Files
crewAI/lib/crewai/tests/utilities/test_events.py
Lorenze Jay d1343b96ed Release/v1.0.0 (#3618)
* feat: add `apps` & `actions` attributes to Agent (#3504)

* feat: add app attributes to Agent

* feat: add actions attribute to Agent

* chore: resolve linter issues

* refactor: merge the apps and actions parameters into a single one

* fix: remove unnecessary print

* feat: logging error when CrewaiPlatformTools fails

* chore: export CrewaiPlatformTools directly from crewai_tools

* style: resolver linter issues

* test: fix broken tests

* style: solve linter issues

* fix: fix broken test

* feat: monorepo restructure and test/ci updates

- Add crewai workspace member
- Fix vcr cassette paths and restore test dirs
- Resolve ci failures and update linter/pytest rules

* chore: update python version to 3.13 and package metadata

* feat: add crewai-tools workspace and fix tests/dependencies

* feat: add crewai-tools workspace structure

* Squashed 'temp-crewai-tools/' content from commit 9bae5633

git-subtree-dir: temp-crewai-tools
git-subtree-split: 9bae56339096cb70f03873e600192bd2cd207ac9

* feat: configure crewai-tools workspace package with dependencies

* fix: apply ruff auto-formatting to crewai-tools code

* chore: update lockfile

* fix: don't allow tool tests yet

* fix: comment out extra pytest flags for now

* fix: remove conflicting conftest.py from crewai-tools tests

* fix: resolve dependency conflicts and test issues

- Pin vcrpy to 7.0.0 to fix pytest-recording compatibility
- Comment out types-requests to resolve urllib3 conflict
- Update requests requirement in crewai-tools to >=2.32.0

* chore: update CI workflows and docs for monorepo structure

* chore: update CI workflows and docs for monorepo structure

* fix: actions syntax

* chore: ci publish and pin versions

* fix: add permission to action

* chore: bump version to 1.0.0a1 across all packages

- Updated version to 1.0.0a1 in pyproject.toml for crewai and crewai-tools
- Adjusted version in __init__.py files for consistency

* WIP: v1 docs (#3626)

(cherry picked from commit d46e20fa09bcd2f5916282f5553ddeb7183bd92c)

* docs: parity for all translations

* docs: full name of acronym AMP

* docs: fix lingering unused code

* docs: expand contextual options in docs.json

* docs: add contextual action to request feature on GitHub (#3635)

* chore: apply linting fixes to crewai-tools

* feat: add required env var validation for brightdata

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* fix: handle properly anyOf oneOf allOf schema's props

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: bump version to 1.0.0a2

* Lorenze/native inference sdks (#3619)

* ruff linted

* using native sdks with litellm fallback

* drop exa

* drop print on completion

* Refactor LLM and utility functions for type consistency

- Updated `max_tokens` parameter in `LLM` class to accept `float` in addition to `int`.
- Modified `create_llm` function to ensure consistent type hints and return types, now returning `LLM | BaseLLM | None`.
- Adjusted type hints for various parameters in `create_llm` and `_llm_via_environment_or_fallback` functions for improved clarity and type safety.
- Enhanced test cases to reflect changes in type handling and ensure proper instantiation of LLM instances.

* fix agent_tests

* fix litellm tests and usagemetrics fix

* drop print

* Refactor LLM event handling and improve test coverage

- Removed commented-out event emission for LLM call failures in `llm.py`.
- Added `from_agent` parameter to `CrewAgentExecutor` for better context in LLM responses.
- Enhanced test for LLM call failure to simulate OpenAI API failure and updated assertions for clarity.
- Updated agent and task ID assertions in tests to ensure they are consistently treated as strings.

* fix test_converter

* fixed tests/agents/test_agent.py

* Refactor LLM context length exception handling and improve provider integration

- Renamed `LLMContextLengthExceededException` to `LLMContextLengthExceededExceptionError` for clarity and consistency.
- Updated LLM class to pass the provider parameter correctly during initialization.
- Enhanced error handling in various LLM provider implementations to raise the new exception type.
- Adjusted tests to reflect the updated exception name and ensure proper error handling in context length scenarios.

* Enhance LLM context window handling across providers

- Introduced CONTEXT_WINDOW_USAGE_RATIO to adjust context window sizes dynamically for Anthropic, Azure, Gemini, and OpenAI LLMs.
- Added validation for context window sizes in Azure and Gemini providers to ensure they fall within acceptable limits.
- Updated context window size calculations to use the new ratio, improving consistency and adaptability across different models.
- Removed hardcoded context window sizes in favor of ratio-based calculations for better flexibility.

* fix test agent again

* fix test agent

* feat: add native LLM providers for Anthropic, Azure, and Gemini

- Introduced new completion implementations for Anthropic, Azure, and Gemini, integrating their respective SDKs.
- Added utility functions for tool validation and extraction to support function calling across LLM providers.
- Enhanced context window management and token usage extraction for each provider.
- Created a common utility module for shared functionality among LLM providers.

* chore: update dependencies and improve context management

- Removed direct dependency on `litellm` from the main dependencies and added it under extras for better modularity.
- Updated the `litellm` dependency specification to allow for greater flexibility in versioning.
- Refactored context length exception handling across various LLM providers to use a consistent error class.
- Enhanced platform-specific dependency markers for NVIDIA packages to ensure compatibility across different systems.

* refactor(tests): update LLM instantiation to include is_litellm flag in test cases

- Modified multiple test cases in test_llm.py to set the is_litellm parameter to True when instantiating the LLM class.
- This change ensures that the tests are aligned with the latest LLM configuration requirements and improves consistency across test scenarios.
- Adjusted relevant assertions and comments to reflect the updated LLM behavior.

* linter

* linted

* revert constants

* fix(tests): correct type hint in expected model description

- Updated the expected description in the test_generate_model_description_dict_field function to use 'Dict' instead of 'dict' for consistency with type hinting conventions.
- This change ensures that the test accurately reflects the expected output format for model descriptions.

