Initial commit: AI Video Assistant fullstack platform.

Add pipecat-based backend with WebRTC/WS voice routes, Next.js frontend, and Docker Compose orchestration.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/routes/voice_ws.py

@@ -0,0 +1,50 @@
+"""WS 输出:裸 WebSocket 音频流(第二种输出方式)。
+
+比 WebRTC 简单——没有 SDP/ICE/STUN/TURN,一条 WS 直接收发音频帧。
+适合:服务端对接、话务网关、自定义客户端、调试。
+
+约定:连接建立后,**第一条文本消息**发 JSON 启动参数:
+    {"assistant_id": "asst_xxx"}            # 推荐:key 服务端解析
+    {"inline_config": {...AssistantConfig}} # 调试:内联
+之后的二进制消息即音频帧(protobuf,与 transports.py serializer 对应)。
+"""
+
+import json
+
+from db.session import SessionLocal
+from fastapi import APIRouter, WebSocket
+from loguru import logger
+from models import AssistantConfig
+from services.config_resolver import resolve_runtime_config
+from starlette.websockets import WebSocketDisconnect
+
+# pipecat 重依赖,惰性导入(见 voice_webrtc.py 说明)
+
+router = APIRouter()
+
+
+async def _resolve_start_config(raw: str) -> AssistantConfig:
+    data = json.loads(raw)
+    if data.get("assistant_id"):
+        async with SessionLocal() as session:
+            return await resolve_runtime_config(session, data["assistant_id"])
+    if data.get("inline_config"):
+        return AssistantConfig(**data["inline_config"])
+    raise ValueError("启动参数缺少 assistant_id 或 inline_config")
+
+
+@router.websocket("/ws/stream")
+async def voice_stream(websocket: WebSocket):
+    from services.pipecat.pipeline import run_pipeline
+    from services.pipecat.transports import build_ws_transport
+
+    await websocket.accept()
+    try:
+        cfg = await _resolve_start_config(await websocket.receive_text())
+        transport = build_ws_transport(websocket)
+        # 直接 await:管线持续读这条 WS 的音频帧,直到对端断开
+        await run_pipeline(transport, cfg)
+    except WebSocketDisconnect:
+        logger.info("WS 音频流断开")
+    except Exception as e:
+        logger.error(f"WS 音频流出错: {e}")