Pipecat 传输层实验：传输层通，帧路由未通
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）
This commit is contained in:
ylhan
@@ -31,7 +31,11 @@ app/ 助手本体（部署到服务器）
|
||||
└── tests/ 4 个测试，共 88 项断言，全部无需硬件
|
||||
|
||||
services/
|
||||
└── tts_server.py Qwen3-TTS 服务（跑在 ~/tts-qwen，独立 venv）
|
||||
├── tts_server.py Qwen3-TTS 服务（跑在 ~/tts-qwen，独立 venv）
|
||||
└── bot_server.py Pipecat SmallWebRTC 服务端（实验，见下）
|
||||
|
||||
client/
|
||||
└── test_client.py 自写 aiortc 客户端（实验用，也是 N5095 客户端的雏形）
|
||||
|
||||
p0/ P0 阶段的验证与基准脚本（保留用于复现）
|
||||
├── verify_deepseek.py DeepSeek 四条路径
|
||||
@@ -76,6 +80,40 @@ cd ~/ai-companion
|
||||
**引擎与传输解耦。** 不依赖 Pipecat、不依赖任何传输方式，只依赖四个接口。
|
||||
好处：可以用文件音频端到端测试；接 WebRTC 时只需写薄适配层。
|
||||
|
||||
## 当前卡点：Pipecat 传了但没接上
|
||||
|
||||
方案文档写"Pipecat 作为唯一会话管线框架"，但**代码里它只在 requirements.txt 里**。
|
||||
|
||||
2026-09-15 做了传输层实验（`services/bot_server.py` + `client/test_client.py`）：
|
||||
|
||||
- ✅ **传输层跑通**：信令、ICE、data channel、双向媒体轨
|
||||
- ❌ **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
|
||||
|
||||
现象是"连接全对、音轨协商成功、但助手永远不说话，且日志里一条错误都没有"。
|
||||
|
||||
**这直接影响 A/B 架构方案**：A 是"Pipecat 只做传输、逻辑归自有引擎"，
|
||||
B 是"按 Pipecat 的 service 模型重构"。帧送不进自定义处理器，
|
||||
说明 A 的核心假设不是开箱即用的。
|
||||
|
||||
根因未定位，两种可能必须区分：接线错误（接缝浅，A 可行）
|
||||
vs 模型不兼容（接缝深，应转 B）。
|
||||
|
||||
完整记录见代码仓库外的 `P0-Pipecat传输层实验报告.md`（在 Obsidian 笔记库里）。
|
||||
|
||||
### 实验挖出的 8 个坑
|
||||
|
||||
每个都表现为"什么都没发生"，极难排查：
|
||||
|
||||
1. Pipecat 客户端 SDK 不覆盖"Linux x86 盒子接 USB 阵列"这种形态 → 客户端得自己写
|
||||
2. 客户端必须建 data channel 并定期发 `"ping"`，否则服务端一帧音频都不推
|
||||
3. offer 里没有媒体时 aiortc **完全不收集 ICE 候选**（连连通性测试都要加静音轨）
|
||||
4. ICE 收集完成前发 offer → SDP 里 0 个候选地址
|
||||
5. `PipelineTask.run()` 要 `WorkerParams(task_manager=...)`，不是 `PipelineParams`
|
||||
6. `TaskManager()` 必须在事件循环内创建
|
||||
7. **后台任务里的异常被静默吞掉**，日志里查不到
|
||||
8. 信令回调里必须 `create_task`，不能 `await task.run()`
|
||||
|
||||
## 踩过的坑
|
||||
|
||||
全部写在对应文件的注释里，这里只列索引，详见 `部署说明.md` §已知的坑：
|
||||
|
||||
@@ -0,0 +1,338 @@
|
||||
#!/usr/bin/env python3
|
||||
"""最小 aiortc 客户端（实验用）。
|
||||
|
||||
**为什么需要它**：Pipecat 的官方客户端 SDK 覆盖浏览器 / 移动端 / C++ / ESP32，
|
||||
唯独没有适配"跑 Linux 的 x86 盒子接 USB 麦克风阵列"——也就是 N5095 的形态。
|
||||
所以客户端必须自己写，这个文件是雏形。
|
||||
|
||||
它同时是验证工具：不依赖浏览器就能测服务端。用法：
|
||||
|
||||
# 发一段 wav，收回应答音频
|
||||
python client/test_client.py --server http://<服务器>:7860 \
|
||||
--wav p0/stt_tts_bench/wavs/stt_1.wav --out /tmp/reply.wav
|
||||
|
||||
# 只做连接测试，不发音频
|
||||
python client/test_client.py --server http://<服务器>:7860 --connect-only
|
||||
|
||||
**它还不是什么**：不做 AEC、不做播客参考、不做打断（那些要真实声卡和硬件），
|
||||
只用文件音频验证信令与媒体通路。
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import asyncio
|
||||
import fractions
|
||||
import json
|
||||
import logging
|
||||
import sys
|
||||
import time
|
||||
import urllib.request
|
||||
import wave
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
from aiortc import (
|
||||
RTCConfiguration,
|
||||
RTCPeerConnection,
|
||||
RTCSessionDescription,
|
||||
)
|
||||
