Deprecate expect_stripped_words option from LLMAssistantAggregatorParams, when used with the newer LLMAssistantAggregator, which now handles word spacing automatically.

This commit does not change how it works in the older `LLMAssistantContextAggregator`.
2025-10-30 15:48:15 -04:00
parent 5e00133e64
commit ac5734d0ed
18 changed files with 130 additions and 133 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -33,13 +33,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

  ```python
  context = LLMContext(messages, tools)
-  context_aggregator = LLMContextAggregatorPair(
-    context,
-    # This part is `OpenAIRealtimeLLMService`-specific.
-    # `expect_stripped_words=False` needed when OpenAI Realtime used with
-    # "audio" modality (the default).
-    assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-  )
+  context_aggregator = LLMContextAggregatorPair(context)
  ```

  (Note that even though `OpenAIRealtimeLLMService` now supports the universal
@@ -116,13 +110,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

  ```python
  context = LLMContext(messages, tools)
-  context_aggregator = LLMContextAggregatorPair(
-    context,
-    # This part is `GeminiLiveLLMService`-specific.
-    # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-    #  modality (the default).
-    assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-  )
+  context_aggregator = LLMContextAggregatorPair(context)
  ```

  (Note that even though `GeminiLiveLLMService` now supports the universal
@@ -202,6 +190,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ### Deprecated

+- The `expect_stripped_words` parameter of `LLMAssistantAggregatorParams` is
+  ignored when used with the newer `LLMAssistantAggregator`, which now handles
+  word spacing automatically.
+
 - `LLMService.request_image_frame()` is deprecated, push a
  `UserImageRequestFrame` instead.

--- a/examples/foundational/19-openai-realtime.py
+++ b/examples/foundational/19-openai-realtime.py
@@ -187,12 +187,7 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
        tools,
    )

-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when OpenAI Realtime used with
-        # "audio" modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/19a-azure-realtime.py
+++ b/examples/foundational/19a-azure-realtime.py
@@ -175,12 +175,7 @@ Remember, your responses should be short. Just one or two sentences, usually. Re
        tools,
    )

-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when OpenAI Realtime used with
-        # "audio" modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26a-gemini-live-transcription.py
+++ b/examples/foundational/26a-gemini-live-transcription.py
@@ -92,12 +92,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            #     },
        ],
    )
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    transcript = TranscriptProcessor()

--- a/examples/foundational/26b-gemini-live-function-calling.py
+++ b/examples/foundational/26b-gemini-live-function-calling.py
@@ -144,12 +144,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    context = LLMContext(
        [{"role": "user", "content": "Say hello."}],
    )
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26c-gemini-live-video.py
+++ b/examples/foundational/26c-gemini-live-video.py
@@ -75,12 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            },
        ],
    )
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26e-gemini-live-google-search.py
+++ b/examples/foundational/26e-gemini-live-google-search.py
@@ -100,12 +100,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
            }
        ],
    )
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26f-gemini-live-files-api.py
+++ b/examples/foundational/26f-gemini-live-files-api.py
@@ -164,12 +164,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
        )

    # Create context aggregator
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    # Build the pipeline
    pipeline = Pipeline(
--- a/examples/foundational/26g-gemini-live-groundingMetadata.py
+++ b/examples/foundational/26g-gemini-live-groundingMetadata.py
@@ -127,12 +127,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):

    # Set up conversation context and management
    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26h-gemini-live-vertex-function-calling.py
+++ b/examples/foundational/26h-gemini-live-vertex-function-calling.py
@@ -140,12 +140,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    llm.register_function("get_restaurant_recommendation", fetch_restaurant_recommendation)

    context = LLMContext([{"role": "user", "content": "Say hello."}])
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/26i-gemini-live-graceful-end.py
+++ b/examples/foundational/26i-gemini-live-graceful-end.py
@@ -157,12 +157,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    context = LLMContext(
        [{"role": "user", "content": "Say hello."}],
    )
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    pipeline = Pipeline(
        [
--- a/examples/foundational/46-video-processing.py
+++ b/examples/foundational/46-video-processing.py
@@ -111,12 +111,7 @@ async def run_bot(pipecat_transport):
    ]

    context = LLMContext(messages)
-    context_aggregator = LLMContextAggregatorPair(
-        context,
-        # `expect_stripped_words=False` needed when Gemini Live used with AUDIO
-        #  modality (the default)
-        assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False),
-    )
+    context_aggregator = LLMContextAggregatorPair(context)

