Merge branch 'main' into bugfix/allow-empthy-input-to-end-human-input

* 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

src/crewai/agent.py

@@ -19,25 +19,17 @@ from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.utilities import Converter, Prompts
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
+from crewai.utilities.events.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-agentops = None
 
-try:
-    import agentops  # type: ignore # Name "agentops" is already defined
-    from agentops import track_agent  # type: ignore
-except ImportError:
-
-    def track_agent():
-        def noop(f):
-            return f
-
-        return noop
-
-
-@track_agent()
 class Agent(BaseAgent):
     """Represents an agent in a system.
 
@@ -240,6 +232,15 @@ class Agent(BaseAgent):
             task_prompt = self._use_trained_data(task_prompt=task_prompt)
 
         try:
+            crewai_event_bus.emit(
+                self,
+                event=AgentExecutionStartedEvent(
+                    agent=self,
+                    tools=self.tools,
+                    task_prompt=task_prompt,
+                    task=task,
+                ),
+            )
             result = self.agent_executor.invoke(
                 {
                     "input": task_prompt,
@@ -251,9 +252,25 @@ class Agent(BaseAgent):
         except Exception as e:
             if e.__class__.__module__.startswith("litellm"):
                 # Do not retry on litellm errors
+                crewai_event_bus.emit(
+                    self,
+                    event=AgentExecutionErrorEvent(
+                        agent=self,
+                        task=task,
+                        error=str(e),
+                    ),
+                )
                 raise e
             self._times_executed += 1
             if self._times_executed > self.max_retry_limit:
+                crewai_event_bus.emit(
+                    self,
+                    event=AgentExecutionErrorEvent(
+                        agent=self,
+                        task=task,
+                        error=str(e),
+                    ),
+                )
                 raise e
             result = self.execute_task(task, context, tools)
 
@@ -266,7 +283,10 @@ class Agent(BaseAgent):
         for tool_result in self.tools_results:  # type: ignore # Item "None" of "list[Any] | None" has no attribute "__iter__" (not iterable)
             if tool_result.get("result_as_answer", False):
                 result = tool_result["result"]
-
+        crewai_event_bus.emit(
+            self,
+            event=AgentExecutionCompletedEvent(agent=self, task=task, output=result),
+        )
         return result
 
     def create_agent_executor(

src/crewai/agents/agent_builder/base_agent.py

@@ -20,8 +20,7 @@ from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
-from crewai.tools import BaseTool
-from crewai.tools.base_tool import Tool
+from crewai.tools.base_tool import BaseTool, Tool
 from crewai.utilities import I18N, Logger, RPMController
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter
@@ -112,7 +111,7 @@ class BaseAgent(ABC, BaseModel):
         default=False,
         description="Enable agent to delegate and ask questions among each other.",
     )
-    tools: Optional[List[Any]] = Field(
+    tools: Optional[List[BaseTool]] = Field(
         default_factory=list, description="Tools at agents' disposal"
     )
     max_iter: int = Field(

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -114,10 +114,15 @@ class CrewAgentExecutorMixin:
             prompt = (
                 "\n\n=====\n"
                 "## HUMAN FEEDBACK: Provide feedback on the Final Result and Agent's actions.\n"
-                "Respond with 'looks good' to accept or provide specific improvement requests.\n"
-                "You can provide multiple rounds of feedback until satisfied.\n"
+                "Please follow these guidelines:\n"
+                " - If you are happy with the result, simply hit Enter without typing anything.\n"
+                " - Otherwise, provide specific improvement requests.\n"
+                " - You can provide multiple rounds of feedback until satisfied.\n"
                 "=====\n"
             )
 
         self._printer.print(content=prompt, color="bold_yellow")
-        return input()
+        response = input()
+        if response.strip() != "":
+            self._printer.print(content="\nProcessing your feedback...", color="cyan")
+        return response

src/crewai/agents/crew_agent_executor.py

@@ -18,6 +18,12 @@ from crewai.tools.base_tool import BaseTool
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N, Printer
 from crewai.utilities.constants import MAX_LLM_RETRY, TRAINING_DATA_FILE
+from crewai.utilities.events import (
+    ToolUsageErrorEvent,
+    ToolUsageStartedEvent,
+    crewai_event_bus,
+)
+from crewai.utilities.events.tool_usage_events import ToolUsageStartedEvent
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -107,11 +113,11 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
             )
             raise
         except Exception as e:
+            self._handle_unknown_error(e)
             if e.__class__.__module__.startswith("litellm"):
                 # Do not retry on litellm errors
                 raise e
             else:
-                self._handle_unknown_error(e)
                 raise e
 
         if self.ask_for_human_input:
@@ -349,40 +355,68 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                 )
 
     def _execute_tool_and_check_finality(self, agent_action: AgentAction) -> ToolResult:
-        tool_usage = ToolUsage(
-            tools_handler=self.tools_handler,
-            tools=self.tools,
-            original_tools=self.original_tools,
-            tools_description=self.tools_description,
-            tools_names=self.tools_names,
-            function_calling_llm=self.function_calling_llm,
-            task=self.task,  # type: ignore[arg-type]
-            agent=self.agent,
-            action=agent_action,
-        )
-        tool_calling = tool_usage.parse_tool_calling(agent_action.text)
-
-        if isinstance(tool_calling, ToolUsageErrorException):
-            tool_result = tool_calling.message
-            return ToolResult(result=tool_result, result_as_answer=False)
-        else:
-            if tool_calling.tool_name.casefold().strip() in [
-                name.casefold().strip() for name in self.tool_name_to_tool_map
-            ] or tool_calling.tool_name.casefold().replace("_", " ") in [
-                name.casefold().strip() for name in self.tool_name_to_tool_map
-            ]:
-                tool_result = tool_usage.use(tool_calling, agent_action.text)
-                tool = self.tool_name_to_tool_map.get(tool_calling.tool_name)
-                if tool:
-                    return ToolResult(
-                        result=tool_result, result_as_answer=tool.result_as_answer
-                    )
-            else:
-                tool_result = self._i18n.errors("wrong_tool_name").format(
-                    tool=tool_calling.tool_name,
-                    tools=", ".join([tool.name.casefold() for tool in self.tools]),
+        try:
+            if self.agent:
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageStartedEvent(
+                        agent_key=self.agent.key,
+                        agent_role=self.agent.role,
+                        tool_name=agent_action.tool,
+                        tool_args=agent_action.tool_input,
+                        tool_class=agent_action.tool,
+                    ),
                 )
-        return ToolResult(result=tool_result, result_as_answer=False)
+            tool_usage = ToolUsage(
+                tools_handler=self.tools_handler,
+                tools=self.tools,
+                original_tools=self.original_tools,
+                tools_description=self.tools_description,
+                tools_names=self.tools_names,
+                function_calling_llm=self.function_calling_llm,
+                task=self.task,  # type: ignore[arg-type]
+                agent=self.agent,
+                action=agent_action,
+            )
+            tool_calling = tool_usage.parse_tool_calling(agent_action.text)
+
+            if isinstance(tool_calling, ToolUsageErrorException):
+                tool_result = tool_calling.message
+                return ToolResult(result=tool_result, result_as_answer=False)
+            else:
+                if tool_calling.tool_name.casefold().strip() in [
+                    name.casefold().strip() for name in self.tool_name_to_tool_map
+                ] or tool_calling.tool_name.casefold().replace("_", " ") in [
+                    name.casefold().strip() for name in self.tool_name_to_tool_map
+                ]:
+                    tool_result = tool_usage.use(tool_calling, agent_action.text)
+                    tool = self.tool_name_to_tool_map.get(tool_calling.tool_name)
+                    if tool:
+                        return ToolResult(
+                            result=tool_result, result_as_answer=tool.result_as_answer
+                        )
+                else:
+                    tool_result = self._i18n.errors("wrong_tool_name").format(
+                        tool=tool_calling.tool_name,
+                        tools=", ".join([tool.name.casefold() for tool in self.tools]),
+                    )
+                return ToolResult(result=tool_result, result_as_answer=False)
+
+        except Exception as e:
+            # TODO: drop
+            if self.agent:
+                crewai_event_bus.emit(
+                    self,
+                    event=ToolUsageErrorEvent(  # validation error
+                        agent_key=self.agent.key,
+                        agent_role=self.agent.role,
+                        tool_name=agent_action.tool,
+                        tool_args=agent_action.tool_input,
+                        tool_class=agent_action.tool,
+                        error=str(e),
+                    ),
+                )
+            raise e
 
     def _summarize_messages(self) -> None:
         messages_groups = []
@@ -514,10 +548,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         self, initial_answer: AgentFinish, feedback: str
     ) -> AgentFinish:
         """Process feedback for training scenarios with single iteration."""
-        self._printer.print(
-            content="\nProcessing training feedback.\n",
-            color="yellow",
-        )
         self._handle_crew_training_output(initial_answer, feedback)
         self.messages.append(
             self._format_msg(
@@ -537,9 +567,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
         answer = current_answer
 
         while self.ask_for_human_input:
-            response = self._get_llm_feedback_response(feedback)
-
-            if not self._feedback_requires_changes(response):
+            # If the user provides a blank response, assume they are happy with the result
+            if feedback.strip() == "":
                 self.ask_for_human_input = False
             else:
                 answer = self._process_feedback_iteration(feedback)
@@ -547,27 +576,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
 
         return answer
 
-    def _get_llm_feedback_response(self, feedback: str) -> Optional[str]:
-        """Get LLM classification of whether feedback requires changes."""
-        prompt = self._i18n.slice("human_feedback_classification").format(
-            feedback=feedback
-        )
-        message = self._format_msg(prompt, role="system")
-
-        for retry in range(MAX_LLM_RETRY):
-            try:
-                response = self.llm.call([message], callbacks=self.callbacks)
-                return response.strip().lower() if response else None
-            except Exception as error:
-                self._log_feedback_error(retry, error)
-
-        self._log_max_retries_exceeded()
-        return None
-
-    def _feedback_requires_changes(self, response: Optional[str]) -> bool:
-        """Determine if feedback response indicates need for changes."""
-        return response == "true" if response else False
-
     def _process_feedback_iteration(self, feedback: str) -> AgentFinish:
         """Process a single feedback iteration."""
         self.messages.append(

src/crewai/crew.py

@@ -44,6 +44,18 @@ from crewai.utilities import I18N, FileHandler, Logger, RPMController
 from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
+from crewai.utilities.events.crew_events import (
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewKickoffStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+    CrewTestStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    CrewTrainStartedEvent,
+)
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.formatter import (
     aggregate_raw_outputs_from_task_outputs,
     aggregate_raw_outputs_from_tasks,
@@ -53,12 +65,6 @@ from crewai.utilities.planning_handler import CrewPlanner
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-try:
-    import agentops  # type: ignore
-except ImportError:
-    agentops = None
-
-
 warnings.filterwarnings("ignore", category=SyntaxWarning, module="pysbd")
 
 
@@ -522,10 +528,19 @@ class Crew(BaseModel):
         self, n_iterations: int, filename: str, inputs: Optional[Dict[str, Any]] = {}
     ) -> None:
         """Trains the crew for a given number of iterations."""
-        train_crew = self.copy()
-        train_crew._setup_for_training(filename)
-
         try:
+            crewai_event_bus.emit(
+                self,
+                CrewTrainStartedEvent(
+                    crew_name=self.name or "crew",
+                    n_iterations=n_iterations,
+                    filename=filename,
+                    inputs=inputs,
+                ),
+            )
+            train_crew = self.copy()
+            train_crew._setup_for_training(filename)
+
             for n_iteration in range(n_iterations):
                 train_crew._train_iteration = n_iteration
                 train_crew.kickoff(inputs=inputs)
@@ -540,7 +555,20 @@ class Crew(BaseModel):
                     CrewTrainingHandler(filename).save_trained_data(
                         agent_id=str(agent.role), trained_data=result.model_dump()
                     )
+
+            crewai_event_bus.emit(
+                self,
+                CrewTrainCompletedEvent(
+                    crew_name=self.name or "crew",
+                    n_iterations=n_iterations,
+                    filename=filename,
+                ),
+            )
         except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                CrewTrainFailedEvent(error=str(e), crew_name=self.name or "crew"),
+            )
             self._logger.log("error", f"Training failed: {e}", color="red")
             CrewTrainingHandler(TRAINING_DATA_FILE).clear()
             CrewTrainingHandler(filename).clear()
@@ -551,60 +579,70 @@ class Crew(BaseModel):
         self,
         inputs: Optional[Dict[str, Any]] = None,
     ) -> CrewOutput:
-        for before_callback in self.before_kickoff_callbacks:
-            if inputs is None:
-                inputs = {}
-            inputs = before_callback(inputs)
+        try:
+            for before_callback in self.before_kickoff_callbacks:
+                if inputs is None:
+                    inputs = {}
+                inputs = before_callback(inputs)
 
-        """Starts the crew to work on its assigned tasks."""
-        self._execution_span = self._telemetry.crew_execution_span(self, inputs)
-        self._task_output_handler.reset()
-        self._logging_color = "bold_purple"
-
-        if inputs is not None:
-            self._inputs = inputs
-            self._interpolate_inputs(inputs)
-        self._set_tasks_callbacks()
-
-        i18n = I18N(prompt_file=self.prompt_file)
-
-        for agent in self.agents:
-            agent.i18n = i18n
-            # type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
-            agent.crew = self  # type: ignore[attr-defined]
-            # TODO: Create an AgentFunctionCalling protocol for future refactoring
-            if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
-                agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
-
-            if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
-                agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
-
-            agent.create_agent_executor()
-
-        if self.planning:
-            self._handle_crew_planning()
-
-        metrics: List[UsageMetrics] = []
-
-        if self.process == Process.sequential:
-            result = self._run_sequential_process()
-        elif self.process == Process.hierarchical:
-            result = self._run_hierarchical_process()
-        else:
-            raise NotImplementedError(
-                f"The process '{self.process}' is not implemented yet."
+            crewai_event_bus.emit(
+                self,
+                CrewKickoffStartedEvent(crew_name=self.name or "crew", inputs=inputs),
             )
 
-        for after_callback in self.after_kickoff_callbacks:
-            result = after_callback(result)
+            # Starts the crew to work on its assigned tasks.
+            self._task_output_handler.reset()
+            self._logging_color = "bold_purple"
 
-        metrics += [agent._token_process.get_summary() for agent in self.agents]
+            if inputs is not None:
+                self._inputs = inputs
+                self._interpolate_inputs(inputs)
+            self._set_tasks_callbacks()
 
-        self.usage_metrics = UsageMetrics()
-        for metric in metrics:
-            self.usage_metrics.add_usage_metrics(metric)
+            i18n = I18N(prompt_file=self.prompt_file)
 
-        return result
+            for agent in self.agents:
+                agent.i18n = i18n
+                # type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
+                agent.crew = self  # type: ignore[attr-defined]
+                # TODO: Create an AgentFunctionCalling protocol for future refactoring
+                if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
+                    agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
+
+                if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
+                    agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
+
+                agent.create_agent_executor()
+
+            if self.planning:
+                self._handle_crew_planning()
+
+            metrics: List[UsageMetrics] = []
+
+            if self.process == Process.sequential:
+                result = self._run_sequential_process()
+            elif self.process == Process.hierarchical:
+                result = self._run_hierarchical_process()
+            else:
+                raise NotImplementedError(
+                    f"The process '{self.process}' is not implemented yet."
+                )
+
+            for after_callback in self.after_kickoff_callbacks:
+                result = after_callback(result)
+
+            metrics += [agent._token_process.get_summary() for agent in self.agents]
+
+            self.usage_metrics = UsageMetrics()
+            for metric in metrics:
+                self.usage_metrics.add_usage_metrics(metric)
+            return result
+        except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                CrewKickoffFailedEvent(error=str(e), crew_name=self.name or "crew"),
+            )
+            raise
 
     def kickoff_for_each(self, inputs: List[Dict[str, Any]]) -> List[CrewOutput]:
         """Executes the Crew's workflow for each input in the list and aggregates results."""
@@ -952,7 +990,12 @@ class Crew(BaseModel):
         final_string_output = final_task_output.raw
         self._finish_execution(final_string_output)
         token_usage = self.calculate_usage_metrics()
-
+        crewai_event_bus.emit(
+            self,
+            CrewKickoffCompletedEvent(
+                crew_name=self.name or "crew", output=final_task_output
+            ),
+        )
         return CrewOutput(
             raw=final_task_output.raw,
             pydantic=final_task_output.pydantic,
@@ -1138,13 +1181,6 @@ class Crew(BaseModel):
     def _finish_execution(self, final_string_output: str) -> None:
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
-        if agentops:
-            agentops.end_session(
-                end_state="Success",
-                end_state_reason="Finished Execution",
-                is_auto_end=True,
-            )
-        self._telemetry.end_crew(self, final_string_output)
 
     def calculate_usage_metrics(self) -> UsageMetrics:
         """Calculates and returns the usage metrics."""
@@ -1166,26 +1202,41 @@ class Crew(BaseModel):
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
-        test_crew = self.copy()
+        try:
+            eval_llm = create_llm(eval_llm)
+            if not eval_llm:
+                raise ValueError("Failed to create LLM instance.")
 
-        eval_llm = create_llm(eval_llm)
+            crewai_event_bus.emit(
+                self,
+                CrewTestStartedEvent(
+                    crew_name=self.name or "crew",
+                    n_iterations=n_iterations,
+                    eval_llm=eval_llm,
+                    inputs=inputs,
+                ),
+            )
+            test_crew = self.copy()
+            evaluator = CrewEvaluator(test_crew, eval_llm)  # type: ignore[arg-type]
 
-        if not eval_llm:
-            raise ValueError("Failed to create LLM instance.")
+            for i in range(1, n_iterations + 1):
+                evaluator.set_iteration(i)
+                test_crew.kickoff(inputs=inputs)
 
-        self._test_execution_span = test_crew._telemetry.test_execution_span(
-            test_crew,
-            n_iterations,
-            inputs,
-            eval_llm.model,  # type: ignore[arg-type]
-        )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, eval_llm)  # type: ignore[arg-type]
+            evaluator.print_crew_evaluation_result()
 
-        for i in range(1, n_iterations + 1):
-            evaluator.set_iteration(i)
-            test_crew.kickoff(inputs=inputs)
-
-        evaluator.print_crew_evaluation_result()
+            crewai_event_bus.emit(
+                self,
+                CrewTestCompletedEvent(
+                    crew_name=self.name or "crew",
+                ),
+            )
+        except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                CrewTestFailedEvent(error=str(e), crew_name=self.name or "crew"),
+            )
+            raise
 
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/flow/flow.py

@@ -17,23 +17,25 @@ from typing import (
 )
 from uuid import uuid4
 
-from blinker import Signal
 from pydantic import BaseModel, Field, ValidationError
 
-from crewai.flow.flow_events import (
-    FlowFinishedEvent,
-    FlowStartedEvent,
-    MethodExecutionFinishedEvent,
-    MethodExecutionStartedEvent,
-)
 from crewai.flow.flow_visualizer import plot_flow
 from crewai.flow.persistence.base import FlowPersistence
 from crewai.flow.utils import get_possible_return_constants
-from crewai.telemetry import Telemetry
 from crewai.traces.unified_trace_controller import (
     init_flow_main_trace,
     trace_flow_step,
 )
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+from crewai.utilities.events.flow_events import (
+    FlowCreatedEvent,
+    FlowFinishedEvent,
+    FlowPlotEvent,
+    FlowStartedEvent,
+    MethodExecutionFailedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionStartedEvent,
+)
 from crewai.utilities.printer import Printer
 
 logger = logging.getLogger(__name__)
@@ -431,7 +433,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
     Type parameter T must be either Dict[str, Any] or a subclass of BaseModel."""
 
