"""Local WebSocket server: one session per connection (protocol in voice_worker.spec.md).""" from __future__ import annotations import asyncio import hmac import ipaddress import itertools import json import time from dataclasses import dataclass from typing import Callable import numpy as np from .log import debug_log from .audio import InputConverter, loudness_equalise from .brain import Brain, MemorySettings from .protocol import KIND_AUDIO, ProtocolError, decode_audio_frame, encode_tts_frame from .scheduler import DecodeOptions, SttResult, SttScheduler, Transcriber from .segmenter import SR, Final, Partial, Segmenter, SpeechStart, VadStream from .settings import SttSettings from .tts import TtsEngine, TtsRequest, TtsService CLOSE_BAD_HELLO = 4400 CLOSE_BAD_TOKEN = 4401 MAX_SPEAKERS = 32 def is_loopback(host: str) -> bool: if host == "localhost": return True try: return ipaddress.ip_address(host).is_loopback except ValueError: return False class VoiceWorker: def __init__(self, token: str, transcriber: Transcriber | None, vad_factory: Callable[[], VadStream], tts_engine: TtsEngine | None = None, hello_timeout_s: float = 5.0, tick_s: float = 0.05, history=None, brain: Brain | None = None, chat_timeout_s: float = 15.0): if not token: raise ValueError("a connection token is required") self.token = token self.transcriber = transcriber self.vad_factory = vad_factory self.tts_engine = tts_engine self.hello_timeout_s = hello_timeout_s self.tick_s = tick_s self.history = history # jarvis.memory.history.HistoryStore or None self.brain = brain self.brain_lock = asyncio.Lock() # one reply at a time self.chat_timeout_s = chat_timeout_s # Per person: how many replies they had (a delete is confirmed only in a later one) and the # deletes they were asked to confirm (chat_channels.spec.md). self.reply_turns: dict[str, int] = {} self.pending_deletes: dict[str, dict] = {} self.scheduler: SttScheduler | None = None self.tts: TtsService | None = None self._ids = itertools.count(1) async def start(self) -> None: if self.history is not None: # A killed worker never closed its sessions' presence; nobody is heard until the app # reports who is there again. n = self.history.close_open_presence(time.time()) if n: debug_log(f"closed {n} presence intervals left open by a previous run", "voice_worker") if self.transcriber is not None: self.scheduler = SttScheduler(self.transcriber) self.scheduler.start() if self.tts_engine is not None: self.tts = TtsService(self.tts_engine) self.tts.start() async def stop(self) -> None: if self.scheduler: await self.scheduler.stop() if self.tts: await self.tts.stop() async def serve(self, host: str, port: int): """Start listening; returns the websockets server. Loopback addresses only.""" if not is_loopback(host): raise ValueError("the voice worker only listens on a loopback address") from websockets.asyncio.server import serve await self.start() return await serve(self.handle, host, port, max_size=2 ** 20) async def handle(self, ws) -> None: try: first = await asyncio.wait_for(ws.recv(), self.hello_timeout_s) hello = json.loads(first) if isinstance(first, str) else None except (asyncio.TimeoutError, ValueError): hello = None except Exception: return if not isinstance(hello, dict) or hello.get("type") != "hello": debug_log("connection refused: no hello", "voice_worker") await ws.close(CLOSE_BAD_HELLO, "hello expected") return token = hello.get("token") if not isinstance(token, str) or not hmac.compare_digest(token.encode(), self.token.encode()): debug_log("connection refused: bad token", "voice_worker") await ws.close(CLOSE_BAD_TOKEN, "bad token") return try: session = Session(self, ws, next(self._ids), hello) except ValueError as e: await ws.close(CLOSE_BAD_HELLO, str(e)[:100]) return await session.run() @dataclass class _Speaker: converter: InputConverter segmenter: Segmenter def _format(value, default: dict, rates: tuple[int, ...] | None) -> dict: if value is None: return dict(default) if not isinstance(value, dict): raise ValueError("format