ylhan
74a30b11d7
新增实验代码 - services/bot_server.py：Pipecat SmallWebRTC 服务端， 把 ConversationEngine 包成一个 FrameProcessor（检验 A 方案的核心假设） - client/test_client.py：自写 aiortc 客户端——Pipecat 的客户端 SDK 覆盖浏览器/移动端/C++/ESP32，没有适配"Linux x86 盒子接 USB 阵列"这种形态 实验结果 - ✅ 传输层跑通：信令（47–280ms 往返）、ICE 连通、data channel、 双向媒体轨（客户端音轨送达服务端，服务端音轨客户端收到） - ❌ 帧路由未通：自定义处理器的 process_frame 调用次数为 0， 连自己注入的 StartFrame 都没进去，引擎从未运行 - 现象：连接全对、音轨协商成功、助手永远不说话，日志里一条错误都没有 对架构决策的影响 A 方案（Pipecat 只做传输、逻辑归自有引擎）的核心假设不是开箱即用的。 B 方案按框架原生 service 重构，绕开了这个接缝。 根因未定位：接线错误（接缝浅，A 可行）vs 模型不兼容（接缝深，应转 B）。 顺带挖出 8 个 Pipecat 集成坑，每个都表现为"什么都没发生"，已记入 README： 客户端需发 data channel ping、offer 无媒体则不收集 ICE 候选、 run() 要 WorkerParams、TaskManager 需在事件循环内建、 后台任务异常被静默吞掉等。 其他 - bot_server.py 保留 [诊断] 前缀日志，供下一轮排查，定位后应清理 - 客户端默认地址改用 tailscale 域名（局域网已于当日重新编址， 从 192.168.0.x 变为 172.16.1.x） - 新增依赖 aiortc（含 av 17.x，注意 18.x 与 aiortc 1.15 不兼容）
423 lines
17 KiB
Python
423 lines
17 KiB
Python
#!/usr/bin/env python3
|
||
"""Pipecat SmallWebRTC 服务端（实验）。
|
||
|
||
**目的**：验证 Pipecat 传输层与自有引擎能否协同工作，并拿到真实传输下的延迟数字。
|
||
不是产品代码——见文件末尾"这还不是什么"。
|
||
|
||
结构：
|
||
|
||
┌──────────────── Pipecat ────────────────┐
|
||
│ transport.input() → EngineProcessor │
|
||
│ ↓ │
|
||
│ transport.output() │
|
||
└─────────────────────────────────────────┘
|
||
↑
|
||
我们的 ConversationEngine
|
||
（STT→记忆→LLM→TTS 全在里面）
|
||
|
||
EngineProcessor 把整条管线"吞"进一个处理器——这是 A 方案的核心假设：
|
||
**Pipecat 提供传输与帧模型，会话语义归我们的引擎。** 这个实验就是在检验它成不成立。
|
||
|
||
用法：
|
||
# 服务器上
|
||
.venv/bin/python services/bot_server.py --host 0.0.0.0 --port 7860
|
||
# 浏览器打开 http://<服务器IP>:7860/ 点连接后说话
|
||
"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import argparse
|
||
import asyncio
|
||
import logging
|
||
import os
|
||
import sys
|
||
import time
|
||
import uuid
|
||
from pathlib import Path
|
||
|
||
import numpy as np
|
||
|
||
sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
|
||
|
||
from fastapi import FastAPI
|
||
from fastapi.responses import RedirectResponse
|
||
from pipecat.frames.frames import (
|
||
CancelFrame,
|
||
EndFrame,
|
||
InputAudioRawFrame,
|
||
InterruptionFrame,
|
||
OutputAudioRawFrame,
|
||
StartFrame,
|
||
TextFrame,
|
||
)
|
||
from pipecat.pipeline.pipeline import Pipeline
|
||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||
from pipecat.transports.base_transport import TransportParams
|
||
from pipecat.transports.smallwebrtc.request_handler import (
|
||
SmallWebRTCRequest,
|
||
SmallWebRTCRequestHandler,
|
||
)
|
||
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
|
||
from pipecat.utils.asyncio.task_manager import TaskManager
|
||
from pipecat.workers.base_worker import WorkerParams
|
||
|
||
from app.config import AppConfig
|
||
from app.engine import ConversationEngine, EventKind
|
||
from app.identity import ManualIdentityProvider
|
||
from app.llm import FallbackProvider, create_provider
|
||
from app.memory import SQLiteMemoryStore
|
||
from app.voice import StreamingSTT, create_tts
|
||
|
||
logging.basicConfig(level=logging.INFO,
|
||
format="%(asctime)s %(levelname)s %(message)s")