-    _telemetry = Telemetry()
     _printer = Printer()
 
     _start_methods: List[str] = []
@@ -439,7 +440,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
     _routers: Set[str] = set()
     _router_paths: Dict[str, List[str]] = {}
     initial_state: Union[Type[T], T, None] = None
-    event_emitter = Signal("event_emitter")
 
     def __class_getitem__(cls: Type["Flow"], item: Type[T]) -> Type["Flow"]:
         class _FlowGeneric(cls):  # type: ignore
@@ -473,7 +473,13 @@ class Flow(Generic[T], metaclass=FlowMeta):
         if kwargs:
             self._initialize_state(kwargs)
 
-        self._telemetry.flow_creation_span(self.__class__.__name__)
+        crewai_event_bus.emit(
+            self,
+            FlowCreatedEvent(
+                type="flow_created",
+                flow_name=self.__class__.__name__,
+            ),
+        )
 
         # Register all flow-related methods
         for method_name in dir(self):
@@ -742,9 +748,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 self._initialize_state(filtered_inputs)
 
         # Start flow execution
-        self.event_emitter.send(
+        crewai_event_bus.emit(
             self,
-            event=FlowStartedEvent(
+            FlowStartedEvent(
                 type="flow_started",
                 flow_name=self.__class__.__name__,
                 inputs=inputs,
@@ -767,10 +773,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         if not self._start_methods:
             raise ValueError("No start method defined")
 
-        self._telemetry.flow_execution_span(
-            self.__class__.__name__, list(self._methods.keys())
-        )
-
         tasks = [
             self._execute_start_method(start_method)
             for start_method in self._start_methods
@@ -779,9 +781,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
 
         final_output = self._method_outputs[-1] if self._method_outputs else None
 
-        self.event_emitter.send(
+        crewai_event_bus.emit(
             self,
-            event=FlowFinishedEvent(
+            FlowFinishedEvent(
                 type="flow_finished",
                 flow_name=self.__class__.__name__,
                 result=final_output,
@@ -816,40 +818,55 @@ class Flow(Generic[T], metaclass=FlowMeta):
     async def _execute_method(
         self, method_name: str, method: Callable, *args: Any, **kwargs: Any
     ) -> Any:
-        dumped_params = {f"_{i}": arg for i, arg in enumerate(args)} | (kwargs or {})
-        self.event_emitter.send(
-            self,
-            event=MethodExecutionStartedEvent(
-                type="method_execution_started",
-                method_name=method_name,
-                flow_name=self.__class__.__name__,
-                params=dumped_params,
-                state=self._copy_state(),
-            ),
-        )
+        try:
+            dumped_params = {f"_{i}": arg for i, arg in enumerate(args)} | (
+                kwargs or {}
+            )
+            crewai_event_bus.emit(
+                self,
+                MethodExecutionStartedEvent(
+                    type="method_execution_started",
+                    method_name=method_name,
+                    flow_name=self.__class__.__name__,
+                    params=dumped_params,
+                    state=self._copy_state(),
+                ),
+            )
 
-        result = (
-            await method(*args, **kwargs)
-            if asyncio.iscoroutinefunction(method)
-            else method(*args, **kwargs)
-        )
-        self._method_outputs.append(result)
-        self._method_execution_counts[method_name] = (
-            self._method_execution_counts.get(method_name, 0) + 1
-        )
+            result = (
+                await method(*args, **kwargs)
+                if asyncio.iscoroutinefunction(method)
+                else method(*args, **kwargs)
+            )
 
-        self.event_emitter.send(
-            self,
-            event=MethodExecutionFinishedEvent(
-                type="method_execution_finished",
-                method_name=method_name,
-                flow_name=self.__class__.__name__,
-                state=self._copy_state(),
-                result=result,
-            ),
-        )
+            self._method_outputs.append(result)
+            self._method_execution_counts[method_name] = (
+                self._method_execution_counts.get(method_name, 0) + 1
+            )
 
-        return result
+            crewai_event_bus.emit(
+                self,
+                MethodExecutionFinishedEvent(
+                    type="method_execution_finished",
+                    method_name=method_name,
+                    flow_name=self.__class__.__name__,
+                    state=self._copy_state(),
+                    result=result,
+                ),
+            )
+
+            return result
+        except Exception as e:
+            crewai_event_bus.emit(
+                self,
+                MethodExecutionFailedEvent(
+                    type="method_execution_failed",
+                    method_name=method_name,
+                    flow_name=self.__class__.__name__,
+                    error=e,
+                ),
+            )
+            raise e
 
     async def _execute_listeners(self, trigger_method: str, result: Any) -> None:
         """
@@ -987,6 +1004,7 @@ class Flow(Generic[T], metaclass=FlowMeta):
         """
         try:
             method = self._methods[listener_name]
+
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
             method_params = [p for p in params if p.name != "self"]
@@ -1036,7 +1054,11 @@ class Flow(Generic[T], metaclass=FlowMeta):
             logger.warning(message)
 
     def plot(self, filename: str = "crewai_flow") -> None:
-        self._telemetry.flow_plotting_span(
-            self.__class__.__name__, list(self._methods.keys())
+        crewai_event_bus.emit(
+            self,
+            FlowPlotEvent(
+                type="flow_plot",
+                flow_name=self.__class__.__name__,
+            ),
         )
         plot_flow(self, filename)

src/crewai/flow/flow_events.py

@@ -1,39 +0,0 @@
-from dataclasses import dataclass, field
-from datetime import datetime
-from typing import Any, Dict, Optional, Union
-
-from pydantic import BaseModel
-
-
-@dataclass
-class Event:
-    type: str
-    flow_name: str
-    timestamp: datetime = field(init=False)
-
-    def __post_init__(self):
-        self.timestamp = datetime.now()
-
-
-@dataclass
-class FlowStartedEvent(Event):
-    inputs: Optional[Dict[str, Any]] = None
-
-
-@dataclass
-class MethodExecutionStartedEvent(Event):
-    method_name: str
-    state: Union[Dict[str, Any], BaseModel]
-    params: Optional[Dict[str, Any]] = None
-
-
-@dataclass
-class MethodExecutionFinishedEvent(Event):
-    method_name: str
-    state: Union[Dict[str, Any], BaseModel]
-    result: Any = None
-
-
-@dataclass
-class FlowFinishedEvent(Event):
-    result: Optional[Any] = None

src/crewai/flow/persistence/decorators.py

@@ -58,7 +58,7 @@ class PersistenceDecorator:
     _printer = Printer()  # Class-level printer instance
 
     @classmethod
-    def persist_state(cls, flow_instance: Any, method_name: str, persistence_instance: FlowPersistence) -> None:
+    def persist_state(cls, flow_instance: Any, method_name: str, persistence_instance: FlowPersistence, verbose: bool = False) -> None:
         """Persist flow state with proper error handling and logging.
 
         This method handles the persistence of flow state data, including proper
@@ -68,6 +68,7 @@ class PersistenceDecorator:
             flow_instance: The flow instance whose state to persist
             method_name: Name of the method that triggered persistence
             persistence_instance: The persistence backend to use
+            verbose: Whether to log persistence operations
 
         Raises:
             ValueError: If flow has no state or state lacks an ID
@@ -88,9 +89,10 @@ class PersistenceDecorator:
             if not flow_uuid:
                 raise ValueError("Flow state must have an 'id' field for persistence")
 
-            # Log state saving with consistent message
-            cls._printer.print(LOG_MESSAGES["save_state"].format(flow_uuid), color="cyan")
-            logger.info(LOG_MESSAGES["save_state"].format(flow_uuid))
+            # Log state saving only if verbose is True
+            if verbose:
+                cls._printer.print(LOG_MESSAGES["save_state"].format(flow_uuid), color="cyan")
+                logger.info(LOG_MESSAGES["save_state"].format(flow_uuid))
 
             try:
                 persistence_instance.save_state(
@@ -115,7 +117,7 @@ class PersistenceDecorator:
             raise ValueError(error_msg) from e
 
 
-def persist(persistence: Optional[FlowPersistence] = None):
+def persist(persistence: Optional[FlowPersistence] = None, verbose: bool = False):
     """Decorator to persist flow state.
 
     This decorator can be applied at either the class level or method level.
@@ -126,6 +128,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
     Args:
         persistence: Optional FlowPersistence implementation to use.
                     If not provided, uses SQLiteFlowPersistence.
+        verbose: Whether to log persistence operations. Defaults to False.
 
     Returns:
         A decorator that can be applied to either a class or method
@@ -135,13 +138,12 @@ def persist(persistence: Optional[FlowPersistence] = None):
         RuntimeError: If state persistence fails
 
     Example:
-        @persist  # Class-level persistence with default SQLite
+        @persist(verbose=True)  # Class-level persistence with logging
         class MyFlow(Flow[MyState]):
             @start()
             def begin(self):
                 pass
     """
-
     def decorator(target: Union[Type, Callable[..., T]]) -> Union[Type, Callable[..., T]]:
         """Decorator that handles both class and method decoration."""
         actual_persistence = persistence or SQLiteFlowPersistence()
@@ -179,7 +181,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
                         @functools.wraps(original_method)
                         async def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
                             result = await original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(self, method_name, actual_persistence)
+                            PersistenceDecorator.persist_state(self, method_name, actual_persistence, verbose)
                             return result
                         return method_wrapper
 
@@ -199,7 +201,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
                         @functools.wraps(original_method)
                         def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
                             result = original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(self, method_name, actual_persistence)
+                            PersistenceDecorator.persist_state(self, method_name, actual_persistence, verbose)
                             return result
                         return method_wrapper
 
@@ -228,7 +230,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
                         result = await method_coro
                     else:
                         result = method_coro
-                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence)
+                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence, verbose)
                     return result
 
                 for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
@@ -240,7 +242,7 @@ def persist(persistence: Optional[FlowPersistence] = None):
                 @functools.wraps(method)
                 def method_sync_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
                     result = method(flow_instance, *args, **kwargs)
-                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence)
+                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence, verbose)
                     return result
 
                 for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:

src/crewai/flow/state_utils.py

@@ -1,12 +1,18 @@
+import json
 from datetime import date, datetime
-from typing import Any
+from typing import Any, Dict, List, Union
 
 from pydantic import BaseModel
 
 from crewai.flow import Flow
 
+SerializablePrimitive = Union[str, int, float, bool, None]
+Serializable = Union[
+    SerializablePrimitive, List["Serializable"], Dict[str, "Serializable"]
+]
 
-def export_state(flow: Flow) -> dict[str, Any]:
+
+def export_state(flow: Flow) -> dict[str, Serializable]:
     """Exports the Flow's internal state as JSON-compatible data structures.
 
     Performs a one-way transformation of a Flow's state into basic Python types
@@ -20,10 +26,27 @@ def export_state(flow: Flow) -> dict[str, Any]:
         dict[str, Any]: The transformed state using JSON-compatible Python
             types.
     """
-    return _to_serializable(flow._state)
+    result = to_serializable(flow._state)
+    assert isinstance(result, dict)
+    return result
 
 
-def _to_serializable(obj: Any, max_depth: int = 5, _current_depth: int = 0) -> Any:
+def to_serializable(
+    obj: Any, max_depth: int = 5, _current_depth: int = 0
+) -> Serializable:
+    """Converts a Python object into a JSON-compatible representation.
+
+    Supports primitives, datetime objects, collections, dictionaries, and
+    Pydantic models. Recursion depth is limited to prevent infinite nesting.
+    Non-convertible objects default to their string representations.
+
+    Args:
+        obj (Any): Object to transform.
+        max_depth (int, optional): Maximum recursion depth. Defaults to 5.
+
+    Returns:
+        Serializable: A JSON-compatible structure.
+    """
     if _current_depth >= max_depth:
         return repr(obj)
 
@@ -32,16 +55,16 @@ def _to_serializable(obj: Any, max_depth: int = 5, _current_depth: int = 0) -> A
     elif isinstance(obj, (date, datetime)):
         return obj.isoformat()
     elif isinstance(obj, (list, tuple, set)):
-        return [_to_serializable(item, max_depth, _current_depth + 1) for item in obj]
+        return [to_serializable(item, max_depth, _current_depth + 1) for item in obj]
     elif isinstance(obj, dict):
         return {
-            _to_serializable_key(key): _to_serializable(
+            _to_serializable_key(key): to_serializable(
                 value, max_depth, _current_depth + 1
             )
             for key, value in obj.items()
         }
     elif isinstance(obj, BaseModel):
-        return _to_serializable(obj.model_dump(), max_depth, _current_depth + 1)
+        return to_serializable(obj.model_dump(), max_depth, _current_depth + 1)
     else:
         return repr(obj)
 
@@ -50,3 +73,19 @@ def _to_serializable_key(key: Any) -> str:
     if isinstance(key, (str, int)):
         return str(key)
     return f"key_{id(key)}_{repr(key)}"
+
+
+def to_string(obj: Any) -> str | None:
+    """Serializes an object into a JSON string.
+
+    Args:
+        obj (Any): Object to serialize.
+
+    Returns:
+        str | None: A JSON-formatted string or `None` if empty.
+    """
+    serializable = to_serializable(obj)
+    if serializable is None:
+        return None
+    else:
+        return json.dumps(serializable)

src/crewai/knowledge/storage/knowledge_storage.py

@@ -76,7 +76,7 @@ class KnowledgeStorage(BaseKnowledgeStorage):
                         "context": fetched["documents"][0][i],  # type: ignore
                         "score": fetched["distances"][0][i],  # type: ignore
                     }
-                    if result["score"] >= score_threshold:  # type: ignore
+                    if result["score"] >= score_threshold:
                         results.append(result)
                 return results
             else:

src/crewai/llm.py

@@ -21,6 +21,8 @@ from typing import (
 from dotenv import load_dotenv
 from pydantic import BaseModel
 
+from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
+
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
     import litellm
@@ -30,6 +32,7 @@ with warnings.catch_warnings():
 
 
 from crewai.traces.unified_trace_controller import trace_llm_call
+from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -335,7 +338,7 @@ class LLM:
                 # --- 5) Handle the tool call
                 tool_call = tool_calls[0]
                 function_name = tool_call.function.name
-
+                print("function_name", function_name)
                 if function_name in available_functions:
                     try:
                         function_args = json.loads(tool_call.function.arguments)
@@ -353,6 +356,15 @@ class LLM:
                         logging.error(
                             f"Error executing function '{function_name}': {e}"
                         )
+                        crewai_event_bus.emit(
+                            self,
+                            event=ToolExecutionErrorEvent(
+                                tool_name=function_name,
+                                tool_args=function_args,
+                                tool_class=fn,
+                                error=str(e),
+                            ),
+                        )
                         return text_response
 
                 else:

src/crewai/task.py

@@ -21,7 +21,6 @@ from typing import (
     Union,
 )
 
-from opentelemetry.trace import Span
 from pydantic import (
     UUID4,
     BaseModel,
@@ -36,10 +35,15 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.guardrail_result import GuardrailResult
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
-from crewai.telemetry.telemetry import Telemetry
 from crewai.tools.base_tool import BaseTool
 from crewai.utilities.config import process_config
 from crewai.utilities.converter import Converter, convert_to_model
+from crewai.utilities.events import (
+    TaskCompletedEvent,
+    TaskFailedEvent,
+    TaskStartedEvent,
+)
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.i18n import I18N
 from crewai.utilities.printer import Printer
 
@@ -183,8 +187,6 @@ class Task(BaseModel):
                     )
         return v
 
-    _telemetry: Telemetry = PrivateAttr(default_factory=Telemetry)
-    _execution_span: Optional[Span] = PrivateAttr(default=None)
     _original_description: Optional[str] = PrivateAttr(default=None)
     _original_expected_output: Optional[str] = PrivateAttr(default=None)
     _original_output_file: Optional[str] = PrivateAttr(default=None)
@@ -348,100 +350,102 @@ class Task(BaseModel):
         tools: Optional[List[Any]],
     ) -> TaskOutput:
         """Run the core execution logic of the task."""
-        agent = agent or self.agent
-        self.agent = agent
-        if not agent:
-            raise Exception(
-                f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
+        try:
+            agent = agent or self.agent
+            self.agent = agent
+            if not agent:
+                raise Exception(
+                    f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
+                )
+
+            self.start_time = datetime.datetime.now()
+
+            self.prompt_context = context
+            tools = tools or self.tools or []
+
+            self.processed_by_agents.add(agent.role)
+            crewai_event_bus.emit(self, TaskStartedEvent(context=context))
+            result = agent.execute_task(
+                task=self,
+                context=context,
+                tools=tools,
             )
 
-        self.start_time = datetime.datetime.now()
-        self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
+            pydantic_output, json_output = self._export_output(result)
+            task_output = TaskOutput(
+                name=self.name,
+                description=self.description,
+                expected_output=self.expected_output,
+                raw=result,
+                pydantic=pydantic_output,
+                json_dict=json_output,
+                agent=agent.role,
+                output_format=self._get_output_format(),
+            )
 
-        self.prompt_context = context
-        tools = tools or self.tools or []
+            if self.guardrail:
+                guardrail_result = GuardrailResult.from_tuple(
+                    self.guardrail(task_output)
+                )
+                if not guardrail_result.success:
+                    if self.retry_count >= self.max_retries:
+                        raise Exception(
+                            f"Task failed guardrail validation after {self.max_retries} retries. "
+                            f"Last error: {guardrail_result.error}"
+                        )
 
-        self.processed_by_agents.add(agent.role)
+                    self.retry_count += 1
+                    context = self.i18n.errors("validation_error").format(
+                        guardrail_result_error=guardrail_result.error,
+                        task_output=task_output.raw,
+                    )
+                    printer = Printer()
+                    printer.print(
+                        content=f"Guardrail blocked, retrying, due to: {guardrail_result.error}\n",
+                        color="yellow",
+                    )
+                    return self._execute_core(agent, context, tools)
 
-        result = agent.execute_task(
-            task=self,
-            context=context,
-            tools=tools,
-        )
-
-        pydantic_output, json_output = self._export_output(result)
-        task_output = TaskOutput(
-            name=self.name,
-            description=self.description,
-            expected_output=self.expected_output,
-            raw=result,
-            pydantic=pydantic_output,
-            json_dict=json_output,
-            agent=agent.role,
-            output_format=self._get_output_format(),
-        )
-
-        if self.guardrail:
-            guardrail_result = GuardrailResult.from_tuple(self.guardrail(task_output))
-            if not guardrail_result.success:
-                if self.retry_count >= self.max_retries:
+                if guardrail_result.result is None:
                     raise Exception(
-                        f"Task failed guardrail validation after {self.max_retries} retries. "
-                        f"Last error: {guardrail_result.error}"
+                        "Task guardrail returned None as result. This is not allowed."
                     )
 
-                self.retry_count += 1
-                context = self.i18n.errors("validation_error").format(
-                    guardrail_result_error=guardrail_result.error,
-                    task_output=task_output.raw,
+                if isinstance(guardrail_result.result, str):
+                    task_output.raw = guardrail_result.result
+                    pydantic_output, json_output = self._export_output(
+                        guardrail_result.result
+                    )
+                    task_output.pydantic = pydantic_output
+                    task_output.json_dict = json_output
+                elif isinstance(guardrail_result.result, TaskOutput):
+                    task_output = guardrail_result.result
+
+            self.output = task_output
+            self.end_time = datetime.datetime.now()
+
+            if self.callback:
+                self.callback(self.output)
+
+            crew = self.agent.crew  # type: ignore[union-attr]
+            if crew and crew.task_callback and crew.task_callback != self.callback:
+                crew.task_callback(self.output)
+
+            if self.output_file:
+                content = (
+                    json_output
+                    if json_output
+                    else pydantic_output.model_dump_json()
+                    if pydantic_output
+                    else result
                 )
-                printer = Printer()
-                printer.print(
-                    content=f"Guardrail blocked, retrying, due to: {guardrail_result.error}\n",
-                    color="yellow",
-                )
-                return self._execute_core(agent, context, tools)
-
-            if guardrail_result.result is None:
-                raise Exception(
-                    "Task guardrail returned None as result. This is not allowed."
-                )
-
-            if isinstance(guardrail_result.result, str):
-                task_output.raw = guardrail_result.result
-                pydantic_output, json_output = self._export_output(
-                    guardrail_result.result
-                )
-                task_output.pydantic = pydantic_output
-                task_output.json_dict = json_output
-            elif isinstance(guardrail_result.result, TaskOutput):
-                task_output = guardrail_result.result
-
-        self.output = task_output
-        self.end_time = datetime.datetime.now()
-
-        if self.callback:
-            self.callback(self.output)
-
-        crew = self.agent.crew  # type: ignore[union-attr]
-        if crew and crew.task_callback and crew.task_callback != self.callback:
-            crew.task_callback(self.output)
-
-        if self._execution_span:
-            self._telemetry.task_ended(self._execution_span, self, agent.crew)
-            self._execution_span = None
-
-        if self.output_file:
-            content = (
-                json_output
-                if json_output
-                else pydantic_output.model_dump_json()
-                if pydantic_output
-                else result
-            )
-            self._save_file(content)
-
-        return task_output
+                self._save_file(content)
+            crewai_event_bus.emit(self, TaskCompletedEvent(output=task_output))
+            return task_output
+        except Exception as e:
+            self.end_time = datetime.datetime.now()
+            crewai_event_bus.emit(self, TaskFailedEvent(error=str(e)))
+            raise e  # Re-raise the exception after emitting the event
 
     def prompt(self) -> str:
         """Prompt the task.
@@ -716,10 +720,9 @@ class Task(BaseModel):
                     file.write(str(result))
         except (OSError, IOError) as e:
             raise RuntimeError(
-                "\n".join([
-                    f"Failed to save output file: {e}",
-                    FILEWRITER_RECOMMENDATION
-                ])
+                "\n".join(
+                    [f"Failed to save output file: {e}", FILEWRITER_RECOMMENDATION]
+                )
             )
         return None
 

src/crewai/tools/tool_usage.py

@@ -11,20 +11,21 @@ from typing import Any, Dict, List, Optional, Union
 import json5
 from json_repair import repair_json
 
-import crewai.utilities.events as events
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
-from crewai.tools.tool_usage_events import ToolUsageError, ToolUsageFinished
 from crewai.utilities import I18N, Converter, ConverterError, Printer
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+from crewai.utilities.events.tool_usage_events import (
+    ToolSelectionErrorEvent,
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolValidateInputErrorEvent,
+)
 