must be an object") rate, channels = value.get("rate", default["rate"]), value.get("channels", default["channels"]) ok_rate = isinstance(rate, int) and (rate in rates if rates else 8000 <= rate <= 96000) if not ok_rate or channels not in (1, 2) or isinstance(channels, bool): raise ValueError("unsupported audio format") return {"rate": rate, "channels": channels} class Session: def __init__(self, worker: VoiceWorker, ws, sid: int, hello: dict): self.worker = worker self.ws = ws self.sid = sid self.audio = _format(hello.get("audio"), {"rate": 48000, "channels": 2}, (16000, 48000)) self.tts_format = _format(hello.get("tts"), {"rate": 48000, "channels": 2}, None) self.settings = SttSettings() stt = hello.get("stt") if stt is not None: if not isinstance(stt, dict): raise ValueError("stt must be an object") self.settings.update(stt) self.memory = MemorySettings() memory = hello.get("memory") if memory is not None: if not isinstance(memory, dict): raise ValueError("memory must be an object") self.memory.update(memory) self.voice_channel: str | None = None self.chat_channels: list[dict] = [] self.chat_waiting: dict[str, asyncio.Future] = {} self._chat_ids = itertools.count(1) self.names: dict[str, str] = {} self.speakers: dict[str, _Speaker] = {} self.tts_requests: dict[str, TtsRequest] = {} self.out: asyncio.Queue = asyncio.Queue() self.closed = False # --- outbound ------------------------------------------------------------------------------- def send(self, msg) -> None: if not self.closed: self.out.put_nowait(msg if isinstance(msg, bytes) else json.dumps(msg, ensure_ascii=False)) def error(self, code: str, message: str, **extra) -> None: self.send({"type": "error", "code": code, "message": message, **extra}) async def _writer(self) -> None: while True: await self.ws.send(await self.out.get()) # --- lifecycle ------------------------------------------------------------------------------ async def run(self) -> None: w = self.worker debug_log(f"session {self.sid} connected audio={self.audio} tts={self.tts_format}", "voice_worker") self.send({"type": "hello_ok", "stt_ready": w.scheduler is not None, "tts_ready": w.tts is not None, "audio": self.audio, "tts": self.tts_format, "stt": self.settings.as_dict()}) writer = asyncio.create_task(self._writer()) ticker = asyncio.create_task(self._ticker()) try: async for frame in self.ws: if isinstance(frame, bytes): self._on_binary(frame) else: self._on_text(frame) except Exception as e: # connection dropped debug_log(f"session {self.sid} receive ended: {type(e).__name__}", "voice_worker") finally: self.closed = True self._leave_voice() for fut in self.chat_waiting.values(): if not fut.done(): fut.set_result({"ok": False, "error": "the app disconnected"}) ticker.cancel() writer.cancel() if w.scheduler: w.scheduler.drop_partials(lambda key: key[0] == self.sid) if w.tts: for req in list(self.tts_requests.values()): w.tts.cancel(req) debug_log(f"session {self.sid} closed", "voice_worker") async def _ticker(self) -> None: while True: await asyncio.sleep(self.worker.tick_s) now = time.monotonic() for speaker, st in list(self.speakers.items()): self._handle_events(speaker, st, st.segmenter.tick(now)) # --- STT ------------------------------------------------------------------------------------ def _on_binary(self, frame: bytes) -> None: if not frame or frame[0] != KIND_AUDIO: self.error("bad_frame", "unknown binary frame kind") return try: speaker, pcm = decode_audio_frame(frame) except ProtocolError as e: self.error("bad_frame", str(e)) return st = self.speakers.get(speaker) if st is None: if len(self.speakers) >= MAX_SPEAKERS: self.error("bad_frame", f"more than {MAX_SPEAKERS} speakers") return st = _Speaker(InputConverter(self.audio["rate"], self.audio["channels"]), Segmenter(self.worker.vad_factory(), self.settings)) self.speakers[speaker] = st samples = st.converter.push(pcm) self._handle_events(speaker, st, st.segmenter.push(samples, time.monotonic())) def _opts(self, beam: int) -> DecodeOptions: return