    # RTVI events for Pipecat client UI
    rtvi = RTVIProcessor()
--- a/src/pipecat/processors/aggregators/llm_response.py
+++ b/src/pipecat/processors/aggregators/llm_response.py
@@ -89,7 +89,9 @@ class LLMAssistantAggregatorParams:

    Parameters:
        expect_stripped_words: Whether to expect and handle stripped words
-            in text frames by adding spaces between tokens.
+            in text frames by adding spaces between tokens. This parameter is
+            ignored when used with the newer LLMAssistantAggregator, which
+            handles word spacing automatically.
    """

    expect_stripped_words: bool = True
--- a/src/pipecat/processors/aggregators/llm_response_universal.py
+++ b/src/pipecat/processors/aggregators/llm_response_universal.py
@@ -13,6 +13,7 @@ LLM processing, and text-to-speech components in conversational AI pipelines.

 import asyncio
 import json
+import warnings
 from abc import abstractmethod
 from typing import Any, Dict, List, Literal, Optional, Set

@@ -65,6 +66,7 @@ from pipecat.processors.aggregators.llm_response import (
    LLMUserAggregatorParams,
 )
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.utils.string import concatenate_aggregated_text
 from pipecat.utils.time import time_now_iso8601


@@ -88,7 +90,7 @@ class LLMContextAggregator(FrameProcessor):
        self._context = context
        self._role = role

-        self._aggregation: str = ""
+        self._aggregation: List[str] = []

    @property
    def messages(self) -> List[LLMContextMessage]:
@@ -168,13 +170,21 @@ class LLMContextAggregator(FrameProcessor):

    async def reset(self):
        """Reset the aggregation state."""
-        self._aggregation = ""
+        self._aggregation = []

    @abstractmethod
    async def push_aggregation(self):
        """Push the current aggregation downstream."""
        pass

+    def aggregation_string(self) -> str:
+        """Get the current aggregation as a string.
+
+        Returns:
+            The concatenated aggregation string.
+        """
+        return concatenate_aggregated_text(self._aggregation)
+

 class LLMUserAggregator(LLMContextAggregator):
    """User LLM aggregator that processes speech-to-text transcriptions.
@@ -212,8 +222,6 @@ class LLMUserAggregator(LLMContextAggregator):
        self._turn_params: Optional[SmartTurnParams] = None

        if "aggregation_timeout" in kwargs:
-            import warnings
-
            with warnings.catch_warnings():
                warnings.simplefilter("always")
                warnings.warn(
@@ -307,7 +315,7 @@ class LLMUserAggregator(LLMContextAggregator):

    async def _process_aggregation(self):
        """Process the current aggregation and push it downstream."""
-        aggregation = self._aggregation
+        aggregation = self.aggregation_string()
        await self.reset()
        self._context.add_message({"role": self.role, "content": aggregation})
        frame = LLMContextFrame(self._context)
@@ -355,7 +363,7 @@ class LLMUserAggregator(LLMContextAggregator):
        """

        async def should_interrupt(strategy: BaseInterruptionStrategy):
-            await strategy.append_text(self._aggregation)
+            await strategy.append_text(self.aggregation_string())
            return await strategy.should_interrupt()

        return any([await should_interrupt(s) for s in self._interruption_strategies])
@@ -425,7 +433,7 @@ class LLMUserAggregator(LLMContextAggregator):
        if not text.strip():
            return

