feat: per-call LLM timing, speaker ID, cancel captures on leave

- llm.py: log each Ollama call's caller + total/load/prompt/gen durations
  so a slow voice turn is attributable to a specific internal call
  (router/enrichment/digest/main); a RELOAD marker flags cold reloads.
- voice.ts: track in-flight Opus captures and abort them on session
  destroy(); drop any utterance that finishes after the user left, so no
  trailing post-leave VAD turns are reported.
- userbot.ts: show the speaker's Discord user ID on each transcript line
  (answered and dropped) so it's clear whose audio produced the turn.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

bot/src/voice.ts

@@ -66,6 +66,13 @@ export class VoiceSession {
   private connection: VoiceConnection;
   private player: AudioPlayer;
   private listening = new Set<string>();
+  /** Set once the session is torn down (user left / leave command). In-flight
+   *  captures check this so we don't run STT/reply or post a transcript for
+   *  audio that arrived after the user already left the channel. */
+  private destroyed = false;
+  /** Opus subscriptions currently capturing, so leave() can end them
+   *  immediately instead of waiting out the silence timeout. */
+  private activeStreams = new Set<{ destroy: () => void }>();
   /** Pending reply clips. Played one at a time so concurrent speakers don't
    *  cut each other's replies off. */
   private playQueue: Buffer[] = [];
@@ -158,11 +165,14 @@ export class VoiceSession {
   }
 
   private async captureUtterance(userId: string): Promise<void> {
+    // Don't start a new capture once we're tearing down (user left).
+    if (this.destroyed) return;
     // "듣기 시작": the moment we begin capturing this speaker's utterance.
     const listenStartMs = Date.now();
     const opusStream = this.connection.receiver.subscribe(userId, {
       end: { behavior: EndBehaviorType.AfterSilence, duration: config.silenceMs },
     });
+    this.activeStreams.add(opusStream);
     const decoder = new prism.opus.Decoder({
       frameSize: 960,
       channels: DISCORD_CHANNELS,
@@ -173,6 +183,11 @@ export class VoiceSession {
     pcmStream.on("data", (c: Buffer) => chunks.push(c));
 
     await new Promise<void>((resolve) => pcmStream.once("end", () => resolve()));
+    this.activeStreams.delete(opusStream);
+    // If the user left while we were capturing, drop this utterance entirely —
+    // don't run STT/reply or report a (usually empty/VAD-blocked) turn for
+    // audio that trailed in after they left.
+    if (this.destroyed) return;
     // "듣기 종료": end of speech (silence detected). Anything after this is
     // STT + reply + TTS on the brain side.
     const listenEndMs = Date.now();
@@ -264,6 +279,18 @@ export class VoiceSession {
   }
 
   destroy() {
+    this.destroyed = true;
+    // End any in-flight captures now so their pcmStream resolves immediately
+    // and the post-capture `destroyed` check drops them (no trailing
+    // post-leave VAD turns).
+    for (const s of this.activeStreams) {
+      try {
+        s.destroy();
+      } catch {
+        /* already ended */
+      }
+    }
+    this.activeStreams.clear();
     try {
       this.connection.destroy();
     } catch {