meshagent-livekit 0.8.3__py3-none-any.whl

meshagent/livekit/__init__.py

@@ -0,0 +1,3 @@
+from .version import __version__
+
+__all__ = [__version__]

meshagent/livekit/agents/meeting_transcriber.py

@@ -0,0 +1,310 @@
+import asyncio
+import logging
+
+from typing import Optional
+
+from datetime import datetime, timezone
+from livekit import rtc
+from livekit.agents import (
+    Agent,
+    AgentSession,
+    RoomInputOptions,
+    RoomIO,
+    RoomOutputOptions,
+    StopResponse,
+    llm,
+    utils,
+)
+from livekit.agents.stt import STT
+
+from meshagent.openai.proxy import get_client
+from livekit.plugins import openai, silero
+from meshagent.api import MeshDocument, SchemaRegistration, SchemaRegistry
+from meshagent.agents import SingleRoomAgent
+from meshagent.tools import RemoteToolkit, ToolContext, Tool
+from meshagent.api.room_server_client import Requirement
+from meshagent.livekit.agents.voice import VoiceConnection
+from meshagent.agents.schemas.transcript import transcript_schema
+
+logger = logging.getLogger("meeting_transcriber")
+
+
+class StartTranscriptionTool(Tool):
+    def __init__(self, *, transcriber: "MeetingTranscriber"):
+        self.transcriber = transcriber
+        super().__init__(
+            name="start_transcription",
+            input_schema={
+                "type": "object",
+                "required": [
+                    "breakout_room",
+                    "path",
+                ],
+                "additionalProperties": False,
+                "properties": {
+                    "breakout_room": {
+                        "type": "string",
+                    },
+                    "path": {
+                        "type": "string",
+                    },
+                },
+            },
+        )
+
+    async def execute(self, context: ToolContext, *, breakout_room: str, path: str):
+        await self.transcriber.start_transcription(
+            breakout_room=breakout_room, path=path
+        )
+        return {"status": "started"}
+
+
+class StopTranscriptionTool(Tool):
+    def __init__(self, *, transcriber: "MeetingTranscriber"):
+        self.transcriber = transcriber
+        super().__init__(
+            name="stop_transcription",
+            input_schema={
+                "type": "object",
+                "required": [
+                    "breakout_room",
+                ],
+                "additionalProperties": False,
+                "properties": {
+                    "breakout_room": {
+                        "type": "string",
+                    },
+                },
+            },
+        )
+
+    async def execute(self, context: ToolContext, *, breakout_room: str):
+        await self.transcriber.stop_transcription(
+            breakout_room=breakout_room,
+        )
+        return {"status": "stopped"}
+
+
+class MeetingTranscriber(SingleRoomAgent):
+    def __init__(
+        self,
+        name: str,
+        requires: Optional[list[Requirement]] = None,
+        stt: Optional[STT] = None,
+    ):
+        super().__init__(
+            name=name,
+            requires=requires,
+        )
+        self._toolkit = RemoteToolkit(
+            name="transcription",
+            tools=[
+                StartTranscriptionTool(transcriber=self),
+                StopTranscriptionTool(transcriber=self),
+            ],
+        )
+        self.stt = stt
+        self._vad = None
+        self._transcription_tasks = dict[str, tuple[asyncio.Task, asyncio.Future]]()
+
+    async def start(self, *, room):
+        await super().start(room=room)
+        await self._toolkit.start(room=room)
+        await room.local_participant.set_attribute("supports_voice", True)
+        await room.messaging.enable()
+
+        self._vad = silero.VAD.load()
+
+    async def start_transcription(self, *, breakout_room: Optional[str], path: str):
+        stop_fut = asyncio.Future()
+
+        async def transcribe():
+            await self.room.local_participant.set_attribute(
+                f"transcribing.{breakout_room}", True
+            )
+
+            try:
+                async with VoiceConnection(
+                    room=self.room, breakout_room=breakout_room
+                ) as conn:
+                    doc = await self.room.sync.open(path=path, create=True)
+
+                    stt = self.stt
+                    if stt is None:
+                        openai_client = get_client(room=self.room)
+                        stt = openai.STT(client=openai_client)
+
+                    transcriber = MultiUserTranscriber(conn, doc, self._vad, stt)
+                    transcriber.start()
+
+                    for participant in conn.livekit_room.remote_participants.values():
+                        # handle all existing participants
+                        transcriber.on_participant_connected(participant)
+
+                    await stop_fut
+
+                    await self.room.local_participant.set_attribute(
+                        f"transcribing.{breakout_room}", False
+                    )
+
+                    await self.room.sync.close(path=path)
+
+                    await transcriber.aclose()
+            except Exception as ex:
+                logger.error(f"error during transcription {ex}", exc_info=ex)
+                pass
+
+            await self.room.local_participant.set_attribute(