from aiortc.mediastreams import AudioStreamTrack, MediaStreamError
|
||||
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s %(levelname)s %(message)s")
|
||||
log = logging.getLogger("client")
|
||||
|
||||
|
||||
class SilentTrack(AudioStreamTrack):
|
||||
"""静音音轨。只为触发 ICE 候选收集，不发真实音频。"""
|
||||
|
||||
kind = "audio"
|
||||
|
||||
def __init__(self, sample_rate: int = 16000):
|
||||
super().__init__()
|
||||
self.sample_rate = sample_rate
|
||||
self._n = 0
|
||||
|
||||
async def recv(self):
|
||||
import fractions as _fr
|
||||
from av import AudioFrame as _AF
|
||||
await asyncio.sleep(0.02)
|
||||
pcm = np.zeros(self.sample_rate // 50, dtype=np.int16)
|
||||
f = _AF(format="s16", layout="mono", samples=len(pcm))
|
||||
f.planes[0].update(pcm.tobytes())
|
||||
f.sample_rate = self.sample_rate
|
||||
f.pts = self._n
|
||||
f.time_base = _fr.Fraction(1, self.sample_rate)
|
||||
self._n += len(pcm)
|
||||
return f
|
||||
|
||||
|
||||
class FileAudioTrack(AudioStreamTrack):
|
||||
"""把 wav 文件当作麦克风音源，按实时速率吐出来。
|
||||
|
||||
实时速率很重要——如果一次性灌完，服务端的 VAD 会把它当成
|
||||
一段超长的连续语音，测出来的延迟也不真实。
|
||||
"""
|
||||
|
||||
kind = "audio"
|
||||
|
||||
def __init__(self, wav_path: Path, *, sample_rate: int = 16000):
|
||||
super().__init__()
|
||||
with wave.open(str(wav_path)) as w:
|
||||
assert w.getnchannels() == 1, "需要单声道"
|
||||
self.src_rate = w.getframerate()
|
||||
pcm = np.frombuffer(w.readframes(w.getnframes()), dtype=np.int16)
|
||||
self.samples = pcm.astype(np.float32) / 32768.0
|
||||
self.sample_rate = sample_rate
|
||||
if self.src_rate != sample_rate:
|
||||
n = int(len(self.samples) * sample_rate / self.src_rate)
|
||||
self.samples = np.interp(np.linspace(0, len(self.samples) - 1, n),
|
||||
np.arange(len(self.samples)), self.samples)
|
||||
self._pos = 0
|
||||
self._t0: float | None = None
|
||||
self._frame_samples = sample_rate // 100 # 10ms
|
||||
|
||||
async def recv(self):
|
||||
"""按 10ms 一块、以真实时间节奏产出。"""
|
||||
if self._t0 is None:
|
||||
self._t0 = time.perf_counter()
|
||||
self._pos = 0
|
||||
|
||||
# 音频放完后持续吐静音，让服务端的 VAD 能判到"说完"
|
||||
if self._pos >= len(self.samples):
|
||||
audio = np.zeros(self._frame_samples, dtype=np.float32)
|
||||
else:
|
||||
audio = self.samples[self._pos:self._pos + self._frame_samples]
|
||||
if len(audio) < self._frame_samples:
|
||||
audio = np.pad(audio, (0, self._frame_samples - len(audio)))
|
||||
self._pos += self._frame_samples
|
||||
|
||||
# 实时节奏
|
||||
target = self._t0 + self._pos / self.sample_rate
|
||||
delay = target - time.perf_counter()
|
||||
if delay > 0:
|
||||
await asyncio.sleep(delay)
|
||||
|
||||
pcm = (np.clip(audio, -1, 1) * 32767).astype(np.int16)
|
||||
from av import AudioFrame
|
||||
f = AudioFrame(format="s16", layout="mono", samples=len(pcm))
|
||||
f.planes[0].update(pcm.tobytes())
|
||||
f.sample_rate = self.sample_rate
|
||||
f.pts = int(self._pos * 90000 / self.sample_rate)
|
||||
f.time_base = fractions.Fraction(1, 90000)
|
||||
return f
|
||||
|
||||
@property
|
||||