DecodeOptions(beam=beam, language=self.settings.language, hotwords=self.settings.hotwords) def _handle_events(self, speaker: str, st: _Speaker, events: list) -> None: sched = self.worker.scheduler for ev in events: if isinstance(ev, SpeechStart): self.send({"type": "speech_start", "speaker": speaker, "utt": ev.utt}) elif isinstance(ev, Partial): if sched and self.settings.partials: sched.submit_partial((self.sid, speaker), loudness_equalise(ev.audio, ev.voiced), self._opts(1), self._partial_cb(speaker, st, ev.utt)) elif isinstance(ev, Final): debug_log(f"utterance end speaker={speaker} utt={ev.utt} reason={ev.reason} " f"ms={len(ev.audio) * 1000 // SR}", "voice_worker") # Where, when and by whom it was said, fixed now: decoding can take a while, and a # move or a late joiner meanwhile must not change who heard it. said = (self.voice_channel, self.names.get(speaker, speaker), time.time() - (time.monotonic() - ev.decided_at)) if sched is None: self._send_final(speaker, ev, SttResult("", 0, "stt unavailable"), said) else: sched.submit_final((self.sid, speaker), loudness_equalise(ev.audio, ev.voiced), self._opts(self.settings.final_beam), lambda res, ev=ev, said=said: self._send_final(speaker, ev, res, said)) def _partial_cb(self, speaker: str, st: _Speaker, utt: int): def cb(res: SttResult) -> None: # Drop it when the utterance already ended or captions were turned off meanwhile. if st.segmenter.open_utt == utt and self.settings.partials and not res.error: self.send({"type": "partial", "speaker": speaker, "utt": utt, "text": res.text}) return cb def _send_final(self, speaker: str, ev: Final, res: SttResult, said: tuple) -> None: channel, name, ts = said store = self.worker.history if store is not None and channel and res.text.strip(): store.add_voice(channel, speaker, name, res.text, ts) self.send({"type": "final", "speaker": speaker, "utt": ev.utt, "text": res.text, "end_reason": ev.reason, "audio_ms": len(ev.audio) * 1000 // SR, "wait_ms": int((time.monotonic() - ev.decided_at) * 1000), "stt_ms": res.stt_ms}) # --- text messages -------------------------------------------------------------------------- def _on_text(self, raw: str) -> None: try: msg = json.loads(raw) except ValueError: self.error("bad_message", "not JSON") return if not isinstance(msg, dict): self.error("bad_message", "not an object") return kind = msg.get("type") handler = {"speaking_end": self._on_speaking_end, "speaker_leave": self._on_speaker_leave, "config": self._on_config, "tts": self._on_tts, "tts_cancel": self._on_tts_cancel, "voice_join": self._on_voice_join, "voice_leave": lambda m: self._leave_voice(), "member_join": self._on_member_join, "member_leave": self._on_member_leave, "chat_message": self._on_chat_message, "chat_edit": self._on_chat_edit, "chat_delete": self._on_chat_delete, "reply": self._on_reply, "chat_channels": self._on_chat_channels, "chat_action_result": self._on_chat_action_result, "memory_config": self._on_memory_config}.get(kind) if handler is None: self.error("bad_message", f"unknown type: {kind!r}") return handler(msg) def _on_speaking_end(self, msg: dict) -> None: st = self.speakers.get(msg.get("speaker")) if st is not None: self._handle_events(msg["speaker"], st, st.segmenter.speaking_end(time.monotonic())) def _on_speaker_leave(self, msg: dict) -> None: # The speaker left the voice channel: finish any open utterance, then free their place. speaker = msg.get("speaker") st = self.speakers.pop(speaker, None) if isinstance(speaker, str) else None if st is not None: self._handle_events(speaker, st, st.segmenter.speaking_end(time.monotonic())) if self.worker.scheduler: self.worker.scheduler.drop_partials(lambda key: key == (self.sid, speaker)) debug_log(f"speaker {speaker} left session {self.sid}", "voice_worker") def _on_config(self, msg: dict) -> None: changes = {k: v for k, v in msg.items() if k != "type"} try: self.settings.update(changes) except ValueError as e: self.error("bad_message", str(e)) return if not self.settings.partials and