From dd402da9e56fe409995d1a114da7d560c09aa017 Mon Sep 17 00:00:00 2001
From: daniil5701133 <daniil@spacestep.ca>
Date: Tue, 25 Jun 2024 14:40:14 +0300
Subject: [PATCH] added handling streamSid after first wss connect

fixx name
---
 examples/twilio-chatbot/bot.py                      | 6 ++++--
 examples/twilio-chatbot/server.py                   | 9 ++++++++-
 src/pipecat/serializers/twilio.py                   | 9 +++------
 src/pipecat/transports/network/fastapi_websocket.py | 4 ++--
 4 files changed, 17 insertions(+), 11 deletions(-)

diff --git a/examples/twilio-chatbot/bot.py b/examples/twilio-chatbot/bot.py
index 8a368f830..7d523ca43 100644
--- a/examples/twilio-chatbot/bot.py
+++ b/examples/twilio-chatbot/bot.py
@@ -15,6 +15,7 @@
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.transports.network.fastapi_websocket import FastAPIWebsocketTransport, FastAPIWebsocketParams
 from pipecat.vad.silero import SileroVADAnalyzer
+from pipecat.serializers.twilio import TwilioFrameSerializer
 
 from loguru import logger
 
@@ -25,7 +26,7 @@
 logger.add(sys.stderr, level="DEBUG")
 
 
-async def run_bot(websocket_client):
+async def run_bot(websocket_client, stream_sid):
     async with aiohttp.ClientSession() as session:
         transport = FastAPIWebsocketTransport(
             websocket=websocket_client,
@@ -34,7 +35,8 @@ async def run_bot(websocket_client):
                 add_wav_header=False,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
-                vad_audio_passthrough=True
+                vad_audio_passthrough=True,
+                serializer=TwilioFrameSerializer(stream_sid)
             )
         )
 
diff --git a/examples/twilio-chatbot/server.py b/examples/twilio-chatbot/server.py
index 025f9dd17..f64e7f309 100644
--- a/examples/twilio-chatbot/server.py
+++ b/examples/twilio-chatbot/server.py
@@ -1,3 +1,5 @@
+import json
+
 import uvicorn
 
 from fastapi import FastAPI, WebSocket
@@ -26,8 +28,13 @@ async def start_call():
 @app.websocket("/ws")
 async def websocket_endpoint(websocket: WebSocket):
     await websocket.accept()
+    start_data = websocket.iter_text()
+    await start_data.__anext__()
+    call_data = json.loads(await start_data.__anext__())
+    print(call_data, flush=True)
+    stream_sid = call_data['start']['streamSid']
     print("WebSocket connection accepted")
-    await run_bot(websocket)
+    await run_bot(websocket, stream_sid)
 
 
 if __name__ == "__main__":
diff --git a/src/pipecat/serializers/twilio.py b/src/pipecat/serializers/twilio.py
index ea7a562aa..713f43a86 100644
--- a/src/pipecat/serializers/twilio.py
+++ b/src/pipecat/serializers/twilio.py
@@ -17,8 +17,8 @@ class TwilioFrameSerializer(FrameSerializer):
         AudioRawFrame: "audio",
     }
 
-    def __init__(self):
-        self._sid = None
+    def __init__(self, stream_sid: str):
+        self._stream_sid = stream_sid
 
     def serialize(self, frame: Frame) -> str | bytes | None:
         if not isinstance(frame, AudioRawFrame):
@@ -30,7 +30,7 @@ def serialize(self, frame: Frame) -> str | bytes | None:
         payload = base64.b64encode(serialized_data).decode("utf-8")
         answer = {
             "event": "media",
-            "streamSid": self._sid,
+            "streamSid": self._stream_sid,
             "media": {
                 "payload": payload
             }
@@ -41,9 +41,6 @@ def serialize(self, frame: Frame) -> str | bytes | None:
     def deserialize(self, data: str | bytes) -> Frame | None:
         message = json.loads(data)
 
-        if not self._sid:
-            self._sid = message["streamSid"] if "streamSid" in message else None
-
         if message["event"] != "media":
             return None
         else:
diff --git a/src/pipecat/transports/network/fastapi_websocket.py b/src/pipecat/transports/network/fastapi_websocket.py
index 0b3eb906f..cf71ee021 100644
--- a/src/pipecat/transports/network/fastapi_websocket.py
+++ b/src/pipecat/transports/network/fastapi_websocket.py
@@ -35,7 +35,7 @@
 class FastAPIWebsocketParams(TransportParams):
     add_wav_header: bool = False
     audio_frame_size: int = 6400  # 200ms
-    serializer: FrameSerializer = TwilioFrameSerializer()
+    serializer: FrameSerializer
 
 
 class FastAPIWebsocketCallbacks(BaseModel):
@@ -125,7 +125,7 @@ class FastAPIWebsocketTransport(BaseTransport):
     def __init__(
             self,
             websocket: WebSocket,
-            params: FastAPIWebsocketParams = FastAPIWebsocketParams(),
+            params: FastAPIWebsocketParams,
             input_name: str | None = None,
             output_name: str | None = None,
             loop: asyncio.AbstractEventLoop | None = None):