def finished(self) -> bool:
|
||||
return self._pos >= len(self.samples)
|
||||
|
||||
|
||||
class ReplyRecorder:
|
||||
"""收服务端音频，写 wav，并记录首音延迟。"""
|
||||
|
||||
def __init__(self, out_path: Path, sample_rate: int = 24000):
|
||||
self.out_path = out_path
|
||||
self.sample_rate = sample_rate
|
||||
self.chunks: list[np.ndarray] = []
|
||||
self.first_at: float | None = None
|
||||
self.t0 = time.perf_counter()
|
||||
|
||||
def feed(self, frame) -> None:
|
||||
if self.first_at is None:
|
||||
self.first_at = time.perf_counter()
|
||||
arr = frame.to_ndarray()
|
||||
# 多声道取第一路
|
||||
if arr.shape[0] > 1:
|
||||
arr = arr[0:1]
|
||||
self.chunks.append(arr.astype(np.float32).reshape(-1) / 32768.0)
|
||||
|
||||
def save(self) -> float:
|
||||
if not self.chunks:
|
||||
return 0.0
|
||||
audio = np.concatenate(self.chunks)
|
||||
pcm = (np.clip(audio, -1, 1) * 32767).astype(np.int16)
|
||||
self.out_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with wave.open(str(self.out_path), "wb") as w:
|
||||
w.setnchannels(1)
|
||||
w.setsampwidth(2)
|
||||
w.setframerate(self.sample_rate)
|
||||
w.writeframes(pcm.tobytes())
|
||||
return len(audio) / self.sample_rate
|
||||
|
||||
@property
|
||||
def first_audio_ms(self) -> float | None:
|
||||
return None if self.first_at is None else (self.first_at - self.t0) * 1000
|
||||
|
||||
|
||||
def post_offer(server: str, sdp: str, type_: str) -> dict:
|
||||
"""把 offer 发给服务端，取回 answer。"""
|
||||
payload = json.dumps({"sdp": sdp, "type": type_, "pc_id": None,
|
||||
"restart_pc": False, "request_data": None}).encode()
|
||||
req = urllib.request.Request(f"{server.rstrip('/')}/api/offer", data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST")
|
||||
with urllib.request.urlopen(req, timeout=30) as r:
|
||||
return json.loads(r.read().decode())
|
||||
|
||||
|
||||
async def run(server: str, wav: Path | None, out: Path, *, connect_only: bool,
|
||||
timeout_s: float) -> int:
|
||||
pc = RTCPeerConnection(RTCConfiguration(iceServers=[]))
|
||||
recorder = ReplyRecorder(out)
|
||||
track = None
|
||||
got_audio = asyncio.Event()
|
||||
|
||||
@pc.on("connectionstatechange")
|
||||
async def _state():
|
||||
log.info("连接状态: %s", pc.connectionState)
|
||||
if pc.connectionState in ("failed", "closed"):
|
||||
got_audio.set()
|
||||
|
||||
@pc.on("track")
|
||||
def _track(t):
|
||||
log.info("收到服务端音轨: %s", t.kind)
|
||||
|
||||
async def _pump():
|
||||
try:
|
||||
while True:
|
||||
frame = await t.recv()
|
||||
recorder.feed(frame)
|
||||
if not got_audio.is_set() and recorder.chunks:
|
||||
pass
|
||||
except (MediaStreamError, asyncio.CancelledError):
|
||||
pass
|
||||
finally:
|
||||
got_audio.set()
|
||||
|
||||
asyncio.ensure_future(_pump())
|
||||
|
||||
if wav and not connect_only:
|
||||
track = FileAudioTrack(wav)
|
||||
pc.addTrack(track)
|
||||
log.info("音源: %s（%d 采样点）", wav.name, len(track.samples))
|
||||
else:
|
||||
# --connect-only 也要加一条（静音）音轨。
|
||||
# **不能省**：aiortc 的 offer 里没有媒体时完全不收集 ICE 候选，
|
