feat: integrate OCI agent streaming and web voice client

src/voice_assistant/audio_gateway/app/main.py

@@ -34,8 +34,13 @@ Architecture:
 
 import json
 import logging
+from pathlib import Path
+
+from fastapi.responses import FileResponse
+from fastapi.staticfiles import StaticFiles
 from fastapi import FastAPI, WebSocket, WebSocketDisconnect
 from pydantic import BaseModel, ValidationError
+from contextlib import aclosing
 
 import asyncio
 
@@ -83,8 +88,16 @@ from voice_assistant.audio_gateway.app.protocol import (
     STTPartial,
     TurnEnded,
     TurnStarted,
+    AgentDelta,
 )
 
+from voice_assistant.voice_pipeline import (
+    PipelineTextDelta,
+    PipelineAgentResponse,
+    PipelineAudioChunk,
+)
+
+
 from voice_assistant.audio_gateway.app.session import SessionState
 
 # logger configuration
@@ -100,6 +113,18 @@ provider_catalog = load_provider_catalog()
 
 MAX_AUDIO_CHUNK_BYTES = 64 * 1024 # 64 KB
 
+WEB_DIR = Path(__file__).resolve().parents[1] / "web"
+
+app.mount(
+    "/web",
+    StaticFiles(directory=WEB_DIR),
+    name="web",
+)
+
+
+@app.get("/ui", include_in_schema=False)
+async def web_client() -> FileResponse:
+    return FileResponse(WEB_DIR / "index.html")
 
 
 def create_turn_manager() -> TurnManager:
@@ -176,27 +201,63 @@ async def forward_stt_events(
                 ),
             )
 
-            result = await pipeline.process_transcript(
-                session_id=session_id,
-                turn_id=turn_id,
-                text=event.text,
-            )
+            if callable(getattr(pipeline.agent, "stream", None)):
+                async with aclosing(
+                    pipeline.stream_turn_response(
+                        session_id=session_id,
+                        turn_id=turn_id,
+                        text=event.text,
+                    )
+                ) as response_events:
+                    async for response_event in response_events:
+                        if not pipeline.is_active_turn(turn_id):
+                            break
 
-            await send_json(
-                websocket,
-                AgentResponse(
+                        if isinstance(response_event, PipelineTextDelta):
+                            await send_json(
+                                websocket,
+                                AgentDelta(
+                                    session_id=session_id,
+                                    turn_id=turn_id,
+                                    text=response_event.text,
+                                ),
+                            )
+
+                        elif isinstance(response_event, PipelineAgentResponse):
+                            await send_json(
+                                websocket,
+                                AgentResponse(
+                                    session_id=session_id,
+                                    turn_id=turn_id,
+                                    text=response_event.text,
+                                ),
+                            )
+
+                        elif isinstance(response_event, PipelineAudioChunk):
+                            await websocket.send_bytes(response_event.audio)
+
+            else:
+                result = await pipeline.process_transcript(
                     session_id=session_id,
                     turn_id=turn_id,
-                    text=result.response_text,
-                ),
-            )
+                    text=event.text,
+                )
 
-            async for audio_chunk in pipeline.synthesize_response(
-                result.response_text,
-            ):
-                await websocket.send_bytes(audio_chunk)
+                await send_json(
+                    websocket,
+                    AgentResponse(
+                        session_id=session_id,
+                        turn_id=turn_id,
+                        text=result.response_text,
+                    ),
+                )
 
-            pipeline.on_tts_complete(turn_id)
+                async for audio_chunk in pipeline.synthesize_response(
+                    result.response_text,
+                ):
+                    await websocket.send_bytes(audio_chunk)
+
+                pipeline.on_tts_complete(turn_id)