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

fix: extend cancel_on_interruption=False regression fix to remaining realtime services

Browse Source 
Applies the same async-tool message routing introduced for AWSNovaSonicLLMService
and OpenAIRealtimeLLMService to additional realtime LLM services where the
flag's intent ("keep talking while the tool runs") is achievable:

- GrokRealtimeLLMService (xAI Realtime — also benefits the deprecated Grok
  alias since it re-exports the xAI module)
- AzureRealtimeLLMService picks up the fix transitively by inheriting from
  OpenAIRealtimeLLMService — no code change needed.

GrokRealtimeLLMService's _process_completed_function_calls now matches
the canonical pattern: skip LLMSpecificMessage, detect async-tool messages
via parse_message and route them — started skipped silently, intermediate
logged as an error and surfaced via push_error, final delivered through
the same channel as a synchronous result.

UltravoxRealtimeLLMService instead gets a one-time warning when async-tool
messages appear in the context. The Ultravox API freezes the conversation
during tool execution
(https://docs.ultravox.ai/tools/async-tools#custom-tool-timeouts), so the
flag's "keep talking while the tool runs" intent isn't achievable there —
applying the same code pattern would mislead users into expecting a UX
Ultravox can't deliver. Surfacing a clear warning is the right behavior
until Ultravox grows true async tool support.

Adds async-tool example files for Grok and Azure modeled on the existing
Nova Sonic / OpenAI Realtime ones (10s simulated network delay, weather
tool registered with cancel_on_interruption=False).

Two services remain excluded:

- GeminiLiveLLMService — the async-tool path needs deeper investigation.
- InworldRealtimeLLMService — appears to have a pre-existing problem
  with even simple synchronous tool calling on its Realtime API (the
  request reaches the server fine, but response generation fails with a
  generic server_error).
This commit is contained in:
Paul Kompfner
2026-05-08 10:04:14 -04:00
parent ad0f0a1294
commit b14a03d01f
5 changed files with 445 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/4447.fixed.md Normal file
View File

@@ -0,0 +1 @@
- Extended the `cancel_on_interruption=False` regression fix to `GrokRealtimeLLMService` and `AzureRealtimeLLMService` (the latter picks up the fix transitively by inheriting from `OpenAIRealtimeLLMService`). Same shape as the original fix for `AWSNovaSonicLLMService` and `OpenAIRealtimeLLMService`: each service now detects async-tool messages in the LLM context and routes the final result to its formal tool-result channel. Streamed intermediate results (`FunctionCallResultProperties(is_final=False)`) are not supported on these realtime services. `UltravoxRealtimeLLMService` now logs a one-time warning when async-tool messages appear in the context, since Ultravox freezes the conversation during tool execution and so the "keep talking while the tool runs" intent of `cancel_on_interruption=False` is structurally not achievable there. `GeminiLiveLLMService` and `InworldRealtimeLLMService` are excluded for now: Gemini Live's async-tool path needs deeper investigation, and Inworld appears to have a pre-existing problem with even simple tool calling on its Realtime API.

195
examples/realtime/realtime-azure-async-tool.py Normal file
View File

@@ -0,0 +1,195 @@
#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
"""Example: async function call with the Azure Realtime LLM service.
The ``get_current_weather`` tool is registered with
``cancel_on_interruption=False`` and simulates a slow API call (10s sleep).
While the call is in flight the conversation continues; the result arrives
later via the async-tool mechanism and is forwarded to Azure Realtime as a
``function_call_output`` so the model can integrate it naturally into its
next turn.
"""
import asyncio
import os
import random
from datetime import datetime
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
LLMContextAggregatorPair,
LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.azure.realtime.llm import AzureRealtimeLLMService
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.openai.realtime.events import (
AudioConfiguration,
AudioInput,
InputAudioTranscription,
SessionProperties,
)
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
# Simulate a long-running API call so we can demonstrate that the
# conversation continues while the tool is in flight.
await asyncio.sleep(10)
temperature = (
random.randint(60, 85)
if params.arguments["format"] == "fahrenheit"
else random.randint(15, 30)
)
await params.result_callback(
{
"conditions": "nice",
"temperature": temperature,
"location": params.arguments["location"],
"format": params.arguments["format"],
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
}
)
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
required=["location", "format"],
)
tools = ToolsSchema(standard_tools=[weather_function])
system_instruction = (
"You are a friendly assistant. The user and you will engage in a spoken "
"dialog exchanging the transcripts of a natural real-time conversation. "
"Keep your responses short, generally two or three sentences for chatty "
"scenarios. When the user asks for the weather, call get_current_weather. "
"While you wait for the result, keep chatting with the user. When the "
"result arrives, share it with the user naturally."
)
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
llm = AzureRealtimeLLMService(
api_key=os.environ["AZURE_REALTIME_API_KEY"],
base_url=os.environ["AZURE_REALTIME_BASE_URL"],
settings=AzureRealtimeLLMService.Settings(
system_instruction=system_instruction,
session_properties=SessionProperties(
audio=AudioConfiguration(
input=AudioInput(
transcription=InputAudioTranscription(model="whisper-1"),
)
),
),
),
)
llm.register_function(
"get_current_weather",
fetch_weather_from_api,
cancel_on_interruption=False,
)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
context,
user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
)
pipeline = Pipeline(
[
transport.input(),
user_aggregator,
llm,
transport.output(),
assistant_aggregator,
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point compatible with Pipecat Cloud."""
transport = await create_transport(runner_args, transport_params)
await run_bot(transport, runner_args)
if __name__ == "__main__":
from pipecat.runner.run import main
main()

