, sy);
+}
+
+// Type text one character at a time at a human, slightly irregular pace.
+export async function humanType(text) {
+  await sleep(rand(220, 420)); // let focus settle so the 1st char isn't dropped
+  for (const ch of text) {
+    await xdo(['type', '--clearmodifiers', '--', ch]);
+    await sleep(rand(70, 200));
+    if (Math.random() < 0.12) await sleep(rand(150, 400)); // occasional pause
+  }
+}
+
+export async function pressKey(key) {
+  await xdo(['key', '--clearmodifiers', key]);
+  await sleep(rand(120, 280));
+}
+
+// Gradual wheel scroll (dir>0 = down). Optionally hover over an element first.
+export async function humanScroll(page, dir, notches, overLocator) {
+  if (overLocator) {
+    const box = await overLocator.boundingBox().catch(() => null);
+    if (box) {
+      const { ox, oy } = await contentOrigin(page);
+      await humanMove(Math.round(ox + box.x + box.width / 2), Math.round(oy + box.y + box.height / 2));
+    }
+  }
+  const button = dir > 0 ? '5' : '4';
+  for (let i = 0; i < notches; i++) {
+    await xdo(['click', button]);
+    await sleep(rand(40, 115));
+    if (i % 6 === 5) await sleep(rand(250, 600)); // pause like reading
+  }
+  await sleep(rand(250, 600));
+}
+
+export { sleep, rand };
--- a/bot/scripts/stream-test/scenario.mjs
+++ b/bot/scripts/stream-test/scenario.mjs
@@ -0,0 +1,77 @@
+// Browse scenario driven with human-like real mouse/keyboard (see human.mjs).
+// Connects to a Chrome already running with --remote-debugging-port (default
+// 9222) on the streamed X display, and performs:
+//   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,
+// the fullscreen button, scrolling, entering 나무위키.
+// API-driven (behind the scenes): window fullscreen, play, quality, autoplay
+// toggle, page navigation, and click fallbacks.
+import { chromium } from 'playwright';
+import { humanClick, humanType, pressKey, 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 SEARCH = process.env.TEST_YT_QUERY || '내손을잡아';
+const NAVER_Q = process.env.TEST_NAVER_QUERY || '아이유';
+
+const b = await chromium.connectOverCDP(`http://localhost:${CDP}`);
+const ctx = b.contexts()[0];
+const page = ctx.pages()[0];
+const s = await ctx.newCDPSession(page);
+page.setDefaultTimeout(25000);
+const winState = async (st) => { const { windowId } = await s.send('Browser.getWindowForTarget'); await s.send('Browser.setWindowBounds', { windowId, bounds: { windowState: st } }); };
+const ensurePlaying = () => page.evaluate(() => { const v = document.querySelector('video'); const p = document.getElementById('movie_player'); try { p && p.playVideo && p.playVideo(); } catch {} if (v && v.paused) v.play().catch(() => {}); });
+const autoplayOff = () => page.evaluate(() => { const btn = document.querySelector('.ytp-autonav-toggle-button'); if (btn && btn.getAttribute('aria-checked') === 'true') btn.click(); });
+
+await page.evaluate(() => { if (document.fullscreenElement) document.exitFullscreen?.(); });
+await winState('normal');
+await page.goto('https://www.youtube.com', { waitUntil: 'domcontentloaded' }); await sleep(2500);
+
+await humanClick(page, page.locator('input#search, input[name=search_query]').first());
+await humanType(SEARCH);
+await pressKey('Return');
+await sleep(3800);
+
+let link = page.locator(`a#video-title[href*="${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);
+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(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 ad.first().click({ timeout: 1500 }).catch(() => {}); await sleep(1200); } else break; }
+
+await ensurePlaying(); await sleep(1200);
+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 {} });
+await autoplayOff();
+console.log('STEP watch-1080-windowed'); await sleep(20000);
+
+await winState('fullscreen'); await sleep(1200);
+await humanClick(page, page.locator('.ytp-fullscreen-button'));
+await sleep(800); await ensurePlaying();
+console.log('STEP fullscreen'); await sleep(20000);
+
+await page.evaluate(() => { if (document.fullscreenElement) document.exitFullscreen?.(); });
+await winState('normal'); await sleep(1500);
+
+await page.goto('https://www.naver.com', { waitUntil: 'domcontentloaded' }); await sleep(2500);
+await humanClick(page, page.locator('input#query').first());
+await humanType(NAVER_Q);
+await pressKey('Return');
+await sleep(2800);
+await humanScroll(page, +1, 18);
+console.log('STEP naver-scrolled');
+
+const namu = page.locator('a[href*="namu.wiki"]').first();
+if (await namu.count().catch(() => 0)) {
+  await humanClick(page, namu);
+  await sleep(3000);
+  await humanScroll(page, +1, 14);
+  await humanScroll(page, -1, 8);
+  await humanScroll(page, +1, 10);
+  console.log('STEP namu-scrolled');
+} else console.log('STEP namu-not-found');
+
+console.log('SCENARIO_DONE');
+await b.close();
--- a/bot/scripts/stream-test/stream-hold.ts
+++ b/bot/scripts/stream-test/stream-hold.ts
@@ -0,0 +1,47 @@
+// Persistent selfbot stream holder for manual/operational testing of the
+// Go-Live broadcast. Joins the voice channel, goes live, and keeps the stream
+// up until stopped (SIGTERM/SIGINT) or HOLD_MS elapses. All parameters come
+// from the environment (.env).