+                f"transcribing.{breakout_room}", False
+            )
+
+        if breakout_room not in self._transcription_tasks:
+            self._transcription_tasks[breakout_room] = (
+                asyncio.create_task(transcribe()),
+                stop_fut,
+            )
+
+    async def stop_transcription(self, *, breakout_room: Optional[str]):
+        if breakout_room in self._transcription_tasks:
+            task, fut = self._transcription_tasks.pop(breakout_room)
+            fut.set_result(True)
+            await asyncio.gather(task)
+
+    async def stop(self):
+        await self._toolkit.stop()
+
+        tasks = []
+        for breakout_room, _ in self._transcription_tasks.items():
+            task, fut = self._transcription_tasks.pop(breakout_room)
+            fut.set_result(True)
+            tasks.append(task)
+
+        await asyncio.gather(*tasks)
+        await super().stop()
+
+
+class TranscriptRegistry(SchemaRegistry):
+    def __init__(self):
+        name = "transcript"
+        super().__init__(
+            name=f"meshagent.schema.{name}",
+            validate_webhook_secret=False,
+            schemas=[SchemaRegistration(name=name, schema=transcript_schema)],
+        )
+
+
+class Transcriber(Agent):
+    def __init__(self, *, participant, doc: MeshDocument, stt):
+        super().__init__(
+            instructions="not-needed",
+            stt=stt,
+        )
+        self.doc = doc
+        self.participant = participant
+
+    async def on_user_turn_completed(
+        self, chat_ctx: llm.ChatContext, new_message: llm.ChatMessage
+    ):
+        segments = self.doc.root
+        segments.append_child(
+            "segment",
+            {
+                "text": new_message.text_content,
+                "participant_name": self.participant.name,
+                "participant_id": self.participant.sid,
+                "time": datetime.now(timezone.utc).isoformat().replace("+00:00", "Z"),
+            },
+        )
+        raise StopResponse()
+
+
+class MultiUserTranscriber:
+    def __init__(self, ctx: VoiceConnection, doc: MeshDocument, vad, stt):
+        self.ctx = ctx
+        self.doc = doc
+        self.vad = vad
+        self.stt = stt
+        self._sessions: dict[str, AgentSession] = {}
+        self._tasks: set[asyncio.Task] = set()
+
+    def start(self):
+        self.ctx.livekit_room.on("participant_connected", self.on_participant_connected)
+        self.ctx.livekit_room.on(
+            "participant_disconnected", self.on_participant_disconnected
+        )
+
+    async def aclose(self):
+        await utils.aio.cancel_and_wait(*self._tasks)
+
+        await asyncio.gather(
+            *[self._close_session(session) for session in self._sessions.values()]
+        )
+
+        self.ctx.livekit_room.off(
+            "participant_connected", self.on_participant_connected
+        )
+        self.ctx.livekit_room.off(
+            "participant_disconnected", self.on_participant_disconnected
+        )
+
+    def on_participant_connected(self, participant: rtc.RemoteParticipant):
+        if participant.identity in self._sessions:
+            return
+
+        logger.info(f"starting session for {participant.identity}")
+        task = asyncio.create_task(self._start_session(participant))
+        self._tasks.add(task)
+
+        def on_task_done(task: asyncio.Task):
+            try:
+                self._sessions[participant.identity] = task.result()
+            finally:
+                self._tasks.discard(task)
+
+        task.add_done_callback(on_task_done)
+
+    def on_participant_disconnected(self, participant: rtc.RemoteParticipant):
+        if (session := self._sessions.pop(participant.identity)) is None:
+            return
+
+        logger.info(f"closing session for {participant.identity}")
+        task = asyncio.create_task(self._close_session(session))
+        self._tasks.add(task)
+        task.add_done_callback(lambda _: self._tasks.discard(task))
+
+    async def _start_session(self, participant: rtc.RemoteParticipant) -> AgentSession:
+        if participant.identity in self._sessions:
+            return self._sessions[participant.identity]
+
+        session = AgentSession(
+            vad=self.vad,
+        )
+        room_io = RoomIO(
+            agent_session=session,
+            room=self.ctx.livekit_room,
+            participant=participant,
+            input_options=RoomInputOptions(
+                # text input is not supported for multiple room participants
+                # if needed, register the text stream handler by yourself
+                # and route the text to different sessions based on the participant identity
+                text_enabled=False,
+                delete_room_on_close=False,
+            ),
+            output_options=RoomOutputOptions(
+                transcription_enabled=True,
+                audio_enabled=False,
+            ),
+        )
+        await room_io.start()
+        await session.start(
+            agent=Transcriber(
+                participant=participant,
+                doc=self.doc,
+                stt=self.stt,
+            )
+        )
+        return session
+
+    async def _close_session(self, sess: AgentSession) -> None:
+        await sess.drain()
+        await sess.aclose()