-try:
-    import agentops  # type: ignore
-except ImportError:
-    agentops = None
 OPENAI_BIGGER_MODELS = [
     "gpt-4",
     "gpt-4o",
@@ -140,7 +141,6 @@ class ToolUsage:
         tool: Any,
         calling: Union[ToolCalling, InstructorToolCalling],
     ) -> str:  # TODO: Fix this return type
-        tool_event = agentops.ToolEvent(name=calling.tool_name) if agentops else None  # type: ignore
         if self._check_tool_repeated_usage(calling=calling):  # type: ignore # _check_tool_repeated_usage of "ToolUsage" does not return a value (it only ever returns None)
             try:
                 result = self._i18n.errors("task_repeated_usage").format(
@@ -219,10 +219,6 @@ class ToolUsage:
                     return error  # type: ignore # No return value expected
 
                 self.task.increment_tools_errors()
-                if agentops:
-                    agentops.record(
-                        agentops.ErrorEvent(exception=e, trigger_event=tool_event)
-                    )
                 return self.use(calling=calling, tool_string=tool_string)  # type: ignore # No return value expected
 
             if self.tools_handler:
@@ -238,9 +234,6 @@ class ToolUsage:
                 self.tools_handler.on_tool_use(
                     calling=calling, output=result, should_cache=should_cache
                 )
-
-        if agentops:
-            agentops.record(tool_event)
         self._telemetry.tool_usage(
             llm=self.function_calling_llm,
             tool_name=tool.name,
@@ -316,14 +309,33 @@ class ToolUsage:
             ):
                 return tool
         self.task.increment_tools_errors()
+        tool_selection_data = {
+            "agent_key": self.agent.key,
+            "agent_role": self.agent.role,
+            "tool_name": tool_name,
+            "tool_args": {},
+            "tool_class": self.tools_description,
+        }
         if tool_name and tool_name != "":
-            raise Exception(
-                f"Action '{tool_name}' don't exist, these are the only available Actions:\n{self.tools_description}"
+            error = f"Action '{tool_name}' don't exist, these are the only available Actions:\n{self.tools_description}"
+            crewai_event_bus.emit(
+                self,
+                ToolSelectionErrorEvent(
+                    **tool_selection_data,
+                    error=error,
+                ),
             )
+            raise Exception(error)
         else:
-            raise Exception(
-                f"I forgot the Action name, these are the only available Actions: {self.tools_description}"
+            error = f"I forgot the Action name, these are the only available Actions: {self.tools_description}"
+            crewai_event_bus.emit(
+                self,
+                ToolSelectionErrorEvent(
+                    **tool_selection_data,
+                    error=error,
+                ),
             )
+            raise Exception(error)
 
     def _render(self) -> str:
         """Render the tool name and description in plain text."""
@@ -459,18 +471,33 @@ class ToolUsage:
             if isinstance(arguments, dict):
                 return arguments
         except Exception as e:
-            self._printer.print(content=f"Failed to repair JSON: {e}", color="red")
+            error = f"Failed to repair JSON: {e}"
+            self._printer.print(content=error, color="red")
 
-        # If all parsing attempts fail, raise an error
-        raise Exception(
+        error_message = (
             "Tool input must be a valid dictionary in JSON or Python literal format"
         )
+        self._emit_validate_input_error(error_message)
+        # If all parsing attempts fail, raise an error
+        raise Exception(error_message)
+
+    def _emit_validate_input_error(self, final_error: str):
+        tool_selection_data = {
+            "agent_key": self.agent.key,
+            "agent_role": self.agent.role,
+            "tool_name": self.action.tool,
+            "tool_args": str(self.action.tool_input),
+            "tool_class": self.__class__.__name__,
+        }
+
+        crewai_event_bus.emit(
+            self,
+            ToolValidateInputErrorEvent(**tool_selection_data, error=final_error),
+        )
 
     def on_tool_error(self, tool: Any, tool_calling: ToolCalling, e: Exception) -> None:
         event_data = self._prepare_event_data(tool, tool_calling)
-        events.emit(
-            source=self, event=ToolUsageError(**{**event_data, "error": str(e)})
-        )
+        crewai_event_bus.emit(self, ToolUsageErrorEvent(**{**event_data, "error": e}))
 
     def on_tool_use_finished(
         self, tool: Any, tool_calling: ToolCalling, from_cache: bool, started_at: float
@@ -484,7 +511,7 @@ class ToolUsage:
                 "from_cache": from_cache,
             }
         )
-        events.emit(source=self, event=ToolUsageFinished(**event_data))
+        crewai_event_bus.emit(self, ToolUsageFinishedEvent(**event_data))
 
     def _prepare_event_data(self, tool: Any, tool_calling: ToolCalling) -> dict:
         return {

src/crewai/tools/tool_usage_events.py

@@ -1,24 +0,0 @@
-from datetime import datetime
-from typing import Any, Dict
-
-from pydantic import BaseModel
-
-
-class ToolUsageEvent(BaseModel):
-    agent_key: str
-    agent_role: str
-    tool_name: str
-    tool_args: Dict[str, Any]
-    tool_class: str
-    run_attempts: int | None = None
-    delegations: int | None = None
-
-
-class ToolUsageFinished(ToolUsageEvent):
-    started_at: datetime
-    finished_at: datetime
-    from_cache: bool = False
-
-
-class ToolUsageError(ToolUsageEvent):
-    error: str

src/crewai/translations/en.json

@@ -23,7 +23,6 @@
     "summary": "This is a summary of our conversation so far:\n{merged_summary}",
     "manager_request": "Your best answer to your coworker asking you this, accounting for the context shared.",
     "formatted_task_instructions": "Ensure your final answer contains only the content in the following format: {output_format}\n\nEnsure the final output does not include any code block markers like ```json or ```python.",
-    "human_feedback_classification": "Determine if the following feedback indicates that the user is satisfied or if further changes are needed. Respond with 'True' if further changes are needed, or 'False' if the user is satisfied. **Important** Do not include any additional commentary outside of your 'True' or 'False' response.\n\nFeedback: \"{feedback}\"",
     "conversation_history_instruction": "You are a member of a crew collaborating to achieve a common goal. Your task is a specific action that contributes to this larger objective. For additional context, please review the conversation history between you and the user that led to the initiation of this crew. Use any relevant information or feedback from the conversation to inform your task execution and ensure your response aligns with both the immediate task and the crew's overall goals.",
     "feedback_instructions": "User feedback: {feedback}\nInstructions: Use this feedback to enhance the next output iteration.\nNote: Do not respond or add commentary."
   },

src/crewai/utilities/constants.py

@@ -4,3 +4,4 @@ DEFAULT_SCORE_THRESHOLD = 0.35
 KNOWLEDGE_DIRECTORY = "knowledge"
 MAX_LLM_RETRY = 3
 MAX_FILE_NAME_LENGTH = 255
+EMITTER_COLOR = "bold_blue"

src/crewai/utilities/evaluators/task_evaluator.py

@@ -3,19 +3,9 @@ from typing import List
 from pydantic import BaseModel, Field
 
 from crewai.utilities import Converter
+from crewai.utilities.events import TaskEvaluationEvent, crewai_event_bus
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
-agentops = None
-try:
-    from agentops import track_agent  # type: ignore
-except ImportError:
-
-    def track_agent(name):
-        def noop(f):
-            return f
-
-        return noop
-
 
 class Entity(BaseModel):
     name: str = Field(description="The name of the entity.")
@@ -48,12 +38,15 @@ class TrainingTaskEvaluation(BaseModel):
     )
 
 
-@track_agent(name="Task Evaluator")
 class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm
+        self.original_agent = original_agent
 
     def evaluate(self, task, output) -> TaskEvaluation:
+        crewai_event_bus.emit(
+            self, TaskEvaluationEvent(evaluation_type="task_evaluation")
+        )
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
             f"Task Description:\n{task.description}\n\n"
@@ -90,6 +83,9 @@ class TaskEvaluator:
             - training_data (dict): The training data to be evaluated.
             - agent_id (str): The ID of the agent.
         """
+        crewai_event_bus.emit(
+            self, TaskEvaluationEvent(evaluation_type="training_data_evaluation")
+        )
 
         output_training_data = training_data[agent_id]
         final_aggregated_data = ""

src/crewai/utilities/events.py

@@ -1,44 +0,0 @@
-from functools import wraps
-from typing import Any, Callable, Dict, Generic, List, Type, TypeVar
-
-from pydantic import BaseModel
-
-T = TypeVar("T")
-EVT = TypeVar("EVT", bound=BaseModel)
-
-
-class Emitter(Generic[T, EVT]):
-    _listeners: Dict[Type[EVT], List[Callable]] = {}
-
-    def on(self, event_type: Type[EVT]):
-        def decorator(func: Callable):
-            @wraps(func)
-            def wrapper(*args, **kwargs):
-                return func(*args, **kwargs)
-
-            self._listeners.setdefault(event_type, []).append(wrapper)
-            return wrapper
-
-        return decorator
-
-    def emit(self, source: T, event: EVT) -> None:
-        event_type = type(event)
-        for func in self._listeners.get(event_type, []):
-            func(source, event)
-
-
-default_emitter = Emitter[Any, BaseModel]()
-
-
-def emit(source: Any, event: BaseModel, raise_on_error: bool = False) -> None:
-    try:
-        default_emitter.emit(source, event)
-    except Exception as e:
-        if raise_on_error:
-            raise e
-        else:
-            print(f"Error emitting event: {e}")
-
-
-def on(event_type: Type[BaseModel]) -> Callable:
-    return default_emitter.on(event_type)

src/crewai/utilities/events/__init__.py

@@ -0,0 +1,40 @@
+from .crew_events import (
+    CrewKickoffStartedEvent,
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewTrainStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    CrewTestStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+)
+from .agent_events import (
+    AgentExecutionStartedEvent,
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+)
+from .task_events import TaskStartedEvent, TaskCompletedEvent, TaskFailedEvent, TaskEvaluationEvent
+from .flow_events import (
+    FlowCreatedEvent,
+    FlowStartedEvent,
+    FlowFinishedEvent,
+    FlowPlotEvent,
+    MethodExecutionStartedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionFailedEvent,
+)
+from .crewai_event_bus import CrewAIEventsBus, crewai_event_bus
+from .tool_usage_events import (
+    ToolUsageFinishedEvent,
+    ToolUsageErrorEvent,
+    ToolUsageStartedEvent,
+    ToolExecutionErrorEvent,
+    ToolSelectionErrorEvent,
+    ToolUsageEvent,
+    ToolValidateInputErrorEvent,
+)
+
+# events
+from .event_listener import EventListener
+from .third_party.agentops_listener import agentops_listener

src/crewai/utilities/events/agent_events.py

@@ -0,0 +1,40 @@
+from typing import TYPE_CHECKING, Any, Dict, Optional, Sequence, Union
+
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.tools.base_tool import BaseTool
+from crewai.tools.structured_tool import CrewStructuredTool
+
+from .base_events import CrewEvent
+
+if TYPE_CHECKING:
+    from crewai.agents.agent_builder.base_agent import BaseAgent
+
+
+class AgentExecutionStartedEvent(CrewEvent):
+    """Event emitted when an agent starts executing a task"""
+
+    agent: BaseAgent
+    task: Any
+    tools: Optional[Sequence[Union[BaseTool, CrewStructuredTool]]]
+    task_prompt: str
+    type: str = "agent_execution_started"
+
+    model_config = {"arbitrary_types_allowed": True}
+
+
+class AgentExecutionCompletedEvent(CrewEvent):
+    """Event emitted when an agent completes executing a task"""
+
+    agent: BaseAgent
+    task: Any
+    output: str
+    type: str = "agent_execution_completed"
+
+
+class AgentExecutionErrorEvent(CrewEvent):
+    """Event emitted when an agent encounters an error during execution"""
+
+    agent: BaseAgent
+    task: Any
+    error: str
+    type: str = "agent_execution_error"

src/crewai/utilities/events/base_event_listener.py

@@ -0,0 +1,14 @@
+from abc import ABC, abstractmethod
+from logging import Logger
+
+from crewai.utilities.events.crewai_event_bus import CrewAIEventsBus, crewai_event_bus
+
+
+class BaseEventListener(ABC):
+    def __init__(self):
+        super().__init__()
+        self.setup_listeners(crewai_event_bus)
+
+    @abstractmethod
+    def setup_listeners(self, crewai_event_bus: CrewAIEventsBus):
+        pass

src/crewai/utilities/events/base_events.py

@@ -0,0 +1,10 @@
+from datetime import datetime
+
+from pydantic import BaseModel, Field
+
+
+class CrewEvent(BaseModel):
+    """Base class for all crew events"""
+
+    timestamp: datetime = Field(default_factory=datetime.now)
+    type: str

src/crewai/utilities/events/crew_events.py

@@ -0,0 +1,81 @@
+from typing import Any, Dict, Optional, Union
+
+from pydantic import InstanceOf
+
+from crewai.utilities.events.base_events import CrewEvent
+
+
+class CrewKickoffStartedEvent(CrewEvent):
+    """Event emitted when a crew starts execution"""
+
+    crew_name: Optional[str]
+    inputs: Optional[Dict[str, Any]]
+    type: str = "crew_kickoff_started"
+
+
+class CrewKickoffCompletedEvent(CrewEvent):
+    """Event emitted when a crew completes execution"""
+
+    crew_name: Optional[str]
+    output: Any
+    type: str = "crew_kickoff_completed"
+
+
+class CrewKickoffFailedEvent(CrewEvent):
+    """Event emitted when a crew fails to complete execution"""
+
+    error: str
+    crew_name: Optional[str]
+    type: str = "crew_kickoff_failed"
+
+
+class CrewTrainStartedEvent(CrewEvent):
+    """Event emitted when a crew starts training"""
+
+    crew_name: Optional[str]
+    n_iterations: int
+    filename: str
+    inputs: Optional[Dict[str, Any]]
+    type: str = "crew_train_started"
+
+
+class CrewTrainCompletedEvent(CrewEvent):
+    """Event emitted when a crew completes training"""
+
+    crew_name: Optional[str]
+    n_iterations: int
+    filename: str
+    type: str = "crew_train_completed"
+
+
+class CrewTrainFailedEvent(CrewEvent):
+    """Event emitted when a crew fails to complete training"""
+
+    error: str
+    crew_name: Optional[str]
+    type: str = "crew_train_failed"
+
+
+class CrewTestStartedEvent(CrewEvent):
+    """Event emitted when a crew starts testing"""
+
+    crew_name: Optional[str]
+    n_iterations: int
+    eval_llm: Optional[Union[str, Any]]
+    inputs: Optional[Dict[str, Any]]
+    type: str = "crew_test_started"
+
+
+class CrewTestCompletedEvent(CrewEvent):
+    """Event emitted when a crew completes testing"""
+
+    crew_name: Optional[str]
+    type: str = "crew_test_completed"
+
+
+class CrewTestFailedEvent(CrewEvent):
+    """Event emitted when a crew fails to complete testing"""
+
+    error: str
+    crew_name: Optional[str]
+    type: str = "crew_test_failed"

src/crewai/utilities/events/crewai_event_bus.py

@@ -0,0 +1,113 @@
+import threading
+from contextlib import contextmanager
+from typing import Any, Callable, Dict, List, Type, TypeVar, cast
+
+from blinker import Signal
+
+from crewai.utilities.events.base_events import CrewEvent
+from crewai.utilities.events.event_types import EventTypes
+
+EventT = TypeVar("EventT", bound=CrewEvent)
+
+
+class CrewAIEventsBus:
+    """
+    A singleton event bus that uses blinker signals for event handling.
+    Allows both internal (Flow/Crew) and external event handling.
+    """
+
+    _instance = None
+    _lock = threading.Lock()
+
+    def __new__(cls):
+        if cls._instance is None:
+            with cls._lock:
+                if cls._instance is None:  # prevent race condition
+                    cls._instance = super(CrewAIEventsBus, cls).__new__(cls)
+                    cls._instance._initialize()
+        return cls._instance
+
+    def _initialize(self) -> None:
+        """Initialize the event bus internal state"""
+        self._signal = Signal("crewai_event_bus")
+        self._handlers: Dict[Type[CrewEvent], List[Callable]] = {}
+
+    def on(
+        self, event_type: Type[EventT]
+    ) -> Callable[[Callable[[Any, EventT], None]], Callable[[Any, EventT], None]]:
+        """
+        Decorator to register an event handler for a specific event type.
+
+        Usage:
+            @crewai_event_bus.on(AgentExecutionCompletedEvent)
+            def on_agent_execution_completed(
+                source: Any, event: AgentExecutionCompletedEvent
+            ):
+                print(f"👍 Agent '{event.agent}' completed task")
+                print(f"   Output: {event.output}")
+        """
+
+        def decorator(
+            handler: Callable[[Any, EventT], None],
+        ) -> Callable[[Any, EventT], None]:
+            if event_type not in self._handlers:
+                self._handlers[event_type] = []
+            self._handlers[event_type].append(
+                cast(Callable[[Any, EventT], None], handler)
+            )
+            return handler
+
+        return decorator
+
+    def emit(self, source: Any, event: CrewEvent) -> None:
+        """
+        Emit an event to all registered handlers
+
+        Args:
+            source: The object emitting the event
+            event: The event instance to emit
+        """
+        event_type = type(event)
+        if event_type in self._handlers:
+            for handler in self._handlers[event_type]:
+                handler(source, event)
+        self._signal.send(source, event=event)
+
+    def clear_handlers(self) -> None:
+        """Clear all registered event handlers - useful for testing"""
+        self._handlers.clear()
+
+    def register_handler(
+        self, event_type: Type[EventTypes], handler: Callable[[Any, EventTypes], None]
+    ) -> None:
+        """Register an event handler for a specific event type"""
+        if event_type not in self._handlers:
+            self._handlers[event_type] = []
+        self._handlers[event_type].append(
+            cast(Callable[[Any, EventTypes], None], handler)
+        )
+
+    @contextmanager
+    def scoped_handlers(self):
+        """
+        Context manager for temporary event handling scope.
+        Useful for testing or temporary event handling.
+
+        Usage:
+            with crewai_event_bus.scoped_handlers():
+                @crewai_event_bus.on(CrewKickoffStarted)
+                def temp_handler(source, event):
+                    print("Temporary handler")
+                # Do stuff...
+            # Handlers are cleared after the context
+        """
+        previous_handlers = self._handlers.copy()
+        self._handlers.clear()
+        try:
+            yield
+        finally:
+            self._handlers = previous_handlers
+
+
+# Global instance
+crewai_event_bus = CrewAIEventsBus()