* refactor(llm): enhance LLM instantiation and error handling

- Updated the LLM class to include validation for the model parameter, ensuring it is a non-empty string.
- Improved error handling by logging warnings when the native SDK fails, allowing for a fallback to LiteLLM.
- Adjusted the instantiation of LLM in test cases to consistently include the is_litellm flag, aligning with recent changes in LLM configuration.
- Modified relevant tests to reflect these updates, ensuring better coverage and accuracy in testing scenarios.

* fixed test

* refactor(llm): enhance token usage tracking and add copy methods

- Updated the LLM class to track token usage and log callbacks in streaming mode, improving monitoring capabilities.
- Introduced shallow and deep copy methods for the LLM instance, allowing for better management of LLM configurations and parameters.
- Adjusted test cases to instantiate LLM with the is_litellm flag, ensuring alignment with recent changes in LLM configuration.

* refactor(tests): reorganize imports and enhance error messages in test cases

- Cleaned up import statements in test_crew.py for better organization and readability.
- Enhanced error messages in test cases to use `re.escape` for improved regex matching, ensuring more robust error handling.
- Adjusted comments for clarity and consistency across test scenarios.
- Ensured that all necessary modules are imported correctly to avoid potential runtime issues.

* feat: add base devtooling

* fix: ensure dep refs are updated for devtools

* fix: allow pre-release

* feat: allow release after tag

* feat: bump versions to 1.0.0a3 

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: match tag and release title, ignore devtools build for pypi

* fix: allow failed pypi publish

* feat: introduce trigger listing and execution commands for local development (#3643)

* chore: exclude tests from ruff linting

* chore: exclude tests from GitHub Actions linter

* fix: replace print statements with logger in agent and memory handling

* chore: add noqa for intentional print in printer utility

* fix: resolve linting errors across codebase

* feat: update docs with new approach to consume Platform Actions (#3675)

* fix: remove duplicate line and add explicit env var

* feat: bump versions to 1.0.0a4 (#3686)

* Update triggers docs (#3678)

* docs: introduce triggers list & triggers run command

* docs: add KO triggers docs

* docs: ensure CREWAI_PLATFORM_INTEGRATION_TOKEN is mentioned on docs (#3687)

* Lorenze/bedrock llm (#3693)

* feat: add AWS Bedrock support and update dependencies

- Introduced BedrockCompletion class for AWS Bedrock integration in LLM.
- Added boto3 as a new dependency in both pyproject.toml and uv.lock.
- Updated LLM class to support Bedrock provider.
- Created new files for Bedrock provider implementation.

* using converse api

* converse

* linted

* refactor: update BedrockCompletion class to improve parameter handling

- Changed max_tokens from a fixed integer to an optional integer.
- Simplified model ID assignment by removing the inference profile mapping method.
- Cleaned up comments and unnecessary code related to tool specifications and model-specific parameters.

* feat: improve event bus thread safety and async support

Add thread-safe, async-compatible event bus with read–write locking and
handler dependency ordering. Remove blinker dependency and implement
direct dispatch. Improve type safety, error handling, and deterministic
event synchronization.

Refactor tests to auto-wait for async handlers, ensure clean teardown,
and add comprehensive concurrency coverage. Replace thread-local state
in AgentEvaluator with instance-based locking for correct cross-thread
access. Enhance tracing reliability and event finalization.

* feat: enhance OpenAICompletion class with additional client parameters (#3701)

* feat: enhance OpenAICompletion class with additional client parameters

- Added support for default_headers, default_query, and client_params in the OpenAICompletion class.
- Refactored client initialization to use a dedicated method for client parameter retrieval.
- Introduced new test cases to validate the correct usage of OpenAICompletion with various parameters.

* fix: correct test case for unsupported OpenAI model

- Updated the test_openai.py to ensure that the LLM instance is created before calling the method, maintaining proper error handling for unsupported models.
- This change ensures that the test accurately checks for the NotFoundError when an invalid model is specified.

* fix: enhance error handling in OpenAICompletion class

- Added specific exception handling for NotFoundError and APIConnectionError in the OpenAICompletion class to provide clearer error messages and improve logging.
- Updated the test case for unsupported models to ensure it raises a ValueError with the appropriate message when a non-existent model is specified.
- This change improves the robustness of the OpenAI API integration and enhances the clarity of error reporting.

* fix: improve test for unsupported OpenAI model handling

- Refactored the test case in test_openai.py to create the LLM instance after mocking the OpenAI client, ensuring proper error handling for unsupported models.
- This change enhances the clarity of the test by accurately checking for ValueError when a non-existent model is specified, aligning with recent improvements in error handling for the OpenAICompletion class.

* feat: bump versions to 1.0.0b1 (#3706)

* Lorenze/tools drop litellm (#3710)

* completely drop litellm and correctly pass config for qdrant

* feat: add support for additional embedding models in EmbeddingService

- Expanded the list of supported embedding models to include Google Vertex, Hugging Face, Jina, Ollama, OpenAI, Roboflow, Watson X, custom embeddings, Sentence Transformers, Text2Vec, OpenClip, and Instructor.
- This enhancement improves the versatility of the EmbeddingService by allowing integration with a wider range of embedding providers.

* fix: update collection parameter handling in CrewAIRagAdapter

- Changed the condition for setting vectors_config in the CrewAIRagAdapter to check for QdrantConfig instance instead of using hasattr. This improves type safety and ensures proper configuration handling for Qdrant integration.

* moved stagehand as optional dep (#3712)

* feat: bump versions to 1.0.0b2 (#3713)

* feat: enhance AnthropicCompletion class with additional client parame… (#3707)

* feat: enhance AnthropicCompletion class with additional client parameters and tool handling

- Added support for client_params in the AnthropicCompletion class to allow for additional client configuration.
- Refactored client initialization to use a dedicated method for retrieving client parameters.
- Implemented a new method to handle tool use conversation flow, ensuring proper execution and response handling.
- Introduced comprehensive test cases to validate the functionality of the AnthropicCompletion class, including tool use scenarios and parameter handling.

* drop print statements

* test: add fixture to mock ANTHROPIC_API_KEY for tests

- Introduced a pytest fixture to automatically mock the ANTHROPIC_API_KEY environment variable for all tests in the test_anthropic.py module.
- This change ensures that tests can run without requiring a real API key, improving test isolation and reliability.