-        self._aggregation += f" {text}" if self._aggregation else text
+        self._aggregation.append(text)
        # We just got a final result, so let's reset interim results.
        self._seen_interim_results = False
        # Reset aggregation timer.
@@ -550,23 +558,31 @@ class LLMAssistantAggregator(LLMContextAggregator):
        Args:
            context: The OpenAI LLM context for conversation storage.
            params: Configuration parameters for aggregation behavior.
-            **kwargs: Additional arguments. Supports deprecated 'expect_stripped_words'.
+            **kwargs: Additional arguments.
        """
        super().__init__(context=context, role="assistant", **kwargs)
        self._params = params or LLMAssistantAggregatorParams()

        if "expect_stripped_words" in kwargs:
-            import warnings
-
            with warnings.catch_warnings():
                warnings.simplefilter("always")
                warnings.warn(
-                    "Parameter 'expect_stripped_words' is deprecated, use 'params' instead.",
+                    "Parameter 'expect_stripped_words' is deprecated. "
+                    "LLMAssistantAggregator now handles word spacing automatically.",
                    DeprecationWarning,
                )

            self._params.expect_stripped_words = kwargs["expect_stripped_words"]

+        if params and not params.expect_stripped_words:
+            with warnings.catch_warnings():
+                warnings.simplefilter("always")
+                warnings.warn(
+                    "params.expect_stripped_words is deprecated. "
+                    "LLMAssistantAggregator now handles word spacing automatically.",
+                    DeprecationWarning,
+                )
+
        self._started = 0
        self._function_calls_in_progress: Dict[str, Optional[FunctionCallInProgressFrame]] = {}
        self._context_updated_tasks: Set[asyncio.Task] = set()
@@ -629,7 +645,7 @@ class LLMAssistantAggregator(LLMContextAggregator):
        if not self._aggregation:
            return

-        aggregation = self._aggregation.strip()
+        aggregation = self.aggregation_string()
        await self.reset()

        if aggregation:
@@ -793,10 +809,11 @@ class LLMAssistantAggregator(LLMContextAggregator):
        if not self._started:
            return

-        if self._params.expect_stripped_words:
-            self._aggregation += f" {frame.text}" if self._aggregation else frame.text
-        else:
-            self._aggregation += frame.text
+        # Make sure we really have text (spaces count, too!)
+        if len(frame.text) == 0:
+            return
+
+        self._aggregation.append(frame.text)

    def _context_updated_task_finished(self, task: asyncio.Task):
        self._context_updated_tasks.discard(task)
--- a/src/pipecat/processors/transcript_processor.py
+++ b/src/pipecat/processors/transcript_processor.py
@@ -26,6 +26,7 @@ from pipecat.frames.frames import (
    TTSTextFrame,
 )
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.utils.string import concatenate_aggregated_text
 from pipecat.utils.time import time_now_iso8601


@@ -140,29 +141,7 @@ class AssistantTranscriptProcessor(BaseTranscriptProcessor):
                Result: "Hello there how are you"
        """
        if self._current_text_parts and self._aggregation_start_time:
-            # Check specifically for space characters, previously isspace() was used
-            # but that includes all whitespace characters (e.g. \n), not just spaces.
-            has_leading_spaces = any(
-                part and part[0] == " " for part in self._current_text_parts[1:]
-            )
-            has_trailing_spaces = any(
-                part and part[-1] == " " for part in self._current_text_parts[:-1]
-            )
-
-            # If there are embedded spaces in the fragments, use direct concatenation
-            contains_spacing_between_fragments = has_leading_spaces or has_trailing_spaces
-
-            # Apply corresponding joining method
-            if contains_spacing_between_fragments:
-                # Fragments already have spacing - just concatenate
-                content = "".join(self._current_text_parts)
-            else:
-                # Word-by-word fragments - join with spaces
-                content = " ".join(self._current_text_parts)
-
-            # Clean up any excessive whitespace
-            content = content.strip()
-
+            content = concatenate_aggregated_text(self._current_text_parts)
            if content:
                logger.trace(f"Emitting aggregated assistant message: {content}")
                message = TranscriptionMessage(
--- a/src/pipecat/utils/string.py
+++ b/src/pipecat/utils/string.py
@@ -18,7 +18,7 @@ Dependencies:
 """

