mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-10 00:28:31 +00:00
WIP crew events emitter (#2048)
* WIP crew events emitter * Refactor event handling and introduce new event types - Migrate from global `emit` function to `event_bus.emit` - Add new event types for task failures, tool usage, and agent execution - Update event listeners and event bus to support more granular event tracking - Remove deprecated event emission methods - Improve event type consistency and add more detailed event information * Add event emission for agent execution lifecycle - Emit AgentExecutionStarted and AgentExecutionError events - Update CrewAgentExecutor to use event_bus for tracking agent execution - Refactor error handling to include event emission - Minor code formatting improvements in task.py and crew_agent_executor.py - Fix a typo in test file * Refactor event system and add third-party event listeners - Move event_bus import to correct module paths - Introduce BaseEventListener abstract base class - Add AgentOpsListener for third-party event tracking - Update event listener initialization and setup - Clean up event-related imports and exports * Enhance event system type safety and error handling - Improve type annotations for event bus and event types - Add null checks for agent and task in event emissions - Update import paths for base tool and base agent - Refactor event listener type hints - Remove unnecessary print statements - Update test configurations to match new event handling * Refactor event classes to improve type safety and naming consistency - Rename event classes to have explicit 'Event' suffix (e.g., TaskStartedEvent) - Update import statements and references across multiple files - Remove deprecated events.py module - Enhance event type hints and configurations - Clean up unnecessary event-related code * Add default model for CrewEvaluator and fix event import order - Set default model to "gpt-4o-mini" in CrewEvaluator when no model is specified - Reorder event-related imports in task.py to follow standard import conventions - Update event bus initialization method return type hint - Export event_bus in events/__init__.py * Fix tool usage and event import handling - Update tool usage to use `.get()` method when checking tool name - Remove unnecessary `__all__` export list in events/__init__.py * Refactor Flow and Agent event handling to use event_bus - Remove `event_emitter` from Flow class and replace with `event_bus.emit()` - Update Flow and Agent tests to use event_bus event listeners - Remove redundant event emissions in Flow methods - Add debug print statements in Flow execution - Simplify event tracking in test cases * Enhance event handling for Crew, Task, and Event classes - Add crew name to failed event types (CrewKickoffFailedEvent, CrewTrainFailedEvent, CrewTestFailedEvent) - Update Task events to remove redundant task and context attributes - Refactor EventListener to use Logger for consistent event logging - Add new event types for Crew train and test events - Improve event bus event tracking in test cases * Remove telemetry and tracing dependencies from Task and Flow classes - Remove telemetry-related imports and private attributes from Task class - Remove `_telemetry` attribute from Flow class - Update event handling to emit events without direct telemetry tracking - Simplify task and flow execution by removing explicit telemetry spans - Move telemetry-related event handling to EventListener * Clean up unused imports and event-related code - Remove unused imports from various event and flow-related files - Reorder event imports to follow standard conventions - Remove unnecessary event type references - Simplify import statements in event and flow modules * Update crew test to validate verbose output and kickoff_for_each method - Enhance test_crew_verbose_output to check specific listener log messages - Modify test_kickoff_for_each_invalid_input to use Pydantic validation error - Improve test coverage for crew logging and input validation * Update crew test verbose output with improved emoji icons - Replace task and agent completion icons from 👍 to ✅ - Enhance readability of test output logging - Maintain consistent test coverage for crew verbose output * Add MethodExecutionFailedEvent to handle flow method execution failures - Introduce new MethodExecutionFailedEvent in flow_events module - Update Flow class to catch and emit method execution failures - Add event listener for method execution failure events - Update event-related imports to include new event type - Enhance test coverage for method execution failure handling * Propagate method execution failures in Flow class - Modify Flow class to re-raise exceptions after emitting MethodExecutionFailedEvent - Reorder MethodExecutionFailedEvent import to maintain consistent import style * Enable test coverage for Flow method execution failure event - Uncomment pytest.raises() in test_events to verify exception handling - Ensure test validates MethodExecutionFailedEvent emission during flow kickoff * Add event handling for tool usage events - Introduce event listeners for ToolUsageFinishedEvent