self.worker.scheduler: self.worker.scheduler.drop_partials(lambda key: key[0] == self.sid) debug_log(f"session {self.sid} settings changed: {sorted(changes)}", "voice_worker") def _on_tts(self, msg: dict) -> None: rid, text, more = msg.get("id"), msg.get("text", ""), msg.get("more", False) if not isinstance(rid, str) or not 0 < len(rid.encode()) < 256 or not isinstance(text, str) \ or not isinstance(more, bool): self.error("bad_message", "tts needs a string id and text, and a boolean more") return tts = self.worker.tts if tts is None: self.error("tts_unavailable", "no TTS engine is loaded", id=rid) return req = self.tts_requests.get(rid) if req is None: req = TtsRequest(rid, self.tts_format["rate"], self._tts_chunk_cb(rid), self._tts_done, self._tts_error) self.tts_requests[rid] = req elif req.closed: self.error("bad_message", "this tts id is already closed", id=rid) return tts.feed(req, text, more) def _on_tts_cancel(self, msg: dict) -> None: req = self.tts_requests.get(msg.get("id")) if req is not None and self.worker.tts: self.worker.tts.cancel(req) # --- history and brain ---------------------------------------------------------------------- def _strings(self, msg: dict, *keys: str) -> tuple | None: values = tuple(msg.get(k) for k in keys) if not all(isinstance(v, str) and v for v in values): self.error("bad_message", f"{msg.get('type')} needs non-empty strings: {', '.join(keys)}", **({"id": msg["id"]} if isinstance(msg.get("id"), str) else {})) return None return values def _leave_voice(self) -> None: if self.voice_channel and self.worker.history is not None: self.worker.history.presence_close_channel(self.voice_channel, time.time()) if self.voice_channel: debug_log(f"session {self.sid} left voice channel {self.voice_channel}", "voice_worker") self.voice_channel = None def _on_voice_join(self, msg: dict) -> None: got = self._strings(msg, "channel") if got is None: return self._leave_voice() self.voice_channel = got[0] debug_log(f"session {self.sid} in voice channel {self.voice_channel}", "voice_worker") def _on_member_join(self, msg: dict) -> None: got = self._strings(msg, "user", "name") if got is None: return user, name = got self.names[user] = name if self.voice_channel and self.worker.history is not None: self.worker.history.presence_join(user, self.voice_channel, time.time()) def _on_member_leave(self, msg: dict) -> None: got = self._strings(msg, "user") if got is not None and self.voice_channel and self.worker.history is not None: self.worker.history.presence_leave(got[0], self.voice_channel, time.time()) def _on_chat_message(self, msg: dict) -> None: got = self._strings(msg, "channel", "message_id", "author", "name") ts, to, text = msg.get("ts"), msg.get("to"), msg.get("text") if got is None: return if not isinstance(text, str) or isinstance(ts, bool) or not isinstance(ts, (int, float)) \ or (to is not None and not isinstance(to, str)): self.error("bad_message", "chat_message needs text, a numeric ts and an optional string to") return if self.worker.history is not None: channel, message_id, author, name = got self.worker.history.add_chat(channel, message_id, author, name, text, float(ts), to_id=to) def _on_chat_edit(self, msg: dict) -> None: got = self._strings(msg, "channel", "message_id") if got is None: return if not isinstance(msg.get("text"), str): self.error("bad_message", "chat_edit needs text") return if self.worker.history is not None: self.worker.history.edit_chat(got[0], got[1], msg["text"]) def _on_chat_delete(self, msg: dict) -> None: got = self._strings(msg, "channel", "message_id") if got is not None and self.worker.history is not None: self.worker.history.delete_chat(*got) _CHAT_FLAGS = ("read", "send", "edit", "react", "delete", "pin") def _on_chat_channels(self, msg: dict) -> None: channels = msg.get("channels") ok = isinstance(channels, list) and all( isinstance(c, dict) and all(isinstance(c.get(k), str) for k in ("id", "name", "description")) and c["id"] and all(isinstance(c.get(f), bool) for f in self._CHAT_FLAGS) for