 import re
-from typing import FrozenSet, Optional, Sequence, Tuple
+from typing import FrozenSet, List, Optional, Sequence, Tuple

 import nltk
 from loguru import logger
@@ -196,3 +196,40 @@ def parse_start_end_tags(
            return (None, len(text))

    return (None, current_tag_index)
+
+
+def concatenate_aggregated_text(text_parts: List[str]) -> str:
+    """Concatenate a list of text parts into a single string.
+
+    This function joins the provided list of text parts into a single string,
+    taking into account whether or not the parts already contain spacing.
+
+    This function is useful for aggregating text segments received from LLMs or
+    transcription services.
+
+    Args:
+        text_parts: A list of strings representing parts of text to concatenate.
+
+    Returns:
+        A single concatenated string.
+    """
+    # Check specifically for space characters, previously isspace() was used
+    # but that includes all whitespace characters (e.g. \n), not just spaces.
+    has_leading_spaces = any(part and part[0] == " " for part in text_parts[1:])
+    has_trailing_spaces = any(part and part[-1] == " " for part in text_parts[:-1])
+
+    # If there are embedded spaces in the fragments, use direct concatenation
+    contains_spacing_between_fragments = has_leading_spaces or has_trailing_spaces
+
+    # Apply corresponding joining method
+    if contains_spacing_between_fragments:
+        # Fragments already have spacing - just concatenate
+        result = "".join(text_parts)
+    else:
+        # Word-by-word fragments - join with spaces
+        result = " ".join(text_parts)
+
+    # Clean up any excessive whitespace
+    result = result.strip()
+
+    return result
--- a/tests/test_context_aggregators.py
+++ b/tests/test_context_aggregators.py
@@ -6,7 +6,7 @@

 import json
 import unittest
-from typing import Any
+from typing import Any, Optional

 from pipecat.audio.interruptions.min_words_interruption_strategy import MinWordsInterruptionStrategy
 from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
@@ -22,6 +22,8 @@ from pipecat.frames.frames import (
    InterimTranscriptionFrame,
    InterruptionFrame,
    InterruptionTaskFrame,
+    LLMContextAssistantTimestampFrame,
+    LLMContextFrame,
    LLMFullResponseEndFrame,
    LLMFullResponseStartFrame,
    OpenAILLMContextAssistantTimestampFrame,
@@ -38,6 +40,7 @@ from pipecat.processors.aggregators.llm_response import (
    LLMUserAggregatorParams,
    LLMUserContextAggregator,
 )
+from pipecat.processors.aggregators.llm_response_universal import LLMAssistantAggregator
 from pipecat.processors.aggregators.openai_llm_context import (
    OpenAILLMContext,
    OpenAILLMContextFrame,
@@ -586,11 +589,16 @@ class BaseTestUserContextAggregator:
        assert context_processor.context_received


-class BaseTestAssistantContextAggreagator:
+class BaseTestAssistantContextAggregator:
    CONTEXT_CLASS = None  # To be set in subclasses
    AGGREGATOR_CLASS = None  # To be set in subclasses
    EXPECTED_CONTEXT_FRAMES = None  # To be set in subclasses

+    def create_assistant_aggregator_params(
+        self, **kwargs
+    ) -> Optional[LLMAssistantAggregatorParams]:
+        return LLMAssistantAggregatorParams(**kwargs)
+
    def check_message_content(self, context: OpenAILLMContext, index: int, content: str):
        assert context.messages[index]["content"] == content