meshagent/livekit/agents/transcriber.py

@@ -0,0 +1,187 @@
+import logging
+import asyncio
+from asyncio import CancelledError
+
+from meshagent.api import RoomMessage, Requirement, Participant, RemoteParticipant
+from meshagent.api.room_server_client import RoomClient
+
+from livekit.agents import Agent, AgentSession
+
+from openai import AsyncOpenAI
+
+from livekit.agents.stt import STT
+from livekit.agents import RoomOutputOptions, StopResponse
+from livekit.agents import llm
+
+from livekit.plugins import openai, silero
+
+from .voice import VoiceConnection
+from livekit import rtc
+
+from typing import Optional
+
+
+from meshagent.agents import SingleRoomAgent
+
+
+import re
+
+logger = logging.getLogger("voice")
+
+
+def _replace_non_matching(text: str, allowed_chars: str, replacement: str) -> str:
+    """
+    Replaces every character in `text` that does not match the given
+    `allowed_chars` regex set with `replacement`.
+
+    Parameters:
+    -----------
+    text : str
+        The input string on which the replacement is to be done.
+    allowed_chars : str
+        A string defining the set of allowed characters (part of a character set).
+        For example, "a-zA-Z0-9" will keep only letters and digits.
+    replacement : str
+        The string to replace non-matching characters with.
+
+    Returns:
+    --------
+    str
+        A new string where all characters not in `allowed_chars` are replaced.
+    """
+    # Build a regex that matches any character NOT in allowed_chars
+    pattern = rf"[^{allowed_chars}]"
+    return re.sub(pattern, replacement, text)
+
+
+def safe_tool_name(name: str):
+    return _replace_non_matching(name, "a-zA-Z0-9_-", "_")
+
+
+class _Transcriber(Agent):
+    def __init__(self, *, stt: STT, room: RoomClient, participant: RemoteParticipant):
+        super().__init__(instructions="not-needed", stt=stt)
+        self.room = room
+        self.participant = participant
+
+    async def on_user_turn_completed(
+        self, chat_ctx: llm.ChatContext, new_message: llm.ChatMessage
+    ):
+        logger.info(f"transcription: {new_message.text_content}")
+        self.room.messaging.send_message_nowait(
+            to=self.participant,
+            type="transcript",
+            message={"text": new_message.text_content},
+        )
+
+        raise StopResponse()
+
+
+class Transcriber(SingleRoomAgent):
+    def __init__(
+        self,
+        name: str,
+        title: Optional[str] = None,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
+        requires: list[Requirement] = None,
+    ):
+        super().__init__(
+            name=name,
+            description=description,
+            title=title,
+            labels=labels,
+            requires=requires,
+        )
+
+    async def start(self, *, room):
+        await super().start(room=room)
+        await room.local_participant.set_attribute("supports_voice", True)
+        await room.messaging.enable()
+        room.messaging.on("message", self.on_message)
+
+    def on_message(self, message: RoomMessage):
+        if message.type == "voice_call":
+            breakout_room = message.message["breakout_room"]
+
+            logger.info(f"joining breakout room {breakout_room}")
+
+            def on_done(task: asyncio.Task):
+                try:
+                    task.result()
+                except CancelledError:
+                    pass
+                except Exception as e:
+                    logger.error(f"{e}", exc_info=e)
+
+            for participant in self.room.messaging.remote_participants:
+                if participant.id == message.from_participant_id:
+                    task = asyncio.create_task(
+                        self.run_voice_agent(
+                            participant=participant, breakout_room=breakout_room
+                        )
+                    )
+                    task.add_done_callback(on_done)
+                    return
+
+            logger.error(f"unable to find participant {message.from_participant_id}")
+
+    async def _wait_for_disconnect(self, room: rtc.Room):
+        disconnected = asyncio.Future()
+
+        def on_disconnected(_):
+            disconnected.set_result(True)
+
+        room.on("disconnected", on_disconnected)
+
+        logger.info("waiting for disconnection")
+        await disconnected
+
+    async def create_agent(
+        self, *, session: AgentSession, participant: RemoteParticipant
+    ):
+        return _Transcriber(
+            stt=openai.STT(),
+            room=self.room,
+            participant=participant,
+        )
+
+    def create_session(self) -> AgentSession:
+        token: str = self.room.protocol.token
+        url: str = self.room.room_url
+
+        room_proxy_url = f"{url}/v1"
+
+        oaiclient = AsyncOpenAI(
+            api_key=token,
+            base_url=room_proxy_url,
+            default_headers={"Meshagent-Session": self.room.session_id},
+        )
+
+        session = AgentSession(
+            max_tool_steps=50,
+            allow_interruptions=False,
+            vad=silero.VAD.load(),
+            stt=openai.STT(client=oaiclient),
+            # turn_detection=MultilingualModel(),
+        )
+        return session
+
+    async def run_voice_agent(self, *, participant: Participant, breakout_room: str):
+        async with VoiceConnection(
+            room=self.room, breakout_room=breakout_room
+        ) as connection:
+            logger.info("starting transcription agent")
+
+            session = self.create_session()
+
+            agent = await self.create_agent(session=session, participant=participant)
+
+            await session.start(
+                agent=agent,
+                room=connection.livekit_room,
+                room_output_options=RoomOutputOptions(transcription_enabled=True),
+            )
+
+            logger.info("started transcription agent")
+            await self._wait_for_disconnect(room=connection.livekit_room)