src/crewai/utilities/events/event_listener.py

@@ -0,0 +1,257 @@
+from pydantic import PrivateAttr
+
+from crewai.telemetry.telemetry import Telemetry
+from crewai.utilities import Logger
+from crewai.utilities.constants import EMITTER_COLOR
+from crewai.utilities.events.base_event_listener import BaseEventListener
+
+from .agent_events import AgentExecutionCompletedEvent, AgentExecutionStartedEvent
+from .crew_events import (
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewKickoffStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+    CrewTestStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    CrewTrainStartedEvent,
+)
+from .flow_events import (
+    FlowCreatedEvent,
+    FlowFinishedEvent,
+    FlowStartedEvent,
+    MethodExecutionFailedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionStartedEvent,
+)
+from .task_events import TaskCompletedEvent, TaskFailedEvent, TaskStartedEvent
+from .tool_usage_events import (
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
+)
+
+
+class EventListener(BaseEventListener):
+    _instance = None
+    _telemetry: Telemetry = PrivateAttr(default_factory=lambda: Telemetry())
+    logger = Logger(verbose=True, default_color=EMITTER_COLOR)
+
+    def __new__(cls):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+            cls._instance._initialized = False
+        return cls._instance
+
+    def __init__(self):
+        if not hasattr(self, "_initialized") or not self._initialized:
+            super().__init__()
+            self._telemetry = Telemetry()
+            self._telemetry.set_tracer()
+            self._initialized = True
+
+    # ----------- CREW EVENTS -----------
+
+    def setup_listeners(self, crewai_event_bus):
+        @crewai_event_bus.on(CrewKickoffStartedEvent)
+        def on_crew_started(source, event: CrewKickoffStartedEvent):
+            self.logger.log(
+                f"🚀 Crew '{event.crew_name}' started",
+                event.timestamp,
+            )
+            self._telemetry.crew_execution_span(source, event.inputs)
+
+        @crewai_event_bus.on(CrewKickoffCompletedEvent)
+        def on_crew_completed(source, event: CrewKickoffCompletedEvent):
+            final_string_output = event.output.raw
+            self._telemetry.end_crew(source, final_string_output)
+            self.logger.log(
+                f"✅ Crew '{event.crew_name}' completed",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewKickoffFailedEvent)
+        def on_crew_failed(source, event: CrewKickoffFailedEvent):
+            self.logger.log(
+                f"❌ Crew '{event.crew_name}' failed",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTestStartedEvent)
+        def on_crew_test_started(source, event: CrewTestStartedEvent):
+            cloned_crew = source.copy()
+            cloned_crew._telemetry.test_execution_span(
+                cloned_crew,
+                event.n_iterations,
+                event.inputs,
+                event.eval_llm,
+            )
+            self.logger.log(
+                f"🚀 Crew '{event.crew_name}' started test",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTestCompletedEvent)
+        def on_crew_test_completed(source, event: CrewTestCompletedEvent):
+            self.logger.log(
+                f"✅ Crew '{event.crew_name}' completed test",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTestFailedEvent)
+        def on_crew_test_failed(source, event: CrewTestFailedEvent):
+            self.logger.log(
+                f"❌ Crew '{event.crew_name}' failed test",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTrainStartedEvent)
+        def on_crew_train_started(source, event: CrewTrainStartedEvent):
+            self.logger.log(
+                f"📋 Crew '{event.crew_name}' started train",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTrainCompletedEvent)
+        def on_crew_train_completed(source, event: CrewTrainCompletedEvent):
+            self.logger.log(
+                f"✅ Crew '{event.crew_name}' completed train",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTrainFailedEvent)
+        def on_crew_train_failed(source, event: CrewTrainFailedEvent):
+            self.logger.log(
+                f"❌ Crew '{event.crew_name}' failed train",
+                event.timestamp,
+            )
+
+        # ----------- TASK EVENTS -----------
+
+        @crewai_event_bus.on(TaskStartedEvent)
+        def on_task_started(source, event: TaskStartedEvent):
+            source._execution_span = self._telemetry.task_started(
+                crew=source.agent.crew, task=source
+            )
+            self.logger.log(
+                f"📋 Task started: {source.description}",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(TaskCompletedEvent)
+        def on_task_completed(source, event: TaskCompletedEvent):
+            if source._execution_span:
+                self._telemetry.task_ended(
+                    source._execution_span, source, source.agent.crew
+                )
+            self.logger.log(
+                f"✅ Task completed: {source.description}",
+                event.timestamp,
+            )
+            source._execution_span = None
+
+        @crewai_event_bus.on(TaskFailedEvent)
+        def on_task_failed(source, event: TaskFailedEvent):
+            if source._execution_span:
+                if source.agent and source.agent.crew:
+                    self._telemetry.task_ended(
+                        source._execution_span, source, source.agent.crew
+                    )
+                source._execution_span = None
+            self.logger.log(
+                f"❌ Task failed: {source.description}",
+                event.timestamp,
+            )
+
+        # ----------- AGENT EVENTS -----------
+
+        @crewai_event_bus.on(AgentExecutionStartedEvent)
+        def on_agent_execution_started(source, event: AgentExecutionStartedEvent):
+            self.logger.log(
+                f"🤖 Agent '{event.agent.role}' started task",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(AgentExecutionCompletedEvent)
+        def on_agent_execution_completed(source, event: AgentExecutionCompletedEvent):
+            self.logger.log(
+                f"✅ Agent '{event.agent.role}' completed task",
+                event.timestamp,
+            )
+
+        # ----------- FLOW EVENTS -----------
+
+        @crewai_event_bus.on(FlowCreatedEvent)
+        def on_flow_created(source, event: FlowCreatedEvent):
+            self._telemetry.flow_creation_span(self.__class__.__name__)
+            self.logger.log(
+                f"🌊 Flow Created: '{event.flow_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(FlowStartedEvent)
+        def on_flow_started(source, event: FlowStartedEvent):
+            self._telemetry.flow_execution_span(
+                source.__class__.__name__, list(source._methods.keys())
+            )
+            self.logger.log(
+                f"🤖 Flow Started: '{event.flow_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(FlowFinishedEvent)
+        def on_flow_finished(source, event: FlowFinishedEvent):
+            self.logger.log(
+                f"👍 Flow Finished: '{event.flow_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(MethodExecutionStartedEvent)
+        def on_method_execution_started(source, event: MethodExecutionStartedEvent):
+            self.logger.log(
+                f"🤖 Flow Method Started: '{event.method_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(MethodExecutionFailedEvent)
+        def on_method_execution_failed(source, event: MethodExecutionFailedEvent):
+            self.logger.log(
+                f"❌ Flow Method Failed: '{event.method_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(MethodExecutionFinishedEvent)
+        def on_method_execution_finished(source, event: MethodExecutionFinishedEvent):
+            self.logger.log(
+                f"👍 Flow Method Finished: '{event.method_name}'",
+                event.timestamp,
+            )
+
+        # ----------- TOOL USAGE EVENTS -----------
+
+        @crewai_event_bus.on(ToolUsageStartedEvent)
+        def on_tool_usage_started(source, event: ToolUsageStartedEvent):
+            self.logger.log(
+                f"🤖 Tool Usage Started: '{event.tool_name}'",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(ToolUsageFinishedEvent)
+        def on_tool_usage_finished(source, event: ToolUsageFinishedEvent):
+            self.logger.log(
+                f"✅ Tool Usage Finished: '{event.tool_name}'",
+                event.timestamp,
+                #
+            )
+
+        @crewai_event_bus.on(ToolUsageErrorEvent)
+        def on_tool_usage_error(source, event: ToolUsageErrorEvent):
+            self.logger.log(
+                f"❌ Tool Usage Error: '{event.tool_name}'",
+                event.timestamp,
+                #
+            )
+
+
+event_listener = EventListener()

src/crewai/utilities/events/event_types.py

@@ -0,0 +1,61 @@
+from typing import Union
+
+from .agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+from .crew_events import (
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewKickoffStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+    CrewTestStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    CrewTrainStartedEvent,
+)
+from .flow_events import (
+    FlowFinishedEvent,
+    FlowStartedEvent,
+    MethodExecutionFailedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionStartedEvent,
+)
+from .task_events import (
+    TaskCompletedEvent,
+    TaskFailedEvent,
+    TaskStartedEvent,
+)
+from .tool_usage_events import (
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageStartedEvent,
+)
+
+EventTypes = Union[
+    CrewKickoffStartedEvent,
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewTestStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+    CrewTrainStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    AgentExecutionStartedEvent,
+    AgentExecutionCompletedEvent,
+    TaskStartedEvent,
+    TaskCompletedEvent,
+    TaskFailedEvent,
+    FlowStartedEvent,
+    FlowFinishedEvent,
+    MethodExecutionStartedEvent,
+    MethodExecutionFinishedEvent,
+    MethodExecutionFailedEvent,
+    AgentExecutionErrorEvent,
+    ToolUsageFinishedEvent,
+    ToolUsageErrorEvent,
+    ToolUsageStartedEvent,
+]

src/crewai/utilities/events/flow_events.py

@@ -0,0 +1,71 @@
+from typing import Any, Dict, Optional, Union
+
+from pydantic import BaseModel
+
+from .base_events import CrewEvent
+
+
+class FlowEvent(CrewEvent):
+    """Base class for all flow events"""
+
+    type: str
+    flow_name: str
+
+
+class FlowStartedEvent(FlowEvent):
+    """Event emitted when a flow starts execution"""
+
+    flow_name: str
+    inputs: Optional[Dict[str, Any]] = None
+    type: str = "flow_started"
+
+
+class FlowCreatedEvent(FlowEvent):
+    """Event emitted when a flow is created"""
+
+    flow_name: str
+    type: str = "flow_created"
+
+
+class MethodExecutionStartedEvent(FlowEvent):
+    """Event emitted when a flow method starts execution"""
+
+    flow_name: str
+    method_name: str
+    state: Union[Dict[str, Any], BaseModel]
+    params: Optional[Dict[str, Any]] = None
+    type: str = "method_execution_started"
+
+
+class MethodExecutionFinishedEvent(FlowEvent):
+    """Event emitted when a flow method completes execution"""
+
+    flow_name: str
+    method_name: str
+    result: Any = None
+    state: Union[Dict[str, Any], BaseModel]
+    type: str = "method_execution_finished"
+
+
+class MethodExecutionFailedEvent(FlowEvent):
+    """Event emitted when a flow method fails execution"""
+
+    flow_name: str
+    method_name: str
+    error: Any
+    type: str = "method_execution_failed"
+
+
+class FlowFinishedEvent(FlowEvent):
+    """Event emitted when a flow completes execution"""
+
+    flow_name: str
+    result: Optional[Any] = None
+    type: str = "flow_finished"
+
+
+class FlowPlotEvent(FlowEvent):
+    """Event emitted when a flow plot is created"""
+
+    flow_name: str
+    type: str = "flow_plot"

src/crewai/utilities/events/task_events.py

@@ -0,0 +1,32 @@
+from typing import Any, Optional
+
+from crewai.tasks.task_output import TaskOutput
+from crewai.utilities.events.base_events import CrewEvent
+
+
+class TaskStartedEvent(CrewEvent):
+    """Event emitted when a task starts"""
+
+    type: str = "task_started"
+    context: Optional[str]
+
+
+class TaskCompletedEvent(CrewEvent):
+    """Event emitted when a task completes"""
+
+    output: TaskOutput
+    type: str = "task_completed"
+
+
+class TaskFailedEvent(CrewEvent):
+    """Event emitted when a task fails"""
+
+    error: str
+    type: str = "task_failed"
+
+
+class TaskEvaluationEvent(CrewEvent):
+    """Event emitted when a task evaluation is completed"""
+
+    type: str = "task_evaluation"
+    evaluation_type: str

src/crewai/utilities/events/third_party/__init__.py

@@ -0,0 +1 @@
+from .agentops_listener import agentops_listener

src/crewai/utilities/events/third_party/agentops_listener.py

@@ -0,0 +1,67 @@
+from typing import Optional
+
+from crewai.utilities.events import (
+    CrewKickoffCompletedEvent,
+    ToolUsageErrorEvent,
+    ToolUsageStartedEvent,
+)
+from crewai.utilities.events.base_event_listener import BaseEventListener
+from crewai.utilities.events.crew_events import CrewKickoffStartedEvent
+from crewai.utilities.events.task_events import TaskEvaluationEvent
+
+try:
+    import agentops
+
+    AGENTOPS_INSTALLED = True
+except ImportError:
+    AGENTOPS_INSTALLED = False
+
+
+class AgentOpsListener(BaseEventListener):
+    tool_event: Optional["agentops.ToolEvent"] = None
+    session: Optional["agentops.Session"] = None
+
+    def __init__(self):
+        super().__init__()
+
+    def setup_listeners(self, crewai_event_bus):
+        if not AGENTOPS_INSTALLED:
+            return
+
+        @crewai_event_bus.on(CrewKickoffStartedEvent)
+        def on_crew_kickoff_started(source, event: CrewKickoffStartedEvent):
+            self.session = agentops.init()
+            for agent in source.agents:
+                if self.session:
+                    self.session.create_agent(
+                        name=agent.role,
+                        agent_id=str(agent.id),
+                    )
+
+        @crewai_event_bus.on(CrewKickoffCompletedEvent)
+        def on_crew_kickoff_completed(source, event: CrewKickoffCompletedEvent):
+            if self.session:
+                self.session.end_session(
+                    end_state="Success",
+                    end_state_reason="Finished Execution",
+                )
+
+        @crewai_event_bus.on(ToolUsageStartedEvent)
+        def on_tool_usage_started(source, event: ToolUsageStartedEvent):
+            self.tool_event = agentops.ToolEvent(name=event.tool_name)
+            if self.session:
+                self.session.record(self.tool_event)
+
+        @crewai_event_bus.on(ToolUsageErrorEvent)
+        def on_tool_usage_error(source, event: ToolUsageErrorEvent):
+            agentops.ErrorEvent(exception=event.error, trigger_event=self.tool_event)
+
+        @crewai_event_bus.on(TaskEvaluationEvent)
+        def on_task_evaluation(source, event: TaskEvaluationEvent):
+            if self.session:
+                self.session.create_agent(
+                    name="Task Evaluator", agent_id=str(source.original_agent.id)
+                )
+
+
+agentops_listener = AgentOpsListener()

src/crewai/utilities/events/tool_usage_events.py

@@ -0,0 +1,64 @@
+from datetime import datetime
+from typing import Any, Callable, Dict
+
+from .base_events import CrewEvent
+
+
+class ToolUsageEvent(CrewEvent):
+    """Base event for tool usage tracking"""
+
+    agent_key: str
+    agent_role: str
+    tool_name: str
+    tool_args: Dict[str, Any] | str
+    tool_class: str
+    run_attempts: int | None = None
+    delegations: int | None = None
+
+    model_config = {"arbitrary_types_allowed": True}
+
+
+class ToolUsageStartedEvent(ToolUsageEvent):
+    """Event emitted when a tool execution is started"""
+
+    type: str = "tool_usage_started"
+
+
+class ToolUsageFinishedEvent(ToolUsageEvent):
+    """Event emitted when a tool execution is completed"""
+
+    started_at: datetime
+    finished_at: datetime
+    from_cache: bool = False
+    type: str = "tool_usage_finished"
+
+
+class ToolUsageErrorEvent(ToolUsageEvent):
+    """Event emitted when a tool execution encounters an error"""
+
+    error: Any
+    type: str = "tool_usage_error"
+
+
+class ToolValidateInputErrorEvent(ToolUsageEvent):
+    """Event emitted when a tool input validation encounters an error"""
+
+    error: Any
+    type: str = "tool_validate_input_error"
+
+
+class ToolSelectionErrorEvent(ToolUsageEvent):
+    """Event emitted when a tool selection encounters an error"""
+
+    error: Any
+    type: str = "tool_selection_error"
+
+
+class ToolExecutionErrorEvent(CrewEvent):
+    """Event emitted when a tool execution encounters an error"""
+
+    error: Any
+    type: str = "tool_execution_error"
+    tool_name: str
+    tool_args: Dict[str, Any]
+    tool_class: Callable

src/crewai/utilities/logger.py

@@ -8,8 +8,11 @@ from crewai.utilities.printer import Printer
 class Logger(BaseModel):
     verbose: bool = Field(default=False)
     _printer: Printer = PrivateAttr(default_factory=Printer)
+    default_color: str = Field(default="bold_yellow")
 
-    def log(self, level, message, color="bold_yellow"):
+    def log(self, level, message, color=None):
+        if color is None:
+            color = self.default_color
         if self.verbose:
             timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
             self._printer.print(

tests/agent_test.py

@@ -1,7 +1,6 @@
 """Test Agent creation and execution basic functionality."""
 
 import os
-from datetime import UTC, datetime, timezone
 from unittest import mock
 from unittest.mock import patch
 
@@ -9,7 +8,7 @@ import pytest
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
-from crewai.agents.crew_agent_executor import CrewAgentExecutor
+from crewai.agents.crew_agent_executor import AgentFinish, CrewAgentExecutor
 from crewai.agents.parser import AgentAction, CrewAgentParser, OutputParserException
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
@@ -17,9 +16,9 @@ from crewai.llm import LLM
 from crewai.tools import tool
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
-from crewai.tools.tool_usage_events import ToolUsageFinished
 from crewai.utilities import RPMController
-from crewai.utilities.events import Emitter
+from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.tool_usage_events import ToolUsageFinishedEvent
 
 
 def test_agent_llm_creation_with_env_vars():
@@ -155,15 +154,19 @@ def test_agent_execution_with_tools():
         agent=agent,
         expected_output="The result of the multiplication.",
     )
-    with patch.object(Emitter, "emit") as emit:
-        output = agent.execute_task(task)
-        assert output == "The result of the multiplication is 12."
-        assert emit.call_count == 1
-        args, _ = emit.call_args
-        assert isinstance(args[1], ToolUsageFinished)
-        assert not args[1].from_cache
-        assert args[1].tool_name == "multiplier"
-        assert args[1].tool_args == {"first_number": 3, "second_number": 4}
+    received_events = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def handle_tool_end(source, event):
+        received_events.append(event)
+
+    output = agent.execute_task(task)
+    assert output == "The result of the multiplication is 12."
+
+    assert len(received_events) == 1
+    assert isinstance(received_events[0], ToolUsageFinishedEvent)
+    assert received_events[0].tool_name == "multiplier"
+    assert received_events[0].tool_args == {"first_number": 3, "second_number": 4}
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -250,10 +253,14 @@ def test_cache_hitting():
         "multiplier-{'first_number': 3, 'second_number': 3}": 9,
         "multiplier-{'first_number': 12, 'second_number': 3}": 36,
     }
+    received_events = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def handle_tool_end(source, event):
+        received_events.append(event)
 
     with (
         patch.object(CacheHandler, "read") as read,
-        patch.object(Emitter, "emit") as emit,
     ):
         read.return_value = "0"
         task = Task(
@@ -266,10 +273,9 @@ def test_cache_hitting():
         read.assert_called_with(
             tool="multiplier", input={"first_number": 2, "second_number": 6}
         )
-        assert emit.call_count == 1
-        args, _ = emit.call_args
-        assert isinstance(args[1], ToolUsageFinished)
-        assert args[1].from_cache
+        assert len(received_events) == 1
+        assert isinstance(received_events[0], ToolUsageFinishedEvent)
+        assert received_events[0].from_cache
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -992,23 +998,35 @@ def test_agent_human_input():
     # Side effect function for _ask_human_input to simulate multiple feedback iterations
     feedback_responses = iter(
         [
-            "Don't say hi, say Hello instead!",  # First feedback
-            "looks good",  # Second feedback to exit loop
+            "Don't say hi, say Hello instead!",  # First feedback: instruct change
+            "",  # Second feedback: empty string signals acceptance
         ]
     )
 
     def ask_human_input_side_effect(*args, **kwargs):
         return next(feedback_responses)
 
-    with patch.object(
-        CrewAgentExecutor, "_ask_human_input", side_effect=ask_human_input_side_effect
-    ) as mock_human_input:
+    # Patch both _ask_human_input and _invoke_loop to avoid real API/network calls.
+    with (
+        patch.object(
+            CrewAgentExecutor,
+            "_ask_human_input",
+            side_effect=ask_human_input_side_effect,
+        ) as mock_human_input,
+        patch.object(
+            CrewAgentExecutor,
+            "_invoke_loop",
+            return_value=AgentFinish(output="Hello", thought="", text=""),
+        ) as mock_invoke_loop,
+    ):
         # Execute the task
         output = agent.execute_task(task)
 
-        # Assertions to ensure the agent behaves correctly
-        assert mock_human_input.call_count == 2  # Should have asked for feedback twice
-        assert output.strip().lower() == "hello"  # Final output should be 'Hello'
+        # Assertions to ensure the agent behaves correctly.
+        # It should have requested feedback twice.
+        assert mock_human_input.call_count == 2
+        # The final result should be processed to "Hello"
+        assert output.strip().lower() == "hello"
 
 
 def test_interpolate_inputs():

