feat: Audio-Streaming (chunked TTS) über WebSocket (#4 Ausbau)

- SentenceChunker (pipeline/sentence_chunker.py): inkrementelle Satzsegmentierung
- Orchestrator.chat_stream(on_audio): satzweise TTS, Audio-Chunk pro fertigem Satz;
  Gesamtaudio zusaetzlich an den Output-Endpunkt
- WS /ws/chat {"audio_stream":true}: audio-Events (json seq + binaerer Frame) live,
  kein finales Vollaudio; mit stream kombinierbar
- Tests: 45 gruen (+2: Sentence-Chunker, Audio-Streaming)
- Doku aktualisiert (README, BEDIENUNGSANLEITUNG, Architektur)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

app/api/ws.py

@@ -96,11 +96,25 @@ async def ws_chat(
 
             voice = msg.get("voice") or settings.openrouter_tts_voice
             stream = bool(msg.get("stream"))
-            try:
-                if stream:
-                    async def on_token(delta):
-                        await websocket.send_json({"type": "token", "text": delta})
+            audio_stream = bool(msg.get("audio_stream"))
 
+            on_token = None
+            if stream:
+                async def on_token(delta):
+                    await websocket.send_json({"type": "token", "text": delta})
+
+            on_audio = None
+            if audio_stream:
+                audio_seq = 0
+
+                async def on_audio(chunk):
+                    nonlocal audio_seq
+                    await websocket.send_json({"type": "audio", "seq": audio_seq})
+                    audio_seq += 1
+                    await websocket.send_bytes(chunk)
+
+            try:
+                if stream or audio_stream:
                     trace, audio = await orchestrator.chat_stream(
                         text,
                         language=route.language,
@@ -108,6 +122,7 @@ async def ws_chat(
                         output=output,
                         history=llm_context,
                         on_token=on_token,
+                        on_audio=on_audio,
                     )
                 else:
                     trace, audio = await orchestrator.chat_text(
@@ -132,7 +147,9 @@ async def ws_chat(
                     "spoken": trace.spoken_response,
                 }
             )
-            await websocket.send_bytes(audio)
+            # Bei audio_stream wurden die Audio-Chunks bereits live gesendet.
+            if not audio_stream:
+                await websocket.send_bytes(audio)
             await websocket.send_json(
                 {"type": "done", "audio_format": "pcm", "sample_rate": 24000}
             )