+//
+//   bun bot/scripts/stream-test/stream-hold.ts
+//
+// Requires in .env: DISCORD_SELFBOT_TOKEN, DISCORD_GUILD_ID,
+// DISCORD_VOICE_CHANNEL_ID. Stream params: VNC_RESOLUTION, VNC_FRAMERATE,
+// VNC_BITRATE_KBPS, STREAM_HW, VNC_DISPLAY (same vars the bot uses).
+import "dotenv/config";
+import { SelfbotStreamer } from "../../src/stream/selfbot.ts";
+
+const config = {
+  selfbotToken: process.env.DISCORD_SELFBOT_TOKEN ?? "",
+  vncDisplay: process.env.VNC_DISPLAY ?? ":1",
+  vncResolution: process.env.VNC_RESOLUTION ?? "1920x1080",
+  vncFramerate: parseInt(process.env.VNC_FRAMERATE ?? "60", 10),
+  vncBitrateKbps: parseInt(process.env.VNC_BITRATE_KBPS ?? "8000", 10),
+  streamHw: (process.env.STREAM_HW ?? "1") !== "0",
+} as any;
+
+const guildId = process.env.DISCORD_GUILD_ID;
+const voiceChannelId = process.env.DISCORD_VOICE_CHANNEL_ID;
+if (!config.selfbotToken || !guildId || !voiceChannelId) {
+  console.error("Missing DISCORD_SELFBOT_TOKEN / DISCORD_GUILD_ID / DISCORD_VOICE_CHANNEL_ID in .env");
+  process.exit(1);
+}
+
+const s = new SelfbotStreamer(config);
+const maxMs = parseInt(process.env.HOLD_MS ?? "7200000", 10);
+let stopped = false;
+const stop = async () => {
+  if (stopped) return;
+  stopped = true;
+  console.log("STREAM_STOPPING");
+  await s.stop();
+  console.log("STREAM_STOPPED");
+  process.exit(0);
+};
+process.on("SIGTERM", stop);
+process.on("SIGINT", stop);
+
+const r = await s.start({ guildId, voiceChannelId } as any);
+console.log(`STREAM_START: ${r} active:${s.isActive()} (${config.vncResolution}@${config.vncFramerate} ${config.vncBitrateKbps}k hw=${config.streamHw})`);
+setTimeout(stop, maxMs);
+setInterval(() => {}, 60000);
--- a/bot/src/stream/selfbot.ts
+++ b/bot/src/stream/selfbot.ts
@@ -131,7 +131,12 @@ export class SelfbotStreamer implements ScreenStreamer {
      // RTX 5050); otherwise it falls back to software x264.
      const hw = this.config.streamHw;
      const kbps = this.config.vncBitrateKbps;
-      const maxKbps = Math.round(kbps * 1.5);
+      // The library advertises a hardcoded max_bitrate of 10 Mbps to Discord
+      // (BaseMediaConnection: `max_bitrate: 10000 * 1000`). If the encoder bursts
+      // above that negotiated ceiling, WebRTC congestion control drops packets
+      // and the viewer sees stutter. Cap -maxrate at 10 Mbps to stay within it.
+      const LIB_MAX_BITRATE_KBPS = 10000;
+      const maxKbps = Math.min(Math.round(kbps * 1.5), LIB_MAX_BITRATE_KBPS);
      const captureCodecArgs = hw
        ? ["-c:v", "h264_nvenc", "-preset", "p4", "-tune", "ll", "-forced-idr", "1"]
        : ["-c:v", "libx264", "-preset", "ultrafast", "-tune", "zerolatency"];