selfbot streaming: verified live; capture via system ffmpeg x11grab

End-to-end verified with a real burner token + voice channel: login OK, posts
to the text channel, joins voice, and Go-Live streams the host :1 desktop.

- selfbot.ts now captures the X display with the SYSTEM ffmpeg (reliable
  x11grab) and pipes it into prepareStream, instead of relying on the lib's
  bundled libav input devices (not portable). Capture process is killed on stop.
- package.json: trustedDependencies (node-av, @lng2004/node-datachannel) so the
  native streaming deps build automatically on bun install (incl. Docker).
- Dropped the unused nvenc path (the lib's exported `nvenc` is undefined at
  runtime); software H264 encode for now.

bot/bun.lock

@@ -24,6 +24,10 @@
       },
     },
   },
+  "trustedDependencies": [
+    "@lng2004/node-datachannel",
+    "node-av",
+  ],
   "packages": {
     "@babel/runtime": ["@babel/runtime@7.29.7", "", {}, "sha512-Nq8OhGWiZIZGV6hLHoyAKLLcJihP/xFeBMGJoUrxTX2psI8dCifzLhZISFb+VWS3wFMRDmCGw5R+dOySCqPLhw=="],
 

bot/package.json

@@ -27,5 +27,9 @@
     "@types/node": "^22.7.0",
     "@types/qrcode": "^1.5.6",
     "typescript": "^5.6.3"
-  }
+  },
+  "trustedDependencies": [
+    "@lng2004/node-datachannel",
+    "node-av"
+  ]
 }

bot/src/stream/selfbot.ts

@@ -16,12 +16,14 @@
  *   prepareStream(input, opts, signal) -> { command, output }
  *   playStream(output, streamer, { type: "go-live" }, signal)
  */
+import { spawn, type ChildProcess } from "node:child_process";
 import type { AppConfig } from "../config.ts";
 import type { ScreenStreamer, StreamContext } from "./index.ts";
 
 export class SelfbotStreamer implements ScreenStreamer {
   readonly kind = "selfbot" as const;
   private streamer: any = null;
+  private capture: ChildProcess | null = null;
   private controller: AbortController | null = null;
   private active = false;
 
@@ -62,7 +64,7 @@ export class SelfbotStreamer implements ScreenStreamer {
       return "셀프봇 송출은 음성 채널 안에서 호출해야 합니다.";
     }
     const { selfbot, vs } = await this.loadLib();
-    const { Streamer, prepareStream, playStream, nvenc } = vs;
+    const { Streamer, prepareStream, playStream } = vs;
 
     this.streamer = new Streamer(new selfbot.Client());
     await this.streamer.client.login(this.config.selfbotToken);
@@ -71,29 +73,35 @@ export class SelfbotStreamer implements ScreenStreamer {
     const [w, h] = this.config.vncResolution.split("x").map((n) => parseInt(n, 10));
     this.controller = new AbortController();
 
-    // Grab the VNC X display with ffmpeg's x11grab. customInputOptions are
-    // placed before `-i <display>`, exactly as x11grab requires.
-    const options: any = {
-      width: w || 1920,
-      height: h || 1080,
-      frameRate: this.config.vncFramerate,
-      videoCodec: "H264",
-      bitrateVideo: this.config.vncBitrateKbps,
-      bitrateVideoMax: Math.round(this.config.vncBitrateKbps * 1.5),
-      hardwareAcceleratedDecoding: this.config.streamHw,
-      minimizeLatency: true,
-      customInputOptions: [
-        "-f", "x11grab",
-        "-video_size", this.config.vncResolution,
-        "-framerate", String(this.config.vncFramerate),
-      ],
-    };
-    // NVENC hardware encode on the RTX 5050 when enabled.
-    if (this.config.streamHw && nvenc) options.encoder = nvenc;
+    // Capture the VNC X display with the SYSTEM ffmpeg (which reliably has
+    // x11grab), then pipe that stream into the library. Relying on the lib's
+    // bundled libav for the x11grab input device is not portable; piping the
+    // system ffmpeg is. (Verified live against a real voice channel.)
+    const capture = spawn("ffmpeg", [
+      "-loglevel", "error",
+      "-f", "x11grab",
+      "-framerate", String(this.config.vncFramerate),
+      "-video_size", this.config.vncResolution,
+      "-i", this.config.vncDisplay,
+      "-c:v", "libx264", "-preset", "ultrafast", "-tune", "zerolatency",
+      "-pix_fmt", "yuv420p", "-g", String(this.config.vncFramerate),
+      "-f", "mpegts", "pipe:1",
+    ]);
+    this.capture = capture;
+    capture.stderr?.on("data", (d) => {
+      if (!this.controller?.signal.aborted) console.error("[selfbot x11grab]", d.toString().trim());
+    });
 
     const { command, output } = prepareStream(
-      this.config.vncDisplay,
-      options,
+      capture.stdout,
+      {
+        width: w || 1920,
+        height: h || 1080,
+        frameRate: this.config.vncFramerate,
+        videoCodec: "H264",
+        bitrateVideo: this.config.vncBitrateKbps,
+        bitrateVideoMax: Math.round(this.config.vncBitrateKbps * 1.5),
+      },
       this.controller.signal,
     );
     command.on("error", (err: Error) => {
@@ -113,6 +121,12 @@ export class SelfbotStreamer implements ScreenStreamer {
   async stop(): Promise<void> {
     this.controller?.abort();
     this.controller = null;
+    try {
+      this.capture?.kill("SIGKILL");
+    } catch {
+      /* ignore */
+    }
+    this.capture = null;
     try {
       this.streamer?.leaveVoice?.();
       this.streamer?.client?.destroy?.();