tests/cassettes/test_agent_human_input.yaml

@@ -1,520 +0,0 @@
-interactions:
-- request:
-    body: !!binary |
-      CqcXCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/hYKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRJ5ChBuJJtOdNaB05mOW/p3915eEgj2tkAd3rZcASoQVG9vbCBVc2FnZSBFcnJvcjAB
-      OYa7/URvKBUYQUpcFEVvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoPCgNsbG0SCAoG
-      Z3B0LTRvegIYAYUBAAEAABLJBwoQifhX01E5i+5laGdALAlZBBIIBuGM1aN+OPgqDENyZXcgQ3Jl
-      YXRlZDABORVGruBvKBUYQaipwOBvKBUYShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuODYuMEoaCg5w
-      eXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19rZXkSIgogN2U2NjA4OTg5ODU5YTY3ZWVj
-      ODhlZWY3ZmNlODUyMjVKMQoHY3Jld19pZBImCiRiOThiNWEwMC01YTI1LTQxMDctYjQwNS1hYmYz
-      MjBhOGYzYThKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAA
-      ShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgB
-      SuQCCgtjcmV3X2FnZW50cxLUAgrRAlt7ImtleSI6ICIyMmFjZDYxMWU0NGVmNWZhYzA1YjUzM2Q3
-      NWU4ODkzYiIsICJpZCI6ICJkNWIyMzM1YS0yMmIyLTQyZWEtYmYwNS03OTc3NmU3MmYzOTIiLCAi
-      cm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAy
-      MCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJn
-      cHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4
-      ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsi
-      Z2V0IGdyZWV0aW5ncyJdfV1KkgIKCmNyZXdfdGFza3MSgwIKgAJbeyJrZXkiOiAiYTI3N2IzNGIy
-      YzE0NmYwYzU2YzVlMTM1NmU4ZjhhNTciLCAiaWQiOiAiMjJiZWMyMzEtY2QyMS00YzU4LTgyN2Ut
-      MDU4MWE4ZjBjMTExIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6
-      IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJEYXRhIFNjaWVudGlzdCIsICJhZ2VudF9rZXkiOiAiMjJh
-      Y2Q2MTFlNDRlZjVmYWMwNWI1MzNkNzVlODg5M2IiLCAidG9vbHNfbmFtZXMiOiBbImdldCBncmVl
-      dGluZ3MiXX1degIYAYUBAAEAABKOAgoQ5WYoxRtTyPjge4BduhL0rRIIv2U6rvWALfwqDFRhc2sg
-      Q3JlYXRlZDABOX068uBvKBUYQZkv8+BvKBUYSi4KCGNyZXdfa2V5EiIKIDdlNjYwODk4OTg1OWE2
-      N2VlYzg4ZWVmN2ZjZTg1MjI1SjEKB2NyZXdfaWQSJgokYjk4YjVhMDAtNWEyNS00MTA3LWI0MDUt
-      YWJmMzIwYThmM2E4Si4KCHRhc2tfa2V5EiIKIGEyNzdiMzRiMmMxNDZmMGM1NmM1ZTEzNTZlOGY4
-      YTU3SjEKB3Rhc2tfaWQSJgokMjJiZWMyMzEtY2QyMS00YzU4LTgyN2UtMDU4MWE4ZjBjMTExegIY
-      AYUBAAEAABKQAQoQXyeDtJDFnyp2Fjk9YEGTpxIIaNE7gbhPNYcqClRvb2wgVXNhZ2UwATkaXTvj
-      bygVGEGvx0rjbygVGEoaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjg2LjBKHAoJdG9vbF9uYW1lEg8K
-      DUdldCBHcmVldGluZ3NKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABLVBwoQMWfznt0qwauEzl7T
-      UOQxRBII9q+pUS5EdLAqDENyZXcgQ3JlYXRlZDABORONPORvKBUYQSAoS+RvKBUYShoKDmNyZXdh
-      aV92ZXJzaW9uEggKBjAuODYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjdKLgoIY3Jld19r
-      ZXkSIgogYzMwNzYwMDkzMjY3NjE0NDRkNTdjNzFkMWRhM2YyN2NKMQoHY3Jld19pZBImCiQ3OTQw
-      MTkyNS1iOGU5LTQ3MDgtODUzMC00NDhhZmEzYmY4YjBKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
-      bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
-      cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSuoCCgtjcmV3X2FnZW50cxLaAgrXAlt7ImtleSI6ICI5
-      OGYzYjFkNDdjZTk2OWNmMDU3NzI3Yjc4NDE0MjVjZCIsICJpZCI6ICI5OTJkZjYyZi1kY2FiLTQy
-      OTUtOTIwNi05MDBkNDExNGIxZTkiLCAicm9sZSI6ICJGcmllbmRseSBOZWlnaGJvciIsICJ2ZXJi
-      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25f
-      Y2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJs
-      ZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9s
-      aW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFsiZGVjaWRlIGdyZWV0aW5ncyJdfV1KmAIKCmNyZXdf
-      dGFza3MSiQIKhgJbeyJrZXkiOiAiODBkN2JjZDQ5MDk5MjkwMDgzODMyZjBlOTgzMzgwZGYiLCAi
-      aWQiOiAiMmZmNjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3IiwgImFzeW5jX2V4ZWN1
-      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJGcmll
-      bmRseSBOZWlnaGJvciIsICJhZ2VudF9rZXkiOiAiOThmM2IxZDQ3Y2U5NjljZjA1NzcyN2I3ODQx
-      NDI1Y2QiLCAidG9vbHNfbmFtZXMiOiBbImRlY2lkZSBncmVldGluZ3MiXX1degIYAYUBAAEAABKO
-      AgoQnjTp5boK7/+DQxztYIpqihIIgGnMUkBtzHEqDFRhc2sgQ3JlYXRlZDABOcpYcuRvKBUYQalE
-      c+RvKBUYSi4KCGNyZXdfa2V5EiIKIGMzMDc2MDA5MzI2NzYxNDQ0ZDU3YzcxZDFkYTNmMjdjSjEK
-      B2NyZXdfaWQSJgokNzk0MDE5MjUtYjhlOS00NzA4LTg1MzAtNDQ4YWZhM2JmOGIwSi4KCHRhc2tf
-      a2V5EiIKIDgwZDdiY2Q0OTA5OTI5MDA4MzgzMmYwZTk4MzM4MGRmSjEKB3Rhc2tfaWQSJgokMmZm
-      NjE5N2UtYmEyNy00YjczLWI0YTctNGZhMDQ4ZTYyYjQ3egIYAYUBAAEAABKTAQoQ26H9pLUgswDN
-      p9XhJwwL6BIIx3bw7mAvPYwqClRvb2wgVXNhZ2UwATmy7NPlbygVGEEvb+HlbygVGEoaCg5jcmV3
-      YWlfdmVyc2lvbhIICgYwLjg2LjBKHwoJdG9vbF9uYW1lEhIKEERlY2lkZSBHcmVldGluZ3NKDgoI
-      YXR0ZW1wdHMSAhgBegIYAYUBAAEAAA==
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '2986'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.27.0
-    method: POST
-    uri: https://telemetry.crewai.com:4319/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Fri, 27 Dec 2024 22:14:53 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\nTo give my best complete final answer to the task
-      use the exact following format:\n\nThought: I now can give a great answer\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\n\nI MUST use these formats, my job depends on
-      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
-      is the expect criteria for your final answer: The word: Hi\nyou MUST return
-      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
-      "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '824'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.52.1
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.52.1
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AjCtZLLrWi8ZASpP9bz6HaCV7xBIn\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
-      Answer: Hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      158,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 170,\n    \"prompt_tokens_details\":
-      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
-      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
-      \"fp_0aa8d3e20b\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8f8caa83deca756b-SEA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 27 Dec 2024 22:14:53 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw;
-        path=/; expires=Fri, 27-Dec-24 22:44:53 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '404'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999816'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_6ac84634bff9193743c4b0911c09b4a6
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "system", "content": "Determine if the following
-      feedback indicates that the user is satisfied or if further changes are needed.
-      Respond with ''True'' if further changes are needed, or ''False'' if the user
-      is satisfied. **Important** Do not include any additional commentary outside
-      of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
-      instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
-      false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '461'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
-        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.52.1
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.52.1
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AjCtZNlWdrrPZhq0MJDqd16sMuQEJ\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"True\",\n        \"refusal\": null\n
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 78,\n    \"completion_tokens\":
-      1,\n    \"total_tokens\": 79,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
-      \"fp_0aa8d3e20b\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8f8caa87094f756b-SEA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 27 Dec 2024 22:14:53 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '156'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999898'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_ec74bef2a9ef7b2144c03fd7f7bbeab0
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\nTo give my best complete final answer to the task
-      use the exact following format:\n\nThought: I now can give a great answer\nFinal
-      Answer: Your final answer must be the great and the most complete as possible,
-      it must be outcome described.\n\nI MUST use these formats, my job depends on
-      it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
-      is the expect criteria for your final answer: The word: Hi\nyou MUST return
-      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
-      can give a great answer  \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
-      Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
-      "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '986'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
-        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.52.1
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.52.1
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AjCtZGv4f3h7GDdhyOy9G0sB1lRgC\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1735337693,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: I understand the feedback and
-      will adjust my response accordingly.  \\nFinal Answer: Hello\",\n        \"refusal\":
-      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 188,\n    \"completion_tokens\":
-      18,\n    \"total_tokens\": 206,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
-      \"fp_0aa8d3e20b\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8f8caa88cac4756b-SEA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 27 Dec 2024 22:14:54 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '358'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999793'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_ae1ab6b206d28ded6fee3c83ed0c2ab7
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "system", "content": "Determine if the following
-      feedback indicates that the user is satisfied or if further changes are needed.
-      Respond with ''True'' if further changes are needed, or ''False'' if the user
-      is satisfied. **Important** Do not include any additional commentary outside
-      of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
-      "gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate
-      connection:
-      - keep-alive
-      content-length:
-      - '439'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=A_ASCLNAVfQoyucWOAIhecWtEpNotYoZr0bAFihgNxs-1735337693273-0.0.1.1-604800000;
-        __cf_bm=wJkq_yLkzE3OdxE0aMJz.G0kce969.9JxRmZ0ratl4c-1735337693-1.0.1.1-OKpUoRrSPFGvWv5Hp5ET1PNZ7iZNHPKEAuakpcQUxxPSeisUIIR3qIOZ31MGmYugqB5.wkvidgbxOAagqJvmnw
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.52.1
-      x-stainless-arch:
-      - x64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - Linux
-      x-stainless-package-version:
-      - 1.52.1
-      x-stainless-raw-response:
-      - 'true'
-      x-stainless-retry-count:
-      - '0'
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.12.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-AjCtaiHL4TY8Dssk0j2miqmjrzquy\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1735337694,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"False\",\n        \"refusal\": null\n
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 73,\n    \"completion_tokens\":
-      1,\n    \"total_tokens\": 74,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
-      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
-      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
-      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"system_fingerprint\":
-      \"fp_0aa8d3e20b\"\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8f8caa8bdd26756b-SEA
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 27 Dec 2024 22:14:54 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      access-control-expose-headers:
-      - X-Request-ID
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '184'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=31536000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '30000'
-      x-ratelimit-limit-tokens:
-      - '150000000'
-      x-ratelimit-remaining-requests:
-      - '29999'
-      x-ratelimit-remaining-tokens:
-      - '149999902'
-      x-ratelimit-reset-requests:
-      - 2ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_652891f79c1104a7a8436275d78a69f1
-    http_version: HTTP/1.1
-    status_code: 200
-version: 1

tests/cassettes/test_tool_execution_error_event.yaml

@@ -0,0 +1,112 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Use the failing tool"}], "model":
+      "gpt-4o-mini", "stop": [], "tools": [{"type": "function", "function": {"name":
+      "failing_tool", "description": "This tool always fails.", "parameters": {"type":
+      "object", "properties": {"param": {"type": "string", "description": "A test
+      parameter"}}, "required": ["param"]}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '353'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-B2P4zoJZuES7Aom8ugEq1modz5Vsl\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739912761,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_F6fJxISpMKUBIGV6dd2vjRNG\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"failing_tool\",\n
+      \             \"arguments\": \"{\\\"param\\\":\\\"test\\\"}\"\n            }\n
+      \         }\n        ],\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"tool_calls\"\n    }\n  ],\n  \"usage\": {\n
+      \   \"prompt_tokens\": 51,\n    \"completion_tokens\": 15,\n    \"total_tokens\":
+      66,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\":
+      0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
+      0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\":
+      0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\":
+      \"fp_00428b782a\"\n}\n"
+    headers:
+      CF-RAY:
+      - 9140fa827f38eb1e-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 18 Feb 2025 21:06:02 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=xbuu3IQpCMh.43ZrqL1TRMECOc6QldgHV0hzOX1GrWI-1739912762-1.0.1.1-t7iyq5xMioPrwfeaHLvPT9rwRPp7Q9A9uIm69icH9dPxRD4xMA3cWqb1aXj1_e2IyAEQQWFe1UWjlmJ22aHh3Q;
+        path=/; expires=Tue, 18-Feb-25 21:36:02 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=x9l.Rhja8_wXDN.j8qcEU1PvvEqAwZp4Fd3s_aj4qwM-1739912762161-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '861'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999978'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8666ec3aa6677cb346ba00993556051d
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -6,7 +6,6 @@ from concurrent.futures import Future
 from unittest import mock
 from unittest.mock import MagicMock, patch
 
-import instructor
 import pydantic_core
 import pytest
 
@@ -18,13 +17,21 @@ from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSourc
 from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
-from crewai.project import crew
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.types.usage_metrics import UsageMetrics
 from crewai.utilities import Logger
+from crewai.utilities.events import (
+    CrewTrainCompletedEvent,
+    CrewTrainStartedEvent,
+    crewai_event_bus,
+)
+from crewai.utilities.events.crew_events import (
+    CrewTestCompletedEvent,
+    CrewTestStartedEvent,
+)
 from crewai.utilities.rpm_controller import RPMController
 from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
@@ -844,8 +851,21 @@ def test_crew_verbose_output(capsys):
     crew.verbose = False
     crew._logger = Logger(verbose=False)
     crew.kickoff()
+    expected_listener_logs = [
+        "[🚀 CREW 'CREW' STARTED]",
+        "[📋 TASK STARTED: RESEARCH AI ADVANCEMENTS.]",
+        "[🤖 AGENT 'RESEARCHER' STARTED TASK]",
+        "[✅ AGENT 'RESEARCHER' COMPLETED TASK]",
+        "[✅ TASK COMPLETED: RESEARCH AI ADVANCEMENTS.]",
+        "[📋 TASK STARTED: WRITE ABOUT AI IN HEALTHCARE.]",
+        "[🤖 AGENT 'SENIOR WRITER' STARTED TASK]",
+        "[✅ AGENT 'SENIOR WRITER' COMPLETED TASK]",
+        "[✅ TASK COMPLETED: WRITE ABOUT AI IN HEALTHCARE.]",
+        "[✅ CREW 'CREW' COMPLETED]",
+    ]
     captured = capsys.readouterr()
-    assert captured.out == ""
+    for log in expected_listener_logs:
+        assert log in captured.out
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1283,9 +1303,9 @@ def test_kickoff_for_each_invalid_input():
 
     crew = Crew(agents=[agent], tasks=[task])
 
-    with pytest.raises(TypeError):
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError):
         # Pass a string instead of a list
-        crew.kickoff_for_each("invalid input")
+        crew.kickoff_for_each(["invalid input"])
 
 
 def test_kickoff_for_each_error_handling():
@@ -2569,6 +2589,16 @@ def test_crew_train_success(
     # Create a mock for the copied crew
     copy_mock.return_value = crew
 
+    received_events = []
+
+    @crewai_event_bus.on(CrewTrainStartedEvent)
+    def on_crew_train_started(source, event: CrewTrainStartedEvent):
+        received_events.append(event)
+
+    @crewai_event_bus.on(CrewTrainCompletedEvent)
+    def on_crew_train_completed(source, event: CrewTrainCompletedEvent):
+        received_events.append(event)
+
     crew.train(
         n_iterations=2, inputs={"topic": "AI"}, filename="trained_agents_data.pkl"
     )
@@ -2614,6 +2644,10 @@ def test_crew_train_success(
         ]
     )
 
+    assert len(received_events) == 2
+    assert isinstance(received_events[0], CrewTrainStartedEvent)
+    assert isinstance(received_events[1], CrewTrainCompletedEvent)
+
 
 def test_crew_train_error():
     task = Task(
@@ -3342,7 +3376,18 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     copy_mock.return_value = crew
 
     n_iterations = 2
-    llm_instance = LLM('gpt-4o-mini')
+    llm_instance = LLM("gpt-4o-mini")
+
+    received_events = []
+
+    @crewai_event_bus.on(CrewTestStartedEvent)
+    def on_crew_test_started(source, event: CrewTestStartedEvent):
+        received_events.append(event)
+
+    @crewai_event_bus.on(CrewTestCompletedEvent)
+    def on_crew_test_completed(source, event: CrewTestCompletedEvent):
+        received_events.append(event)
+
     crew.test(n_iterations, llm_instance, inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
@@ -3352,13 +3397,17 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
 
     crew_evaluator.assert_has_calls(
         [
-            mock.call(crew,llm_instance),
+            mock.call(crew, llm_instance),
             mock.call().set_iteration(1),
             mock.call().set_iteration(2),
             mock.call().print_crew_evaluation_result(),
         ]
     )
 
+    assert len(received_events) == 2
+    assert isinstance(received_events[0], CrewTestStartedEvent)
+    assert isinstance(received_events[1], CrewTestCompletedEvent)
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_verbose_manager_agent():

tests/flow/test_state_utils.py

@@ -6,7 +6,7 @@ import pytest
 from pydantic import BaseModel
 
 from crewai.flow import Flow
-from crewai.flow.state_utils import export_state
+from crewai.flow.state_utils import export_state, to_string
 
 
 class Address(BaseModel):
@@ -119,16 +119,10 @@ def test_pydantic_model_serialization(mock_flow):
     )
 
     result = export_state(flow)
-
-    assert result["single_model"]["street"] == "123 Main St"
-
-    assert result["nested_model"]["name"] == "John Doe"
-    assert result["nested_model"]["address"]["city"] == "Tech City"
-    assert result["nested_model"]["birthday"] == "1994-01-01"
-
-    assert len(result["model_list"]) == 2
-    assert all(m["street"] == "123 Main St" for m in result["model_list"])
-    assert result["model_dict"]["home"]["city"] == "Tech City"
+    assert (
+        to_string(result)
+        == '{"single_model": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "nested_model": {"name": "John Doe", "age": 30, "address": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, "birthday": "1994-01-01", "skills": ["Python", "Testing"]}, "model_list": [{"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}, {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}], "model_dict": {"home": {"street": "123 Main St", "city": "Tech City", "country": "Pythonia"}}}'
+    )
 
 
 def test_depth_limit(mock_flow):

tests/flow_test.py

@@ -7,12 +7,14 @@ import pytest
 from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, and_, listen, or_, router, start
-from crewai.flow.flow_events import (
+from crewai.utilities.events import (
     FlowFinishedEvent,
     FlowStartedEvent,
     MethodExecutionFinishedEvent,
     MethodExecutionStartedEvent,
+    crewai_event_bus,
 )
+from crewai.utilities.events.flow_events import FlowPlotEvent
 
 
 def test_simple_sequential_flow():
@@ -434,90 +436,65 @@ def test_unstructured_flow_event_emission():
         @listen(finish_poem)
         def save_poem_to_database(self):
             # A method without args/kwargs to ensure events are sent correctly
-            pass
-
-    event_log = []
-
-    def handle_event(_, event):
-        event_log.append(event)
+            return "roses are red\nviolets are blue"
 
     flow = PoemFlow()
-    flow.event_emitter.connect(handle_event)
+    received_events = []
+
+    @crewai_event_bus.on(FlowStartedEvent)
+    def handle_flow_start(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(MethodExecutionStartedEvent)
+    def handle_method_start(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(FlowFinishedEvent)
+    def handle_flow_end(source, event):
+        received_events.append(event)
+
     flow.kickoff(inputs={"separator": ", "})
+    assert isinstance(received_events[0], FlowStartedEvent)
+    assert received_events[0].flow_name == "PoemFlow"
+    assert received_events[0].inputs == {"separator": ", "}
+    assert isinstance(received_events[0].timestamp, datetime)
 
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "PoemFlow"
-    assert event_log[0].inputs == {"separator": ", "}
-    assert isinstance(event_log[0].timestamp, datetime)
-
-    # Asserting for concurrent start method executions in a for loop as you
-    # can't guarantee ordering in asynchronous executions
-    for i in range(1, 5):
-        event = event_log[i]
+    # All subsequent events are MethodExecutionStartedEvent
+    for event in received_events[1:-1]:
+        assert isinstance(event, MethodExecutionStartedEvent)
+        assert event.flow_name == "PoemFlow"
         assert isinstance(event.state, dict)
         assert isinstance(event.state["id"], str)
+        assert event.state["separator"] == ", "
 
-        if event.method_name == "prepare_flower":
-            if isinstance(event, MethodExecutionStartedEvent):
-                assert event.params == {}
-                assert event.state["separator"] == ", "
-            elif isinstance(event, MethodExecutionFinishedEvent):
-                assert event.result == "foo"
-                assert event.state["flower"] == "roses"
-                assert event.state["separator"] == ", "
-            else:
-                assert False, "Unexpected event type for prepare_flower"
-        elif event.method_name == "prepare_color":
-            if isinstance(event, MethodExecutionStartedEvent):
-                assert event.params == {}
-                assert event.state["separator"] == ", "
-            elif isinstance(event, MethodExecutionFinishedEvent):
-                assert event.result == "bar"
-                assert event.state["color"] == "red"
-                assert event.state["separator"] == ", "
-            else:
-                assert False, "Unexpected event type for prepare_color"
-        else:
-            assert False, f"Unexpected method {event.method_name} in prepare events"
+    assert received_events[1].method_name == "prepare_flower"
+    assert received_events[1].params == {}
+    assert "flower" not in received_events[1].state
 
-    assert isinstance(event_log[5], MethodExecutionStartedEvent)
-    assert event_log[5].method_name == "write_first_sentence"
-    assert event_log[5].params == {}
-    assert isinstance(event_log[5].state, dict)
-    assert event_log[5].state["flower"] == "roses"
-    assert event_log[5].state["color"] == "red"
-    assert event_log[5].state["separator"] == ", "
+    assert received_events[2].method_name == "prepare_color"
+    assert received_events[2].params == {}
+    print("received_events[2]", received_events[2])
+    assert "flower" in received_events[2].state
 
-    assert isinstance(event_log[6], MethodExecutionFinishedEvent)
-    assert event_log[6].method_name == "write_first_sentence"
-    assert event_log[6].result == "roses are red"
+    assert received_events[3].method_name == "write_first_sentence"
+    assert received_events[3].params == {}
+    assert received_events[3].state["flower"] == "roses"
+    assert received_events[3].state["color"] == "red"
 
-    assert isinstance(event_log[7], MethodExecutionStartedEvent)
-    assert event_log[7].method_name == "finish_poem"
-    assert event_log[7].params == {"_0": "roses are red"}
-    assert isinstance(event_log[7].state, dict)
-    assert event_log[7].state["flower"] == "roses"
-    assert event_log[7].state["color"] == "red"
+    assert received_events[4].method_name == "finish_poem"
+    assert received_events[4].params == {"_0": "roses are red"}
+    assert received_events[4].state["flower"] == "roses"
+    assert received_events[4].state["color"] == "red"
 
-    assert isinstance(event_log[8], MethodExecutionFinishedEvent)
-    assert event_log[8].method_name == "finish_poem"
-    assert event_log[8].result == "roses are red, violets are blue"
+    assert received_events[5].method_name == "save_poem_to_database"
+    assert received_events[5].params == {}
+    assert received_events[5].state["flower"] == "roses"
+    assert received_events[5].state["color"] == "red"
 
-    assert isinstance(event_log[9], MethodExecutionStartedEvent)
-    assert event_log[9].method_name == "save_poem_to_database"
-    assert event_log[9].params == {}
-    assert isinstance(event_log[9].state, dict)
-    assert event_log[9].state["flower"] == "roses"
-    assert event_log[9].state["color"] == "red"
-
-    assert isinstance(event_log[10], MethodExecutionFinishedEvent)
-    assert event_log[10].method_name == "save_poem_to_database"
-    assert event_log[10].result is None
-
-    assert isinstance(event_log[11], FlowFinishedEvent)
-    assert event_log[11].flow_name == "PoemFlow"
-    assert event_log[11].result is None
-    assert isinstance(event_log[11].timestamp, datetime)
+    assert isinstance(received_events[6], FlowFinishedEvent)
+    assert received_events[6].flow_name == "PoemFlow"
+    assert received_events[6].result == "roses are red\nviolets are blue"
+    assert isinstance(received_events[6].timestamp, datetime)
 
 
 def test_structured_flow_event_emission():
@@ -538,40 +515,54 @@ def test_structured_flow_event_emission():
             self.state.sent = True
             return f"Welcome, {self.state.name}!"
 
