explain how to use event listener

Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>

.gitignore

@@ -21,4 +21,5 @@ crew_tasks_output.json
 .mypy_cache
 .ruff_cache
 .venv
-agentops.log
+agentops.log
+test_flow.html

README.md

@@ -1,10 +1,18 @@
 <div align="center">
 
-![Logo of CrewAI, two people rowing on a boat](./docs/crewai_logo.png)
+![Logo of CrewAI](./docs/crewai_logo.png)
 
 # **CrewAI**
 
-🤖 **CrewAI**: Production-grade framework for orchestrating sophisticated AI agent systems. From simple automations to complex real-world applications, CrewAI provides precise control and deep customization. By fostering collaborative intelligence through flexible, production-ready architecture, CrewAI empowers agents to work together seamlessly, tackling complex business challenges with predictable, consistent results.
+**CrewAI**: Production-grade framework for orchestrating sophisticated AI agent systems. From simple automations to complex real-world applications, CrewAI provides precise control and deep customization. By fostering collaborative intelligence through flexible, production-ready architecture, CrewAI empowers agents to work together seamlessly, tackling complex business challenges with predictable, consistent results.
+
+**CrewAI Enterprise**
+Want to plan, build (+ no code), deploy, monitor and interare your agents: [CrewAI Enterprise](https://www.crewai.com/enterprise). Designed for complex, real-world applications, our enterprise solution offers:
+
+- **Seamless Integrations**
+- **Scalable & Secure Deployment**
+- **Actionable Insights**
+- **24/7 Support**
 
 <h3>
 
@@ -392,7 +400,7 @@ class AdvancedAnalysisFlow(Flow[MarketState]):
             goal="Gather and validate supporting market data",
             backstory="You excel at finding and correlating multiple data sources"
         )
-        
+
         analysis_task = Task(
             description="Analyze {sector} sector data for the past {timeframe}",
             expected_output="Detailed market analysis with confidence score",
@@ -403,7 +411,7 @@ class AdvancedAnalysisFlow(Flow[MarketState]):
             expected_output="Corroborating evidence and potential contradictions",
             agent=researcher
         )
-        
+
         # Demonstrate crew autonomy
         analysis_crew = Crew(
             agents=[analyst, researcher],

docs/concepts/cli.mdx

@@ -136,17 +136,21 @@ crewai test -n 5 -m gpt-3.5-turbo
 
 ### 8. Run
 
-Run the crew.
+Run the crew or flow.
 
 ```shell Terminal
 crewai run
 ```
+
+<Note>
+Starting from version 0.103.0, the `crewai run` command can be used to run both standard crews and flows. For flows, it automatically detects the type from pyproject.toml and runs the appropriate command. This is now the recommended way to run both crews and flows.
+</Note>
+
 <Note>
 Make sure to run these commands from the directory where your CrewAI project is set up. 
 Some commands may require additional configuration or setup within your project structure.
 </Note>
 
