Files
ai-video-fullstack/backend/routes/voice_webrtc.py
Xin Wang 86639692ba feat: implement OpenAI-compatible Realtime API with authentication and management features
- Added support for public Realtime API, including new routes for managing API keys and handling WebRTC connections.
- Introduced RealtimeApiKey model and associated CRUD operations for admin management of API keys.
- Implemented authentication mechanisms for API keys and client secrets.
- Enhanced environment configuration with new secrets for Realtime API.
- Created OpenAIRealtime session management and event processing for real-time interactions.
- Updated schemas and settings to accommodate new features and ensure compatibility with existing systems.
2026-08-11 10:05:55 +08:00

263 lines
9.2 KiB
Python

"""WebRTC 输出:SmallWebRTC 信令握手。
参考 dograh 的 webrtc_signaling.py,砍掉鉴权/配额/DB/org/ICE 过滤策略/TURN。
握手消息:
client → {type:"offer", payload:{pc_id, sdp, type, assistant_id}}
server → {type:"answer", payload:{pc_id, sdp, type}}
both → {type:"ice-candidate", payload:{pc_id, candidate:{...}}}
server → {type:"error", payload:{message}}
"""
import base64
import json
from collections.abc import Coroutine
from typing import Any
from fastapi import APIRouter, Body, Depends, Request, WebSocket
from loguru import logger
from models import AssistantConfig, SignalingOffer
from services.auth import require_admin, require_admin_websocket
from services.realtime import lifecycle as realtime_lifecycle
from services.realtime.launcher import (
resolve_assistant_config,
validate_visual_runtime,
)
from services.runtime_variables import DynamicVariableError, prepare_dynamic_config
from starlette.websockets import WebSocketDisconnect, WebSocketState
from services.webrtc_ice import aiortc_ice_servers, client_ice_servers
# 注意:pipecat 是重依赖(语音才用),在 _handle_offer 等处惰性导入。
router = APIRouter(tags=["voice"])
_http_peers: dict[str, object] = {}
_active_connections = realtime_lifecycle.active_connections
_pipeline_tasks = realtime_lifecycle.pipeline_tasks
_connection_tasks = realtime_lifecycle.connection_tasks
PIPELINE_CLOSE_GRACE_SECONDS = 10.0
def _start_pipeline_task(
connection: object,
coroutine: Coroutine[Any, Any, None],
) -> object:
"""Compatibility proxy for existing RTVI callers and tests."""
return realtime_lifecycle.start_pipeline_task(
connection,
coroutine,
protocol="webrtc",
)
async def _wait_for_pipeline_close(
task,
*,
connection_id: str,
) -> None:
await realtime_lifecycle.wait_for_pipeline_close(
task,
connection_id=connection_id,
timeout=PIPELINE_CLOSE_GRACE_SECONDS,
)
async def shutdown_active_sessions() -> None:
"""Compatibility proxy; now drains RTVI and OpenAI Realtime sessions."""
_http_peers.clear()
await realtime_lifecycle.shutdown_active_sessions(
timeout=PIPELINE_CLOSE_GRACE_SECONDS,
)
@router.get("/api/webrtc/ice-servers", dependencies=[Depends(require_admin)])
async def ice_servers():
"""Browser fetches STUN/TURN config (with ephemeral TURN creds when configured)."""
return {"iceServers": client_ice_servers()}
@router.post("/api/webrtc/offer", dependencies=[Depends(require_admin)])
async def http_offer(request: Request, payload: dict = Body(...)):
"""Official SmallWebRTC JS transport offer endpoint."""
request_data = payload.get("requestData") or {}
encoded_variables = request.headers.get("x-pipecat-dynamic-variables", "")
header_variables = {}
if encoded_variables:
padding = "=" * (-len(encoded_variables) % 4)
header_variables = json.loads(
base64.urlsafe_b64decode(encoded_variables + padding).decode("utf-8")
)
offer_payload = {
**payload,
"assistant_id": request.headers.get("x-pipecat-assistant-id"),
"dynamic_variables": header_variables,
**request_data,
}
answer = await _handle_offer_payload(offer_payload, _http_peers)
return answer
@router.patch("/api/webrtc/offer", dependencies=[Depends(require_admin)])
async def http_ice_candidates(payload: dict = Body(...)):
"""Accept the batched trickle ICE format used by the official JS client."""
