Merge edmundman's UFC_FIGHT_PREDICTOR contribution

environments/community/router_env/engine/agents/telephony_agent.py

@@ -0,0 +1,99 @@
+import logging
+import os
+from pathlib import Path
+
+from dotenv import load_dotenv
+from livekit import api
+from livekit.agents import (
+    Agent,
+    AgentSession,
+    ChatContext,
+    JobContext,
+    RunContext,
+    WorkerOptions,
+    cli,
+    get_job_context,
+)
+from livekit.agents.llm import function_tool
+from livekit.plugins import deepgram, openai, silero
+from livekit.plugins.turn_detector.multilingual import MultilingualModel
+
+
+# Add this function definition anywhere
+async def hangup_call():
+    ctx = get_job_context()
+    if ctx is None:
+        # Not running in a job context
+        return
+
+    await ctx.api.room.delete_room(
+        api.DeleteRoomRequest(
+            room=ctx.room.name,
+        )
+    )
+
+
+load_dotenv(os.path.join(os.path.dirname(__file__), "..", "..", ".env"))
+
+
+logger = logging.getLogger("mcp-agent")
+
+load_dotenv(dotenv_path=Path(__file__).parent.parent / ".env")
+
+
+class MyAgent(Agent):
+    def __init__(self, chat_ctx: ChatContext) -> None:
+        super().__init__(
+            instructions=(
+                "You can have phone calls. The interface is voice-based: "
+                "accept spoken user queries and respond with synthesized speech."
+            ),
+            chat_ctx=chat_ctx,
+        )
+
+    @function_tool
+    async def end_call(self, ctx: RunContext):
+        """Called when the user wants to end the call"""
+        # let the agent finish speaking
+        current_speech = ctx.session.current_speech
+        if current_speech:
+            await current_speech.wait_for_playout()
+
+        await hangup_call()
+
+    @function_tool
+    async def end_call_finished_by_you(self, ctx: RunContext):
+        """Called when you have accomplished your task and can end the call safely"""
+        # let the agent finish speaking
+        current_speech = ctx.session.current_speech
+        if current_speech:
+            await current_speech.wait_for_playout()
+
+        await hangup_call()
+
+    async def on_enter(self):
+        self.session.generate_reply()
+
+
+async def entrypoint(ctx: JobContext):
+    await ctx.connect()
+
+    session = AgentSession(
+        vad=silero.VAD.load(),
+        stt=deepgram.STT(model="nova-3", language="multi"),
+        llm=openai.LLM(model="gpt-4o-mini"),
+        tts=openai.TTS(voice="ash"),
+        turn_detection=MultilingualModel(),
+    )
+
+    await session.start(agent=MyAgent(chat_ctx=session._chat_ctx), room=ctx.room)
+
+    await session.generate_reply(
+        instructions="Greet the user and offer your assistance."
+    )
+
+
+if __name__ == "__main__":
+    cli.run_app(
+        WorkerOptions(entrypoint_fnc=entrypoint, agent_name="my-telephony-agent")
+    )