* refactor: streamline streaming message handling in AnthropicCompletion class

- Removed the 'stream' parameter from the API call as it is set internally by the SDK.
- Simplified the handling of tool use events and response construction by extracting token usage from the final message.
- Enhanced the flow for managing tool use conversation, ensuring proper integration with the streaming API response.

* fix streaming here too

* fix: improve error handling in tool conversion for AnthropicCompletion class

- Enhanced exception handling during tool conversion by catching KeyError and ValueError.
- Added logging for conversion errors to aid in debugging and maintain robustness in tool integration.

* feat: enhance GeminiCompletion class with client parameter support (#3717)

* feat: enhance GeminiCompletion class with client parameter support

- Added support for client_params in the GeminiCompletion class to allow for additional client configuration.
- Refactored client initialization into a dedicated method for improved parameter handling.
- Introduced a new method to retrieve client parameters, ensuring compatibility with the base class.
- Enhanced error handling during client initialization to provide clearer messages for missing configuration.
- Updated documentation to reflect the changes in client parameter usage.

* add optional dependancies

* refactor: update test fixture to mock GOOGLE_API_KEY

- Renamed the fixture from `mock_anthropic_api_key` to `mock_google_api_key` to reflect the change in the environment variable being mocked.
- This update ensures that all tests in the module can run with a mocked GOOGLE_API_KEY, improving test isolation and reliability.

* fix tests

* feat: enhance BedrockCompletion class with advanced features

* feat: enhance BedrockCompletion class with advanced features and error handling

- Added support for guardrail configuration, additional model request fields, and custom response field paths in the BedrockCompletion class.
- Improved error handling for AWS exceptions and added token usage tracking with stop reason logging.
- Enhanced streaming response handling with comprehensive event management, including tool use and content block processing.
- Updated documentation to reflect new features and initialization parameters.
- Introduced a new test suite for BedrockCompletion to validate functionality and ensure robust integration with AWS Bedrock APIs.

* chore: add boto typing

* fix: use typing_extensions.Required for Python 3.10 compatibility

---------

Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: azure native tests

* feat: add Azure AI Inference support and related tests

- Introduced the `azure-ai-inference` package with version `1.0.0b9` and its dependencies in `uv.lock` and `pyproject.toml`.
- Added new test files for Azure LLM functionality, including tests for Azure completion and tool handling.
- Implemented comprehensive test cases to validate Azure-specific behavior and integration with the CrewAI framework.
- Enhanced the testing framework to mock Azure credentials and ensure proper isolation during tests.

* feat: enhance AzureCompletion class with Azure OpenAI support

- Added support for the Azure OpenAI endpoint in the AzureCompletion class, allowing for flexible endpoint configurations.
- Implemented endpoint validation and correction to ensure proper URL formats for Azure OpenAI deployments.
- Enhanced error handling to provide clearer messages for common HTTP errors, including authentication and rate limit issues.
- Updated tests to validate the new endpoint handling and error messaging, ensuring robust integration with Azure AI Inference.
- Refactored parameter preparation to conditionally include the model parameter based on the endpoint type.

* refactor: convert project module to metaclass with full typing

* Lorenze/OpenAI base url backwards support (#3723)

* fix: enhance OpenAICompletion class base URL handling

- Updated the base URL assignment in the OpenAICompletion class to prioritize the new `api_base` attribute and fallback to the environment variable `OPENAI_BASE_URL` if both are not set.
- Added `api_base` to the list of parameters in the OpenAICompletion class to ensure proper configuration and flexibility in API endpoint management.

* feat: enhance OpenAICompletion class with api_base support

- Added the `api_base` parameter to the OpenAICompletion class to allow for flexible API endpoint configuration.
- Updated the `_get_client_params` method to prioritize `base_url` over `api_base`, ensuring correct URL handling.
- Introduced comprehensive tests to validate the behavior of `api_base` and `base_url` in various scenarios, including environment variable fallback.
- Enhanced test coverage for client parameter retrieval, ensuring robust integration with the OpenAI API.

* fix: improve OpenAICompletion class configuration handling

- Added a debug print statement to log the client configuration parameters during initialization for better traceability.
- Updated the base URL assignment logic to ensure it defaults to None if no valid base URL is provided, enhancing robustness in API endpoint configuration.
- Refined the retrieval of the `api_base` environment variable to streamline the configuration process.

* drop print

* feat: improvements on import native sdk support (#3725)

* feat: add support for Anthropic provider and enhance logging

- Introduced the `anthropic` package with version `0.69.0` in `pyproject.toml` and `uv.lock`, allowing for integration with the Anthropic API.
- Updated logging in the LLM class to provide clearer error messages when importing native providers, enhancing debugging capabilities.
- Improved error handling in the AnthropicCompletion class to guide users on installation via the updated error message format.
- Refactored import error handling in other provider classes to maintain consistency in error messaging and installation instructions.

* feat: enhance LLM support with Bedrock provider and update dependencies

- Added support for the `bedrock` provider in the LLM class, allowing integration with AWS Bedrock APIs.
- Updated `uv.lock` to replace `boto3` with `bedrock` in the dependencies, reflecting the new provider structure.
- Introduced `SUPPORTED_NATIVE_PROVIDERS` to include `bedrock` and ensure proper error handling when instantiating native providers.
- Enhanced error handling in the LLM class to raise informative errors when native provider instantiation fails.
- Added tests to validate the behavior of the new Bedrock provider and ensure fallback mechanisms work correctly for unsupported providers.

* test: update native provider fallback tests to expect ImportError

* adjust the test with the expected bevaior - raising ImportError

* this is exoecting the litellm format, all gemini native tests are in test_google.py

---------

Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>

* fix: remove stdout prints, improve test determinism, and update trace handling

Removed `print` statements from the `LLMStreamChunkEvent` handler to prevent
LLM response chunks from being written directly to stdout. The listener now
only tracks chunks internally.

Fixes #3715

Added explicit return statements for trace-related tests.

Updated cassette for `test_failed_evaluation` to reflect new behavior where
an empty trace dict is used instead of returning early.

Ensured deterministic cleanup order in test fixtures by making
`clear_event_bus_handlers` depend on `setup_test_environment`. This guarantees
event bus shutdown and file handle cleanup occur before temporary directory
deletion, resolving intermittent “Directory not empty” errors in CI.