-    event_log = []
-
-    def handle_event(_, event):
-        event_log.append(event)
-
     flow = OnboardingFlow()
-    flow.event_emitter.connect(handle_event)
     flow.kickoff(inputs={"name": "Anakin"})
 
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "OnboardingFlow"
-    assert event_log[0].inputs == {"name": "Anakin"}
-    assert isinstance(event_log[0].timestamp, datetime)
+    received_events = []
 
-    assert isinstance(event_log[1], MethodExecutionStartedEvent)
-    assert event_log[1].method_name == "user_signs_up"
+    @crewai_event_bus.on(FlowStartedEvent)
+    def handle_flow_start(source, event):
+        received_events.append(event)
 
-    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
-    assert event_log[2].method_name == "user_signs_up"
+    @crewai_event_bus.on(MethodExecutionStartedEvent)
+    def handle_method_start(source, event):
+        received_events.append(event)
 
-    assert isinstance(event_log[3], MethodExecutionStartedEvent)
-    assert event_log[3].method_name == "send_welcome_message"
-    assert event_log[3].params == {}
-    assert getattr(event_log[3].state, "sent") is False
+    @crewai_event_bus.on(MethodExecutionFinishedEvent)
+    def handle_method_end(source, event):
+        received_events.append(event)
 
-    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
-    assert event_log[4].method_name == "send_welcome_message"
-    assert getattr(event_log[4].state, "sent") is True
-    assert event_log[4].result == "Welcome, Anakin!"
+    @crewai_event_bus.on(FlowFinishedEvent)
+    def handle_flow_end(source, event):
+        received_events.append(event)
 
-    assert isinstance(event_log[5], FlowFinishedEvent)
-    assert event_log[5].flow_name == "OnboardingFlow"
-    assert event_log[5].result == "Welcome, Anakin!"
-    assert isinstance(event_log[5].timestamp, datetime)
+    flow.kickoff(inputs={"name": "Anakin"})
+
+    assert isinstance(received_events[0], FlowStartedEvent)
+    assert received_events[0].flow_name == "OnboardingFlow"
+    assert received_events[0].inputs == {"name": "Anakin"}
+    assert isinstance(received_events[0].timestamp, datetime)
+
+    assert isinstance(received_events[1], MethodExecutionStartedEvent)
+    assert received_events[1].method_name == "user_signs_up"
+
+    assert isinstance(received_events[2], MethodExecutionFinishedEvent)
+    assert received_events[2].method_name == "user_signs_up"
+
+    assert isinstance(received_events[3], MethodExecutionStartedEvent)
+    assert received_events[3].method_name == "send_welcome_message"
+    assert received_events[3].params == {}
+    assert getattr(received_events[3].state, "sent") is False
+
+    assert isinstance(received_events[4], MethodExecutionFinishedEvent)
+    assert received_events[4].method_name == "send_welcome_message"
+    assert getattr(received_events[4].state, "sent") is True
+    assert received_events[4].result == "Welcome, Anakin!"
+
+    assert isinstance(received_events[5], FlowFinishedEvent)
+    assert received_events[5].flow_name == "OnboardingFlow"
+    assert received_events[5].result == "Welcome, Anakin!"
+    assert isinstance(received_events[5].timestamp, datetime)
 
 
 def test_stateless_flow_event_emission():
@@ -593,30 +584,73 @@ def test_stateless_flow_event_emission():
         event_log.append(event)
 
     flow = StatelessFlow()
-    flow.event_emitter.connect(handle_event)
+    received_events = []
+
+    @crewai_event_bus.on(FlowStartedEvent)
+    def handle_flow_start(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(MethodExecutionStartedEvent)
+    def handle_method_start(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(MethodExecutionFinishedEvent)
+    def handle_method_end(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(FlowFinishedEvent)
+    def handle_flow_end(source, event):
+        received_events.append(event)
+
     flow.kickoff()
 
-    assert isinstance(event_log[0], FlowStartedEvent)
-    assert event_log[0].flow_name == "StatelessFlow"
-    assert event_log[0].inputs is None
-    assert isinstance(event_log[0].timestamp, datetime)
+    assert isinstance(received_events[0], FlowStartedEvent)
+    assert received_events[0].flow_name == "StatelessFlow"
+    assert received_events[0].inputs is None
+    assert isinstance(received_events[0].timestamp, datetime)
 
-    assert isinstance(event_log[1], MethodExecutionStartedEvent)
-    assert event_log[1].method_name == "init"
+    assert isinstance(received_events[1], MethodExecutionStartedEvent)
+    assert received_events[1].method_name == "init"
 
-    assert isinstance(event_log[2], MethodExecutionFinishedEvent)
-    assert event_log[2].method_name == "init"
+    assert isinstance(received_events[2], MethodExecutionFinishedEvent)
+    assert received_events[2].method_name == "init"
 
-    assert isinstance(event_log[3], MethodExecutionStartedEvent)
-    assert event_log[3].method_name == "process"
+    assert isinstance(received_events[3], MethodExecutionStartedEvent)
+    assert received_events[3].method_name == "process"
 
-    assert isinstance(event_log[4], MethodExecutionFinishedEvent)
-    assert event_log[4].method_name == "process"
+    assert isinstance(received_events[4], MethodExecutionFinishedEvent)
+    assert received_events[4].method_name == "process"
 
-    assert isinstance(event_log[5], FlowFinishedEvent)
-    assert event_log[5].flow_name == "StatelessFlow"
+    assert isinstance(received_events[5], FlowFinishedEvent)
+    assert received_events[5].flow_name == "StatelessFlow"
     assert (
-        event_log[5].result
+        received_events[5].result
         == "Deeds will not be less valiant because they are unpraised."
     )
-    assert isinstance(event_log[5].timestamp, datetime)
+    assert isinstance(received_events[5].timestamp, datetime)
+
+
+def test_flow_plotting():
+    class StatelessFlow(Flow):
+        @start()
+        def init(self):
+            return "Initializing flow..."
+
+        @listen(init)
+        def process(self):
+            return "Deeds will not be less valiant because they are unpraised."
+
+    flow = StatelessFlow()
+    flow.kickoff()
+    received_events = []
+
+    @crewai_event_bus.on(FlowPlotEvent)
+    def handle_flow_plot(source, event):
+        received_events.append(event)
+
+    flow.plot("test_flow")
+
+    assert len(received_events) == 1
+    assert isinstance(received_events[0], FlowPlotEvent)
+    assert received_events[0].flow_name == "StatelessFlow"
+    assert isinstance(received_events[0].timestamp, datetime)

tests/llm_test.py

@@ -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

tests/test_flow_persistence.py

@@ -13,11 +13,12 @@ from crewai.flow.persistence.sqlite import SQLiteFlowPersistence
 
 class TestState(FlowState):
     """Test state model with required id field."""
+
     counter: int = 0
     message: str = ""
 
 
-def test_persist_decorator_saves_state(tmp_path):
+def test_persist_decorator_saves_state(tmp_path, caplog):
     """Test that @persist decorator saves state in SQLite."""
     db_path = os.path.join(tmp_path, "test_flows.db")
     persistence = SQLiteFlowPersistence(db_path)
@@ -73,7 +74,6 @@ def test_flow_state_restoration(tmp_path):
 
     # First flow execution to create initial state
     class RestorableFlow(Flow[TestState]):
-
         @start()
         @persist(persistence)
         def set_message(self):
@@ -89,10 +89,7 @@ def test_flow_state_restoration(tmp_path):
 
     # Test case 1: Restore using restore_uuid with field override
     flow2 = RestorableFlow(persistence=persistence)
-    flow2.kickoff(inputs={
-        "id": original_uuid,
-        "counter": 43
-    })
+    flow2.kickoff(inputs={"id": original_uuid, "counter": 43})
 
     # Verify state restoration and selective field override
     assert flow2.state.id == original_uuid
@@ -101,10 +98,7 @@ def test_flow_state_restoration(tmp_path):
 
     # Test case 2: Restore using kwargs['id']
     flow3 = RestorableFlow(persistence=persistence)
-    flow3.kickoff(inputs={
-        "id": original_uuid,
-        "message": "Updated message"
-    })
+    flow3.kickoff(inputs={"id": original_uuid, "message": "Updated message"})
 
     # Verify state restoration and selective field override
     assert flow3.state.id == original_uuid
@@ -174,3 +168,43 @@ def test_multiple_method_persistence(tmp_path):
     final_state = flow2.state
     assert final_state.counter == 99999
     assert final_state.message == "Step 99999"
+
+
+def test_persist_decorator_verbose_logging(tmp_path, caplog):
+    """Test that @persist decorator's verbose parameter controls logging."""
+    # Set logging level to ensure we capture all logs
+    caplog.set_level("INFO")
+
+    db_path = os.path.join(tmp_path, "test_flows.db")
+    persistence = SQLiteFlowPersistence(db_path)
+
+    # Test with verbose=False (default)
+    class QuietFlow(Flow[Dict[str, str]]):
+        initial_state = dict()
+
+        @start()
+        @persist(persistence)  # Default verbose=False
+        def init_step(self):
+            self.state["message"] = "Hello, World!"
+            self.state["id"] = "test-uuid-1"
+
+    flow = QuietFlow(persistence=persistence)
+    flow.kickoff()
+    assert "Saving flow state" not in caplog.text
+
+    # Clear the log
+    caplog.clear()
+
+    # Test with verbose=True
+    class VerboseFlow(Flow[Dict[str, str]]):
+        initial_state = dict()
+
+        @start()
+        @persist(persistence, verbose=True)
+        def init_step(self):
+            self.state["message"] = "Hello, World!"
+            self.state["id"] = "test-uuid-2"
+
+    flow = VerboseFlow(persistence=persistence)
+    flow.kickoff()
+    assert "Saving flow state" in caplog.text

tests/tools/test_tool_usage.py

@@ -1,6 +1,6 @@
 import json
 import random
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 
 import pytest
 from pydantic import BaseModel, Field
@@ -8,6 +8,11 @@ from pydantic import BaseModel, Field
 from crewai import Agent, Task
 from crewai.tools import BaseTool
 from crewai.tools.tool_usage import ToolUsage
+from crewai.utilities.events import crewai_event_bus
+from crewai.utilities.events.tool_usage_events import (
+    ToolSelectionErrorEvent,
+    ToolValidateInputErrorEvent,
+)
 
 
 class RandomNumberToolInput(BaseModel):
@@ -226,7 +231,7 @@ def test_validate_tool_input_with_special_characters():
     )
 
     # Input with special characters
-    tool_input = '{"message": "Hello, world! \u263A", "valid": True}'
+    tool_input = '{"message": "Hello, world! \u263a", "valid": True}'
     expected_arguments = {"message": "Hello, world! ☺", "valid": True}
 
     arguments = tool_usage._validate_tool_input(tool_input)
@@ -331,6 +336,19 @@ def test_validate_tool_input_with_trailing_commas():
 
 
 def test_validate_tool_input_invalid_input():
+    # Create mock agent with proper string values
+    mock_agent = MagicMock()
+    mock_agent.key = "test_agent_key"  # Must be a string
+    mock_agent.role = "test_agent_role"  # Must be a string
+    mock_agent._original_role = "test_agent_role"  # Must be a string
+    mock_agent.i18n = MagicMock()
+    mock_agent.verbose = False
+
+    # Create mock action with proper string value
+    mock_action = MagicMock()
+    mock_action.tool = "test_tool"  # Must be a string
+    mock_action.tool_input = "test_input"  # Must be a string
+
     tool_usage = ToolUsage(
         tools_handler=MagicMock(),
         tools=[],
@@ -339,8 +357,8 @@ def test_validate_tool_input_invalid_input():
         tools_names="",
         task=MagicMock(),
         function_calling_llm=None,
-        agent=MagicMock(),
-        action=MagicMock(),
+        agent=mock_agent,
+        action=mock_action,
     )
 
     invalid_inputs = [
@@ -360,7 +378,7 @@ def test_validate_tool_input_invalid_input():
 
     # Test for None input separately
     arguments = tool_usage._validate_tool_input(None)
-    assert arguments == {}  # Expecting an empty dictionary
+    assert arguments == {}
 
 
 def test_validate_tool_input_complex_structure():
@@ -468,18 +486,141 @@ def test_validate_tool_input_large_json_content():
     assert arguments == expected_arguments
 
 
-def test_validate_tool_input_none_input():
+def test_tool_selection_error_event_direct():
+    """Test tool selection error event emission directly from ToolUsage class."""
+    mock_agent = MagicMock()
+    mock_agent.key = "test_key"
+    mock_agent.role = "test_role"
+    mock_agent.i18n = MagicMock()
+    mock_agent.verbose = False
+
+    mock_task = MagicMock()
+    mock_tools_handler = MagicMock()
+
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool"
+
+        def _run(self, input: dict) -> str:
+            return "test result"
+
+    test_tool = TestTool()
+
     tool_usage = ToolUsage(
-        tools_handler=MagicMock(),
-        tools=[],
-        original_tools=[],
-        tools_description="",
-        tools_names="",
-        task=MagicMock(),
+        tools_handler=mock_tools_handler,
+        tools=[test_tool],
+        original_tools=[test_tool],
+        tools_description="Test Tool Description",
+        tools_names="Test Tool",
+        task=mock_task,
         function_calling_llm=None,
-        agent=MagicMock(),
+        agent=mock_agent,
         action=MagicMock(),
     )
 
-    arguments = tool_usage._validate_tool_input(None)
-    assert arguments == {}  # Expecting an empty dictionary
+    received_events = []
+
+    @crewai_event_bus.on(ToolSelectionErrorEvent)
+    def event_handler(source, event):
+        received_events.append(event)
+
+    with pytest.raises(Exception) as exc_info:
+        tool_usage._select_tool("Non Existent Tool")
+    assert len(received_events) == 1
+    event = received_events[0]
+    assert isinstance(event, ToolSelectionErrorEvent)
+    assert event.agent_key == "test_key"
+    assert event.agent_role == "test_role"
+    assert event.tool_name == "Non Existent Tool"
+    assert event.tool_args == {}
+    assert event.tool_class == "Test Tool Description"
+    assert "don't exist" in event.error
+
+    received_events.clear()
+    with pytest.raises(Exception) as exc_info:
+        tool_usage._select_tool("")
+
+    assert len(received_events) == 1
+    event = received_events[0]
+    assert isinstance(event, ToolSelectionErrorEvent)
+    assert event.agent_key == "test_key"
+    assert event.agent_role == "test_role"
+    assert event.tool_name == ""
+    assert event.tool_args == {}
+    assert event.tool_class == "Test Tool Description"
+    assert "forgot the Action name" in event.error
+
+
+def test_tool_validate_input_error_event():
+    """Test tool validation input error event emission from ToolUsage class."""
+    # Mock agent and required components
+    mock_agent = MagicMock()
+    mock_agent.key = "test_key"
+    mock_agent.role = "test_role"
+    mock_agent.verbose = False
+    mock_agent._original_role = "test_role"
+
+    # Mock i18n with error message
+    mock_i18n = MagicMock()
+    mock_i18n.errors.return_value = (
+        "Tool input must be a valid dictionary in JSON or Python literal format"
+    )
+    mock_agent.i18n = mock_i18n
+
+    # Mock task and tools handler
+    mock_task = MagicMock()
+    mock_tools_handler = MagicMock()
+
+    # Mock printer
+    mock_printer = MagicMock()
+
+    # Create test tool
+    class TestTool(BaseTool):
+        name: str = "Test Tool"
+        description: str = "A test tool"
+
+        def _run(self, input: dict) -> str:
+            return "test result"
+
+    test_tool = TestTool()
+
+    # Create ToolUsage instance
+    tool_usage = ToolUsage(
+        tools_handler=mock_tools_handler,
+        tools=[test_tool],
+        original_tools=[test_tool],
+        tools_description="Test Tool Description",
+        tools_names="Test Tool",
+        task=mock_task,
+        function_calling_llm=None,
+        agent=mock_agent,
+        action=MagicMock(tool="test_tool"),
+    )
+    tool_usage._printer = mock_printer
+
+    # Mock all parsing attempts to fail
+    with (
+        patch("json.loads", side_effect=json.JSONDecodeError("Test Error", "", 0)),
+        patch("ast.literal_eval", side_effect=ValueError),
+        patch("json5.loads", side_effect=json.JSONDecodeError("Test Error", "", 0)),
+        patch("json_repair.repair_json", side_effect=Exception("Failed to repair")),
+    ):
+        received_events = []
+
+        @crewai_event_bus.on(ToolValidateInputErrorEvent)
+        def event_handler(source, event):
+            received_events.append(event)
+
+        # Test invalid input
+        invalid_input = "invalid json {[}"
+        with pytest.raises(Exception) as exc_info:
+            tool_usage._validate_tool_input(invalid_input)
+
+        # Verify event was emitted
+        assert len(received_events) == 1, "Expected one event to be emitted"
+        event = received_events[0]
+        assert isinstance(event, ToolValidateInputErrorEvent)
+        assert event.agent_key == "test_key"
+        assert event.agent_role == "test_role"
+        assert event.tool_name == "test_tool"
+        assert "must be a valid dictionary" in event.error

tests/utilities/cassettes/test_agent_emits_execution_started_and_completed_events.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzTXAk4GatJOmLO9sEOCCITIjf1Dx\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739214900,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90fe6ce92eba67b3-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 10 Feb 2025 19:15:01 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
+        path=/; expires=Mon, 10-Feb-25 19:45:01 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '571'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a95183a7a85e6bdfe381b2510bf70f34
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=pjX1I6y8RlqCjS.gvOqvXk4vM69UNwFwmslh1BhALNg-1739214901-1.0.1.1-nJcNlSdNcug82eDl7KSvteLbsg0xCiEh2yI1TZX2jMAblL7AMQ8LFhvXkJLlAMfk49RMzRzWy2aiQgeM7WRHPg;
+        _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzTXDcgKWq3yosIyBal8LcY8dDrn1\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739214903,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_c41SAnqyEKNXEAZd5XV3jKF3\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider specifying
+      the tone or context of the greeting for more engaging interactions.\\\",\\\"Clarify
+      if additional greetings or responses are acceptable to enhance the task's scope.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
+      }\"\n            }\n          }\n        ],\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 273,\n    \"completion_tokens\": 43,\n
+      \   \"total_tokens\": 316,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90fe6cf8c96e67b3-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 10 Feb 2025 19:15:04 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1181'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b2286c8ae6f9b2a42f46a3e2c52b4211
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_end_kickoff_event.yaml

@@ -0,0 +1,315 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJK2OCJSkUj1plgbj59b4dC39QV2\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698990,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd396c0ab71698-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:56:30 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '951'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_2c3cb5caed61ccd1e058ef3e6301c691
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cq0TCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkShBMKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKkBwoQzBQBWCz+GLuI1awj3OPWrRIIGpT16t5bk6MqDENyZXcgQ3JlYXRlZDABOUBz
+      OyuEGSEYQYDBSCuEGSEYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
+      NzQ2MjhjSjEKB2NyZXdfaWQSJgokMDE3NjQ5ZWMtYTBlMS00MzYxLWFlNjgtYzA1N2E3ZGM5YzI5
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jl
+      d19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEi
+      LCAiaWQiOiAiOGU3NzgyN2QtN2Y2OC00ZDA2LWI2YTctOWI4YjRkMGE0YzMzIiwgInJvbGUiOiAi
+      YmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0i
+      OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIs
+      ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBm
+      YWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdf
+      dGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAi
+      aWQiOiAiOTJiZDIzMWYtYzAxMC00ZDI3LWIxNGYtZjE5NjEyZTBmZTkzIiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNl
+      X2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChC22Au0eMkAAjV6cfU1NrNIEggxb1Bq
+      Xnll/ioMVGFzayBDcmVhdGVkMAE5IOJaK4QZIRhBwG5bK4QZIRhKLgoIY3Jld19rZXkSIgogZTU4
+      MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiQwMTc2NDllYy1hMGUx
+      LTQzNjEtYWU2OC1jMDU3YTdkYzljMjlKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4
+      OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQ5MmJkMjMxZi1jMDEwLTRkMjctYjE0Zi1mMTk2
+      MTJlMGZlOTN6AhgBhQEAAQAAEqQHChC63jCLGR8RP8RmYiHrdNVeEggZ39ffmGm5xyoMQ3JldyBD
+      cmVhdGVkMAE5GFEe04QZIRhBELEq04QZIRhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoa
+      Cg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
+      ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiQ5MTY4YmQxNC0yN2Q2LTQ3NWMtODljOC01
+      NjJjOTAyMGIxOTBKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkS
+      AhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMS
+      AhgBStECCgtjcmV3X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2
+      YjI0OWM0YzY0YSIsICJpZCI6ICI4ZTc3ODI3ZC03ZjY4LTRkMDYtYjZhNy05YjhiNGQwYTRjMzMi
+      LCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIw
+      LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
+      dC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      XUr/AQoKY3Jld190YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNi
+      MjZhMTNkMiIsICJpZCI6ICI5MmJkMjMxZi1jMDEwLTRkMjctYjE0Zi1mMTk2MTJlMGZlOTMiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogImJhc2VfYWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
+      MjQ5YzRjNjRhIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEOo6FGs7r9hHrN+f
+      qhMTUysSCJgbYV+vQMbCKgxUYXNrIENyZWF0ZWQwATlAxjrThBkhGEEYIDvThBkhGEouCghjcmV3
+      X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDkx
+      NjhiZDE0LTI3ZDYtNDc1Yy04OWM4LTU2MmM5MDIwYjE5MEouCgh0YXNrX2tleRIiCiAxYjE1ZWYy
+      MzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDkyYmQyMzFmLWMwMTAtNGQy
+      Ny1iMTRmLWYxOTYxMmUwZmU5M3oCGAGFAQABAAA=
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '2480'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Tue, 04 Feb 2025 19:56:31 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJK3bJiyqGhPeqdCcCjoeNavGHrR\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698991,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_uAFkclWHIRqgrXFrQFcEoUIS\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Include additional
+      context for the greeting to make it more meaningful.\\\",\\\"Specify if you
+      want a casual or formal tone for greetings.\\\",\\\"Provide examples of variations
+      of the greeting if necessary.\\\"],\\\"quality\\\":10,\\\"entities\\\":[],\\\"relationships\\\":[]}\"\n
+      \           }\n          }\n        ],\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 273,\n    \"completion_tokens\": 50,\n
+      \   \"total_tokens\": 323,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd3973589f1698-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:56:32 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1408'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_519fd27ca3d5da4d541c4331654e0520
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_end_task_event.yaml

