fix(gateway): EPIPE crash on media stop — stream error handlers + no shutdown on transient stream errors

services/discord-gateway/src/app/bootstrap.ts

@@ -279,6 +279,25 @@ export async function initializeDiscordGateway() {
   });
 
   process.on("uncaughtException", (err) => {
+    const code =
+      typeof (err as NodeJS.ErrnoException).code === "string"
+        ? (err as NodeJS.ErrnoException).code
+        : "";
+    // Transient stream-teardown errors (voice stop/disconnect races, child
+    // process stdin closed while we still write) are NOT fatal — crashing the
+    // gateway on EPIPE takes the whole bot offline mid-music. Log + continue.
+    if (
+      code === "EPIPE" ||
+      code === "ERR_STREAM_DESTROYED" ||
+      code === "ERR_STREAM_WRITE_AFTER_END" ||
+      code === "ECONNRESET"
+    ) {
+      logger.warn(
+        { error: err },
+        "Uncaught transient stream error — continuing",
+      );
+      return;
+    }
     logger.error({ error: err }, "Uncaught exception");
     gracefulShutdown("uncaughtException");
   });

services/discord-gateway/src/modules/voice-recording/mediaSource.ts

@@ -79,6 +79,22 @@ export function transcodeToHighQualityOgg(
   );
 
   input.pipe(proc.stdin);
+  // ffmpeg teardown closes stdin while the upstream source may still write —
+  // swallow EPIPE / destroyed-stream errors so they don't crash the gateway.
+  proc.stdin.on("error", (err: NodeJS.ErrnoException) => {
+    if (
+      err.code === "EPIPE" ||
+      err.code === "ERR_STREAM_DESTROYED" ||
+      err.code === "ERR_STREAM_WRITE_AFTER_END"
+    ) {
+      logger.debug(
+        { code: err.code },
+        "Transcode stdin closed during teardown",
+      );
+    } else {
+      logger.error({ error: err.message }, "Transcode stdin error");
+    }
+  });
   activeProcesses.add(proc);
 
   const cleanup = () => {
@@ -248,6 +264,20 @@ export function resolveMediaUrl(
     // `--print` headers to stderr — pipe stdout immediately so the child
     // never blocks on a full pipe while we wait for the headers on stderr.
     const mediaStream = new PassThrough();
+    // Teardown (player stop / ffmpeg exit) destroys this stream while
+    // yt-dlp may still push bytes — without a listener an EPIPE /
+    // ERR_STREAM_DESTROYED surfaces as an uncaughtException.
+    mediaStream.on("error", (err: NodeJS.ErrnoException) => {
+      if (
+        err.code === "EPIPE" ||
+        err.code === "ERR_STREAM_DESTROYED" ||
+        err.code === "ERR_STREAM_WRITE_AFTER_END"
+      ) {
+        logger.debug({ code: err.code }, "Media stream closed during teardown");
+      } else {
+        logger.error({ error: err.message }, "Media stream error");
+      }
+    });
     proc.stdout.pipe(mediaStream);
 
     let stderrBuf = "";

services/discord-gateway/src/modules/voice-recording/transmitter.ts

@@ -56,6 +56,24 @@ export class VoiceTransmitter {
       // Create PCM input stream
       this.pcmStream = new PassThrough();
       this.pcmStream.setMaxListeners(32); // drain listeners accumulate during backpressure
+      // Voice teardown (stop / disconnect / ffmpeg exit) destroys this stream
+      // while Redis PCM messages may still be in flight. Without a listener,
+      // EPIPE / ERR_STREAM_DESTROYED / ERR_STREAM_WRITE_AFTER_END surface as
+      // an uncaughtException and crash the whole gateway.
+      this.pcmStream.on("error", (err: NodeJS.ErrnoException) => {
+        if (
+          err.code === "EPIPE" ||
+          err.code === "ERR_STREAM_DESTROYED" ||
+          err.code === "ERR_STREAM_WRITE_AFTER_END"
+        ) {
+          logger.debug(
+            { code: err.code },
+            "PCM stream closed during voice teardown — ignoring",
+          );
+        } else {
+          logger.error({ error: err.message }, "PCM stream error");
+        }
+      });
 
       // Spawn FFmpeg to encode 24kHz mono PCM → OggOpus
       // Input: 24kHz mono s16le (raw PCM)
@@ -146,7 +164,12 @@ export class VoiceTransmitter {
       );
 
       this.redisSub.on("message", (channel, message) => {
-        if (channel !== this.TRANSMIT_CHANNEL || !this.pcmStream) return;
+        if (
+          !this.isActive ||
+          channel !== this.TRANSMIT_CHANNEL ||
+          !this.pcmStream
+        )
+          return;
 
         try {
           const data = JSON.parse(message);
@@ -161,11 +184,21 @@ export class VoiceTransmitter {
                 this.draining = false;
                 // Re-acquire stream reference (could have been replaced by restart)
                 const currentStream = this.pcmStream;
-                if (!currentStream) return;
+                if (!currentStream || !this.isActive) return;
                 // Flush queued chunks
                 while (this.backpressureQueue.length > 0) {
                   const queued = this.backpressureQueue.shift()!;
-                  if (!currentStream.write(queued)) break;
+                  try {
+                    if (!currentStream.write(queued)) break;
+                  } catch (err) {
+                    logger.debug(
+                      {
+                        error: err instanceof Error ? err.message : String(err),
+                      },
+                      "PCM flush write failed during teardown — ignoring",
+                    );
+                    break;
+                  }
                 }
               });
             }