* chore: remove lib/crewai exclusion from pre-commit hooks

* feat: enhance task guardrail functionality and validation

* feat: enhance task guardrail functionality and validation

- Introduced support for multiple guardrails in the Task class, allowing for sequential processing of guardrails.
- Added a new `guardrails` field to the Task model to accept a list of callable guardrails or string descriptions.
- Implemented validation to ensure guardrails are processed correctly, including handling of retries and error messages.
- Enhanced the `_invoke_guardrail_function` method to manage guardrail execution and integrate with existing task output processing.
- Updated tests to cover various scenarios involving multiple guardrails, including success, failure, and retry mechanisms.

This update improves the flexibility and robustness of task execution by allowing for more complex validation scenarios.

* refactor: enhance guardrail type handling in Task model

- Updated the Task class to improve guardrail type definitions, introducing GuardrailType and GuardrailsType for better clarity and type safety.
- Simplified the validation logic for guardrails, ensuring that both single and multiple guardrails are processed correctly.
- Enhanced error messages for guardrail validation to provide clearer feedback when incorrect types are provided.
- This refactor improves the maintainability and robustness of task execution by standardizing guardrail handling.

* feat: implement per-guardrail retry tracking in Task model

- Introduced a new private attribute `_guardrail_retry_counts` to the Task class for tracking retry attempts on a per-guardrail basis.
- Updated the guardrail processing logic to utilize the new retry tracking, allowing for independent retry counts for each guardrail.
- Enhanced error handling to provide clearer feedback when guardrails fail validation after exceeding retry limits.
- Modified existing tests to validate the new retry tracking behavior, ensuring accurate assertions on guardrail retries.

This update improves the robustness and flexibility of task execution by allowing for more granular control over guardrail validation and retry mechanisms.

* chore: 1.0.0b3 bump (#3734)

* chore: full ruff and mypy

improved linting, pre-commit setup, and internal architecture. Configured Ruff to respect .gitignore, added stricter rules, and introduced a lock pre-commit hook with virtualenv activation. Fixed type shadowing in EXASearchTool using a type_ alias to avoid PEP 563 conflicts and resolved circular imports in agent executor and guardrail modules. Removed agent-ops attributes, deprecated watson alias, and dropped crewai-enterprise tools with corresponding test updates. Refactored cache and memoization for thread safety and cleaned up structured output adapters and related logic.

* New MCL DSL (#3738)

* Adding MCP implementation

* New tests for MCP implementation

* fix tests

* update docs

* Revert "New tests for MCP implementation"

This reverts commit 0bbe6dee90.

* linter

* linter

* fix

* verify mcp pacakge exists

* adjust docs to be clear only remote servers are supported

* reverted

* ensure args schema generated properly

* properly close out

---------

Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>
Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>

* feat: a2a experimental

experimental a2a support

---------

Co-authored-by: Lucas Gomide <lucaslg200@gmail.com>
Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>
Co-authored-by: Tony Kipkemboi <iamtonykipkemboi@gmail.com>
Co-authored-by: Mike Plachta <mplachta@users.noreply.github.com>
Co-authored-by: João Moura <joaomdmoura@gmail.com>
2025-10-20 14:10:19 -07:00