179
examples/realtime/realtime-grok-async-tool.py Normal file
View File

@@ -0,0 +1,179 @@
#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#
"""Example: async function call with the Grok Realtime LLM service.
The ``get_current_weather`` tool is registered with
``cancel_on_interruption=False`` and simulates a slow API call (10s sleep).
While the call is in flight the conversation continues; the result arrives
later via the async-tool mechanism and is forwarded to Grok Realtime as a
``function_call_output`` so the model can integrate it naturally into its
next turn.
"""
import asyncio
import os
import random
from datetime import datetime
from dotenv import load_dotenv
from loguru import logger
from pipecat.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.llm_service import FunctionCallParams
from pipecat.services.xai.realtime.events import SessionProperties
from pipecat.services.xai.realtime.llm import GrokRealtimeLLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
load_dotenv(override=True)
async def fetch_weather_from_api(params: FunctionCallParams):
# Simulate a long-running API call so we can demonstrate that the
# conversation continues while the tool is in flight.
await asyncio.sleep(10)
temperature = (
random.randint(60, 85)
if params.arguments["format"] == "fahrenheit"
else random.randint(15, 30)
)
await params.result_callback(
{
"conditions": "nice",
"temperature": temperature,
"location": params.arguments["location"],
"format": params.arguments["format"],
"timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
}
)
weather_function = FunctionSchema(
name="get_current_weather",
description="Get the current weather",
properties={
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"format": {
"type": "string",
"enum": ["celsius", "fahrenheit"],
"description": "The temperature unit to use. Infer this from the users location.",
},
},
required=["location", "format"],
)
tools = ToolsSchema(standard_tools=[weather_function])
system_instruction = (
"You are a friendly assistant. The user and you will engage in a spoken "
"dialog exchanging the transcripts of a natural real-time conversation. "
"Keep your responses short, generally two or three sentences for chatty "
"scenarios. When the user asks for the weather, call get_current_weather. "
"While you wait for the result, keep chatting with the user. When the "
"result arrives, share it with the user naturally."
)
# Note: Grok has built-in server-side VAD, so we don't need local VAD.
transport_params = {
"daily": lambda: DailyParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"twilio": lambda: FastAPIWebsocketParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
"webrtc": lambda: TransportParams(
audio_in_enabled=True,
audio_out_enabled=True,
),
}
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
logger.info(f"Starting bot")
llm = GrokRealtimeLLMService(
api_key=os.environ["XAI_API_KEY"],
settings=GrokRealtimeLLMService.Settings(
system_instruction=system_instruction,
session_properties=SessionProperties(
voice="Ara",
),
),
)
llm.register_function(
"get_current_weather",
fetch_weather_from_api,
cancel_on_interruption=False,
)
context = LLMContext(tools=tools)
user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context)
pipeline = Pipeline(
[
transport.input(),
user_aggregator,
llm,
transport.output(),
assistant_aggregator,
]
)
task = PipelineTask(
pipeline,
params=PipelineParams(
enable_metrics=True,
enable_usage_metrics=True,
),
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
)
@transport.event_handler("on_client_connected")
async def on_client_connected(transport, client):
logger.info(f"Client connected")
context.add_message(
{"role": "developer", "content": "Please introduce yourself to the user."}
)
await task.queue_frames([LLMRunFrame()])
@transport.event_handler("on_client_disconnected")
async def on_client_disconnected(transport, client):
logger.info(f"Client disconnected")
await task.cancel()
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
await runner.run(task)
async def bot(runner_args: RunnerArguments):
"""Main bot entry point compatible with Pipecat Cloud."""
transport = await create_transport(runner_args, transport_params)
await run_bot(transport, runner_args)
if __name__ == "__main__":
from pipecat.runner.run import main
main()