and ToolUsageErrorEvent - Log tool usage events with descriptive emoji icons (✅ and ❌) - Update event_listener to track and log tool usage lifecycle * Reorder and clean up event imports in event_listener - Reorganize imports for tool usage events and other event types - Maintain consistent import ordering and remove unused imports - Ensure clean and organized import structure in event_listener module * moving to dedicated eventlistener * dont forget crew level * Refactor AgentOps event listener for crew-level tracking - Modify AgentOpsListener to handle crew-level events - Initialize and end AgentOps session at crew kickoff and completion - Create agents for each crew member during session initialization - Improve session management and event recording - Clean up and simplify event handling logic * Update test_events to validate tool usage error event handling - Modify test to assert single error event with correct attributes - Use pytest.raises() to verify error event generation - Simplify error event validation in test case * Improve AgentOps listener type hints and formatting - Add string type hints for AgentOps classes to resolve potential import issues - Clean up unnecessary whitespace and improve code indentation - Simplify initialization and event handling logic * Update test_events to validate multiple tool usage events - Modify test to assert 75 events instead of a single error event - Remove pytest.raises() check, allowing crew kickoff to complete - Adjust event validation to support broader event tracking * Rename event_bus to crewai_event_bus for improved clarity and specificity - Replace all references to `event_bus` with `crewai_event_bus` - Update import statements across multiple files - Remove the old `event_bus.py` file - Maintain existing event handling functionality * Enhance EventListener with singleton pattern and color configuration - Implement singleton pattern for EventListener to ensure single instance - Add default color configuration using EMITTER_COLOR from constants - Modify log method calls to use default color and remove redundant color parameters - Improve initialization logic to prevent multiple initializations * Add FlowPlotEvent and update event bus to support flow plotting - Introduce FlowPlotEvent to track flow plotting events - Replace Telemetry method with event bus emission in Flow.plot() - Update event bus to support new FlowPlotEvent type - Add test case to validate flow plotting event emission * Remove RunType enum and clean up crew events module - Delete unused RunType enum from crew_events.py - Simplify crew_events.py by removing unnecessary enum definition - Improve code clarity by removing unneeded imports * Enhance event handling for tool usage and agent execution - Add new events for tool usage: ToolSelectionErrorEvent, ToolValidateInputErrorEvent - Improve error tracking and event emission in ToolUsage and LLM classes - Update AgentExecutionStartedEvent to use task_prompt instead of inputs - Add comprehensive test coverage for new event types and error scenarios * Refactor event system and improve crew testing - Extract base CrewEvent class to a new base_events.py module - Update event imports across multiple event-related files - Modify CrewTestStartedEvent to use eval_llm instead of openai_model_name - Add LLM creation validation in crew testing method - Improve type handling and event consistency * Refactor task events to use base CrewEvent - Move CrewEvent import from crew_events to base_events - Remove unnecessary blank lines in task_events.py - Simplify event class structure for task-related events * Update AgentExecutionStartedEvent to use task_prompt - Modify test_events.py to use task_prompt instead of inputs - Simplify event input validation in test case - Align with recent event system refactoring * Improve type hinting for TaskCompletedEvent handler - Add explicit type annotation for TaskCompletedEvent in event_listener.py - Enhance type safety for event handling in EventListener * Improve test_validate_tool_input_invalid_input with mock objects - Add explicit mock objects for agent and action in test case - Ensure proper string values for mock agent and action attributes - Simplify test setup for ToolUsage validation method * Remove ToolUsageStartedEvent emission in tool usage process - Remove unnecessary event emission for tool usage start - Simplify tool usage event handling - Eliminate redundant event data preparation step * refactor: clean up and organize imports in llm and flow modules * test: Improve flow persistence test cases and logging
This commit is contained in:
Lorenze Jay
@@ -7,7 +7,8 @@ from pydantic import BaseModel
|
||||
|
||||
from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
|
||||
from crewai.llm import LLM
|
||||
from crewai.tools import tool
|
||||
from crewai.utilities.events import crewai_event_bus
|
||||
from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
|
||||
from crewai.utilities.token_counter_callback import TokenCalcHandler
|
||||
|
||||
|
||||
@@ -291,32 +292,36 @@ def anthropic_llm():
|
||||
"""Fixture providing an Anthropic LLM instance."""