1107 lines
36 KiB
Python

import threading
from datetime import datetime
import os
from unittest.mock import Mock, patch
from crewai.agent import Agent
from crewai.agents.crew_agent_executor import CrewAgentExecutor
from crewai.crew import Crew
from crewai.events.event_bus import crewai_event_bus
from crewai.events.event_listener import EventListener
from crewai.events.types.agent_events import (
AgentExecutionCompletedEvent,
AgentExecutionErrorEvent,
AgentExecutionStartedEvent,
)
from crewai.events.types.crew_events import (
CrewKickoffCompletedEvent,
CrewKickoffFailedEvent,
CrewKickoffStartedEvent,
CrewTestCompletedEvent,
CrewTestResultEvent,
CrewTestStartedEvent,
)
from crewai.events.types.flow_events import (
FlowCreatedEvent,
FlowFinishedEvent,
FlowStartedEvent,
MethodExecutionFailedEvent,
MethodExecutionStartedEvent,
)
from crewai.events.types.llm_events import (
LLMCallCompletedEvent,
LLMCallFailedEvent,
LLMCallStartedEvent,
LLMStreamChunkEvent,
)
from crewai.events.types.task_events import (
TaskCompletedEvent,
TaskFailedEvent,
TaskStartedEvent,
)
from crewai.events.types.tool_usage_events import (
ToolUsageErrorEvent,
ToolUsageFinishedEvent,
)
from crewai.flow.flow import Flow, listen, start
from crewai.llm import LLM
from crewai.task import Task
from crewai.tools.base_tool import BaseTool
from pydantic import Field
import pytest
from ..utils import wait_for_event_handlers
@pytest.fixture(scope="module")
def vcr_config(request) -> dict:
return {
"cassette_library_dir": os.path.join(os.path.dirname(__file__), "cassettes"),
}
@pytest.fixture(scope="module")
def base_agent():
return Agent(
role="base_agent",
llm="gpt-4o-mini",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
@pytest.fixture(scope="module")
def base_task(base_agent):
return Task(
description="Just say hi",
expected_output="hi",
agent=base_agent,
)
@pytest.fixture
def reset_event_listener_singleton():
"""Reset EventListener singleton for clean test state."""
original_instance = EventListener._instance
original_initialized = (
getattr(EventListener._instance, "_initialized", False)
if EventListener._instance
else False
)
EventListener._instance = None
yield
EventListener._instance = original_instance
if original_instance and original_initialized:
EventListener._instance._initialized = original_initialized
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_start_kickoff_event(
base_agent, base_task, reset_event_listener_singleton
):
received_events = []
mock_span = Mock()
@crewai_event_bus.on(CrewKickoffStartedEvent)
def handle_crew_start(source, event):
received_events.append(event)
mock_telemetry = Mock()
mock_telemetry.crew_execution_span = Mock(return_value=mock_span)
mock_telemetry.end_crew = Mock(return_value=mock_span)
mock_telemetry.set_tracer = Mock()
mock_telemetry.task_started = Mock(return_value=mock_span)
mock_telemetry.task_ended = Mock(return_value=mock_span)
# Patch the Telemetry class to return our mock
with patch("crewai.events.event_listener.Telemetry", return_value=mock_telemetry):
# Now when Crew creates EventListener, it will use our mocked telemetry
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
wait_for_event_handlers()
mock_telemetry.crew_execution_span.assert_called_once_with(crew, None)
mock_telemetry.end_crew.assert_called_once_with(crew, "hi")
assert len(received_events) == 1
assert received_events[0].crew_name == "TestCrew"
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_end_kickoff_event(base_agent, base_task):
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(CrewKickoffCompletedEvent)
def handle_crew_end(source, event):
received_events.append(event)
event_received.set()
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert event_received.wait(timeout=5), (
"Timeout waiting for crew kickoff completed event"
)
assert len(received_events) == 1
assert received_events[0].crew_name == "TestCrew"
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_test_kickoff_type_event(base_agent, base_task):
received_events = []
@crewai_event_bus.on(CrewTestStartedEvent)
def handle_crew_end(source, event):
received_events.append(event)
@crewai_event_bus.on(CrewTestCompletedEvent)
def handle_crew_test_end(source, event):
received_events.append(event)
@crewai_event_bus.on(CrewTestResultEvent)
def handle_crew_test_result(source, event):
received_events.append(event)
eval_llm = LLM(model="gpt-4o-mini")
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.test(n_iterations=1, eval_llm=eval_llm)
wait_for_event_handlers()
assert len(received_events) == 3
assert received_events[0].crew_name == "TestCrew"
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_test_started"
assert received_events[1].crew_name == "TestCrew"
assert isinstance(received_events[1].timestamp, datetime)
assert received_events[1].type == "crew_test_result"
assert received_events[2].crew_name == "TestCrew"
assert isinstance(received_events[2].timestamp, datetime)
assert received_events[2].type == "crew_test_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_kickoff_failed_event(base_agent, base_task):
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(CrewKickoffFailedEvent)
def handle_crew_failed(source, event):
received_events.append(event)
event_received.set()
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
with patch.object(Crew, "_execute_tasks") as mock_execute:
error_message = "Simulated crew kickoff failure"
mock_execute.side_effect = Exception(error_message)
with pytest.raises(Exception): # noqa: B017
crew.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for failed event"
assert len(received_events) == 1
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_failed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_start_task_event(base_agent, base_task):
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(TaskStartedEvent)
def handle_task_start(source, event):
received_events.append(event)
event_received.set()
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for task started event"
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_crew_emits_end_task_event(
base_agent, base_task, reset_event_listener_singleton
):
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(TaskCompletedEvent)
def handle_task_end(source, event):
received_events.append(event)
event_received.set()
mock_span = Mock()
mock_telemetry = Mock()
mock_telemetry.task_started = Mock(return_value=mock_span)
mock_telemetry.task_ended = Mock(return_value=mock_span)
mock_telemetry.set_tracer = Mock()
mock_telemetry.crew_execution_span = Mock()
mock_telemetry.end_crew = Mock()
with patch("crewai.events.event_listener.Telemetry", return_value=mock_telemetry):
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
mock_telemetry.task_started.assert_called_once_with(crew=crew, task=base_task)
mock_telemetry.task_ended.assert_called_once_with(mock_span, base_task, crew)
assert event_received.wait(timeout=5), "Timeout waiting for task completed event"
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_task_emits_failed_event_on_execution_error(base_agent, base_task):
received_events = []
received_sources = []
event_received = threading.Event()
@crewai_event_bus.on(TaskFailedEvent)
def handle_task_failed(source, event):
received_events.append(event)
received_sources.append(source)
event_received.set()
with patch.object(
Task,
"_execute_core",
) as mock_execute:
error_message = "Simulated task failure"
mock_execute.side_effect = Exception(error_message)
agent = Agent(
role="base_agent",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
task = Task(
description="Just say hi",