meshagent/livekit/agents/voice.py

@@ -0,0 +1,394 @@
+import logging
+import asyncio
+from asyncio import CancelledError
+
+from meshagent.api import (
+    RoomMessage,
+    ErrorResponse,
+    Requirement,
+    Participant,
+    JsonResponse,
+    EmptyResponse,
+    TextResponse,
+)
+from meshagent.api.room_server_client import RoomClient
+
+from meshagent.agents import ToolResponseAdapter
+from meshagent.tools import ToolContext, Toolkit
+from livekit.agents import Agent, AgentSession, ChatContext
+from livekit.agents.llm import RawFunctionTool, ToolError, function_tool
+
+from meshagent.openai.proxy import get_client
+from meshagent.agents import AgentChatContext
+from livekit.agents import (
+    BackgroundAudioPlayer,
+    AudioConfig,
+    BuiltinAudioClip,
+    RoomInputOptions,
+    RoomOutputOptions,
+)
+
+from livekit.plugins import openai, silero
+# from livekit.plugins.turn_detector.multilingual import MultilingualModel
+
+
+import json
+
+from typing import Any
+
+
+from livekit import rtc
+
+from typing import Optional
+
+
+from meshagent.agents import SingleRoomAgent
+
+
+import re
+
+logger = logging.getLogger("voice")
+
+
+def _replace_non_matching(text: str, allowed_chars: str, replacement: str) -> str:
+    """
+    Replaces every character in `text` that does not match the given
+    `allowed_chars` regex set with `replacement`.
+
+    Parameters:
+    -----------
+    text : str
+        The input string on which the replacement is to be done.
+    allowed_chars : str
+        A string defining the set of allowed characters (part of a character set).
+        For example, "a-zA-Z0-9" will keep only letters and digits.
+    replacement : str
+        The string to replace non-matching characters with.
+
+    Returns:
+    --------
+    str
+        A new string where all characters not in `allowed_chars` are replaced.
+    """
+    # Build a regex that matches any character NOT in allowed_chars
+    pattern = rf"[^{allowed_chars}]"
+    return re.sub(pattern, replacement, text)
+
+
+def safe_tool_name(name: str):
+    return _replace_non_matching(name, "a-zA-Z0-9_-", "_")
+
+
+class VoiceConnection:
+    def __init__(self, *, room: RoomClient, breakout_room: str):
+        self.room = room
+        self.breakout_room = breakout_room
+
+    async def __aenter__(self):
+        client = self.room
+
+        room_options = rtc.RoomOptions(auto_subscribe=True)
+
+        room = rtc.Room()
+
+        self.livekit_room = room
+
+        connection_info = await client.livekit.get_connection_info(
+            breakout_room=self.breakout_room
+        )
+
+        await room.connect(
+            url=connection_info.url, token=connection_info.token, options=room_options
+        )
+
+        return self
+
+    async def __aexit__(self, exc_type, exc, tb):
+        await self.livekit_room.disconnect()
+
+
+class VoiceBot(SingleRoomAgent):
+    def __init__(
+        self,
+        name: str,
+        title: Optional[str] = None,
+        description: Optional[str] = None,
+        labels: Optional[list[str]] = None,
+        rules: Optional[list[str]] = None,
+        auto_greet_message: Optional[str] = None,
+        auto_greet_prompt: Optional[str] = None,
+        tool_adapter: ToolResponseAdapter = None,
+        toolkits: list[Toolkit] = None,
+        requires: list[Requirement] = None,
+        client_rules: Optional[dict[str, list[str]]] = None,
+    ):
+        if toolkits is None:
+            toolkits = []
+
+        self.toolkits = toolkits
+
+        if rules is None:
+            rules = ["You are a helpful assistant communicating through voice."]
+
+        self.tool_adapter = tool_adapter
+        self.auto_greet_message = auto_greet_message
+        self.auto_greet_prompt = auto_greet_prompt
+
+        self.rules = rules
+
+        self.client_rules = client_rules
+
+        super().__init__(
+            name=name,
+            description=description,
+            title=title,
+            labels=labels,
+            requires=requires,
+        )
+
+    async def start(self, *, room):
+        await super().start(room=room)
+        await room.local_participant.set_attribute("supports_voice", True)
+        await room.messaging.enable()
+        room.messaging.on("message", self.on_message)
+
+    def on_message(self, message: RoomMessage):
+        if message.type == "voice_call":
+            breakout_room = message.message["breakout_room"]
+
+            logger.info(f"joining breakout room {breakout_room}")
+
+            def on_done(task: asyncio.Task):
+                try:
+                    task.result()
+                except CancelledError:
+                    pass
+                except Exception as e:
+                    logger.error(f"{e}", exc_info=e)
+
+            for participant in self.room.messaging.remote_participants:
+                if participant.id == message.from_participant_id:
+                    task = asyncio.create_task(
+                        self.run_voice_agent(
+                            participant=participant, breakout_room=breakout_room
+                        )
+                    )
+                    task.add_done_callback(on_done)
+                    return
+
+            logger.error(f"unable to find participant {message.from_participant_id}")
+
+    async def _wait_for_disconnect(self, room: rtc.Room):
+        disconnected = asyncio.Future()
+
+        def on_disconnected(_):
+            disconnected.set_result(True)
+
+        room.on("disconnected", on_disconnected)
+
+        logger.info("waiting for disconnection")
+        await disconnected
+
+    async def make_function_tools(self, *, context: ToolContext):
+        toolkits = [*await self.get_required_toolkits(context=context), *self.toolkits]
+
+        tools = []
+
+        for toolkit in toolkits:
+            for tool in toolkit.tools:
+                tools.append(
+                    self._make_function_tool(
+                        toolkits,
+                        context,
+                        tool.name,
+                        tool.description,
+                        tool.input_schema,
+                    )
+                )
+
+        return tools
+
+    def _make_function_tool(
+        self,
+        toolkits: list[Toolkit],
+        context: ToolContext,
+        name: str,
+        description: str | None,
+        input_schema: dict,
