Initial commit: Voice Assistant Gateway mit Konfig-/Routing-Fundament

- FastAPI-Gateway mit REST-Endpunkten (chat/speak/transcribe/devices/sessions/config)
- Geschichtete Konfiguration mit Profilen (local-dev/hybrid/cloud) via TOML + ENV
- Registry-Pattern + einheitliche Route-Aufloesung (Default->Profil->ENV->Session->Request)
- Device Router (strikt, Singleton) und Output-Lifecycle im Orchestrator
- OpenRouter-Adapter (STT multipart/LLM/TTS) + lokale Provider-Stubs
- Regelbasierte Pipeline (Cleaner/Spoken-Adapter/TTS-Normalizer)
- 22 automatisierte Tests; Doku: README, BEDIENUNGSANLEITUNG, Architektur
- Secrets ausschliesslich ueber Umgebung; .env und lokale config gitignored

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

app/audio/endpoints/input/base.py

@@ -0,0 +1,17 @@
+from abc import ABC, abstractmethod
+from app.schemas import AudioChunk, EndpointCapabilities
+
+class AudioInputEndpoint(ABC):
+    endpoint_id: str
+
+    @abstractmethod
+    async def capabilities(self) -> EndpointCapabilities: ...
+
+    @abstractmethod
+    async def open(self) -> None: ...
+
+    @abstractmethod
+    async def read_chunk(self) -> AudioChunk: ...
+
+    @abstractmethod
+    async def close(self) -> None: ...

app/audio/endpoints/input/bluetooth.py

@@ -0,0 +1,23 @@
+from app.audio.endpoints.input.base import AudioInputEndpoint
+from app.schemas import AudioChunk, EndpointCapabilities
+
+class BluetoothInput(AudioInputEndpoint):
+    endpoint_id = "bt-headset-01"
+
+    async def capabilities(self) -> EndpointCapabilities:
+        return EndpointCapabilities(
+            id=self.endpoint_id,
+            kind="bluetooth",
+            direction="input",
+            latency_class="medium",
+            bluetooth=True,
+        )
+
+    async def open(self) -> None:
+        return None
+
+    async def read_chunk(self) -> AudioChunk:
+        return AudioChunk(data=b"", format="wav", timestamp_ms=0)
+
+    async def close(self) -> None:
+        return None

app/audio/endpoints/input/local_default.py

@@ -0,0 +1,24 @@
+from app.audio.endpoints.input.base import AudioInputEndpoint
+from app.schemas import AudioChunk, EndpointCapabilities
+
+class LocalDefaultInput(AudioInputEndpoint):
+    endpoint_id = "local-default-mic"
+
+    async def capabilities(self) -> EndpointCapabilities:
+        return EndpointCapabilities(
+            id=self.endpoint_id,
+            kind="local-default",
+            direction="input",
+            latency_class="low",
+            supports_barge_in=True,
+            default=True,
+        )
+
+    async def open(self) -> None:
+        return None
+
+    async def read_chunk(self) -> AudioChunk:
+        return AudioChunk(data=b"", format="wav", timestamp_ms=0)
+
+    async def close(self) -> None:
+        return None

app/audio/endpoints/input/mobile_webrtc.py

@@ -0,0 +1,25 @@
+from app.audio.endpoints.input.base import AudioInputEndpoint
+from app.schemas import AudioChunk, EndpointCapabilities
+
+class MobileWebRTCInput(AudioInputEndpoint):
+    endpoint_id = "mobile-webrtc-client"
+
+    async def capabilities(self) -> EndpointCapabilities:
+        return EndpointCapabilities(
+            id=self.endpoint_id,
+            kind="mobile-webrtc",
+            direction="input",
+            latency_class="low",
+            networked=True,
+            mobile=True,
+            supports_barge_in=True,
+        )
+
+    async def open(self) -> None:
+        return None
+
+    async def read_chunk(self) -> AudioChunk:
+        return AudioChunk(data=b"", format="wav", timestamp_ms=0)
+
+    async def close(self) -> None:
+        return None

app/audio/endpoints/input/mobile_ws.py

@@ -0,0 +1,24 @@
+from app.audio.endpoints.input.base import AudioInputEndpoint
+from app.schemas import AudioChunk, EndpointCapabilities
+
+class MobileWebSocketInput(AudioInputEndpoint):
+    endpoint_id = "mobile-ws-client"
+
+    async def capabilities(self) -> EndpointCapabilities:
+        return EndpointCapabilities(
+            id=self.endpoint_id,
+            kind="mobile-ws",
+            direction="input",
+            latency_class="medium",
+            networked=True,
+            mobile=True,
+        )
+
+    async def open(self) -> None:
+        return None
+
+    async def read_chunk(self) -> AudioChunk:
+        return AudioChunk(data=b"", format="wav", timestamp_ms=0)
+
+    async def close(self) -> None:
+        return None