-
 ### 9. Chat
 
 Starting in version `0.98.0`, when you run the `crewai chat` command, you start an interactive session with your crew. The AI assistant will guide you by asking for necessary inputs to execute the crew. Once all inputs are provided, the crew will execute its tasks.
@@ -175,7 +179,6 @@ def crew(self) -> Crew:
 ```
 </Note>
 
-
 ### 10. API Keys
 
 When running ```crewai create crew``` command, the CLI will first show you the top 5 most common LLM providers and ask you to select one.

docs/concepts/event-listner.mdx

@@ -0,0 +1,349 @@
+---
+title: 'Event Listeners'
+description: 'Tap into CrewAI events to build custom integrations and monitoring'
+---
+
+# Event Listeners
+
+CrewAI provides a powerful event system that allows you to listen for and react to various events that occur during the execution of your Crew. This feature enables you to build custom integrations, monitoring solutions, logging systems, or any other functionality that needs to be triggered based on CrewAI's internal events.
+
+## How It Works
+
+CrewAI uses an event bus architecture to emit events throughout the execution lifecycle. The event system is built on the following components:
+
+1. **CrewAIEventsBus**: A singleton event bus that manages event registration and emission
+2. **CrewEvent**: Base class for all events in the system
+3. **BaseEventListener**: Abstract base class for creating custom event listeners
+
+When specific actions occur in CrewAI (like a Crew starting execution, an Agent completing a task, or a tool being used), the system emits corresponding events. You can register handlers for these events to execute custom code when they occur.
+
+## Creating a Custom Event Listener
+
+To create a custom event listener, you need to:
+
+1. Create a class that inherits from `BaseEventListener`
+2. Implement the `setup_listeners` method
+3. Register handlers for the events you're interested in
+4. Create an instance of your listener in the appropriate file
+
+Here's a simple example of a custom event listener class:
+
+```python
+from crewai.utilities.events import (
+    CrewKickoffStartedEvent,
+    CrewKickoffCompletedEvent,
+    AgentExecutionCompletedEvent,
+)
+from crewai.utilities.events.base_event_listener import BaseEventListener
+
+class MyCustomListener(BaseEventListener):
+    def __init__(self):
+        super().__init__()
+    
+    def setup_listeners(self, crewai_event_bus):
+        @crewai_event_bus.on(CrewKickoffStartedEvent)
+        def on_crew_started(source, event):
+            print(f"Crew '{event.crew_name}' has started execution!")
+        
+        @crewai_event_bus.on(CrewKickoffCompletedEvent)
+        def on_crew_completed(source, event):
+            print(f"Crew '{event.crew_name}' has completed execution!")
+            print(f"Output: {event.output}")
+        
+        @crewai_event_bus.on(AgentExecutionCompletedEvent)
+        def on_agent_execution_completed(source, event):
+            print(f"Agent '{event.agent.role}' completed task")
+            print(f"Output: {event.output}")
+```
+
+## Properly Registering Your Listener
+
+Simply defining your listener class isn't enough. You need to create an instance of it and ensure it's imported in your application. This ensures that:
+
+1. The event handlers are registered with the event bus
+2. The listener instance remains in memory (not garbage collected)
+3. The listener is active when events are emitted
+
+### Option 1: Import and Instantiate in Your Crew or Flow Implementation
+
+The most important thing is to create an instance of your listener in the file where your Crew or Flow is defined and executed:
+
+#### For Crew-based Applications
+
+Create and import your listener at the top of your Crew implementation file:
+
+```python
+# In your crew.py file
+from crewai import Agent, Crew, Task
+from my_listeners import MyCustomListener
+
+# Create an instance of your listener
+my_listener = MyCustomListener()
+
+class MyCustomCrew:
+    # Your crew implementation...
+    
+    def crew(self):
+        return Crew(
+            agents=[...],
+            tasks=[...],
+            # ...
+        )
+```
+
+#### For Flow-based Applications
+
+Create and import your listener at the top of your Flow implementation file:
+
+```python
+# In your main.py or flow.py file
+from crewai.flow import Flow, listen, start
+from my_listeners import MyCustomListener
+
+# Create an instance of your listener
+my_listener = MyCustomListener()
+
+class MyCustomFlow(Flow):
+    # Your flow implementation...
+    
+    @start()
+    def first_step(self):
+        # ...
+```
+
+This ensures that your listener is loaded and active when your Crew or Flow is executed.
+
+### Option 2: Create a Package for Your Listeners
+
+For a more structured approach, especially if you have multiple listeners:
+
+1. Create a package for your listeners:
+
+```
+my_project/
+  ├── listeners/
+  │   ├── __init__.py
+  │   ├── my_custom_listener.py
+  │   └── another_listener.py
+```
+
+2. In `my_custom_listener.py`, define your listener class and create an instance:
+
+```python
+# my_custom_listener.py
+from crewai.utilities.events.base_event_listener import BaseEventListener
+# ... import events ...
+
+class MyCustomListener(BaseEventListener):
+    # ... implementation ...
+
+# Create an instance of your listener
+my_custom_listener = MyCustomListener()
+```
+
+3. In `__init__.py`, import the listener instances to ensure they're loaded:
+
+```python
+# __init__.py
+from .my_custom_listener import my_custom_listener
+from .another_listener import another_listener
+
+# Optionally export them if you need to access them elsewhere
+__all__ = ['my_custom_listener', 'another_listener']
+```
+
+4. Import your listeners package in your Crew or Flow file:
+
+```python
+# In your crew.py or flow.py file
+import my_project.listeners  # This loads all your listeners
+
+class MyCustomCrew:
+    # Your crew implementation...
+```
+
+This is exactly how CrewAI's built-in `agentops_listener` is registered. In the CrewAI codebase, you'll find:
+
+```python
+# src/crewai/utilities/events/third_party/__init__.py
+from .agentops_listener import agentops_listener
+```
+
+This ensures the `agentops_listener` is loaded when the `crewai.utilities.events` package is imported.
+
+## Available Event Types
+
+CrewAI provides a wide range of events that you can listen for:
+
+### Crew Events
+
+- **CrewKickoffStartedEvent**: Emitted when a Crew starts execution
+- **CrewKickoffCompletedEvent**: Emitted when a Crew completes execution
+- **CrewKickoffFailedEvent**: Emitted when a Crew fails to complete execution
+- **CrewTestStartedEvent**: Emitted when a Crew starts testing
+- **CrewTestCompletedEvent**: Emitted when a Crew completes testing
+- **CrewTestFailedEvent**: Emitted when a Crew fails to complete testing
+- **CrewTrainStartedEvent**: Emitted when a Crew starts training
+- **CrewTrainCompletedEvent**: Emitted when a Crew completes training
+- **CrewTrainFailedEvent**: Emitted when a Crew fails to complete training
+
+### Agent Events
+
+- **AgentExecutionStartedEvent**: Emitted when an Agent starts executing a task
+- **AgentExecutionCompletedEvent**: Emitted when an Agent completes executing a task
+- **AgentExecutionErrorEvent**: Emitted when an Agent encounters an error during execution
+
+### Task Events
+
+- **TaskStartedEvent**: Emitted when a Task starts execution
+- **TaskCompletedEvent**: Emitted when a Task completes execution
+- **TaskFailedEvent**: Emitted when a Task fails to complete execution
+- **TaskEvaluationEvent**: Emitted when a Task is evaluated
+
+### Tool Usage Events
+
+- **ToolUsageStartedEvent**: Emitted when a tool execution is started
+- **ToolUsageFinishedEvent**: Emitted when a tool execution is completed
+- **ToolUsageErrorEvent**: Emitted when a tool execution encounters an error
+- **ToolValidateInputErrorEvent**: Emitted when a tool input validation encounters an error
+- **ToolExecutionErrorEvent**: Emitted when a tool execution encounters an error
+- **ToolSelectionErrorEvent**: Emitted when there's an error selecting a tool
+
+### Flow Events
+
+- **FlowCreatedEvent**: Emitted when a Flow is created
+- **FlowStartedEvent**: Emitted when a Flow starts execution
+- **FlowFinishedEvent**: Emitted when a Flow completes execution
+- **FlowPlotEvent**: Emitted when a Flow is plotted
+- **MethodExecutionStartedEvent**: Emitted when a Flow method starts execution
+- **MethodExecutionFinishedEvent**: Emitted when a Flow method completes execution
+- **MethodExecutionFailedEvent**: Emitted when a Flow method fails to complete execution
+
+### LLM Events
+
+- **LLMCallStartedEvent**: Emitted when an LLM call starts
+- **LLMCallCompletedEvent**: Emitted when an LLM call completes
+- **LLMCallFailedEvent**: Emitted when an LLM call fails
+
+## Event Handler Structure
+
+Each event handler receives two parameters:
+
+1. **source**: The object that emitted the event
+2. **event**: The event instance, containing event-specific data
+
+The structure of the event object depends on the event type, but all events inherit from `CrewEvent` and include:
+
+- **timestamp**: The time when the event was emitted
+- **type**: A string identifier for the event type
+
+Additional fields vary by event type. For example, `CrewKickoffCompletedEvent` includes `crew_name` and `output` fields.
+
+## Real-World Example: Integration with AgentOps
+
+CrewAI includes an example of a third-party integration with [AgentOps](https://github.com/AgentOps-AI/agentops), a monitoring and observability platform for AI agents. Here's how it's implemented:
+
+```python
+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)
+```
+
+This listener initializes an AgentOps session when a Crew starts, registers agents with AgentOps, tracks tool usage, and ends the session when the Crew completes.
+
+The AgentOps listener is registered in CrewAI's event system through the import in `src/crewai/utilities/events/third_party/__init__.py`:
+
+```python
+from .agentops_listener import agentops_listener
+```
+
+This ensures the `agentops_listener` is loaded when the `crewai.utilities.events` package is imported.
+
+## Advanced Usage: Scoped Handlers
+
+For temporary event handling (useful for testing or specific operations), you can use the `scoped_handlers` context manager:
+
+```python
+from crewai.utilities.events import crewai_event_bus, CrewKickoffStartedEvent
+
+with crewai_event_bus.scoped_handlers():
+    @crewai_event_bus.on(CrewKickoffStartedEvent)
+    def temp_handler(source, event):
+        print("This handler only exists within this context")
+    
+    # Do something that emits events
+    
+# Outside the context, the temporary handler is removed
+```
+
+## Use Cases
+
+Event listeners can be used for a variety of purposes:
+
+1. **Logging and Monitoring**: Track the execution of your Crew and log important events
+2. **Analytics**: Collect data about your Crew's performance and behavior
+3. **Debugging**: Set up temporary listeners to debug specific issues
+4. **Integration**: Connect CrewAI with external systems like monitoring platforms, databases, or notification services
+5. **Custom Behavior**: Trigger custom actions based on specific events
+
+## Best Practices
+
+1. **Keep Handlers Light**: Event handlers should be lightweight and avoid blocking operations
+2. **Error Handling**: Include proper error handling in your event handlers to prevent exceptions from affecting the main execution
+3. **Cleanup**: If your listener allocates resources, ensure they're properly cleaned up
+4. **Selective Listening**: Only listen for events you actually need to handle
+5. **Testing**: Test your event listeners in isolation to ensure they behave as expected
+
+By leveraging CrewAI's event system, you can extend its functionality and integrate it seamlessly with your existing infrastructure.

docs/concepts/flows.mdx

@@ -150,12 +150,12 @@ final_output = flow.kickoff()
 
 print("---- Final Output ----")
 print(final_output)
-````
+```
 
