rkllm vor Diar/Identify freigeben — TitaNet-OOM neben residentem LLM

llm.stopServer() am Anfang von rediarize() und analyzeRecording():
spk-embed starb sonst OOM (48 Roh-Sprecher auf #71). E2E #71: 48->2
Sprecher + saubere Whole-Pass-Summary. Offen: identify-spk-Fehler
auch mit freiem RAM (Voice-Auto-Naming tot).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0113vDKdSNtD3Dwcw4QMu9yV

app/server.js

@@ -86,6 +86,11 @@ async function identifySpeakers(recData) {
 // and a long Gemma generation hit 95-97°C uncapped on the fanless board (#70,
 // 16-min run) — same shutdown risk transcribeWav/rediarize already guard against.
 async function analyzeRecording(id) {
+  // Free the resident rkllm (~5.9GB) BEFORE identifySpeakers: the TitaNet
+  // spk-embed helper OOM-dies next to it ("spk beendet" per cluster, #71 got
+  // 48 raw speakers). llm.analyze() below respawns it (~96s load, noise
+  // against a 15-min analysis).
+  llm.stopServer();
   await pexec('sudo', ['-n', '/opt/callrec/aime-cpucap.sh', '1608000']).catch(() => {});
   try {
     const rec = await db.getRecording(id);
@@ -261,6 +266,10 @@ async function rediarize(id, numSpeakers) {
   const wav = path.join(REC_DIR, r.wav_file);
   if (!fs.existsSync(wav)) throw new Error('wav-Datei nicht gefunden: ' + r.wav_file);
   const words = r.words || [];
+  // Free the resident rkllm first — diar's consolidation embeds every cluster
+  // via TitaNet, which OOM-dies next to a resident 5.9GB LLM (see
+  // analyzeRecording; on #71 that silently yielded 48 raw speakers).
+  llm.stopServer();
   // Diarization runs on the A76 cores; the board is fanless, so cap the clock
   // for the whole run (transcribeWav does this for the record path — rediarize
   // is the other entry point and must do it too, or a long re-diar overheats).