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

Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based.

Browse Source 
This fixes a bug where spaces were sometimes missing from assistant messages in context.
This commit is contained in:
Paul Kompfner
2025-11-10 12:28:40 -05:00
parent c2ce143e6c
commit 913194844e
10 changed files with 113 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
tests/test_context_aggregators.py
View File

@@ -35,6 +35,7 @@ from pipecat.frames.frames import (
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.task import PipelineParams
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response import (
LLMAssistantAggregatorParams,
LLMUserAggregatorParams,
@@ -651,12 +652,20 @@ class BaseTestAssistantContextAggregator:
aggregator = self.AGGREGATOR_CLASS(
context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
)
# The newer LLMAssistantAggregator expects TextFrames to declare
# when they include inter-frame spaces.
def make_text_frame(text: str) -> TextFrame:
frame = TextFrame(text=text)
frame.includes_inter_frame_spaces = True
return frame
frames_to_send = [
LLMFullResponseStartFrame(),
TextFrame(text="Hello "),
TextFrame(text="Pipecat. "),
TextFrame(text="How are "),
TextFrame(text="you?"),
make_text_frame("Hello "),
make_text_frame("Pipecat. "),
make_text_frame("How are "),
make_text_frame("you?"),
LLMFullResponseEndFrame(),
]
expected_down_frames = [*self.EXPECTED_CONTEXT_FRAMES]
@@ -697,14 +706,22 @@ class BaseTestAssistantContextAggregator:
aggregator = self.AGGREGATOR_CLASS(
context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
)
# The newer LLMAssistantAggregator expects TextFrames to declare
# when they include inter-frame spaces.
def make_text_frame(text: str) -> TextFrame:
frame = TextFrame(text=text)
frame.includes_inter_frame_spaces = True
return frame
frames_to_send = [
LLMFullResponseStartFrame(),
TextFrame(text="Hello "),
TextFrame(text="Pipecat."),
make_text_frame("Hello "),
make_text_frame("Pipecat."),
LLMFullResponseEndFrame(),
LLMFullResponseStartFrame(),
TextFrame(text="How are "),
TextFrame(text="you?"),
make_text_frame(text="How are "),
make_text_frame(text="you?"),
LLMFullResponseEndFrame(),
]
expected_down_frames = [*self.EXPECTED_CONTEXT_FRAMES, *self.EXPECTED_CONTEXT_FRAMES]
@@ -724,16 +741,24 @@ class BaseTestAssistantContextAggregator:
aggregator = self.AGGREGATOR_CLASS(
context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
)
# The newer LLMAssistantAggregator expects TextFrames to declare
# when they include inter-frame spaces.
def make_text_frame(text: str) -> TextFrame:
frame = TextFrame(text=text)
frame.includes_inter_frame_spaces = True
return frame
frames_to_send = [
LLMFullResponseStartFrame(),
TextFrame(text="Hello "),
TextFrame(text="Pipecat."),
make_text_frame("Hello "),
make_text_frame("Pipecat."),
LLMFullResponseEndFrame(),
SleepFrame(AGGREGATION_SLEEP),
InterruptionFrame(),
LLMFullResponseStartFrame(),
TextFrame(text="How are "),
TextFrame(text="you?"),
make_text_frame("How are "),
make_text_frame("you?"),
LLMFullResponseEndFrame(),
]
expected_down_frames = [
@@ -969,7 +994,7 @@ class TestOpenAIAssistantContextAggregator(
class TestLLMAssistantAggregator(
BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
):
CONTEXT_CLASS = OpenAILLMContext
CONTEXT_CLASS = LLMContext
AGGREGATOR_CLASS = LLMAssistantAggregator
EXPECTED_CONTEXT_FRAMES = [LLMContextFrame, LLMContextAssistantTimestampFrame]

21
tests/test_transcript_processor.py
View File

@@ -438,17 +438,22 @@ class TestUserTranscriptProcessor(unittest.IsolatedAsyncioTestCase):
received_updates.append(frame)
# Test the specific pattern shared
def make_tts_text_frame(text: str) -> TTSTextFrame:
frame = TTSTextFrame(text=text)
frame.includes_inter_frame_spaces = True
return frame
frames_to_send = [
BotStartedSpeakingFrame(),
SleepFrame(),
TTSTextFrame(text="Hello"),
TTSTextFrame(text=" there"),
TTSTextFrame(text="!"),
TTSTextFrame(text=" How"),
TTSTextFrame(text="'s"),
TTSTextFrame(text=" it"),
TTSTextFrame(text=" going"),
TTSTextFrame(text="?"),
make_tts_text_frame("Hello"),
make_tts_text_frame(" there"),
make_tts_text_frame("!"),
make_tts_text_frame(" How"),
make_tts_text_frame("'s"),
make_tts_text_frame(" it"),
make_tts_text_frame(" going"),
make_tts_text_frame("?"),
BotStoppedSpeakingFrame(),
]