c in channels) if not ok: self.error("bad_message", "chat_channels needs channels with id, name, description and " "boolean read, send, edit, react, delete, pin") return self.chat_channels = [{k: c[k] for k in ("id", "name", "description", *self._CHAT_FLAGS)} for c in channels] debug_log(f"session {self.sid} chat channels: {len(self.chat_channels)}", "voice_worker") async def chat_action(self, action: str, channel: str, args: dict) -> dict: """Ask the app to do a chat action and wait for its answer (or a timeout).""" aid = f"a{next(self._chat_ids)}" fut = asyncio.get_running_loop().create_future() self.chat_waiting[aid] = fut self.send({"type": "chat_action", "id": aid, "action": action, "channel": channel, **{k: v for k, v in args.items() if v is not None}}) debug_log(f"chat action {aid} {action} channel={channel}", "voice_worker") try: return await asyncio.wait_for(fut, self.worker.chat_timeout_s) except asyncio.TimeoutError: return {"ok": False, "error": "the app did not answer in time"} finally: self.chat_waiting.pop(aid, None) def _on_chat_action_result(self, msg: dict) -> None: fut = self.chat_waiting.get(msg.get("id")) if fut is None or fut.done(): return ids = msg.get("message_ids") or [] result = {"ok": msg.get("ok") is True} if result["ok"]: result["message_ids"] = [str(i) for i in ids if isinstance(i, (str, int))] else: result["error"] = str(msg.get("error") or "the app could not do it") fut.set_result(result) def _on_memory_config(self, msg: dict) -> None: changes = {k: v for k, v in msg.items() if k != "type"} try: self.memory.update(changes) except ValueError as e: self.error("bad_message", str(e)) return debug_log(f"session {self.sid} memory settings changed: {sorted(changes)}", "voice_worker") def _on_reply(self, msg: dict) -> None: got = self._strings(msg, "id", "user", "text") if got is None: return rid, user, text = got via, speak = msg.get("via"), msg.get("speak", False) if via not in ("voice", "chat") or not isinstance(speak, bool) or len(rid.encode()) > 255: self.error("bad_message", "reply needs via voice|chat, a boolean speak and an id under 256 bytes", id=rid) return if self.worker.brain is None: self.error("brain_unavailable", "the worker was started without --brain", id=rid) return asyncio.get_running_loop().create_task(self._reply(rid, user, text, via, speak)) async def _reply(self, rid: str, user: str, text: str, via: str, speak: bool) -> None: w = self.worker channel = self.voice_channel async with w.brain_lock: if self.closed: return now = time.time() if w.history is not None: m = self.memory history = await asyncio.to_thread( w.history.context, user, text, now, m.scope(now), minutes=m.recent_minutes, max_records=m.recent_records, limit=m.matches, budget_tokens=m.budget_tokens) else: from jarvis.memory.history import HistoryContext history = HistoryContext() turn = w.reply_turns[user] = w.reply_turns.get(user, 0) + 1 from .chat_bridge import ChatBridge chat = ChatBridge(self, asyncio.get_running_loop(), turn, w.pending_deletes.setdefault(user, {})) \ if self.chat_channels else None try: answer = await asyncio.to_thread(w.brain.reply, user, text, history, chat=chat) except Exception as e: # the brain must never take the session down debug_log(f"brain reply {rid} failed: {type(e).__name__}", "voice_worker") answer = None answer = (answer or "").strip() self.send({"type": "reply_text", "id": rid, "text": answer, "failed": not answer}) if not answer: return if via == "voice" and channel and w.history is not None: w.history.add_reply(channel, user, answer, time.time()) if speak: self._on_tts({"type": "tts", "id": rid, "text": answer, "more": False}) def _tts_chunk_cb(self, rid: str): def cb(seq: int, pcm: np.ndarray) -> None: pcm = np.asarray(pcm, dtype=" None: self.tts_requests.pop(req.id, None) self.send({"type": "tts_done", "id": req.id, "chunks": req.chunks, "cancelled": req.cancelled, "failed": req.failed}) def _tts_error(self, req: TtsRequest, message: str) -> None: self.error("tts_failed", message, id=req.id)