pc_id = payload.get("pc_id")
pc = _http_peers.get(pc_id) if pc_id else None
if not pc:
return {"ok": False}
from aiortc.sdp import candidate_from_sdp
for item in payload.get("candidates") or []:
candidate = candidate_from_sdp(item.get("candidate", ""))
candidate.sdpMid = item.get("sdp_mid")
candidate.sdpMLineIndex = item.get("sdp_mline_index")
await pc.add_ice_candidate(candidate)
return {"ok": True}
@router.websocket("/ws/voice")
async def voice_signaling(websocket: WebSocket):
if not await require_admin_websocket(websocket):
return
await websocket.accept()
peers: dict = {}
try:
while True:
message = await websocket.receive_json()
try:
if message.get("type") == "offer":
await _handle_offer(websocket, message.get("payload", {}), peers)
elif message.get("type") == "ice-candidate":
await _handle_ice(message.get("payload", {}), peers)
except Exception as e:
logger.exception(f"处理 WebRTC 信令消息失败: {e}")
if websocket.application_state == WebSocketState.CONNECTED:
await websocket.send_json(
{
"type": "error",
"payload": {
"message": (
str(e)
if isinstance(e, DynamicVariableError)
else f"语音会话启动失败: {type(e).__name__}"
)
},
}
)
except WebSocketDisconnect:
logger.info("WebRTC 信令断开")
except Exception as e:
logger.error(f"WebRTC 信令出错: {e}")
finally:
# disconnect() triggers the registered closed callback, which removes
# the peer from this dict. Iterate over a snapshot to avoid mutation.
for pc in list(peers.values()):
await pc.disconnect()
async def _resolve_config(offer: SignalingOffer) -> AssistantConfig:
"""优先用 assistant_id 从 DB 解析(含真 key);否则用调试内联配置。"""
if offer.assistant_id:
return await resolve_assistant_config(
offer.assistant_id,
dynamic_variables=offer.dynamic_variables,
)
if offer.inline_config:
return prepare_dynamic_config(
offer.inline_config,
offer.dynamic_variables,
assistant_id=None,
)
raise ValueError("offer 缺少 assistant_id 或 inline_config")
async def _handle_offer(websocket, payload, peers):
answer = await _handle_offer_payload(payload, peers)
if websocket.application_state == WebSocketState.CONNECTED:
await websocket.send_json(
{
"type": "answer",
"payload": answer,
}
)
async def _handle_offer_payload(payload, peers):
from pipecat.transports.smallwebrtc.connection import SmallWebRTCConnection
from services.pipecat.pipeline import run_pipeline
from services.pipecat.transports import build_webrtc_transport
offer = SignalingOffer(**payload)
pc_id = offer.pc_id
restart_pc = bool(payload.get("restart_pc"))
if restart_pc and pc_id and pc_id in peers:
old_pc = peers.pop(pc_id)
old_task = _connection_tasks.get(old_pc)
await old_pc.disconnect()
await _wait_for_pipeline_close(
old_task,
connection_id=str(getattr(old_pc, "pc_id", pc_id)),
)
if pc_id and pc_id in peers:
pc = peers[pc_id]
await pc.renegotiate(sdp=offer.sdp, type=offer.type, restart_pc=False)
else:
cfg = await _resolve_config(offer) # 解析放在建连前,配置错就别建连
# 服务端助手配置是视觉理解的唯一授权来源;客户端 offer 只负责携带媒体轨。
vision_enabled = validate_visual_runtime(cfg)
pc = SmallWebRTCConnection(ice_servers=aiortc_ice_servers())
if pc_id:
pc._pc_id = pc_id
await pc.initialize(sdp=offer.sdp, type=offer.type)
peers[pc.pc_id] = pc
# 后台跑管线:WebRTC transport + 解析出的运行时配置
transport = build_webrtc_transport(
pc,
video_in_enabled=vision_enabled,
)
pipeline_task = _start_pipeline_task(
pc,
run_pipeline(
transport,
cfg,
vision_enabled=vision_enabled,
assistant_id=offer.assistant_id,
channel="webrtc",
),
)
@pc.event_handler("closed")
async def _on_closed(conn: SmallWebRTCConnection):
peers.pop(conn.pc_id, None)
_active_connections.discard(conn)
await _wait_for_pipeline_close(
pipeline_task,
connection_id=conn.pc_id,
)
answer = pc.get_answer()
return {
"pc_id": answer["pc_id"],
"sdp": answer["sdp"],
"type": answer["type"],
}
async def _handle_ice(payload, peers):
from aiortc.sdp import candidate_from_sdp
pc_id = payload.get("pc_id")
candidate_data = payload.get("candidate")
pc = peers.get(pc_id) if pc_id else None
if not pc or not candidate_data:
return
try:
candidate = candidate_from_sdp(candidate_data.get("candidate", ""))
candidate.sdpMid = candidate_data.get("sdpMid")
candidate.sdpMLineIndex = candidate_data.get("sdpMLineIndex")
await pc.add_ice_candidate(candidate)
except Exception as e:
logger.error(f"添加 ICE candidate 失败: {e}")