+    ) -> RawFunctionTool:
+        name = safe_tool_name(name)
+
+        async def _tool_called(raw_arguments: dict) -> Any:
+            try:
+                tool = None
+                for toolkit in toolkits:
+                    for t in toolkit.tools:
+                        if safe_tool_name(t.name) == name:
+                            tool = t
+
+                if tool is None:
+                    raise ToolError(f"Could not find tool {name}")
+
+                try:
+                    logger.info(f"executing tool {name}: {raw_arguments}")
+                    tool_result = await tool.execute(context=context, **raw_arguments)
+                except Exception as e:
+                    logger.error(f"failed to call tool {tool.name}: {e}")
+                    return ToolError("f{e}")
+                if self.tool_adapter is None:
+                    if isinstance(tool_result, ErrorResponse):
+                        raise ToolError(tool_result.text)
+
+                    if isinstance(tool_result, JsonResponse):
+                        return json.dumps(tool_result.json)
+
+                    if isinstance(tool_result, TextResponse):
+                        return tool_result.text
+
+                    if isinstance(tool_result, EmptyResponse):
+                        return "success"
+
+                    if tool_result is None:
+                        return "success"
+
+                    raise ToolError(
+                        f"Tool '{name}' returned an unexpected result {type(tool_result)}, attach a tool response adapter"
+                    )
+
+                else:
+                    text = await self.tool_adapter.to_plain_text(
+                        room=context.room, response=tool_result
+                    )
+                    if text is None:
+                        text = "success"
+                    return text
+
+            except Exception as e:
+                logger.error("unable to call tool", exc_info=e)
+                raise
+
+        return function_tool(
+            _tool_called,
+            raw_schema={
+                "name": name,
+                "description": description,
+                "strict": True,
+                "parameters": input_schema,
+            },
+        )
+
+    async def create_agent(self, *, context: ToolContext, session: AgentSession):
+        ctx = ChatContext()
+
+        initial_context = await self.init_chat_context()
+
+        rules = await self.get_rules(participant=context.caller)
+
+        initial_context.replace_rules(rules)
+
+        for message in initial_context.messages:
+            ctx.add_message(role=message["role"], content=message["content"])
+
+        return Agent(
+            chat_ctx=ctx,
+            instructions="\n".join(self.rules),
+            allow_interruptions=True,
+            tools=[*await self.make_function_tools(context=context)],
+        )
+
+        # agent = Agent(
+        #    instructions="""
+        #        You are a helpful assistant communicating through voice.
+        #    """,
+        #    stt=openai.STT(),
+        #    llm=openai.LLM(model="gpt-4o"),
+        #    tts=openai.TTS(),
+        #    vad=silero.VAD.load(),
+        #   allow_interruptions=True
+        # )
+
+    async def get_rules(self, *, participant: Participant):
+        rules = [*self._rules]
+        client = participant.get_attribute("client")
+
+        if self.client_rules is not None and client is not None:
+            cr = self.client_rules.get(client)
+            if cr is not None:
+                rules.extend(cr)
+
+        return rules
+
+    async def init_chat_context(self) -> AgentChatContext:
+        return AgentChatContext()
+
+    def create_session(self, *, context: ToolContext) -> AgentSession:
+        oaiclient = get_client(room=self.room)
+
+        session = AgentSession(
+            max_tool_steps=50,
+            allow_interruptions=True,
+            vad=silero.VAD.load(),
+            stt=openai.STT(client=oaiclient),
+            tts=openai.TTS(client=oaiclient),
+            llm=openai.LLM(client=oaiclient),
+            # turn_detection=MultilingualModel(),
+        )
+        return session
+
+    async def run_voice_agent(self, *, participant: Participant, breakout_room: str):
+        async with VoiceConnection(
+            room=self.room, breakout_room=breakout_room
+        ) as connection:
+            logger.info("starting voice agent")
+
+            context = ToolContext(
+                room=self.room,
+                caller=self.room.local_participant,
+                on_behalf_of=participant,
+            )
+
+            session = self.create_session(context=context)
+
+            agent = await self.create_agent(context=context, session=session)
+
+            background_audio = BackgroundAudioPlayer(
+                thinking_sound=[
+                    # AudioConfig(
+                    #    os.path.dirname(os.path.abspath(__file__)) +"/sfx/thinking.mp3", volume=0.2),
+                    AudioConfig(BuiltinAudioClip.KEYBOARD_TYPING, volume=0.3),
+                    AudioConfig(BuiltinAudioClip.KEYBOARD_TYPING2, volume=0.4),
+                ],
+            )
+            await background_audio.start(
+                room=connection.livekit_room, agent_session=session
+            )
+
+            await session.start(
+                agent=agent,
+                room=connection.livekit_room,
+                room_input_options=RoomInputOptions(
+                    text_enabled=False,
+                    delete_room_on_close=False,
+                ),
+                room_output_options=RoomOutputOptions(
+                    transcription_enabled=True,
+                    audio_enabled=True,
+                ),
+            )
+
+            if self.auto_greet_prompt is not None:
+                session.generate_reply(user_input=self.auto_greet_prompt)
+
+            if self.auto_greet_message is not None:
+                session.say(self.auto_greet_message)
+
+            logger.info("started voice agent")
+            await self._wait_for_disconnect(room=connection.livekit_room)
+
+
+class Voicebot(VoiceBot):
+    def __init__(self, **kwargs):
+        logger.warning(
+            "Voicebot is deprecated, use VoiceBot instead. This class will be removed in a future release."
+        )
+        super().__init__(**kwargs)