|
||||
return LLM(model="anthropic/claude-3-sonnet")
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def system_message():
|
||||
"""Fixture providing a system message."""
|
||||
return {"role": "system", "content": "test"}
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def user_message():
|
||||
"""Fixture providing a user message."""
|
||||
return {"role": "user", "content": "test"}
|
||||
|
||||
|
||||
def test_anthropic_message_formatting_edge_cases(anthropic_llm):
|
||||
"""Test edge cases for Anthropic message formatting."""
|
||||
# Test None messages
|
||||
with pytest.raises(TypeError, match="Messages cannot be None"):
|
||||
anthropic_llm._format_messages_for_provider(None)
|
||||
|
||||
|
||||
# Test empty message list
|
||||
formatted = anthropic_llm._format_messages_for_provider([])
|
||||
assert len(formatted) == 1
|
||||
assert formatted[0]["role"] == "user"
|
||||
assert formatted[0]["content"] == "."
|
||||
|
||||
|
||||
# Test invalid message format
|
||||
with pytest.raises(TypeError, match="Invalid message format"):
|
||||
anthropic_llm._format_messages_for_provider([{"invalid": "message"}])
|
||||
|
||||
|
||||
def test_anthropic_model_detection():
|
||||
"""Test Anthropic model detection with various formats."""
|
||||
models = [
|
||||
@@ -327,11 +332,12 @@ def test_anthropic_model_detection():
|
||||
("", False),
|
||||
("anthropomorphic", False), # Should not match partial words
|
||||
]
|
||||
|
||||
|
||||
for model, expected in models:
|
||||
llm = LLM(model=model)
|
||||
assert llm.is_anthropic == expected, f"Failed for model: {model}"
|
||||
|
||||
|
||||
def test_anthropic_message_formatting(anthropic_llm, system_message, user_message):
|
||||
"""Test Anthropic message formatting with fixtures."""
|
||||
# Test when first message is system
|
||||
@@ -371,3 +377,51 @@ def test_deepseek_r1_with_open_router():
|
||||
result = llm.call("What is the capital of France?")
|
||||
assert isinstance(result, str)
|
||||
assert "Paris" in result
|
||||
|
||||
|
||||
@pytest.mark.vcr(filter_headers=["authorization"])
|
||||
def test_tool_execution_error_event():
|
||||
llm = LLM(model="gpt-4o-mini")
|
||||
|
||||
def failing_tool(param: str) -> str:
|
||||
"""This tool always fails."""
|
||||
raise Exception("Tool execution failed!")
|
||||
|
||||
tool_schema = {
|
||||
"type": "function",
|
||||
"function": {
|
||||
"name": "failing_tool",
|
||||
"description": "This tool always fails.",
|
||||
"parameters": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"param": {"type": "string", "description": "A test parameter"}
|
||||
},
|
||||
"required": ["param"],
|
||||
},
|
||||
},
|
||||
}
|
||||
|
||||
received_events = []
|
||||
|
||||
@crewai_event_bus.on(ToolExecutionErrorEvent)
|
||||
def event_handler(source, event):
|
||||
received_events.append(event)
|
||||
|
||||
available_functions = {"failing_tool": failing_tool}
|
||||
|
||||
messages = [{"role": "user", "content": "Use the failing tool"}]
|
||||
|
||||
llm.call(
|
||||
messages,
|
||||
tools=[tool_schema],
|
||||
available_functions=available_functions,
|
||||
)
|
||||
|
||||
assert len(received_events) == 1
|
||||
event = received_events[0]
|
||||
assert isinstance(event, ToolExecutionErrorEvent)
|
||||
assert event.tool_name == "failing_tool"
|
||||
assert event.tool_args == {"param": "test"}
|
||||
assert event.tool_class == failing_tool
|
||||
assert "Tool execution failed!" in event.error
|
||||
|
||||
Reference in New Issue
Block a user