@@ -641,7 +649,7 @@ class BaseTestAssistantContextAggreagator:

        context = self.CONTEXT_CLASS()
        aggregator = self.AGGREGATOR_CLASS(
-            context, params=LLMAssistantAggregatorParams(expect_stripped_words=False)
+            context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
        )
        frames_to_send = [
            LLMFullResponseStartFrame(),
@@ -687,7 +695,7 @@ class BaseTestAssistantContextAggreagator:

        context = self.CONTEXT_CLASS()
        aggregator = self.AGGREGATOR_CLASS(
-            context, params=LLMAssistantAggregatorParams(expect_stripped_words=False)
+            context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
        )
        frames_to_send = [
            LLMFullResponseStartFrame(),
@@ -714,7 +722,7 @@ class BaseTestAssistantContextAggreagator:

        context = self.CONTEXT_CLASS()
        aggregator = self.AGGREGATOR_CLASS(
-            context, params=LLMAssistantAggregatorParams(expect_stripped_words=False)
+            context, params=self.create_assistant_aggregator_params(expect_stripped_words=False)
        )
        frames_to_send = [
            LLMFullResponseStartFrame(),
@@ -838,7 +846,7 @@ class TestAnthropicUserContextAggregator(


 class TestAnthropicAssistantContextAggregator(
-    BaseTestAssistantContextAggreagator, unittest.IsolatedAsyncioTestCase
+    BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
 ):
    CONTEXT_CLASS = AnthropicLLMContext
    AGGREGATOR_CLASS = AnthropicAssistantContextAggregator
@@ -873,7 +881,7 @@ class TestAWSBedrockUserContextAggregator(


 class TestAWSBedrockAssistantContextAggregator(
-    BaseTestAssistantContextAggreagator, unittest.IsolatedAsyncioTestCase
+    BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
 ):
    CONTEXT_CLASS = AWSBedrockLLMContext
    AGGREGATOR_CLASS = AWSBedrockAssistantContextAggregator
@@ -914,7 +922,7 @@ class TestGoogleUserContextAggregator(


 class TestGoogleAssistantContextAggregator(
-    BaseTestAssistantContextAggreagator, unittest.IsolatedAsyncioTestCase
+    BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
 ):
    CONTEXT_CLASS = GoogleLLMContext
    AGGREGATOR_CLASS = GoogleAssistantContextAggregator
@@ -948,8 +956,27 @@ class TestOpenAIUserContextAggregator(


 class TestOpenAIAssistantContextAggregator(
-    BaseTestAssistantContextAggreagator, unittest.IsolatedAsyncioTestCase
+    BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
 ):
    CONTEXT_CLASS = OpenAILLMContext
    AGGREGATOR_CLASS = OpenAIAssistantContextAggregator
    EXPECTED_CONTEXT_FRAMES = [OpenAILLMContextFrame, OpenAILLMContextAssistantTimestampFrame]
+
+
+#
+# Universal
+#
+class TestLLMAssistantAggregator(
+    BaseTestAssistantContextAggregator, unittest.IsolatedAsyncioTestCase
+):
+    CONTEXT_CLASS = OpenAILLMContext
+    AGGREGATOR_CLASS = LLMAssistantAggregator
+    EXPECTED_CONTEXT_FRAMES = [LLMContextFrame, LLMContextAssistantTimestampFrame]
+
+    # Override to remove 'expect_stripped_words' parameter, which is deprecated
+    # for LLMAssistantAggregator
+    def create_assistant_aggregator_params(
+        self, **kwargs
+    ) -> Optional[LLMAssistantAggregatorParams]:
+        kwargs.pop("expect_stripped_words", None)
+        return LLMAssistantAggregatorParams(**kwargs) if kwargs else None
--- a/tests/test_langchain.py
+++ b/tests/test_langchain.py
@@ -65,9 +65,7 @@ class TestLangchain(unittest.IsolatedAsyncioTestCase):
        self.mock_proc = self.MockProcessor("token_collector")

        context = LLMContext()
-        context_aggregator = LLMContextAggregatorPair(
-            context, assistant_params=LLMAssistantAggregatorParams(expect_stripped_words=False)
-        )
+        context_aggregator = LLMContextAggregatorPair(context)

        pipeline = Pipeline(
            [context_aggregator.user(), proc, self.mock_proc, context_aggregator.assistant()]