expected_output="hi",
agent=agent,
)
with pytest.raises(Exception): # noqa: B017
agent.execute_task(task=task)
assert event_received.wait(timeout=5), (
"Timeout waiting for task failed event"
)
assert len(received_events) == 1
assert received_sources[0] == task
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "task_failed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_emits_execution_started_and_completed_events(base_agent, base_task):
received_events = []
lock = threading.Lock()
all_events_received = threading.Event()
@crewai_event_bus.on(AgentExecutionStartedEvent)
def handle_agent_start(source, event):
with lock:
received_events.append(event)
@crewai_event_bus.on(AgentExecutionCompletedEvent)
def handle_agent_completed(source, event):
with lock:
received_events.append(event)
if len(received_events) >= 2:
all_events_received.set()
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert all_events_received.wait(timeout=5), (
"Timeout waiting for agent execution events"
)
assert len(received_events) == 2
assert received_events[0].agent == base_agent
assert received_events[0].task == base_task
assert received_events[0].tools == []
assert isinstance(received_events[0].task_prompt, str)
assert (
received_events[0].task_prompt
== "Just say hi\n\nThis is the expected criteria for your final answer: hi\nyou MUST return the actual complete content as the final answer, not a summary."
)
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "agent_execution_started"
assert isinstance(received_events[1].timestamp, datetime)
assert received_events[1].type == "agent_execution_completed"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_agent_emits_execution_error_event(base_agent, base_task):
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(AgentExecutionErrorEvent)
def handle_agent_start(source, event):
received_events.append(event)
event_received.set()
error_message = "Error happening while sending prompt to model."
base_agent.max_retry_limit = 0
with patch.object(
CrewAgentExecutor, "invoke", wraps=base_agent.agent_executor.invoke
) as invoke_mock:
invoke_mock.side_effect = Exception(error_message)
with pytest.raises(Exception): # noqa: B017
base_agent.execute_task(
task=base_task,
)
assert event_received.wait(timeout=5), (
"Timeout waiting for agent execution error event"
)
assert len(received_events) == 1
assert received_events[0].agent == base_agent
assert received_events[0].task == base_task
assert received_events[0].error == error_message
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "agent_execution_error"
class SayHiTool(BaseTool):
name: str = Field(default="say_hi", description="The name of the tool")
description: str = Field(
default="Say hi", description="The description of the tool"
)
def _run(self) -> str:
return "hi"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tools_emits_finished_events():
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(ToolUsageFinishedEvent)
def handle_tool_end(source, event):
received_events.append(event)
event_received.set()
agent = Agent(
role="base_agent",
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
tools=[SayHiTool()],
)
task = Task(
description="Just say hi",
expected_output="hi",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
crew.kickoff()
assert event_received.wait(timeout=5), (
"Timeout waiting for tool usage finished event"
)
assert len(received_events) == 1
assert received_events[0].agent_key == agent.key
assert received_events[0].agent_role == agent.role
assert received_events[0].tool_name == SayHiTool().name
assert received_events[0].tool_args == "{}" or received_events[0].tool_args == {}
assert received_events[0].type == "tool_usage_finished"
assert isinstance(received_events[0].timestamp, datetime)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_tools_emits_error_events():
received_events = []
lock = threading.Lock()
all_events_received = threading.Event()
@crewai_event_bus.on(ToolUsageErrorEvent)
def handle_tool_end(source, event):
with lock:
received_events.append(event)
if len(received_events) >= 48:
all_events_received.set()
class ErrorTool(BaseTool):
name: str = Field(
default="error_tool", description="A tool that raises an error"
)
description: str = Field(
default="This tool always raises an error",
description="The description of the tool",
)
def _run(self) -> str:
raise Exception("Simulated tool error")
agent = Agent(
role="base_agent",
goal="Try to use the error tool",
backstory="You are an assistant that tests error handling",
tools=[ErrorTool()],
llm=LLM(model="gpt-4o-mini"),
)
task = Task(
description="Use the error tool",
expected_output="This should error",
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task], name="TestCrew")
crew.kickoff()
assert all_events_received.wait(timeout=5), (
"Timeout waiting for tool usage error events"
)
assert len(received_events) == 48
assert received_events[0].agent_key == agent.key
assert received_events[0].agent_role == agent.role
assert received_events[0].tool_name == "error_tool"
assert received_events[0].tool_args == "{}" or received_events[0].tool_args == {}
assert str(received_events[0].error) == "Simulated tool error"
assert received_events[0].type == "tool_usage_error"
assert isinstance(received_events[0].timestamp, datetime)
def test_flow_emits_start_event(reset_event_listener_singleton):
received_events = []
event_received = threading.Event()
mock_span = Mock()
@crewai_event_bus.on(FlowStartedEvent)
def handle_flow_start(source, event):
received_events.append(event)
event_received.set()
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
mock_telemetry = Mock()
mock_telemetry.flow_execution_span = Mock(return_value=mock_span)
mock_telemetry.flow_creation_span = Mock()
mock_telemetry.set_tracer = Mock()
with patch("crewai.events.event_listener.Telemetry", return_value=mock_telemetry):
# Force creation of EventListener singleton with mocked telemetry
_ = EventListener()
flow = TestFlow()
flow.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for flow started event"
mock_telemetry.flow_execution_span.assert_called_once_with("TestFlow", ["begin"])
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_started"
def test_flow_name_emitted_to_event_bus():
received_events = []
event_received = threading.Event()
class MyFlowClass(Flow):
name = "PRODUCTION_FLOW"
@start()
def start(self):
return "Hello, world!"
@crewai_event_bus.on(FlowStartedEvent)
def handle_flow_start(source, event):
received_events.append(event)
event_received.set()
flow = MyFlowClass()
flow.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for flow started event"
assert len(received_events) == 1
assert received_events[0].flow_name == "PRODUCTION_FLOW"
def test_flow_emits_finish_event():
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(FlowFinishedEvent)
def handle_flow_finish(source, event):
received_events.append(event)
event_received.set()
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "completed"
flow = TestFlow()
result = flow.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for finish event"
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_finished"
assert received_events[0].result == "completed"
assert result == "completed"
def test_flow_emits_method_execution_started_event():
received_events = []
lock = threading.Lock()
second_event_received = threading.Event()
@crewai_event_bus.on(MethodExecutionStartedEvent)
async def handle_method_start(source, event):
with lock:
received_events.append(event)
if event.method_name == "second_method":
second_event_received.set()
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