meshagent/livekit/livekit_protocol.py

@@ -0,0 +1,50 @@
+from meshagent.api.protocol import Protocol
+
+from livekit import rtc
+import logging
+
+logger = logging.getLogger("protocol.livekit")
+
+
+class LivekitProtocol(Protocol):
+    def __init__(self, room: rtc.Room, remote: rtc.RemoteParticipant, topic: str):
+        super().__init__()
+        self.room = room
+        self.local = room.local_participant
+        self.remote = remote
+        self.topic = topic
+
+    async def __aenter__(self):
+        self.room.on("data_received", self._on_data_packet)
+        return await super().__aenter__()
+
+    async def __aexit__(self, exc_type, exc, tb):
+        self.room.off("data_received", self._on_data_packet)
+
+        return await super().__aexit__(exc_type, exc, tb)
+
+    async def send_packet(self, data: bytes) -> None:
+        logger.info(
+            "sending data packet %s  %s to %s",
+            self.topic,
+            self.remote.identity,
+            self.room.remote_participants[self.remote.identity].sid,
+        )
+
+        await self.local.publish_data(
+            payload=data,
+            topic=self.topic,
+            reliable=True,
+            destination_identities=[self.remote.identity],
+        )
+
+    def _on_data_packet(self, evt: rtc.DataPacket):
+        if self.remote != evt.participant:
+            return
+
+        logger.info(
+            "received data packet %s from %s", evt.topic, evt.participant.identity
+        )
+
+        if evt.topic == self.topic:
+            self.receive_packet(evt.data)

meshagent/livekit/livekit_protocol_test.py

@@ -0,0 +1,116 @@
+import sys
+from pathlib import Path
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+import logging
+import pytest
+import os
+
+from livekit import api
+from livekit import rtc
+
+import livekit_protocol
+import asyncio
+
+logger = logging.getLogger(__name__)
+
+
+@pytest.mark.asyncio
+async def test_protocol():
+    url = os.getenv("LIVEKIT_URL")
+    api_key = os.getenv("LIVEKIT_API_KEY")
+    api_secret = os.getenv("LIVEKIT_API_SECRET")
+
+    token1 = (
+        api.AccessToken(api_key=api_key, api_secret=api_secret)
+        .with_identity("core:user.test.agent-send")
+        .with_name("Agent")
+        .with_kind("agent")
+        .with_grants(
+            api.VideoGrants(
+                can_update_own_metadata=True,
+                room_join=True,
+                room="test-process",
+                agent=True,
+            )
+        )
+    )
+
+    jwt1 = token1.to_jwt()
+
+    token2 = (
+        api.AccessToken(api_key=api_key, api_secret=api_secret)
+        .with_identity("core:user.test.agent-recv")
+        .with_name("Agent")
+        .with_kind("agent")
+        .with_grants(
+            api.VideoGrants(
+                can_update_own_metadata=True,
+                room_join=True,
+                room="test-process",
+                agent=True,
+            )
+        )
+    )
+
+    jwt2 = token2.to_jwt()
+
+    room1 = rtc.Room()
+    await room1.connect(url=url, token=jwt1)
+
+    room2 = rtc.Room()
+    await room2.connect(url=url, token=jwt2)
+
+    topic = "test_topic"
+
+    while True:
+        await asyncio.sleep(0.1)
+
+        if (
+            room2.local_participant.identity in room1.remote_participants
+            and room1.local_participant.identity in room2.remote_participants
+        ):
+            break
+
+    async with livekit_protocol.LivekitProtocol(
+        room=room1,
+        remote=room1.remote_participants[room2.local_participant.identity],
+        topic=topic,
+    ) as proto1:
+        async with livekit_protocol.LivekitProtocol(
+            room=room2,
+            remote=room2.remote_participants[room1.local_participant.identity],
+            topic=topic,
+        ) as proto2:
+            test_data_builder = bytearray()
+            for i in range(1024 * 1024):
+                test_data_builder.append(i % 255)
+
+            test_data = bytes(test_data_builder)
+
+            done = asyncio.Future[bool]()
+
+            matches = 0
+
+            async def test_fn(protocol, id: int, type: str, data: bytes):
+                nonlocal matches
+                logger.info("Message received")
+                if test_data != data:
+                    raise "data isn't equal"
+                matches += 1
+
+                if matches == 2:
+                    done.set_result(True)
+
+            proto2.register_handler("test", test_fn)
+
+            await asyncio.sleep(1)
+
+            await proto1.send("test", test_data)
+            await proto1.send("test", test_data)
+
+            await done
+
+    await room2.disconnect()
+    await room1.disconnect()