 ```text Output
 ---- Final Output ----
 Second method received: Output from first_method
-````
+```
 
 </CodeGroup>
 
@@ -738,3 +738,34 @@ Also, check out our YouTube video on how to use flows in CrewAI below!
   referrerpolicy="strict-origin-when-cross-origin"
   allowfullscreen
 ></iframe>
+
+## Running Flows
+
+There are two ways to run a flow:
+
+### Using the Flow API
+
+You can run a flow programmatically by creating an instance of your flow class and calling the `kickoff()` method:
+
+```python
+flow = ExampleFlow()
+result = flow.kickoff()
+```
+
+### Using the CLI
+
+Starting from version 0.103.0, you can run flows using the `crewai run` command:
+
+```shell
+crewai run
+```
+
+This command automatically detects if your project is a flow (based on the `type = "flow"` setting in your pyproject.toml) and runs it accordingly. This is the recommended way to run flows from the command line.
+
+For backward compatibility, you can also use:
+
+```shell
+crewai flow kickoff
+```
+
+However, the `crewai run` command is now the preferred method as it works for both crews and flows.

docs/concepts/knowledge.mdx

@@ -91,7 +91,7 @@ result = crew.kickoff(inputs={"question": "What city does John live in and how o
 ```
 
 
-Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including TXT, PDF, DOCX, HTML, and more. 
+Here's another example with the `CrewDoclingSource`. The CrewDoclingSource is actually quite versatile and can handle multiple file formats including MD, PDF, DOCX, HTML, and more. 
 
 <Note>
   You need to install `docling` for the following example to work: `uv add docling`
@@ -152,10 +152,10 @@ Here are examples of how to use different types of knowledge sources:
 
 ### Text File Knowledge Source
 ```python
-from crewai.knowledge.source.crew_docling_source import CrewDoclingSource
+from crewai.knowledge.source.text_file_knowledge_source import TextFileKnowledgeSource
 