@listen("begin")
def second_method(self):
return "executed"
flow = TestFlow()
flow.kickoff()
assert second_event_received.wait(timeout=5), (
"Timeout waiting for second_method event"
)
assert len(received_events) == 2
# Events may arrive in any order due to async handlers, so check both are present
method_names = {event.method_name for event in received_events}
assert method_names == {"begin", "second_method"}
for event in received_events:
assert event.flow_name == "TestFlow"
assert event.type == "method_execution_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_register_handler_adds_new_handler(base_agent, base_task):
received_events = []
event_received = threading.Event()
def custom_handler(source, event):
received_events.append(event)
event_received.set()
crewai_event_bus.register_handler(CrewKickoffStartedEvent, custom_handler)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for handler event"
assert len(received_events) == 1
assert isinstance(received_events[0].timestamp, datetime)
assert received_events[0].type == "crew_kickoff_started"
@pytest.mark.vcr(filter_headers=["authorization"])
def test_multiple_handlers_for_same_event(base_agent, base_task):
received_events_1 = []
received_events_2 = []
event_received = threading.Event()
def handler_1(source, event):
received_events_1.append(event)
def handler_2(source, event):
received_events_2.append(event)
event_received.set()
crewai_event_bus.register_handler(CrewKickoffStartedEvent, handler_1)
crewai_event_bus.register_handler(CrewKickoffStartedEvent, handler_2)
crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
crew.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for handler events"
assert len(received_events_1) == 1
assert len(received_events_2) == 1
assert received_events_1[0].type == "crew_kickoff_started"
assert received_events_2[0].type == "crew_kickoff_started"
def test_flow_emits_created_event():
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(FlowCreatedEvent)
def handle_flow_created(source, event):
received_events.append(event)
event_received.set()
class TestFlow(Flow[dict]):
@start()
def begin(self):
return "started"
flow = TestFlow()
flow.kickoff()
assert event_received.wait(timeout=5), "Timeout waiting for flow created event"
assert len(received_events) == 1
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "flow_created"
def test_flow_emits_method_execution_failed_event():
received_events = []
event_received = threading.Event()
error = Exception("Simulated method failure")
@crewai_event_bus.on(MethodExecutionFailedEvent)
def handle_method_failed(source, event):
received_events.append(event)
event_received.set()
class TestFlow(Flow[dict]):
@start()
def begin(self):
raise error
flow = TestFlow()
with pytest.raises(Exception): # noqa: B017
flow.kickoff()
assert event_received.wait(timeout=5), (
"Timeout waiting for method execution failed event"
)
assert len(received_events) == 1
assert received_events[0].method_name == "begin"
assert received_events[0].flow_name == "TestFlow"
assert received_events[0].type == "method_execution_failed"
assert received_events[0].error == error
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_emits_call_started_event():
received_events = []
@crewai_event_bus.on(LLMCallStartedEvent)
def handle_llm_call_started(source, event):
received_events.append(event)
@crewai_event_bus.on(LLMCallCompletedEvent)
def handle_llm_call_completed(source, event):
received_events.append(event)
llm = LLM(model="gpt-4o-mini")
llm.call("Hello, how are you?")
wait_for_event_handlers()
assert len(received_events) == 2
assert received_events[0].type == "llm_call_started"
assert received_events[1].type == "llm_call_completed"
assert received_events[0].task_name is None
assert received_events[0].agent_role is None
assert received_events[0].agent_id is None
assert received_events[0].task_id is None
@pytest.mark.vcr(filter_headers=["authorization"])
@pytest.mark.isolated
def test_llm_emits_call_failed_event():
received_events = []
event_received = threading.Event()
@crewai_event_bus.on(LLMCallFailedEvent)
def handle_llm_call_failed(source, event):
received_events.append(event)
event_received.set()
error_message = "OpenAI API call failed: Simulated API failure"
with patch(
"crewai.llms.providers.openai.completion.OpenAICompletion._handle_completion"
) as mock_handle_completion:
mock_handle_completion.side_effect = Exception("Simulated API failure")
llm = LLM(model="gpt-4o-mini")
with pytest.raises(Exception) as exc_info:
llm.call("Hello, how are you?")
assert str(exc_info.value) == "Simulated API failure"
assert event_received.wait(timeout=5), "Timeout waiting for failed event"
assert len(received_events) == 1
assert received_events[0].type == "llm_call_failed"
assert received_events[0].error == error_message
assert received_events[0].task_name is None
assert received_events[0].agent_role is None
assert received_events[0].agent_id is None
assert received_events[0].task_id is None
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_emits_stream_chunk_events():
"""Test that LLM emits stream chunk events when streaming is enabled."""
received_chunks = []
event_received = threading.Event()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_stream_chunk(source, event):
received_chunks.append(event.chunk)
if len(received_chunks) >= 1:
event_received.set()
# Create an LLM with streaming enabled
llm = LLM(model="gpt-4o", stream=True)
# Call the LLM with a simple message
response = llm.call("Tell me a short joke")
# Wait for at least one chunk
assert event_received.wait(timeout=5), "Timeout waiting for stream chunks"
# Verify that we received chunks
assert len(received_chunks) > 0
# Verify that concatenating all chunks equals the final response
assert "".join(received_chunks) == response
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_no_stream_chunks_when_streaming_disabled():
"""Test that LLM doesn't emit stream chunk events when streaming is disabled."""
received_chunks = []
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_stream_chunk(source, event):
received_chunks.append(event.chunk)
# Create an LLM with streaming disabled
llm = LLM(model="gpt-4o", stream=False)
# Call the LLM with a simple message
response = llm.call("Tell me a short joke")
# Verify that we didn't receive any chunks
assert len(received_chunks) == 0
# Verify we got a response
assert response and isinstance(response, str)
@pytest.mark.vcr(filter_headers=["authorization"])
def test_streaming_fallback_to_non_streaming():
"""Test that streaming falls back to non-streaming when there's an error."""
received_chunks = []
fallback_called = False
event_received = threading.Event()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_stream_chunk(source, event):
received_chunks.append(event.chunk)
if len(received_chunks) >= 2:
event_received.set()
# Create an LLM with streaming enabled
llm = LLM(model="gpt-4o", stream=True)
# Store original methods
original_call = llm.call
# Create a mock call method that handles the streaming error
def mock_call(messages, tools=None, callbacks=None, available_functions=None):
nonlocal fallback_called
# Emit a couple of chunks to simulate partial streaming
crewai_event_bus.emit(llm, event=LLMStreamChunkEvent(chunk="Test chunk 1"))
crewai_event_bus.emit(llm, event=LLMStreamChunkEvent(chunk="Test chunk 2"))
# Mark that fallback would be called
fallback_called = True
# Return a response as if fallback succeeded
return "Fallback response after streaming error"
# Replace the call method with our mock
llm.call = mock_call
try:
# Call the LLM
response = llm.call("Tell me a short joke")
wait_for_event_handlers()
assert event_received.wait(timeout=5), "Timeout waiting for stream chunks"
# Verify that we received some chunks
assert len(received_chunks) == 2
assert received_chunks[0] == "Test chunk 1"
assert received_chunks[1] == "Test chunk 2"
# Verify fallback was triggered
assert fallback_called
# Verify we got the fallback response
assert response == "Fallback response after streaming error"
finally:
# Restore the original method
llm.call = original_call
@pytest.mark.vcr(filter_headers=["authorization"])
def test_streaming_empty_response_handling():
"""Test that streaming handles empty responses correctly."""
received_chunks = []
event_received = threading.Event()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_stream_chunk(source, event):
received_chunks.append(event.chunk)
if len(received_chunks) >= 3:
event_received.set()
# Create an LLM with streaming enabled
llm = LLM(model="gpt-3.5-turbo", stream=True)
# Store original methods
original_call = llm.call
# Create a mock call method that simulates empty chunks
def mock_call(messages, tools=None, callbacks=None, available_functions=None):
# Emit a few empty chunks
for _ in range(3):
crewai_event_bus.emit(llm, event=LLMStreamChunkEvent(chunk=""))
# Return the default message for empty responses
return "I apologize, but I couldn't generate a proper response. Please try again or rephrase your request."
# Replace the call method with our mock
llm.call = mock_call
try:
# Call the LLM - this should handle empty response
response = llm.call("Tell me a short joke")
assert event_received.wait(timeout=5), "Timeout waiting for empty chunks"
# Verify that we received empty chunks
assert len(received_chunks) == 3
assert all(chunk == "" for chunk in received_chunks)
# Verify the response is the default message for empty responses
assert "I apologize" in response and "couldn't generate" in response
finally:
# Restore the original method
llm.call = original_call
@pytest.mark.vcr(filter_headers=["authorization"])
def test_stream_llm_emits_event_with_task_and_agent_info():
completed_event = []
failed_event = []
started_event = []
stream_event = []
event_received = threading.Event()
@crewai_event_bus.on(LLMCallFailedEvent)
def handle_llm_failed(source, event):
failed_event.append(event)
@crewai_event_bus.on(LLMCallStartedEvent)
def handle_llm_started(source, event):
started_event.append(event)
@crewai_event_bus.on(LLMCallCompletedEvent)
def handle_llm_completed(source, event):
completed_event.append(event)
if len(started_event) >= 1 and len(stream_event) >= 12:
event_received.set()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_llm_stream_chunk(source, event):
stream_event.append(event)
if (
len(completed_event) >= 1
and len(started_event) >= 1
and len(stream_event) >= 12
):
event_received.set()
agent = Agent(
role="TestAgent",
llm=LLM(model="gpt-4o-mini", stream=True),
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
task = Task(
description="Just say hi",
expected_output="hi",
llm=LLM(model="gpt-4o-mini", stream=True),
agent=agent,
)
crew = Crew(agents=[agent], tasks=[task])
crew.kickoff()
assert event_received.wait(timeout=10), "Timeout waiting for LLM events"
assert len(completed_event) == 1
assert len(failed_event) == 0
assert len(started_event) == 1
assert len(stream_event) == 12
all_events = completed_event + failed_event + started_event + stream_event
all_agent_roles = [event.agent_role for event in all_events]
all_agent_id = [event.agent_id for event in all_events]
all_task_id = [event.task_id for event in all_events]
all_task_name = [event.task_name for event in all_events]
# ensure all events have the agent + task props set
assert len(all_agent_roles) == 14
assert len(all_agent_id) == 14
assert len(all_task_id) == 14
assert len(all_task_name) == 14
assert set(all_agent_roles) == {agent.role}
assert set(all_agent_id) == {str(agent.id)}
assert set(all_task_id) == {str(task.id)}
assert set(all_task_name) == {task.name or task.description}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_emits_event_with_task_and_agent_info(base_agent, base_task):
completed_event = []
failed_event = []
started_event = []
stream_event = []
event_received = threading.Event()
@crewai_event_bus.on(LLMCallFailedEvent)
def handle_llm_failed(source, event):
failed_event.append(event)
@crewai_event_bus.on(LLMCallStartedEvent)
def handle_llm_started(source, event):
started_event.append(event)
@crewai_event_bus.on(LLMCallCompletedEvent)
def handle_llm_completed(source, event):
completed_event.append(event)
if len(started_event) >= 1:
event_received.set()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_llm_stream_chunk(source, event):
stream_event.append(event)
crew = Crew(agents=[base_agent], tasks=[base_task])
crew.kickoff()
assert event_received.wait(timeout=10), "Timeout waiting for LLM events"
assert len(completed_event) == 1
assert len(failed_event) == 0
assert len(started_event) == 1
assert len(stream_event) == 0
all_events = completed_event + failed_event + started_event + stream_event
all_agent_roles = [event.agent_role for event in all_events]
all_agent_id = [event.agent_id for event in all_events]
all_task_id = [event.task_id for event in all_events]
all_task_name = [event.task_name for event in all_events]
# ensure all events have the agent + task props set
assert len(all_agent_roles) == 2
assert len(all_agent_id) == 2
assert len(all_task_id) == 2
assert len(all_task_name) == 2
assert set(all_agent_roles) == {base_agent.role}
assert set(all_agent_id) == {str(base_agent.id)}
assert set(all_task_id) == {str(base_task.id)}
assert set(all_task_name) == {base_task.name or base_task.description}
@pytest.mark.vcr(filter_headers=["authorization"])
def test_llm_emits_event_with_lite_agent():
completed_event = []
failed_event = []
started_event = []
stream_event = []
all_events_received = threading.Event()
@crewai_event_bus.on(LLMCallFailedEvent)
def handle_llm_failed(source, event):
failed_event.append(event)
@crewai_event_bus.on(LLMCallStartedEvent)
def handle_llm_started(source, event):
started_event.append(event)
@crewai_event_bus.on(LLMCallCompletedEvent)
def handle_llm_completed(source, event):
completed_event.append(event)
if len(started_event) >= 1 and len(stream_event) >= 15:
all_events_received.set()
@crewai_event_bus.on(LLMStreamChunkEvent)
def handle_llm_stream_chunk(source, event):
stream_event.append(event)
if (
len(completed_event) >= 1
and len(started_event) >= 1
and len(stream_event) >= 15
):
all_events_received.set()
agent = Agent(
role="Speaker",
llm=LLM(model="gpt-4o-mini", stream=True),
goal="Just say hi",
backstory="You are a helpful assistant that just says hi",
)
agent.kickoff(messages=[{"role": "user", "content": "say hi!"}])
assert all_events_received.wait(timeout=10), "Timeout waiting for all events"
assert len(completed_event) == 1
assert len(failed_event) == 0
assert len(started_event) == 1
assert len(stream_event) == 15
all_events = completed_event + failed_event + started_event + stream_event
all_agent_roles = [event.agent_role for event in all_events]
all_agent_id = [event.agent_id for event in all_events]
all_task_id = [event.task_id for event in all_events if event.task_id]
all_task_name = [event.task_name for event in all_events if event.task_name]
# ensure all events have the agent + task props set
assert len(all_agent_roles) == 17
assert len(all_agent_id) == 17
assert len(all_task_id) == 0
assert len(all_task_name) == 0
assert set(all_agent_roles) == {agent.role}
assert set(all_agent_id) == {str(agent.id)}