meshagent/livekit/version.py

@@ -0,0 +1 @@
+__version__ = "0.8.3"

meshagent_livekit-0.8.3.dist-info/METADATA

@@ -0,0 +1,39 @@
+Metadata-Version: 2.4
+Name: meshagent-livekit
+Version: 0.8.3
+Summary: Livekit support for Meshagent
+License-Expression: Apache-2.0
+Project-URL: Documentation, https://docs.meshagent.com
+Project-URL: Website, https://www.meshagent.com
+Project-URL: Source, https://www.meshagent.com
+Requires-Python: >=3.13
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pytest~=8.4
+Requires-Dist: pytest-asyncio~=0.26
+Requires-Dist: strip-markdown~=1.3
+Requires-Dist: livekit-api>=1.0
+Requires-Dist: livekit-agents~=1.2
+Requires-Dist: livekit-plugins-openai~=1.2
+Requires-Dist: livekit-plugins-silero~=1.2
+Requires-Dist: livekit-plugins-turn-detector~=1.2
+Requires-Dist: meshagent-api~=0.8.3
+Requires-Dist: meshagent-tools~=0.8.3
+Dynamic: license-file
+
+# [Meshagent](https://www.meshagent.com)
+
+## MeshAgent LiveKit
+The ``meshagent.livekit`` package equips agents with real-time audio and voice capabilities via the LiveKit SDK. 
+
+### VoiceBot
+The ``VoiceBot`` agent handles two-way voice conversations allowing users to interact with the agent verbally. Agents based on the ``VoiceBot`` class can be given the same tools as ``ChatBot`` based agents. This means you only need to write a tool once and the same tool can be used across both text and voice based agents. Check out the [Build a Voice Agent](https://docs.meshagent.com/agents/standard/buildanddeployvoicebot) example to learn how to create a simple Voice Agent without tools then add built-in MeshAgent tools and custom tools to the agent.
+
+---
+### Learn more about MeshAgent on our website or check out the docs for additional examples!
+
+**Website**: [www.meshagent.com](https://www.meshagent.com/)
+
+**Documentation**: [docs.meshagent.com](https://docs.meshagent.com/)
+
+---

meshagent_livekit-0.8.3.dist-info/RECORD

@@ -0,0 +1,12 @@
+meshagent/livekit/__init__.py,sha256=X78Z4yEg5XfkNKH0HiIdG4k1q5ktB-ampTuXHLNFrAw,58
+meshagent/livekit/livekit_protocol.py,sha256=5Zu4ymLWEGt5SGXLNu94gOeyjnjhaV6uTS2FhSdODqs,1470
+meshagent/livekit/livekit_protocol_test.py,sha256=o7yYxXad4tMazcxFkq44yW-A9tJ0Lk6WdZpG5ifxcU4,2980
+meshagent/livekit/version.py,sha256=otnwfmvJLUamPajTPUaIekiO9mA-2HPi-_h_E0N-uOQ,22
+meshagent/livekit/agents/meeting_transcriber.py,sha256=4B5Qi0vKP0TU00vR4KsNdIiR2uyvfgiOL2hjuzhLotw,10210
+meshagent/livekit/agents/transcriber.py,sha256=S992oVVBt3ShWDQQWprLjyl6Yh0hyNRd8d3qCmg_toU,5795
+meshagent/livekit/agents/voice.py,sha256=Fayrgi9JYNDVSGLEnMbBpzkrQF70P5RrfUHSyd1WKwM,12417
+meshagent_livekit-0.8.3.dist-info/licenses/LICENSE,sha256=eTt0SPW-sVNdkZe9PS_S8WfCIyLjRXRl7sUBWdlteFg,10254
+meshagent_livekit-0.8.3.dist-info/METADATA,sha256=QpqzZpHIAZHRj91j7ncNhgKfbanuNBEuWEghgFBq8qY,1749
+meshagent_livekit-0.8.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+meshagent_livekit-0.8.3.dist-info/top_level.txt,sha256=GlcXnHtRP6m7zlG3Df04M35OsHtNXy_DY09oFwWrH74,10
+meshagent_livekit-0.8.3.dist-info/RECORD,,

meshagent_livekit-0.8.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (80.9.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