|
||
log = logging.getLogger("bot")
|
||
|
||
#: 输入音频格式（WebRTC 侧协商后的格式）
|
||
IN_RATE = 16000
|
||
IN_CHANNELS = 1
|
||
#: 输出音频格式（Qwen3-TTS 输出 24kHz）
|
||
OUT_RATE = 24000
|
||
|
||
#: 管线参数。给 PipelineTask 构造用。
|
||
PIPELINE_PARAMS = PipelineParams(
|
||
audio_in_sample_rate=IN_RATE,
|
||
audio_out_sample_rate=OUT_RATE,
|
||
enable_metrics=True,
|
||
)
|
||
|
||
#: 注意：PipelineTask.run() 要的是 WorkerParams（内含 task_manager），
|
||
#: **不是** PipelineParams。传错会依次报两个错，且都发生在后台任务里，
|
||
#: 主日志里什么都看不到：
|
||
#: 1. 不传 → "PipelineWorker.run() missing 1 required positional argument: 'params'"
|
||
#: 2. 传错 → "'PipelineParams' object has no attribute 'task_manager'"
|
||
#: 而且 TaskManager() 内部调用 asyncio.get_running_loop()，
|
||
#: **不能在模块级创建**（会报 "no running event loop"），必须在异步上下文里建。
|
||
#: 参考实现：pipecat/workers/runner.py
|
||
|
||
|
||
# ---------------------------------------------------------------- 能量 VAD
|
||
|
||
class SimpleVAD:
|
||
"""极简能量判定。
|
||
|
||
**这是实验用的占位实现**，不是最终方案。方案 §5 把"说完判定"列为需要
|
||
实测的部分，正式的 VAD 还没选（候选：Pipecat 的 Silero、
|
||
sherpa-onnx VAD、或客户端 VAD + 服务端二次确认）。
|
||
|
||
用它的唯一原因是：先把传输层跑通，VAD 的好坏不影响"Pipecat 能不能
|
||
当传输层用"这个结论。
|
||
"""
|
||
|
||
def __init__(self, *, threshold: float = 350.0,
|
||
silence_ms: int = 700, min_speech_ms: int = 300):
|
||
self.threshold = threshold # PCM16 的 RMS 阈值
|
||
self.silence_ms = silence_ms
|
||
self.min_speech_ms = min_speech_ms
|
||
self._silence = 0.0
|
||
self._speech = 0.0
|
||
|
||
def reset(self) -> None:
|
||
self._silence = 0.0
|
||
self._speech = 0.0
|
||
|
||
def feed(self, pcm16: np.ndarray, chunk_ms: float) -> str | None:
|
||
"""喂一块音频，返回 'start' / 'end' / None。"""
|
||
if pcm16.size == 0:
|
||
return None
|
||
rms = float(np.sqrt(np.mean(pcm16.astype(np.float32) ** 2)))
|
||
event = None
|
||
if rms >= self.threshold:
|
||
if self._speech == 0.0:
|
||
event = "start"
|
||
self._speech += chunk_ms
|
||
self._silence = 0.0
|
||
else:
|
||
if self._speech > 0:
|
||
self._silence += chunk_ms
|
||
if self._silence >= self.silence_ms:
|
||
if self._speech >= self.min_speech_ms:
|
||
event = "end"
|
||
self.reset()
|
||
return event
|
||
|
||
|
||
# ---------------------------------------------------------------- 引擎处理器
|
||
|
||
class EngineProcessor(FrameProcessor):
|
||
"""把 ConversationEngine 包成一个 Pipecat 处理器。
|
||
|
||
A 方案的核心假设在这里被检验：**一个处理器吞掉整条会话逻辑，
|
||
Pipecat 只负责音频进出和帧路由。**
|
||
"""
|
||
|
||
def __init__(self, cfg: AppConfig, transport: SmallWebRTCTransport):
|
||
super().__init__()
|
||
log.info("[诊断] EngineProcessor 已创建")
|
||
self.cfg = cfg
|
||
self.transport = transport
|
||
self._vad = SimpleVAD()
|
||
self._buf = bytearray() # 当前话语的 PCM16
|
||
self._turn: asyncio.Task | None = None
|
||
self._engine: ConversationEngine | None = None
|
||
self._session = ""
|
||
self._bot_speaking = False
|
||
# 计时：用于拿真实延迟数字
|
||
self._t_speech_end = 0.0
|
||
self._t_first_audio = 0.0
|
||
|
||
# ------------------------------------------------------------ 生命周期
|
||
|
||
async def _ensure_engine(self) -> ConversationEngine:
|
||
if self._engine is None:
|
||
mem = SQLiteMemoryStore(Path.home() / ".local/share/ai_assistant/memory.db")
|
||
await mem.open()
|
||
llm = FallbackProvider(create_provider(self.cfg.llm),
|
||
create_provider(self.cfg.llm_fallback))
|
||
self._engine = ConversationEngine(
|
||
self.cfg, llm, mem, ManualIdentityProvider(),
|
||
create_tts(self.cfg.voice), StreamingSTT(self.cfg.voice))
|
||
self._session = await self._engine.start_session(user_id="u_ylhan")
|
||
return self._engine
|
||
|
||
async def setup(self, setup):
|
||
log.info("[诊断] EngineProcessor.setup() 被调用")
|
||
await super().setup(setup)
|
||
log.info("[诊断] EngineProcessor 初始化完成")
|
||
|
||
async def process_frame(self, frame, direction: FrameDirection):
|
||
log.info("[诊断·顶] 进入 process_frame: %s", type(frame).__name__)
|
||
await super().process_frame(frame, direction)
|
||
|
||
# [诊断] 记录到达的帧类型分布
|
||
self._seen = getattr(self, "_seen", {})
|
||
k = type(frame).__name__
|
||
self._seen[k] = self._seen.get(k, 0) + 1
|
||
if sum(self._seen.values()) <= 40 or self._seen[k] == 1:
|
||
log.info("[诊断] 帧: %s (累计 %d)", k, sum(self._seen.values()))
|
||
|
||
if isinstance(frame, StartFrame):
|
||
await self.push_frame(frame, direction)
|
||
|
||
elif isinstance(frame, InputAudioRawFrame):
|
||
await self._on_audio(frame)
|
||
|
||
elif isinstance(frame, InterruptionFrame):
|
||
# 客户端判定打断后发来的信号（或 Pipecat 内部产生）
|
||
log.info("收到打断信号，取消当前生成")
|
||
await self._cancel_turn()
|
||
await self.push_frame(frame, direction)
|
||
|
||
elif isinstance(frame, (EndFrame, CancelFrame)):
|
||
await self._cancel_turn()
|
||
await self.push_frame(frame, direction)
|
||
|
||
else:
|
||
await self.push_frame(frame, direction)
|
||
|
||
# ------------------------------------------------------------ 音频处理
|
||
|
||
async def _on_audio(self, frame: InputAudioRawFrame) -> None:
|
||
pcm16 = np.frombuffer(frame.audio, dtype=np.int16)
|
||
chunk_ms = len(pcm16) / IN_RATE * 1000.0
|
||
|
||
# 头几帧打日志，用于确认音频真的到了处理器
|
||
self._n_audio = getattr(self, "_n_audio", 0) + 1
|
||
if self._n_audio <= 3:
|
||
rms = float(np.sqrt(np.mean(pcm16.astype(np.float32) ** 2))) if pcm16.size else 0.0
|
||
log.info("收到音频帧 #%d: %d 采样, %.0fms, RMS=%.0f",
|
||
self._n_audio, pcm16.size, chunk_ms, rms)
|
||
|
||
# 助手正在说话时收到的音频 = 用户插话的候选。
|
||
# 这里只记日志，真正的打断判定在客户端（见方案 §5 的边界决定）。
|
||
if self._bot_speaking and float(np.sqrt(np.mean(pcm16.astype(np.float32) ** 2))) > self._vad.threshold:
|
||
log.info("检测到用户插话（助手正在播放）")
|
||
|
||
self._buf.extend(frame.audio)
|
||
event = self._vad.feed(pcm16, chunk_ms)
|
||
|
||
if event == "end":
|
||
audio = np.frombuffer(bytes(self._buf), dtype=np.int16).astype(np.float32) / 32768.0
|
||
self._buf.clear()
|
||
if len(audio) > IN_RATE * 0.3: # 太短的不处理
|
||
self._t_speech_end = time.perf_counter()
|
||
self._t_first_audio = 0.0
|
||
await self._cancel_turn()
|
||
self._turn = asyncio.create_task(self._run_turn(audio))
|
||
|
||
async def _cancel_turn(self) -> None:
|
||
if self._turn and not self._turn.done():
|
||
self._turn.cancel()