@@ -0,0 +1,357 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJlK2np8dMxYgsDIuyz2TSKKELWh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738700682,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd62c1fdb0fa6a-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 20:24:42 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '326'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_22be86be6fd9d69ca8d310ef534e7bec
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      Cp0mCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS9CUKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKkBwoQfRmsiIy66Scw43CcUw5ZiBIIfYDEhWJTOTkqDENyZXcgQ3JlYXRlZDABOcD6
+      XvsOGyEYQWC2bPsOGyEYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
+      NzQ2MjhjSjEKB2NyZXdfaWQSJgokMDMzNTZiYmEtMzJmZC00OThmLTgxYTItYzc1ZDBkMzc2N2Qx
+      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
+      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jl
+      d19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEi
+      LCAiaWQiOiAiZjY5YTRmYTMtMzQ4OC00MmFhLTlhMTQtMGEzZmEyOWJmYjZjIiwgInJvbGUiOiAi
+      YmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0i
+      OiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIs
+      ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBm
+      YWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdf
+      dGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAi
+      aWQiOiAiNDllNzk0MmMtZTJiMy00YmE1LTg5MTUtMTYwYjQxMDU2ZmVlIiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNl
+      X2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
+      ICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChCLgjutPq/3tkNyPqVjfbZhEgjhB7lb
+      clxzdyoMVGFzayBDcmVhdGVkMAE5CC9++w4bIRhBeMN++w4bIRhKLgoIY3Jld19rZXkSIgogZTU4
+      MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiQwMzM1NmJiYS0zMmZk
+      LTQ5OGYtODFhMi1jNzVkMGQzNzY3ZDFKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4
+      OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQ0OWU3OTQyYy1lMmIzLTRiYTUtODkxNS0xNjBi
+      NDEwNTZmZWV6AhgBhQEAAQAAEqQHChC7SpRSs6eG9XFmYuMQgghQEghpZMlScOy2DyoMQ3JldyBD
+      cmVhdGVkMAE50O2cAA8bIRhBOFmrAA8bIRhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoa
+      Cg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
+      ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRlYTQ1MWY2OS00Zjk3LTQ4MjYtOWNlYi04
+      NTAzMDk2MTQ2MDlKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkS
+      AhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMS
+      AhgBStECCgtjcmV3X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2
+      YjI0OWM0YzY0YSIsICJpZCI6ICJmNjlhNGZhMy0zNDg4LTQyYWEtOWExNC0wYTNmYTI5YmZiNmMi
+      LCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIw
+      LCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdw
+      dC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119
+      XUr/AQoKY3Jld190YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNi
+      MjZhMTNkMiIsICJpZCI6ICI0OWU3OTQyYy1lMmIzLTRiYTUtODkxNS0xNjBiNDEwNTZmZWUiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogImJhc2VfYWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
+      MjQ5YzRjNjRhIiwgInRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEM1q5zTl6Q6WKHPQ
+      eIqEm7sSCCWi2wvaFqpfKgxUYXNrIENyZWF0ZWQwATmIObwADxshGEEAo7wADxshGEouCghjcmV3
+      X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJGVh
+      NDUxZjY5LTRmOTctNDgyNi05Y2ViLTg1MDMwOTYxNDYwOUouCgh0YXNrX2tleRIiCiAxYjE1ZWYy
+      MzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDQ5ZTc5NDJjLWUyYjMtNGJh
+      NS04OTE1LTE2MGI0MTA1NmZlZXoCGAGFAQABAAASpAcKEEhIZzGdZRAdvfcluDR5qvESCFMGo60X
+      V/dYKgxDcmV3IENyZWF0ZWQwATnY8LgBDxshGEGQrsUBDxshGEobCg5jcmV3YWlfdmVyc2lvbhIJ
+      CgcwLjEwMC4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuOEouCghjcmV3X2tleRIiCiBlNTgw
+      NzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDA3MDJmOGU1LWRjMTYt
+      NDlhYi1hMWY1LThjOWQyY2IwMDYwYkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtj
+      cmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVy
+      X29mX2FnZW50cxICGAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImFkMTUzMTYxYzVj
+      NWE4NTZhYTBkMDZiMjQ5YzRjNjRhIiwgImlkIjogImY2OWE0ZmEzLTM0ODgtNDJhYS05YTE0LTBh
+      M2ZhMjliZmI2YyIsICJyb2xlIjogImJhc2VfYWdlbnQiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1h
+      eF9pdGVyIjogMjAsICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIs
+      ICJsbG0iOiAiZ3B0LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxs
+      b3dfY29kZV9leGVjdXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNf
+      bmFtZXMiOiBbXX1dSv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjFiMTVlZjIzOTE1YjI3
+      NTVlODlhMGVjM2IyNmExM2QyIiwgImlkIjogIjQ5ZTc5NDJjLWUyYjMtNGJhNS04OTE1LTE2MGI0
+      MTA1NmZlZSIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxz
+      ZSwgImFnZW50X3JvbGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9rZXkiOiAiYWQxNTMxNjFjNWM1
+      YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQ
+      PkgvMtq3aT5YPXE8gCRxPBIIMx/zQOuC+8sqDFRhc2sgQ3JlYXRlZDABOYjk2AEPGyEYQZiI2QEP
+      GyEYSi4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2Ny
+      ZXdfaWQSJgokMDcwMmY4ZTUtZGMxNi00OWFiLWExZjUtOGM5ZDJjYjAwNjBiSi4KCHRhc2tfa2V5
+      EiIKIDFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tfaWQSJgokNDllNzk0
+      MmMtZTJiMy00YmE1LTg5MTUtMTYwYjQxMDU2ZmVlegIYAYUBAAEAABKkBwoQex7nA0gUUrZHbN6F
+      gWp/gBIIKPd4fiRi7DwqDENyZXcgQ3JlYXRlZDABOTiIrAIPGyEYQdCAtwIPGyEYShsKDmNyZXdh
+      aV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi44Si4KCGNyZXdf
+      a2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokMGNm
+      YjUzZWItMDA2Mi00YmVmLTk1ZTgtMDgwMjQ3NmNkMWRlShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1
+      ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoV
+      Y3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAi
+      YWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiZjY5YTRmYTMtMzQ4OC00
+      MmFhLTlhMTQtMGEzZmEyOWJmYjZjIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6
+      IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGlu
+      Z19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/Ijog
+      ZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6
+      IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMWIx
+      NWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiNDllNzk0MmMtZTJiMy00YmE1
+      LTg5MTUtMTYwYjQxMDU2ZmVlIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lu
+      cHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFnZW50X2tleSI6ICJh
+      ZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgB
+      hQEAAQAAEo4CChD+ymllejCksajGYDua8tgNEghnjlejrbuw2SoMVGFzayBDcmVhdGVkMAE5EDrI
+      Ag8bIRhBGIzIAg8bIRhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3
+      NDYyOGNKMQoHY3Jld19pZBImCiQwY2ZiNTNlYi0wMDYyLTRiZWYtOTVlOC0wODAyNDc2Y2QxZGVK
+      LgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDJKMQoHdGFza19p
+      ZBImCiQ0OWU3OTQyYy1lMmIzLTRiYTUtODkxNS0xNjBiNDEwNTZmZWV6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '4896'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Tue, 04 Feb 2025 20:24:47 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJlLVC3gCB9gRI0ZSkoPCZY7EwpQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738700683,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_mgwImOITW8lkjzAyf9Pp76cL\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide context or
+      additional information to make tasks more engaging.\\\",\\\"Encourage variations
+      in responses to make the interaction more dynamic.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
+      common word used to initiate a conversation or express friendliness.\\\",\\\"relationships\\\":[\\\"initiates
+      conversation\\\",\\\"expresses friendliness\\\"]}]}\"\n            }\n          }\n
+      \       ],\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      273,\n    \"completion_tokens\": 71,\n    \"total_tokens\": 344,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90cd62c4ba41fa6a-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 20:24:50 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '7347'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_aec28dd3fe998d628754e8429623bf9e
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_kickoff_events.yaml

@@ -0,0 +1,245 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJIrSWAFqDEsNtLRhcM8vMHO9Ejw\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698917,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd37a83f5f176a-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:55:18 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
+        path=/; expires=Tue, 04-Feb-25 20:25:18 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '894'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_864253996bbc0f797f9a2c1b9247a0d5
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rKQWp4fbAvcCp4rasEN6DqiTjQfiWYpLfjcLpWcmzi0-1738698918-1.0.1.1-qlcCSdBY3KWbzVms0eLtz5ub5SSLGs_sRLxTdNhDk_purQuz9k6EFp8PHJfN3aP_sLnuyKnFlppM3.2k_dCtPQ;
+        _cfuvid=Oi91zDXvjWohBYXSVqK4hFsq3_GZePEIIbi7b7wrjcI-1738698918130-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJIsVEppA04iGQh0k6sanKnVObrO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698918,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_AQ3iizjGWjEvk1SmhGCzjbf1\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide context for
+      the greeting, like a specific scenario or recipient.\\\",\\\"Encourage responses
+      or follow-ups to promote engagement.\\\",\\\"Specify the tone or formality of
+      the greeting, if relevant.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
+      common informal expression used to initiate conversation or acknowledge someone.\\\",\\\"relationships\\\":[\\\"used
+      in conversation\\\",\\\"expresses friendliness\\\"]}]}\"\n            }\n          }\n
+      \       ],\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      273,\n    \"completion_tokens\": 84,\n    \"total_tokens\": 357,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90cd37aec8c8176a-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:55:21 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '3269'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e6e67a3f5c6f2d48e0351cdce95edd97
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_start_kickoff_event.yaml

@@ -0,0 +1,243 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJJzafmayYpGTsTAWbOyZkmQJNa5\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698987,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 90cd395b0e641698-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:56:27 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
+        path=/; expires=Tue, 04-Feb-25 20:26:27 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '839'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_577b484a927b455c40ed80f9fd4d9106
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJJz10KP7iadNPdKsbcsvHBa7cic\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738698987,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_czeHQgy5eiOVa0zlrtcfwepe\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
+      or details for similar tasks to enhance output expectations.\\\",\\\"Encourage
+      creativity in responses for simple tasks to engage users more effectively.\\\"],\\\"quality\\\":10,\\\"entities\\\":[]
+      }\"\n            }\n          }\n        ],\n        \"refusal\": null\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 273,\n    \"completion_tokens\": 40,\n
+      \   \"total_tokens\": 313,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd39615b281698-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 19:56:29 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1411'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_3e717a80c7d9c5ea19893dd990aaae26
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_start_task_event.yaml

@@ -0,0 +1,245 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=4s6sWmJ49B9F_wNc1STtdZF1nikfl6uN9_ov3Xzfa8U-1738698987-1.0.1.1-lmbRRS1MHrDbnU93Gh16CP3qNczxxIrQnyBU7vpHSwNf6PdmuWOHKd1mkl5SBx6rg7p1NLaNUMyqDDcE0Mvjzw;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJiiHEQwIXsiG0Sd5wofcuhxVbo9\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738700520,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd5ecd0f7667ee-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 20:22:01 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
+        path=/; expires=Tue, 04-Feb-25 20:52:01 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '450'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_10eaafc81640a98a0a4789d270dd94d9
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1962'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=nedOdWE1YnKQYt1kSbrcA.zhwa3bZDzmZqTOjZYER0c-1738700521-1.0.1.1-xQk9iXOvqvyXNhkIOgc8Ws2WYcT1mJFkDCvCC8xA5joFD8QfNrBIAr_Qs6sIxt2EzXyeFwBA6gA8ZgWApCHx0Q;
+        _cfuvid=Cl48aI8.jSRja0Pqr6Jrh3mAnigd4rDn6lhGicyjMPY-1738698987673-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AxJijOhk12Ua6lS23IwtZTachfjq9\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1738700521,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_DSteeMHHPf5RanJb8qjCo4qx\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Consider adding context
+      for the greeting to make it more engaging.\\\",\\\"Specify if any additional
+      information or tone is desired in the greeting.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"greeting\\\",\\\"type\\\":\\\"text\\\",\\\"description\\\":\\\"A
+      simple greeting phrase\\\",\\\"relationships\\\":[\\\"is a\\\",\\\"is part of
+      a conversation\\\"]}]}\"\n            }\n          }\n        ],\n        \"refusal\":
+      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 273,\n    \"completion_tokens\":
+      67,\n    \"total_tokens\": 340,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_bd83329f63\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90cd5ed20cb267ee-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 04 Feb 2025 20:22:02 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1624'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999876'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4ee944acdd3928afbf6c5562403b064a
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_crew_emits_task_failed_event.yaml

@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzpkZLpCyjKT5d6Udfx4zAme2sOMy\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739300299,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 910691d3ab90ebef-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Feb 2025 18:58:20 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MOH5EY6n3p8JKY53.yz7qzLuLYsEB8QdQXH09loUMBM-1739300300-1.0.1.1-hjb4mk04sMygPFhoFyiySKZSqB_fN5PbhbOyn.kipa3.eLvk7EtriDyjvGkBFIAV13DYnc08BfF_l2kxdx9hfQ;
+        path=/; expires=Tue, 11-Feb-25 19:28:20 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=uu.cEiV.FfgvSvCdKOooDYJWrwjVEuFeGdQodijGUUI-1739300300232-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1357'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_2277503f851195e7d7a43b66eb044454
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_multiple_handlers_for_same_event.yaml

@@ -0,0 +1,111 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000;
+        __cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzpWx6pctOvzu6xsbyg0XfSAc0q9V\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739299455,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 91067d3ddc68fa16-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Feb 2025 18:44:16 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '703'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_89222c00e4608e8557a135e91b223556
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_register_handler_adds_new_handler.yaml

@@ -0,0 +1,114 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nTo
+      give my best complete final answer to the task respond using the exact following
+      format:\n\nThought: I now can give a great answer\nFinal Answer: Your final
+      answer must be the great and the most complete as possible, it must be outcome
+      described.\n\nI MUST use these formats, my job depends on it!"}, {"role": "user",
+      "content": "\nCurrent Task: Just say hi\n\nThis is the expect criteria for your
+      final answer: hi\nyou MUST return the actual complete content as the final answer,
+      not a summary.\n\nBegin! This is VERY important to you, use the tools available
+      and give your best Final Answer, your job depends on it!\n\nThought:"}], "model":
+      "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '836'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=gsNyCo_jrDOolzf8SXHDaxQQrEgdR3jgv4OAH8MziDE-1739291824699-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzpWxLzAcRzigZuIGmjP3ckQgxAom\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739299455,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"I now can give a great answer  \\nFinal
+      Answer: hi\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      161,\n    \"completion_tokens\": 12,\n    \"total_tokens\": 173,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 91067d389e90fa16-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Tue, 11 Feb 2025 18:44:15 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=cRijYuylMGzRGxv3udQL5PhHOR5mRN_9_eLLwevlM_o-1739299455-1.0.1.1-Fszr_Msw0B1.IBMkiunP.VF2ilul1YGZZV8TqMcO3Q2SHvSlqfgm9NHgns1bJrm0wWRvHiCE7wdZfUAOx7T3Lg;
+        path=/; expires=Tue, 11-Feb-25 19:14:15 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '716'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999810'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_ef807dc3223d40332aae8a313e96ef3a
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_tools_emits_finished_events.yaml