 # Create a text file knowledge source
-text_source = CrewDoclingSource(
+text_source = TextFileKnowledgeSource(
     file_paths=["document.txt", "another.txt"]
 )
 

docs/concepts/memory.mdx

@@ -58,41 +58,107 @@ my_crew = Crew(
 ### Example: Use Custom Memory Instances e.g FAISS as the VectorDB
 
 ```python Code
-from crewai import Crew, Agent, Task, Process
+from crewai import Crew, Process
+from crewai.memory import LongTermMemory, ShortTermMemory, EntityMemory
+from crewai.memory.storage import LTMSQLiteStorage, RAGStorage
+from typing import List, Optional
 
 # Assemble your crew with memory capabilities
-my_crew = Crew(
-    agents=[...],
-    tasks=[...],
-    process="Process.sequential",
-    memory=True,
-    long_term_memory=EnhanceLongTermMemory(
+my_crew: Crew = Crew(
+    agents = [...],
+    tasks = [...],
+    process = Process.sequential,
+    memory = True,
+    # Long-term memory for persistent storage across sessions
+    long_term_memory = LongTermMemory(
         storage=LTMSQLiteStorage(
-            db_path="/my_data_dir/my_crew1/long_term_memory_storage.db"
+            db_path="/my_crew1/long_term_memory_storage.db"
         )
     ),
-    short_term_memory=EnhanceShortTermMemory(
-        storage=CustomRAGStorage(
-            crew_name="my_crew",
-            storage_type="short_term",
-            data_dir="//my_data_dir",
-            model=embedder["model"],
-            dimension=embedder["dimension"],
+    # Short-term memory for current context using RAG
+    short_term_memory = ShortTermMemory(
+        storage = RAGStorage(
+                embedder_config={
+                    "provider": "openai",
+                    "config": {
+                        "model": 'text-embedding-3-small'
+                    }
+                },
+                type="short_term",
+                path="/my_crew1/"
+            )
         ),
     ),
-    entity_memory=EnhanceEntityMemory(
-        storage=CustomRAGStorage(
-            crew_name="my_crew",
-            storage_type="entities",
-            data_dir="//my_data_dir",
-            model=embedder["model"],
-            dimension=embedder["dimension"],
-        ),
+    # Entity memory for tracking key information about entities
+    entity_memory = EntityMemory(
+        storage=RAGStorage(
+            embedder_config={
+                "provider": "openai",
+                "config": {
+                    "model": 'text-embedding-3-small'
+                }
+            },
+            type="short_term",
+            path="/my_crew1/"
+        )
     ),
     verbose=True,
 )
 ```
 
+## Security Considerations
+
+When configuring memory storage:
+- Use environment variables for storage paths (e.g., `CREWAI_STORAGE_DIR`)
+- Never hardcode sensitive information like database credentials
+- Consider access permissions for storage directories
+- Use relative paths when possible to maintain portability
+
+Example using environment variables:
+```python
+import os
+from crewai import Crew
+from crewai.memory import LongTermMemory
+from crewai.memory.storage import LTMSQLiteStorage
+
+# Configure storage path using environment variable
+storage_path = os.getenv("CREWAI_STORAGE_DIR", "./storage")
+crew = Crew(
+    memory=True,
+    long_term_memory=LongTermMemory(
+        storage=LTMSQLiteStorage(
+            db_path="{storage_path}/memory.db".format(storage_path=storage_path)
+        )
+    )
+)
+```
+
+## Configuration Examples
+
+### Basic Memory Configuration
+```python
+from crewai import Crew
+from crewai.memory import LongTermMemory
+
+# Simple memory configuration
+crew = Crew(memory=True)  # Uses default storage locations
+```
+
+### Custom Storage Configuration
+```python
+from crewai import Crew
+from crewai.memory import LongTermMemory
+from crewai.memory.storage import LTMSQLiteStorage
+
+# Configure custom storage paths
+crew = Crew(
+    memory=True,
+    long_term_memory=LongTermMemory(
+        storage=LTMSQLiteStorage(db_path="./memory.db")
+    )
+)
+```
+
 ## Integrating Mem0 for Enhanced User Memory
 
 [Mem0](https://mem0.ai/) is a self-improving memory layer for LLM applications, enabling personalized AI experiences. 
@@ -216,6 +282,19 @@ my_crew = Crew(
 