||||
# 现象是"信令成功、SDP 交换正常、但 ICE 永远停在 new"。
|
||||
pc.addTrack(SilentTrack())
|
||||
log.info("连接测试模式：已加静音音轨（仅为触发 ICE 收集）")
|
||||
|
||||
# **必须建 data channel 并定期发 "ping"。**
|
||||
# Pipecat 的 SmallWebRTC 用 data channel 上的消息来判断"客户端还活着"：
|
||||
# if isinstance(message, str) and message.startswith("ping"):
|
||||
# self._last_received_time = time.time()
|
||||
# 而 connection 的 connected 事件、进而 on_client_connected 回调、
|
||||
# 进而 StartFrame（音频推流的开关）都依赖它。
|
||||
# 不发 ping 的现象是：ICE 连通、音轨协商成功、但**服务端一帧音频都不推**、
|
||||
# 助手永远不说话，而且日志里只有一句 "Data channel not established within 10s"。
|
||||
channel = pc.createDataChannel("pipecat")
|
||||
dc_state = {"ok": False}
|
||||
|
||||
@channel.on("open")
|
||||
def _dc_open():
|
||||
dc_state["ok"] = True
|
||||
log.info("data channel 已打开，开始发心跳")
|
||||
|
||||
async def _keepalive():
|
||||
while pc.connectionState not in ("closed", "failed"):
|
||||
if dc_state["ok"]:
|
||||
try:
|
||||
channel.send("ping")
|
||||
except Exception: # noqa: BLE001
|
||||
pass
|
||||
await asyncio.sleep(1.0)
|
||||
|
||||
asyncio.ensure_future(_keepalive())
|
||||
|
||||
offer = await pc.createOffer()
|
||||
await pc.setLocalDescription(offer)
|
||||
|
||||
# 等 ICE 收集完成再发 offer——**这步不能省**。
|
||||
# 不等的话 SDP 里没有任何候选地址，服务端拿到的是一份"空地址"的 offer，
|
||||
# 信令看着成功，但 ICE 永远连不上（状态停在 new）。
|
||||
# 这叫非 trickle ICE：把候选都塞进 SDP 一次发完。
|
||||
# 真实产品会用 trickle（边收集边发候选），但那样需要额外的信令端点。
|
||||
for _ in range(100):
|
||||
if pc.iceGatheringState == "complete":
|
||||
break
|
||||
await asyncio.sleep(0.1)
|
||||
n_cand = pc.localDescription.sdp.count("candidate:")
|
||||
log.info("ICE 收集: %s，SDP 含 %d 个候选", pc.iceGatheringState, n_cand)
|
||||
if n_cand == 0:
|
||||
log.warning("SDP 里没有候选地址，ICE 很可能连不上")
|
||||
|
||||
log.info("本地 SDP 已生成，发给服务端…")
|
||||
|
||||
t_send = time.perf_counter()
|
||||
answer = post_offer(server, pc.localDescription.sdp, pc.localDescription.type)
|
||||
if answer.get("type") not in ("answer", None):
|
||||
log.error("服务端返回异常: %s", answer)
|
||||
return 1
|
||||
if answer.get("sdp"):
|
||||
await pc.setRemoteDescription(RTCSessionDescription(
|
||||
sdp=answer["sdp"], type=answer["type"]))
|
||||
log.info("远端 SDP 已设置（往返 %.0f ms）", (time.perf_counter() - t_send) * 1000)
|
||||
else:
|
||||
log.info("服务端未返回 SDP（可能是 pc_id 复用）: %s", answer)
|
||||
|
||||
# 等 ICE 连通
|
||||
for _ in range(100):
|
||||
if pc.connectionState in ("connected", "completed"):
|
||||
break
|
||||
if pc.connectionState in ("failed", "closed"):
|
||||
log.error("连接失败")
|
||||
await pc.close()
|
||||
return 1
|
||||
await asyncio.sleep(0.1)
|
||||
log.info("✅ ICE 已连通（%s）", pc.connectionState)
|
||||
print(f" ✅ 连接建立，状态 {pc.connectionState}")
|
||||
|
||||
if track:
|
||||
# 等音频放完 + 留出响应时间
|
||||
t0 = time.perf_counter()
|
||||
while not track.finished and time.perf_counter() - t0 < timeout_s:
|
||||
await asyncio.sleep(0.2)
|
||||
log.info("音频已发完，等待回复…")
|
||||
# 等首个回复音频
|
||||
t_wait = time.perf_counter()
|
||||
while time.perf_counter() - t_wait < timeout_s:
|
||||
if recorder.chunks:
|
||||
break
|
||||
await asyncio.sleep(0.1)
|
||||
# 再收一会儿，让回复说完
|
||||
await asyncio.sleep(6)
|
||||
|
||||
dur = recorder.save()
|
||||
await pc.close()
|
||||
got_audio.set()
|
||||
|
||||
print()
|
||||
print("=== 结果 ===")
|
||||
print(f" 连接: {'✅ 成功' if dur > 0 else '⚠️ 无音频返回'}")
|
||||
if dur:
|
||||
print(f" 收到音频: {dur:.2f} 秒 → {out}")
|
||||
fa = recorder.first_audio_ms
|
||||
if fa:
|
||||
print(f" 首音延迟（发完到收到首段）: {fa:.0f} ms")
|
||||
return 0 if dur > 0 else 1
|
||||
|
||||
|
||||
def main() -> int:
|
||||
p = argparse.ArgumentParser()
|
||||
p.add_argument("--server", default="http://cadadmin-server.taild0f91d.ts.net:7860",
|
||||
help="服务端地址。默认用 tailscale 域名——LAN 地址会被重新编址"
|
||||
"（2026-09-15 实测从 192.168.0.x 变成 172.16.1.x）")
|
||||
p.add_argument("--wav", type=Path)
|
||||
p.add_argument("--out", type=Path, default=Path("/tmp/client_reply.wav"))
|
||||
p.add_argument("--connect-only", action="store_true")
|
||||
p.add_argument("--timeout", type=float, default=30.0)
|
||||
a = p.parse_args()
|
||||
if not a.connect_only and not a.wav:
|
||||
print("需要 --wav 或 --connect-only", file=sys.stderr)
|
||||
return 2
|
||||
return asyncio.run(run(a.server, a.wav, a.out,
|
||||
connect_only=a.connect_only, timeout_s=a.timeout))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
@@ -0,0 +1,422 @@
|
||||
#!/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())
|
||||
@@ -51,6 +51,8 @@ DoA 读取和网络桥接，不跑任何推理。
|
||||
|
||||
```
|
||||
~/ai-companion/ 助手主体
|
||||
├── client/test_client.py 自写 aiortc 客户端（实验用）
|
||||
├── services/bot_server.py Pipecat SmallWebRTC 服务端（实验，端口 7860）
|
||||
├── app/ 24 个 py 文件
|
||||
│ ├── config.py 配置，支持环境变量覆盖
|
||||
│ ├── prompts.py 单条 system 每轮重建
|
||||
@@ -98,7 +100,11 @@ TTS 的线程扩展方向又和 STT 相反（越多越快）。
|
||||
cd ~/tts-qwen && setsid nohup .venv/bin/python tts_server.py --port 18040 \
|
||||
> logs/tts_service.log 2>&1 < /dev/null &
|
||||
|
||||
# 2. 确认就绪
|
||||
# 2. （可选）Pipecat 传输层服务端 —— 实验状态，帧路由未通
|
||||
cd ~/ai-companion && setsid nohup .venv/bin/python services/bot_server.py \
|
||||
--host 0.0.0.0 --port 7860 > logs/bot_server.log 2>&1 < /dev/null &
|
||||
|
||||
# 3. 确认就绪
|
||||
curl -s http://127.0.0.1:18040/health
|
||||
|
||||
# 3. 跑测试
|
||||
@@ -154,6 +160,19 @@ rsync -az --delete --exclude '__pycache__' --exclude '*.pyc' \
|
||||
（vLLM 0.28 拉上来的）；源码编译要从 GitHub 拉依赖，而这台机器下
|
||||
GitHub release 会断连。
|
||||
|
||||
## 当前卡点：Pipecat 帧路由未通
|
||||
|
||||
2026-09-15 的传输层实验：**传输层跑通（信令/ICE/data channel/双向媒体轨），
|
||||
但帧送不进自定义处理器**——`process_frame` 调用次数为 0，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**。
|
||||
|
||||
这直接影响 A/B 架构方案（A：Pipecat 只做传输；B：按框架 service 模型重构）。
|
||||
根因未定位。完整记录见 Obsidian 笔记库里的 `P0-Pipecat传输层实验报告.md`。
|
||||
|
||||
**注意** `services/bot_server.py` 里目前还带着 `[诊断]` 前缀的日志，
|
||||
是留给下一轮排查用的，定位后应清理。
|
||||
|
||||
## 未做的事
|
||||
|
||||
- **没有常驻服务**：TTS 服务和助手都没有 systemd 开机自启（方案 §10 要求 P2 后做）
|
||||
|
||||
Reference in New Issue
Block a user