|
||
try:
|
||
await self._turn
|
||
except (asyncio.CancelledError, Exception): # noqa: BLE001
|
||
pass
|
||
self._turn = None
|
||
|
||
# ------------------------------------------------------------ 跑一轮
|
||
|
||
async def _run_turn(self, audio: np.ndarray) -> None:
|
||
try:
|
||
engine = await self._ensure_engine()
|
||
async for ev in engine.respond_to_audio(audio, session_id=self._session):
|
||
if ev.kind == EventKind.RESPONSE_DELTA and ev.text:
|
||
await self.push_frame(TextFrame(text=ev.text))
|
||
elif ev.kind == EventKind.SPEAK and ev.audio is not None and len(ev.audio):
|
||
if self._t_first_audio == 0.0:
|
||
self._t_first_audio = time.perf_counter()
|
||
log.info("首音延迟（说完→首段音频）: %.0f ms",
|
||
(self._t_first_audio - self._t_speech_end) * 1000)
|
||
await self._push_audio(ev.audio, ev.sample_rate)
|
||
elif ev.kind == EventKind.METRICS and ev.metrics:
|
||
log.info("本轮指标: %s", ev.metrics.summary())
|
||
except asyncio.CancelledError:
|
||
log.info("本轮被取消")
|
||
raise
|
||
except Exception as e: # noqa: BLE001
|
||
log.exception("跑轮失败: %s", e)
|
||
|
||
async def _push_audio(self, samples: np.ndarray, sample_rate: int) -> None:
|
||
"""把 float32 音频推给传输层。必要时重采样到 OUT_RATE。"""
|
||
if sample_rate != OUT_RATE:
|
||
# 简单线性重采样。实验够用；正式实现应该用 soxr/sox（已装）。
|
||
n = int(len(samples) * OUT_RATE / sample_rate)
|
||
samples = np.interp(np.linspace(0, len(samples) - 1, n),
|
||
np.arange(len(samples)), samples).astype(np.float32)
|
||
pcm = (np.clip(samples, -1, 1) * 32767).astype(np.int16)
|
||
self._bot_speaking = True
|
||
# 按 20ms 一块推，模拟渐进播放
|
||
step = OUT_RATE // 50
|
||
for i in range(0, len(pcm), step):
|
||
chunk = pcm[i:i + step]
|
||
await self.push_frame(OutputAudioRawFrame(
|
||
audio=chunk.tobytes(), sample_rate=OUT_RATE, num_channels=1))
|
||
self._bot_speaking = False
|
||
|
||
async def cleanup(self):
|
||
await self._cancel_turn()
|
||
await super().cleanup()
|
||
|
||
|
||
# ---------------------------------------------------------------- HTTP 服务
|
||
|
||
app = FastAPI(title="AI Companion · Pipecat experimental server")
|
||
handler = SmallWebRTCRequestHandler()
|
||
_cfg: AppConfig | None = None
|
||
_tasks: list[PipelineTask] = []
|
||
_bg_tasks: set[asyncio.Task] = set() # 持有后台 task 引用，避免被 GC
|
||
|
||
|
||
@app.post("/api/offer")
|
||
async def offer(request: SmallWebRTCRequest):
|
||
"""WebRTC 信令：客户端发 offer，我们回 answer。"""
|
||
|
||
async def on_connection(connection):
|
||
transport = SmallWebRTCTransport(
|
||
webrtc_connection=connection,
|
||
params=TransportParams(
|
||
audio_in_enabled=True,
|
||
audio_in_sample_rate=IN_RATE,
|
||
audio_in_channels=IN_CHANNELS,
|
||
audio_out_enabled=True,
|
||
audio_out_sample_rate=OUT_RATE,
|
||
audio_out_channels=1,
|
||
),
|
||
)
|
||
engine_proc = EngineProcessor(_cfg, transport)
|
||
pipeline = Pipeline([transport.input(), engine_proc, transport.output()])
|
||
# 注意：这个版本里 PipelineParams 没有 allow_interruptions——
|
||
# 打断在 1.10 已移到 pipecat/turns/ 框架。实验阶段我们不用它的
|
||
# 轮次框架（方案 §5 的边界决定是"打断由客户端判定"），
|
||