 ### Using Google AI embeddings
 
+#### Prerequisites
+Before using Google AI embeddings, ensure you have:
+- Access to the Gemini API
+- The necessary API keys and permissions
+
+You will need to update your *pyproject.toml* dependencies:
+```YAML
+dependencies = [
+    "google-generativeai>=0.8.4", #main version in January/2025 - crewai v.0.100.0 and crewai-tools 0.33.0
+    "crewai[tools]>=0.100.0,<1.0.0"
+]
+```
+
 ```python Code
 from crewai import Crew, Agent, Task, Process
 
@@ -368,7 +447,66 @@ my_crew = Crew(
 )
 ```
 
-### Resetting Memory
+### Using Amazon Bedrock embeddings
+
+```python Code
+# Note: Ensure you have installed `boto3` for Bedrock embeddings to work.
+
+import os
+import boto3
+from crewai import Crew, Agent, Task, Process
+
+boto3_session = boto3.Session(
+    region_name=os.environ.get("AWS_REGION_NAME"),
+    aws_access_key_id=os.environ.get("AWS_ACCESS_KEY_ID"),
+    aws_secret_access_key=os.environ.get("AWS_SECRET_ACCESS_KEY")
+)
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    embedder={
+    "provider": "bedrock",
+        "config":{
+            "session": boto3_session,
+            "model": "amazon.titan-embed-text-v2:0",
+            "vector_dimension": 1024
+        }
+    }
+    verbose=True
+)
+```
+
+### Adding Custom Embedding Function
+
+```python Code
+from crewai import Crew, Agent, Task, Process
+from chromadb import Documents, EmbeddingFunction, Embeddings
+
+# Create a custom embedding function
+class CustomEmbedder(EmbeddingFunction):
+    def __call__(self, input: Documents) -> Embeddings:
+        # generate embeddings
+        return [1, 2, 3] # this is a dummy embedding
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "custom",
+        "config": {
+            "embedder": CustomEmbedder()
+        }
+    }
+)
+```
+
+### Resetting Memory via cli
 
 ```shell
 crewai reset-memories [OPTIONS]
@@ -382,8 +520,46 @@ crewai reset-memories [OPTIONS]
 | `-s`, `--short`    | Reset SHORT TERM memory.         | Flag (boolean) | False   |
 | `-e`, `--entities` | Reset ENTITIES memory.           | Flag (boolean) | False   |
 | `-k`, `--kickoff-outputs` | Reset LATEST KICKOFF TASK OUTPUTS. | Flag (boolean) | False   |
+| `-kn`, `--knowledge` | Reset KNOWLEDEGE storage | Flag (boolean) | False   |
 | `-a`, `--all`      | Reset ALL memories.              | Flag (boolean) | False   |
 
+Note: To use the cli command you need to have your crew in a file called crew.py in the same directory.
+
+
+
+
+### Resetting Memory via crew object
+
+```python
+
+my_crew = Crew(
+    agents=[...],
+    tasks=[...],
+    process=Process.sequential,
+    memory=True,
+    verbose=True,
+    embedder={
+        "provider": "custom",
+        "config": {
+            "embedder": CustomEmbedder()
+        }
+    }
+)
+
+my_crew.reset_memories(command_type = 'all') # Resets all the memory
+```
+
+#### Resetting Memory Options
+
+| Command Type       | Description                      |
+| :----------------- | :------------------------------- |
+| `long`             | Reset LONG TERM memory.          | 
+| `short`            | Reset SHORT TERM memory.         | 
+| `entities`         | Reset ENTITIES memory.           | 
+| `kickoff_outputs`  | Reset LATEST KICKOFF TASK OUTPUTS. |
+| `knowledge`        | Reset KNOWLEDGE memory.          |
+| `all`              | Reset ALL memories.              |
+
 
 ## Benefits of Using CrewAI's Memory System
 

docs/concepts/tasks.mdx

@@ -268,7 +268,7 @@ analysis_task = Task(
 
 Task guardrails provide a way to validate and transform task outputs before they
 are passed to the next task. This feature helps ensure data quality and provides
-efeedback to agents when their output doesn't meet specific criteria.
+feedback to agents when their output doesn't meet specific criteria.
 
 ### Using Task Guardrails
 

docs/how-to/kickoff-async.mdx

@@ -54,7 +54,8 @@ coding_agent = Agent(
 # Create a task that requires code execution
 data_analysis_task = Task(