meshagent_livekit-0.8.3.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction,
+and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by
+the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all
+other entities that control, are controlled by, or are under common
+control with that entity. For the purposes of this definition,
+"control" means (i) the power, direct or indirect, to cause the
+direction or management of such entity, whether by contract or
+otherwise, or (ii) ownership of fifty percent (50%) or more of the
+outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity
+exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation
+source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical
+transformation or translation of a Source form, including but
+not limited to compiled object code, generated documentation,
+and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or
+Object form, made available under the License, as indicated by a
+copyright notice that is included in or attached to the work
+(an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object
+form, that is based on (or derived from) the Work and for which the
+editorial revisions, annotations, elaborations, or other modifications
+represent, as a whole, an original work of authorship. For the purposes
+of this License, Derivative Works shall not include works that remain
+separable from, or merely link (or bind by name) to the interfaces of,
+the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including
+the original version of the Work and any modifications or additions
+to that Work or Derivative Works thereof, that is intentionally
+submitted to Licensor for inclusion in the Work by the copyright owner
+or by an individual or Legal Entity authorized to submit on behalf of
+the copyright owner. For the purposes of this definition, "submitted"
+means any form of electronic, verbal, or written communication sent
+to the Licensor or its representatives, including but not limited to
+communication on electronic mailing lists, source code control systems,
+and issue tracking systems that are managed by, or on behalf of, the
+Licensor for the purpose of discussing and improving the Work, but
+excluding communication that is conspicuously marked or otherwise
+designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity
+on behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+copyright license to reproduce, prepare Derivative Works of,
+publicly display, publicly perform, sublicense, and distribute the
+Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+(except as stated in this section) patent license to make, have made,
+use, offer to sell, sell, import, and otherwise transfer the Work,
+where such license applies only to those patent claims licensable
+by such Contributor that are necessarily infringed by their
+Contribution(s) alone or by combination of their Contribution(s)
+with the Work to which such Contribution(s) was submitted. If You
+institute patent litigation against any entity (including a
+cross-claim or counterclaim in a lawsuit) alleging that the Work
+or a Contribution incorporated within the Work constitutes direct
+or contributory patent infringement, then any patent licenses
+granted to You under this License for that Work shall terminate
+as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+Work or Derivative Works thereof in any medium, with or without
+modifications, and in Source or Object form, provided that You
+meet the following conditions:
+
+(a) You must give any other recipients of the Work or
+Derivative Works a copy of this License; and
+
+(b) You must cause any modified files to carry prominent notices
+stating that You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works
+that You distribute, all copyright, patent, trademark, and
+attribution notices from the Source form of the Work,
+excluding those notices that do not pertain to any part of
+the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its
+distribution, then any Derivative Works that You distribute must
+include a readable copy of the attribution notices contained
+within such NOTICE file, excluding those notices that do not
+pertain to any part of the Derivative Works, in at least one
+of the following places: within a NOTICE text file distributed
+as part of the Derivative Works; within the Source form or
+documentation, if provided along with the Derivative Works; or,
+within a display generated by the Derivative Works, if and
+wherever such third-party notices normally appear. The contents
+of the NOTICE file are for informational purposes only and
+do not modify the License. You may add Your own attribution
+notices within Derivative Works that You distribute, alongside
+or as an addendum to the NOTICE text from the Work, provided
+that such additional attribution notices cannot be construed
+as modifying the License.
+
+You may add Your own copyright statement to Your modifications and
+may provide additional or different license terms and conditions
+for use, reproduction, or distribution of Your modifications, or
+for any such Derivative Works as a whole, provided Your use,
+reproduction, and distribution of the Work otherwise complies with
+the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+any Contribution intentionally submitted for inclusion in the Work
+by You to the Licensor shall be under the terms and conditions of
+this License, without any additional terms or conditions.
+Notwithstanding the above, nothing herein shall supersede or modify
+the terms of any separate license agreement you may have executed
+with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+names, trademarks, service marks, or product names of the Licensor,
+except as required for reasonable and customary use in describing the
+origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+agreed to in writing, Licensor provides the Work (and each
+Contributor provides its Contributions) on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+implied, including, without limitation, any warranties or conditions
+of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Work and assume any
+risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise,
+unless required by applicable law (such as deliberate and grossly
+negligent acts) or agreed to in writing, shall any Contributor be
+liable to You for damages, including any direct, indirect, special,
+incidental, or consequential damages of any character arising as a
+result of this License or out of the use or inability to use the
+Work (including but not limited to damages for loss of goodwill,
+work stoppage, computer failure or malfunction, or any and all
+other commercial damages or losses), even if such Contributor
+has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+the Work or Derivative Works thereof, You may choose to offer,
+and charge a fee for, acceptance of support, warranty, indemnity,
+or other liability obligations and/or rights consistent with this
+License. However, in accepting such obligations, You may act only
+on Your own behalf and on Your sole responsibility, not on behalf
+of any other Contributor, and only if You agree to indemnify,
+defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason
+of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS
+
+APPENDIX: How to apply the Apache License to your work.
+
+To apply the Apache License to your work, attach the following
+boilerplate notice, with the fields enclosed by brackets "[]"
+replaced with your own identifying information. (Don't include
+the brackets!)  The text should be enclosed in the appropriate
+comment syntax for the file format. We also recommend that a
+file or class name and description of purpose be included on the
+same "printed page" as the copyright notice for easier
+identification within third-party archives.
+
+Copyright [yyyy] [name of copyright owner]
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.

meshagent_livekit-0.8.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+meshagent