@@ -0,0 +1,512 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
+      Say hi\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, only one
+      name of [say_hi], just the name, exactly as it''s written.\nAction Input: the
+      input to the action, just a simple JSON object, enclosed in curly braces, using
+      \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Just say
+      hi\n\nThis is the expect criteria for your final answer: hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1275'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzUA6kJQfpUvB4CGot4gSfAIR0foh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739217314,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"you should always think about what to
+      do  \\nAction: say_hi  \\nAction Input: {}  \",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 257,\n    \"completion_tokens\":
+      19,\n    \"total_tokens\": 276,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\":
+      0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n
+      \     \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90fea7d78e1fceb9-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 10 Feb 2025 19:55:15 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q;
+        path=/; expires=Mon, 10-Feb-25 20:25:15 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '526'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999703'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_f6358ff0cc7a2b8d2e167ab00a40f2a4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are base_agent. You are
+      a helpful assistant that just says hi\nYour personal goal is: Just say hi\nYou
+      ONLY have access to the following tools, and should NEVER make up tools that
+      are not listed here:\n\nTool Name: say_hi\nTool Arguments: {}\nTool Description:
+      Say hi\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought:
+      you should always think about what to do\nAction: the action to take, only one
+      name of [say_hi], just the name, exactly as it''s written.\nAction Input: the
+      input to the action, just a simple JSON object, enclosed in curly braces, using
+      \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce
+      all necessary information is gathered, return the following format:\n\n```\nThought:
+      I now know the final answer\nFinal Answer: the final answer to the original
+      input question\n```"}, {"role": "user", "content": "\nCurrent Task: Just say
+      hi\n\nThis is the expect criteria for your final answer: hi\nyou MUST return
+      the actual complete content as the final answer, not a summary.\n\nBegin! This
+      is VERY important to you, use the tools available and give your best Final Answer,
+      your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "you
+      should always think about what to do  \nAction: say_hi  \nAction Input: {}  \nObservation:
+      hi"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1410'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
+        __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzUA7QdlQy1WZZijxNWUv25sZycg0\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739217315,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
+      Answer: hi\\n```\",\n        \"refusal\": null\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      283,\n    \"completion_tokens\": 17,\n    \"total_tokens\": 300,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90fea7dc5ba6ceb9-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 10 Feb 2025 19:55:15 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '388'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999680'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_7d7c68b90b3a9c3ac6092fe17ac1185a
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: !!binary |
+      CoMzCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS2jIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKOAgoQ2EINIGZRoXD589od63oHmBIIMfUgEWudUbIqDFRhc2sgQ3JlYXRlZDABOcjI
+      7lbu8CIYQZB471bu8CIYSi4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhj
+      NzQ2MjhjSjEKB2NyZXdfaWQSJgokNTE4ODdiOTktY2FlMy00Yjc4LWJjMGEtMDY4MmVmNWEzNGQ0
+      Si4KCHRhc2tfa2V5EiIKIDFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tf
+      aWQSJgokMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQ
+      RzhWoF6ewSTS/qUc9yeFRhIIM3SNZCwjz5AqDENyZXcgQ3JlYXRlZDABOQjrGlru8CIYQdgbKVru
+      8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      Mi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2Ny
+      ZXdfaWQSJgokYzk4ODFkY2YtMmM0MS00ZjRlLTgzMjctNjJjYjFhYjJkOTg4ShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIK
+      vgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2
+      NzJiMDgtOTU4ZC00MjljLWE3ZTctY2ZlN2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIs
+      ICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVu
+      Y3Rpb25fY2FsbGluZ19sbG0iOiAiIiwgImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9u
+      X2VuYWJsZWQ/IjogZmFsc2UsICJhbGxvd19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9y
+      ZXRyeV9saW1pdCI6IDIsICJ0b29sc19uYW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFb
+      eyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlm
+      MWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVkMDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxz
+      ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFn
+      ZW50X2tleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1l
+      cyI6IFtdfV16AhgBhQEAAQAAEo4CChB8AxWkb2Uwpdc8RpyCRqw5EggJAxbgNu81XyoMVGFzayBD
+      cmVhdGVkMAE5+HQ8Wu7wIhhB+PE8Wu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVh
+      ZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRjOTg4MWRjZi0yYzQxLTRmNGUtODMyNy02
+      MmNiMWFiMmQ5ODhKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEz
+      ZDJKMQoHdGFza19pZBImCiQzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgB
+      hQEAAQAAEqQHChCcXvdbsgYC+gzCMrXs3LN/EgijKwJLCRIiHioMQ3JldyBDcmVhdGVkMAE5iJqz
+      vu7wIhhBqKC/vu7wIhhKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVy
+      c2lvbhIICgYzLjEyLjhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3
+      NDYyOGNKMQoHY3Jld19pZBImCiQ2Zjk1ZWI3Yy0wOWM5LTQxOTYtYWFiYi1kOWIxNmMxMzZjODdK
+      HAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdf
+      bnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStECCgtjcmV3
+      X2FnZW50cxLBAgq+Alt7ImtleSI6ICJhZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIs
+      ICJpZCI6ICI1NTY3MmIwOC05NThkLTQyOWMtYTdlNy1jZmU3ZThjYzA4ZmQiLCAicm9sZSI6ICJi
+      YXNlX2FnZW50IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6
+      IG51bGwsICJmdW5jdGlvbl9jYWxsaW5nX2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwg
+      ImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZh
+      bHNlLCAibWF4X3JldHJ5X2xpbWl0IjogMiwgInRvb2xzX25hbWVzIjogW119XUr/AQoKY3Jld190
+      YXNrcxLwAQrtAVt7ImtleSI6ICIxYjE1ZWYyMzkxNWIyNzU1ZTg5YTBlYzNiMjZhMTNkMiIsICJp
+      ZCI6ICIzOWYwOWYxZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzQiLCAiYXN5bmNfZXhlY3V0
+      aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogImJhc2Vf
+      YWdlbnQiLCAiYWdlbnRfa2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZiMjQ5YzRjNjRhIiwg
+      InRvb2xzX25hbWVzIjogW119XXoCGAGFAQABAAASjgIKEExDo5nPLyHb2H8DfYjPoX4SCLEYs+24
+      8EenKgxUYXNrIENyZWF0ZWQwATmI4NG+7vAiGEFYZdK+7vAiGEouCghjcmV3X2tleRIiCiBlNTgw
+      NzAxZDUyZWI2NWFmZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDZmOTVlYjdjLTA5Yzkt
+      NDE5Ni1hYWJiLWQ5YjE2YzEzNmM4N0ouCgh0YXNrX2tleRIiCiAxYjE1ZWYyMzkxNWIyNzU1ZTg5
+      YTBlYzNiMjZhMTNkMkoxCgd0YXNrX2lkEiYKJDM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZl
+      ZDA5N2YzNHoCGAGFAQABAAASpAcKEBBQzR2bcR/7woQ+VkaJ4kQSCD1LFx3SNPPPKgxDcmV3IENy
+      ZWF0ZWQwATlotsW/7vAiGEEgA9C/7vAiGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwMC4wShoK
+      DnB5dGhvbl92ZXJzaW9uEggKBjMuMTIuOEouCghjcmV3X2tleRIiCiBlNTgwNzAxZDUyZWI2NWFm
+      ZjI0ZWVmZTc4Yzc0NjI4Y0oxCgdjcmV3X2lkEiYKJDJiMWI2MGYzLTNlZTMtNGNjYi05MDM2LTdk
+      MzE4OTJiYjVkZkocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRIC
+      EABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxIC
+      GAFK0QIKC2NyZXdfYWdlbnRzEsECCr4CW3sia2V5IjogImFkMTUzMTYxYzVjNWE4NTZhYTBkMDZi
+      MjQ5YzRjNjRhIiwgImlkIjogIjU1NjcyYjA4LTk1OGQtNDI5Yy1hN2U3LWNmZTdlOGNjMDhmZCIs
+      ICJyb2xlIjogImJhc2VfYWdlbnQiLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjAs
+      ICJtYXhfcnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0
+      LTRvLW1pbmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVj
+      dXRpb24/IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1d
+      Sv8BCgpjcmV3X3Rhc2tzEvABCu0BW3sia2V5IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2Iy
+      NmExM2QyIiwgImlkIjogIjM5ZjA5ZjFlLTkyZjgtNGRiYi04MzQwLTY1NmZlZDA5N2YzNCIsICJh
+      c3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3Jv
+      bGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9rZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIy
+      NDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBbXX1degIYAYUBAAEAABKOAgoQmT07KMiFRgzOOPQf
+      I4bJPhIIqzN+pCYM6IUqDFRhc2sgQ3JlYXRlZDABOYjr3r/u8CIYQehY37/u8CIYSi4KCGNyZXdf
+      a2V5EiIKIGU1ODA3MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokMmIx
+      YjYwZjMtM2VlMy00Y2NiLTkwMzYtN2QzMTg5MmJiNWRmSi4KCHRhc2tfa2V5EiIKIDFiMTVlZjIz
+      OTE1YjI3NTVlODlhMGVjM2IyNmExM2QySjEKB3Rhc2tfaWQSJgokMzlmMDlmMWUtOTJmOC00ZGJi
+      LTgzNDAtNjU2ZmVkMDk3ZjM0egIYAYUBAAEAABKkBwoQE53vZNAWshkoNK1bqTvovRII83djkBUL
+      EbcqDENyZXcgQ3JlYXRlZDABORBBzsDu8CIYQbAU2MDu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkK
+      BzAuMTAwLjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIGU1ODA3
+      MDFkNTJlYjY1YWZmMjRlZWZlNzhjNzQ2MjhjSjEKB2NyZXdfaWQSJgokNTQ0MWY0MWYtOTVjMC00
+      YzdkLTkxM2QtNDUxODcwY2YyZjYzShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2Ny
+      ZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJf
+      b2ZfYWdlbnRzEgIYAUrRAgoLY3Jld19hZ2VudHMSwQIKvgJbeyJrZXkiOiAiYWQxNTMxNjFjNWM1
+      YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAiaWQiOiAiNTU2NzJiMDgtOTU4ZC00MjljLWE3ZTctY2Zl
+      N2U4Y2MwOGZkIiwgInJvbGUiOiAiYmFzZV9hZ2VudCIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4
+      X2l0ZXIiOiAyMCwgIm1heF9ycG0iOiBudWxsLCAiZnVuY3Rpb25fY2FsbGluZ19sbG0iOiAiIiwg
+      ImxsbSI6ICJncHQtNG8tbWluaSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJhbGxv
+      d19jb2RlX2V4ZWN1dGlvbj8iOiBmYWxzZSwgIm1heF9yZXRyeV9saW1pdCI6IDIsICJ0b29sc19u
+      YW1lcyI6IFtdfV1K/wEKCmNyZXdfdGFza3MS8AEK7QFbeyJrZXkiOiAiMWIxNWVmMjM5MTViMjc1
+      NWU4OWEwZWMzYjI2YTEzZDIiLCAiaWQiOiAiMzlmMDlmMWUtOTJmOC00ZGJiLTgzNDAtNjU2ZmVk
+      MDk3ZjM0IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
+      LCAiYWdlbnRfcm9sZSI6ICJiYXNlX2FnZW50IiwgImFnZW50X2tleSI6ICJhZDE1MzE2MWM1YzVh
+      ODU2YWEwZDA2YjI0OWM0YzY0YSIsICJ0b29sc19uYW1lcyI6IFtdfV16AhgBhQEAAQAAEo4CChBV
+      JNEz3VIdOlQM9VT3bctVEgisogN707a2AioMVGFzayBDcmVhdGVkMAE5kGbnwO7wIhhBaMDnwO7w
+      IhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jl
+      d19pZBImCiQ1NDQxZjQxZi05NWMwLTRjN2QtOTEzZC00NTE4NzBjZjJmNjNKLgoIdGFza19rZXkS
+      IgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2YTEzZDJKMQoHdGFza19pZBImCiQzOWYwOWYx
+      ZS05MmY4LTRkYmItODM0MC02NTZmZWQwOTdmMzR6AhgBhQEAAQAAErQHChDA7zaLCfy56rd5t3oS
+      rDPZEgjYoSW3mq6WJyoMQ3JldyBDcmVhdGVkMAE5cP/5we7wIhhBIH0Dwu7wIhhKGwoOY3Jld2Fp
+      X3ZlcnNpb24SCQoHMC4xMDAuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjEyLjhKLgoIY3Jld19r
+      ZXkSIgogZTU4MDcwMWQ1MmViNjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjcz
+      MTc1ZS04Y2Q1LTQ1ZWUtYTZiOS0xYWFjMTliODQxZWJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVl
+      bnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVj
+      cmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStkCCgtjcmV3X2FnZW50cxLJAgrGAlt7ImtleSI6ICJh
+      ZDE1MzE2MWM1YzVhODU2YWEwZDA2YjI0OWM0YzY0YSIsICJpZCI6ICJmMGUwMGIzZi0wZWNmLTQ2
+      OGQtYjdjMC0yZmJhN2I5OTc5YjMiLCAicm9sZSI6ICJiYXNlX2FnZW50IiwgInZlcmJvc2U/Ijog
+      ZmFsc2UsICJtYXhfaXRlciI6IDIwLCAibWF4X3JwbSI6IG51bGwsICJmdW5jdGlvbl9jYWxsaW5n
+      X2xsbSI6ICIiLCAibGxtIjogImdwdC00by1taW5pIiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBm
+      YWxzZSwgImFsbG93X2NvZGVfZXhlY3V0aW9uPyI6IGZhbHNlLCAibWF4X3JldHJ5X2xpbWl0Ijog
+      MiwgInRvb2xzX25hbWVzIjogWyJzYXlfaGkiXX1dSocCCgpjcmV3X3Rhc2tzEvgBCvUBW3sia2V5
+      IjogIjFiMTVlZjIzOTE1YjI3NTVlODlhMGVjM2IyNmExM2QyIiwgImlkIjogImFhMGFmMmE2LTdm
+      MTktNDZmNi1iMjMxLTg1M2JjYzYxYzhiZiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJo
+      dW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiYmFzZV9hZ2VudCIsICJhZ2VudF9r
+      ZXkiOiAiYWQxNTMxNjFjNWM1YTg1NmFhMGQwNmIyNDljNGM2NGEiLCAidG9vbHNfbmFtZXMiOiBb
+      InNheV9oaSJdfV16AhgBhQEAAQAAEo4CChBH8NUZY1Cv8sM2lfQLaEogEgiFlW7Wp7QpdyoMVGFz
+      ayBDcmVhdGVkMAE5MNkPwu7wIhhBUCcQwu7wIhhKLgoIY3Jld19rZXkSIgogZTU4MDcwMWQ1MmVi
+      NjVhZmYyNGVlZmU3OGM3NDYyOGNKMQoHY3Jld19pZBImCiRmNjczMTc1ZS04Y2Q1LTQ1ZWUtYTZi
+      OS0xYWFjMTliODQxZWJKLgoIdGFza19rZXkSIgogMWIxNWVmMjM5MTViMjc1NWU4OWEwZWMzYjI2
+      YTEzZDJKMQoHdGFza19pZBImCiRhYTBhZjJhNi03ZjE5LTQ2ZjYtYjIzMS04NTNiY2M2MWM4YmZ6
+      AhgBhQEAAQAAEooBChCJg/wSACw+HIDy4vvYISP/EgjoC/oI/1V0cCoKVG9vbCBVc2FnZTABOWA0
+      ifTu8CIYQTD0lPTu8CIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTAwLjBKFQoJdG9vbF9uYW1l
+      EggKBnNheV9oaUoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6534'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.27.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Mon, 10 Feb 2025 19:55:17 GMT
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "Assess the quality of the task
+      completed based on the description, expected output, and actual results.\n\nTask
+      Description:\nJust say hi\n\nExpected Output:\nhi\n\nActual Output:\nhi\n```\n\nPlease
+      provide:\n- Bullet points suggestions to improve future similar tasks\n- A score
+      from 0 to 10 evaluating on completion, quality, and overall performance- Entities
+      extracted from the task output, if any, their type, description, and relationships"}],
+      "model": "gpt-4o-mini", "tool_choice": {"type": "function", "function": {"name":
+      "TaskEvaluation"}}, "tools": [{"type": "function", "function": {"name": "TaskEvaluation",
+      "description": "Correctly extracted `TaskEvaluation` with all the required parameters
+      with correct types", "parameters": {"$defs": {"Entity": {"properties": {"name":
+      {"description": "The name of the entity.", "title": "Name", "type": "string"},
+      "type": {"description": "The type of the entity.", "title": "Type", "type":
+      "string"}, "description": {"description": "Description of the entity.", "title":
+      "Description", "type": "string"}, "relationships": {"description": "Relationships
+      of the entity.", "items": {"type": "string"}, "title": "Relationships", "type":
+      "array"}}, "required": ["name", "type", "description", "relationships"], "title":
+      "Entity", "type": "object"}}, "properties": {"suggestions": {"description":
+      "Suggestions to improve future similar tasks.", "items": {"type": "string"},
+      "title": "Suggestions", "type": "array"}, "quality": {"description": "A score
+      from 0 to 10 evaluating on completion, quality, and overall performance, all
+      taking into account the task description, expected output, and the result of
+      the task.", "title": "Quality", "type": "number"}, "entities": {"description":
+      "Entities extracted from the task output.", "items": {"$ref": "#/$defs/Entity"},
+      "title": "Entities", "type": "array"}}, "required": ["entities", "quality",
+      "suggestions"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1967'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=efIHP1NUsh1dFewGJBu4YoBu6hhGa8vjOOKQglYQGno-1739214901306-0.0.1.1-604800000;
+        __cf_bm=fmlg1wjOwuOwZhUUOEtL1tQYluAPumn7AHLF8s0EU2Y-1739217315-1.0.1.1-PQDvxn8TOhzaznlHjwVsqPZUzbAyJWFkvzCubfNJydTu2_AyA1cJ8hkM0khsEE4UY_xp8iPe2gSGmH1ydrDa0Q
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.61.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.61.0
+      x-stainless-raw-response:
+      - 'true'
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.8
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-AzUA8oE0A2d99i1Khpu0CI7fSgRtZ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1739217316,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": null,\n        \"tool_calls\": [\n          {\n
+      \           \"id\": \"call_bk3duHRErK1qCyvWJ1uVmmGl\",\n            \"type\":
+      \"function\",\n            \"function\": {\n              \"name\": \"TaskEvaluation\",\n
+      \             \"arguments\": \"{\\\"suggestions\\\":[\\\"Provide more context
+      or details for similar tasks to enhance clarity.\\\",\\\"Specify desired tone
+      or style for the output.\\\",\\\"Consider adding more variety in tasks to keep
+      engagement high.\\\"],\\\"quality\\\":10,\\\"entities\\\":[{\\\"name\\\":\\\"hi\\\",\\\"type\\\":\\\"greeting\\\",\\\"description\\\":\\\"A
+      casual way to say hello or acknowledge someone's presence.\\\",\\\"relationships\\\":[\\\"used
+      as a greeting\\\",\\\"expresses friendliness\\\"]}]}\"\n            }\n          }\n
+      \       ],\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      275,\n    \"completion_tokens\": 80,\n    \"total_tokens\": 355,\n    \"prompt_tokens_details\":
+      {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\":
+      {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\":
+      0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\":
+      \"default\",\n  \"system_fingerprint\": \"fp_72ed7ab54c\"\n}\n"
+    headers:
+      CF-RAY:
+      - 90fea7dfef41ceb9-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 10 Feb 2025 19:55:17 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      cf-cache-status:
+      - DYNAMIC
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '1535'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '30000'
+      x-ratelimit-limit-tokens:
+      - '150000000'
+      x-ratelimit-remaining-requests:
+      - '29999'
+      x-ratelimit-remaining-tokens:
+      - '149999874'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_55d8eb91b4318245556b73d3f4c1e7c4
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/test_events.py

@@ -0,0 +1,497 @@
+import json
+from datetime import datetime
+from unittest.mock import MagicMock, patch
+
+import pytest
+from pydantic import Field
+
+from crewai.agent import Agent
+from crewai.agents.crew_agent_executor import CrewAgentExecutor
+from crewai.crew import Crew
+from crewai.flow.flow import Flow, listen, start
+from crewai.task import Task
+from crewai.tools.base_tool import BaseTool
+from crewai.tools.tool_usage import ToolUsage
+from crewai.utilities.events.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+from crewai.utilities.events.crew_events import (
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewKickoffStartedEvent,
+)
+from crewai.utilities.events.crewai_event_bus import crewai_event_bus
+from crewai.utilities.events.event_types import ToolUsageFinishedEvent
+from crewai.utilities.events.flow_events import (
+    FlowCreatedEvent,
+    FlowFinishedEvent,
+    FlowStartedEvent,
+    MethodExecutionFailedEvent,
+    MethodExecutionStartedEvent,
+)
+from crewai.utilities.events.task_events import (
+    TaskCompletedEvent,
+    TaskFailedEvent,
+    TaskStartedEvent,
+)
+from crewai.utilities.events.tool_usage_events import (
+    ToolUsageErrorEvent,
+)
+
+base_agent = Agent(
+    role="base_agent",
+    llm="gpt-4o-mini",
+    goal="Just say hi",
+    backstory="You are a helpful assistant that just says hi",
+)
+
+base_task = Task(
+    description="Just say hi",
+    expected_output="hi",
+    agent=base_agent,
+)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_emits_start_kickoff_event():
+    received_events = []
+
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(CrewKickoffStartedEvent)
+        def handle_crew_start(source, event):
+            received_events.append(event)
+
+        crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+
+        crew.kickoff()
+
+        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():
+    received_events = []
+
+    @crewai_event_bus.on(CrewKickoffCompletedEvent)
+    def handle_crew_end(source, event):
+        received_events.append(event)
+
+    crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+
+    crew.kickoff()
+
+    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_kickoff_failed_event():
+    received_events = []
+
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(CrewKickoffFailedEvent)
+        def handle_crew_failed(source, event):
+            received_events.append(event)
+
+        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):
+                crew.kickoff()
+
+        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():
+    received_events = []
+
+    @crewai_event_bus.on(TaskStartedEvent)
+    def handle_task_start(source, event):
+        received_events.append(event)
+
+    crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+
+    crew.kickoff()
+
+    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():
+    received_events = []
+
+    @crewai_event_bus.on(TaskCompletedEvent)
+    def handle_task_end(source, event):
+        received_events.append(event)
+
+    crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+
+    crew.kickoff()
+
+    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():
+    received_events = []
+    received_sources = []
+
+    @crewai_event_bus.on(TaskFailedEvent)
+    def handle_task_failed(source, event):
+        received_events.append(event)
+        received_sources.append(source)
+
+    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):
+            agent.execute_task(task=task)
+
+            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():
+    received_events = []
+
+    @crewai_event_bus.on(AgentExecutionStartedEvent)
+    def handle_agent_start(source, event):
+        received_events.append(event)
+
+    @crewai_event_bus.on(AgentExecutionCompletedEvent)
+    def handle_agent_completed(source, event):
+        received_events.append(event)
+
+    crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+    crew.kickoff()
+    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():
+    received_events = []
+
+    @crewai_event_bus.on(AgentExecutionErrorEvent)
+    def handle_agent_start(source, event):
+        received_events.append(event)
+
+    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) as e:
+            base_agent.execute_task(
+                task=base_task,
+            )
+
+        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 = []
+
+    @crewai_event_bus.on(ToolUsageFinishedEvent)
+    def handle_tool_end(source, event):
+        received_events.append(event)
+
+    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 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 == {}
+    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 = []
+
+    @crewai_event_bus.on(ToolUsageErrorEvent)
+    def handle_tool_end(source, event):
+        received_events.append(event)
+
+    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()],
+    )
+
+    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 len(received_events) == 75
+    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 == {}
+    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():
+    received_events = []
+
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(FlowStartedEvent)
+        def handle_flow_start(source, event):
+            received_events.append(event)
+
+        class TestFlow(Flow[dict]):
+            @start()
+            def begin(self):
+                return "started"
+
+        flow = TestFlow()
+        flow.kickoff()
+
+        assert len(received_events) == 1
+        assert received_events[0].flow_name == "TestFlow"
+        assert received_events[0].type == "flow_started"
+
+
+def test_flow_emits_finish_event():
+    received_events = []
+
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(FlowFinishedEvent)
+        def handle_flow_finish(source, event):
+            received_events.append(event)
+
+        class TestFlow(Flow[dict]):
+            @start()
+            def begin(self):
+                return "completed"
+
+        flow = TestFlow()
+        result = flow.kickoff()
+
+        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 = []
+
+    with crewai_event_bus.scoped_handlers():
+
+        @crewai_event_bus.on(MethodExecutionStartedEvent)
+        def handle_method_start(source, event):
+            print("event in method name", event.method_name)
+            received_events.append(event)
+
+        class TestFlow(Flow[dict]):
+            @start()
+            def begin(self):
+                return "started"
+
+            @listen("begin")
+            def second_method(self):
+                return "executed"
+
+        flow = TestFlow()
+        flow.kickoff()
+
+        assert len(received_events) == 2
+
+        assert received_events[0].method_name == "begin"
+        assert received_events[0].flow_name == "TestFlow"
+        assert received_events[0].type == "method_execution_started"
+
+        assert received_events[1].method_name == "second_method"
+        assert received_events[1].flow_name == "TestFlow"
+        assert received_events[1].type == "method_execution_started"
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_register_handler_adds_new_handler():
+    received_events = []
+
+    def custom_handler(source, event):
+        received_events.append(event)
+
+    with crewai_event_bus.scoped_handlers():
+        crewai_event_bus.register_handler(CrewKickoffStartedEvent, custom_handler)
+
+        crew = Crew(agents=[base_agent], tasks=[base_task], name="TestCrew")
+        crew.kickoff()
+
+        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():
+    received_events_1 = []
+    received_events_2 = []
+
+    def handler_1(source, event):
+        received_events_1.append(event)
+
+    def handler_2(source, event):
+        received_events_2.append(event)
+
+    with crewai_event_bus.scoped_handlers():
+        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 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 = []
+
+    @crewai_event_bus.on(FlowCreatedEvent)
+    def handle_flow_created(source, event):
+        received_events.append(event)
+
+    class TestFlow(Flow[dict]):
+        @start()
+        def begin(self):
+            return "started"
+
+    flow = TestFlow()
+    flow.kickoff()
+
+    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 = []
+    error = Exception("Simulated method failure")
+
+    @crewai_event_bus.on(MethodExecutionFailedEvent)
+    def handle_method_failed(source, event):
+        received_events.append(event)
+
+    class TestFlow(Flow[dict]):
+        @start()
+        def begin(self):
+            raise error
+
+    flow = TestFlow()
+    with pytest.raises(Exception):
+        flow.kickoff()
+
+    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