31
src/pipecat/services/ultravox/llm.py
View File

@@ -45,7 +45,8 @@ from pipecat.frames.frames import (
UserAudioRawFrame,
VADUserStoppedSpeakingFrame,
)
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators import async_tool_messages
from pipecat.processors.aggregators.llm_context import LLMContext, LLMSpecificMessage
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.llm_service import FunctionCallFromLLM, LLMService
from pipecat.services.settings import NOT_GIVEN, LLMSettings, _NotGiven, assert_given
@@ -218,6 +219,7 @@ class UltravoxRealtimeLLMService(LLMService):
self._disconnecting = False
self._bot_responding: Literal[None, "text", "voice"] = None
self._last_user_id: str | None = None
self._async_tool_warning_logged: bool = False
self._sample_rate = 48000
self._resampler = create_stream_resampler()
@@ -413,6 +415,33 @@ class UltravoxRealtimeLLMService(LLMService):
await self.push_frame(frame, direction)
async def _handle_context(self, context: LLMContext):
# If the user registered a function with cancel_on_interruption=False,
# the aggregator emits async-tool-style messages into the context. We
# don't (currently) honor those on Ultravox: the Ultravox API freezes
# the conversation during tool execution
# (https://docs.ultravox.ai/tools/async-tools#custom-tool-timeouts),
# so the "keep talking while the tool runs" intent of the flag is
# structurally not achievable here. Surface a one-time warning so
# users see they're not getting what they expect.
if not self._async_tool_warning_logged:
for message in context.get_messages():
if isinstance(message, LLMSpecificMessage):
continue
if async_tool_messages.parse_message(message) is not None:
logger.error(
f"{self}: cancel_on_interruption=False is not supported by "
f"Ultravox: the conversation freezes during tool execution, so "
f"the 'keep talking while the tool runs' intent of the flag "
f"would not be achievable anyway. Use "
f"cancel_on_interruption=True (the default) or a non-realtime "
f"LLM service if your tool needs the async semantics."
)
await self.push_error(
error_msg="cancel_on_interruption=False is not supported by Ultravox.",
)
self._async_tool_warning_logged = True
break
# Ultravox handles all context server-side, so the only context we may
# need to handle here is new function call results.
for message in reversed(context.messages):

41
src/pipecat/services/xai/realtime/llm.py
View File

@@ -47,7 +47,8 @@ from pipecat.frames.frames import (
UserStoppedSpeakingFrame,
)
from pipecat.metrics.metrics import LLMTokenUsage
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators import async_tool_messages
from pipecat.processors.aggregators.llm_context import LLMContext, LLMSpecificMessage
from pipecat.processors.frame_processor import FrameDirection
from pipecat.services.llm_service import FunctionCallFromLLM, LLMService
from pipecat.services.settings import (
@@ -913,6 +914,43 @@ class GrokRealtimeLLMService(LLMService[GrokRealtimeLLMAdapter]):
sent_new_result = False
for message in self._context.get_messages():
# LLMSpecificMessages are opaque provider-specific payloads, not
# standard tool-result messages — skip them.
if isinstance(message, LLMSpecificMessage):
continue
# Async-tool messages live alongside regular tool messages in the
# context; detect and route them before the regular logic so we
# don't try to send the async-tool envelope JSON as a tool result.
async_payload = async_tool_messages.parse_message(message)
if async_payload is not None:
if async_payload.tool_call_id in self._completed_tool_calls:
continue
if async_payload.kind == "started":
# The provider already issued the tool call and natively
# awaits a result; nothing to send for the started marker.
continue
if async_payload.kind == "intermediate":
logger.error(
f"{self}: Grok Realtime does not support streamed async "
f"tool results; dropping intermediate result for "
f"tool_call_id={async_payload.tool_call_id}. Use a "
f"non-realtime LLM service if your tool needs to "
f"stream intermediate results."
)
await self.push_error(
error_msg="Grok Realtime does not support streamed async tool results.",
)
continue
# kind == "final": deliver via the formal tool-result channel
# — same path as a synchronous tool result, just delayed.
if send_new_results:
sent_new_result = True
await self._send_tool_result(async_payload.tool_call_id, async_payload.result)
self._completed_tool_calls.add(async_payload.tool_call_id)
continue
# Look for newly-completed "regular" (as opposed to async-tool) results
if message.get("role") and message.get("content") != "IN_PROGRESS":
tool_call_id = message.get("tool_call_id")
if tool_call_id and tool_call_id not in self._completed_tool_calls:
@@ -939,6 +977,7 @@ class GrokRealtimeLLMService(LLMService[GrokRealtimeLLMAdapter]):
async def _send_tool_result(self, tool_call_id: str, result: str):
"""Send a tool call result to Grok."""
logger.debug(f"Sending tool result to Grok Realtime for tool_call_id={tool_call_id}")
item = events.ConversationItem(
type="function_call_output",
call_id=tool_call_id,