# 所以这里只开指标。
|
||
# 注意：这个版本的 PipelineTask.run(params) **要求单独传 params**，
|
||
# 只传给构造函数不够。漏传的报错是
|
||
# "PipelineWorker.run() missing 1 required positional argument: 'params'"
|
||
# 而这个异常发生在后台任务里，会被静默吞掉——
|
||
# 现象是"连接正常但什么反应都没有"，而且日志里一条错误都看不到。
|
||
# 所以下面的 _run_task 里必须 log.exception，不能让异常无声消失。
|
||
task = PipelineTask(pipeline)
|
||
_tasks.append(task)
|
||
log.info("新连接已建立，管线启动")
|
||
|
||
@transport.event_handler("on_client_connected")
|
||
async def _on_conn(t, client):
|
||
# **这一步不能省。** 传输层的音频推流由 StartFrame 驱动
|
||
# （base_input.start()），而 PipelineTask.run() 自己不会补发。
|
||
# 不喂 StartFrame 的话：ICE 连通、信令全对、但一帧音频都收不到，
|
||
# 表现为"连上了但助手永远不说话"。
|
||
log.info("客户端已连接，发送 StartFrame 启动音频流")
|
||
await task.queue_frames([StartFrame()])
|
||
|
||
@transport.event_handler("on_client_disconnected")
|
||
async def _on_disc(t, client):
|
||
log.info("客户端断开")
|
||
await task.cancel()
|
||
|
||
# **必须作为后台任务跑，不能 await。**
|
||
# 这个回调是被 handle_web_request 调用的，而后者又在 HTTP 请求里被 await。
|
||
# 如果这里 `await task.run()`，就会在信令请求里阻塞整个会话的生命周期，
|
||
# 管线初始化的时序会歪掉——实测表现为 setup()/connect() 不被调用，
|
||
# 于是 on_client_connected 永远不触发、StartFrame 不发、一帧音频都收不到。
|
||
# 官方 runner 用的是 background_tasks.add_task(bot, args)，同样的道理。
|
||
async def _run_task():
|
||
log.info("[诊断] PipelineTask 开始运行")
|
||
try:
|
||
# TaskManager 必须在这里建——模块级没有运行中的事件循环
|
||
await task.run(WorkerParams(task_manager=TaskManager()))
|
||
except Exception as e: # noqa: BLE001
|
||
log.exception("[诊断] PipelineTask 异常退出: %s", e)
|
||
log.info("[诊断] PipelineTask 已结束")
|
||
|
||
bg = asyncio.create_task(_run_task())
|
||
_bg_tasks.add(bg)
|
||
bg.add_done_callback(_bg_tasks.discard)
|
||
|
||
answer = await handler.handle_web_request(request, on_connection)
|
||
if answer is None:
|
||
return {"status": "ok"}
|
||
return answer
|
||
|
||
|
||
@app.get("/health")
|
||
async def health():
|
||
return {"status": "ok", "connections": len([t for t in _tasks if not t.has_finished()])}
|
||
|
||
|
||
@app.get("/")
|
||
async def root():
|
||
return RedirectResponse("/client/")
|
||
|
||
|
||
def mount_client() -> bool:
|
||
"""挂载 prebuilt 网页客户端（用于测试）。"""
|
||
try:
|
||
from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
|
||
app.mount("/client", SmallWebRTCPrebuiltUI, name="client")
|
||
return True
|
||
except Exception as e: # noqa: BLE001
|
||
log.warning("prebuilt 客户端不可用（不影响服务端）: %s", e)
|
||
return False
|
||
|
||
|
||
def main() -> int:
|
||
global _cfg
|
||
p = argparse.ArgumentParser()
|
||
p.add_argument("--host", default="0.0.0.0")
|
||
p.add_argument("--port", type=int, default=7860)
|
||
a = p.parse_args()
|
||
|
||
_cfg = AppConfig.load()
|
||
log.info("LLM=%s TTS=%s/%s STT=%d线程",
|
||
_cfg.llm.model, _cfg.voice.tts_backend, _cfg.voice.tts_speaker,
|
||
_cfg.voice.stt_threads)
|
||
mounted = mount_client()
|
||
log.info("网页客户端: %s", "已挂载 /client/" if mounted else "未挂载")
|
||
|
||
import uvicorn
|
||
uvicorn.run(app, host=a.host, port=a.port, log_level="warning")
|
||
return 0
|
||
|
||
|
||
if __name__ == "__main__":
|
||
sys.exit(main())
|