wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Remove deprecated EmulateUser{Started,Stopped}SpeakingFrame and emulated field

Browse Source 
Remove EmulateUserStartedSpeakingFrame, EmulateUserStoppedSpeakingFrame
(deprecated since v0.0.99), and the emulated field from
UserStartedSpeakingFrame and UserStoppedSpeakingFrame. Clean up the
handling code in base_input.py and a stale comment in nova_sonic/llm.py.
This commit is contained in:
Mark Backman
2026-04-02 11:31:29 -04:00
parent d503383c23
commit 5b67dcd9e7
3 changed files with 7 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
src/pipecat/frames/frames.py
View File

@@ -866,16 +866,9 @@ class UserStartedSpeakingFrame(SystemFrame):
Emitted when the user turn starts, which usually means that some
transcriptions are already available.
Parameters:
emulated: Whether this event was emulated rather than detected by VAD.
.. deprecated:: 0.0.99
This field is deprecated and will be removed in a future version.
"""
emulated: bool = False
pass
@dataclass
@@ -884,16 +877,9 @@ class UserStoppedSpeakingFrame(SystemFrame):
Emitted when the user turn ends. This usually coincides with the start of
the bot turn.
Parameters:
emulated: Whether this event was emulated rather than detected by VAD.
.. deprecated:: 0.0.99
This field is deprecated and will be removed in a future version.
"""
emulated: bool = False
pass
@dataclass
@@ -928,56 +914,6 @@ class UserSpeakingFrame(SystemFrame):
pass
@dataclass
class EmulateUserStartedSpeakingFrame(SystemFrame):
"""Frame to emulate user started speaking behavior.
Emitted by internal processors upstream to emulate VAD behavior when a
user starts speaking.
.. deprecated:: 0.0.99
This frame is deprecated and will be removed in a future version.
"""
def __post_init__(self):
super().__post_init__()
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"EmulateUserStartedSpeakingFrame is deprecated and will be removed in a future version.",
DeprecationWarning,
stacklevel=2,
)
@dataclass
class EmulateUserStoppedSpeakingFrame(SystemFrame):
"""Frame to emulate user stopped speaking behavior.
Emitted by internal processors upstream to emulate VAD behavior when a
user stops speaking.
.. deprecated:: 0.0.99
This frame is deprecated and will be removed in a future version.
"""
def __post_init__(self):
super().__post_init__()
import warnings
with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"EmulateUserStoppedSpeakingFrame is deprecated and will be removed in a future version.",
DeprecationWarning,
stacklevel=2,
)
@dataclass
class VADUserStartedSpeakingFrame(SystemFrame):
"""Frame emitted when VAD definitively detects user started speaking.

14
src/pipecat/services/aws/nova_sonic/llm.py
View File

@@ -1281,18 +1281,8 @@ class AWSNovaSonicLLMService(LLMService):
# HACK: Check if this transcription was triggered by our own
# assistant response trigger. If so, we need to wrap it with
# UserStarted/StoppedSpeakingFrames; otherwise the user aggregator
# would fire an EmulatedUserStartedSpeakingFrame, which would
# trigger an interruption, which would prevent us from writing the
# assistant response to context.
#
# Sending an EmulateUserStartedSpeakingFrame ourselves doesn't
# work: it just causes the interruption we're trying to avoid.
#
# Setting enable_emulated_vad_interruptions also doesn't work: at
# the time the user aggregator receives the TranscriptionFrame, it
# doesn't yet know the assistant has started responding, so it
# doesn't know that emulating the user starting to speak would
# cause an interruption.
# would trigger an interruption, which would prevent us from
# writing the assistant response to context.
should_wrap_in_user_started_stopped_speaking_frames = (
self._waiting_for_trigger_transcription
and self._user_text_buffer.strip().lower() == "ready"

16
src/pipecat/transports/base_input.py
View File

@@ -25,8 +25,6 @@ from pipecat.frames.frames import (
BotStartedSpeakingFrame,
BotStoppedSpeakingFrame,
CancelFrame,
EmulateUserStartedSpeakingFrame,
EmulateUserStoppedSpeakingFrame,
EndFrame,
FilterUpdateSettingsFrame,
Frame,
@@ -313,12 +311,6 @@ class BaseInputTransport(FrameProcessor):
elif isinstance(frame, BotStoppedSpeakingFrame):
await self._deprecated_handle_bot_stopped_speaking(frame)
await self.push_frame(frame, direction)
elif isinstance(frame, EmulateUserStartedSpeakingFrame):
logger.debug("Emulating user started speaking")
await self._deprecated_handle_user_interruption(VADState.SPEAKING, emulated=True)
elif isinstance(frame, EmulateUserStoppedSpeakingFrame):
logger.debug("Emulating user stopped speaking")
await self._deprecated_handle_user_interruption(VADState.QUIET, emulated=True)
# All other system frames
elif isinstance(frame, SystemFrame):
await self.push_frame(frame, direction)
@@ -500,15 +492,13 @@ class BaseInputTransport(FrameProcessor):
"""Update bot speaking state when bot stops speaking."""
self._bot_speaking = False
async def _deprecated_handle_user_interruption(
self, vad_state: VADState, emulated: bool = False
):
async def _deprecated_handle_user_interruption(self, vad_state: VADState):
"""Handle user interruption events based on speaking state."""
if vad_state == VADState.SPEAKING:
logger.debug("User started speaking")
self._user_speaking = True
await self.broadcast_frame(UserStartedSpeakingFrame, emulated=emulated)
await self.broadcast_frame(UserStartedSpeakingFrame)
# Make sure we notify about interruptions quickly out-of-band.
await self.broadcast_interruption()
@@ -516,7 +506,7 @@ class BaseInputTransport(FrameProcessor):
logger.debug("User stopped speaking")
self._user_speaking = False
await self.broadcast_frame(UserStoppedSpeakingFrame, emulated=emulated)
await self.broadcast_frame(UserStoppedSpeakingFrame)
async def _deprecated_old_handle_vad(
self, audio_frame: InputAudioRawFrame, vad_state: VADState