     description="Analyze the given dataset and calculate the average age of participants. Ages: {ages}",
-    agent=coding_agent
+    agent=coding_agent,
+    expected_output="The average age of the participants."
 )
 
 # Create a crew and add the task
@@ -116,4 +117,4 @@ async def async_multiple_crews():
 
 # Run the async function
 asyncio.run(async_multiple_crews())
-```
+```

docs/how-to/langfuse-observability.mdx

@@ -0,0 +1,100 @@
+---
+title: Agent Monitoring with Langfuse
+description: Learn how to integrate Langfuse with CrewAI via OpenTelemetry using OpenLit
+icon: magnifying-glass-chart
+---
+
+# Integrate Langfuse with CrewAI
+
+This notebook demonstrates how to integrate **Langfuse** with **CrewAI** using OpenTelemetry via the **OpenLit** SDK. By the end of this notebook, you will be able to trace your CrewAI applications with Langfuse for improved observability and debugging.
+
+> **What is Langfuse?** [Langfuse](https://langfuse.com) is an open-source LLM engineering platform. It provides tracing and monitoring capabilities for LLM applications, helping developers debug, analyze, and optimize their AI systems. Langfuse integrates with various tools and frameworks via native integrations, OpenTelemetry, and APIs/SDKs.
+
+[![Langfuse Overview Video](https://github.com/user-attachments/assets/3926b288-ff61-4b95-8aa1-45d041c70866)](https://langfuse.com/watch-demo)
+
+## Get Started
+
+We'll walk through a simple example of using CrewAI and integrating it with Langfuse via OpenTelemetry using OpenLit.
+
+### Step 1: Install Dependencies
+
+
+```python
+%pip install langfuse openlit crewai crewai_tools
+```
+
+### Step 2: Set Up Environment Variables
+
+Set your Langfuse API keys and configure OpenTelemetry export settings to send traces to Langfuse. Please refer to the [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started) for more information on the Langfuse OpenTelemetry endpoint `/api/public/otel` and authentication.
+
+
+```python
+import os
+import base64
+
+LANGFUSE_PUBLIC_KEY="pk-lf-..."
+LANGFUSE_SECRET_KEY="sk-lf-..."
+LANGFUSE_AUTH=base64.b64encode(f"{LANGFUSE_PUBLIC_KEY}:{LANGFUSE_SECRET_KEY}".encode()).decode()
+
+os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://cloud.langfuse.com/api/public/otel" # EU data region
+# os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://us.cloud.langfuse.com/api/public/otel" # US data region
+os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = f"Authorization=Basic {LANGFUSE_AUTH}"
+
+# your openai key
+os.environ["OPENAI_API_KEY"] = "sk-..."
+```
+
+### Step 3: Initialize OpenLit
+
+Initialize the OpenLit OpenTelemetry instrumentation SDK to start capturing OpenTelemetry traces.
+
+
+```python
+import openlit
+
+openlit.init()
+```
+
+### Step 4: Create a Simple CrewAI Application
+
+We'll create a simple CrewAI application where multiple agents collaborate to answer a user's question.
+
+
+```python
+from crewai import Agent, Task, Crew
+
+from crewai_tools import (
+    WebsiteSearchTool
+)
+
+web_rag_tool = WebsiteSearchTool()
+
+writer = Agent(
+        role="Writer",
+        goal="You make math engaging and understandable for young children through poetry",
+        backstory="You're an expert in writing haikus but you know nothing of math.",
+        tools=[web_rag_tool],  
+    )
+
+task = Task(description=("What is {multiplication}?"),
+            expected_output=("Compose a haiku that includes the answer."),
+            agent=writer)
+
+crew = Crew(
+  agents=[writer],
+  tasks=[task],
+  share_crew=False
+)
+```
+
+### Step 5: See Traces in Langfuse
+
+After running the agent, you can view the traces generated by your CrewAI application in [Langfuse](https://cloud.langfuse.com). You should see detailed steps of the LLM interactions, which can help you debug and optimize your AI agent.
+
+![CrewAI example trace in Langfuse](https://langfuse.com/images/cookbook/integration_crewai/crewai-example-trace.png)
+
+_[Public example trace in Langfuse](https://cloud.langfuse.com/project/cloramnkj0002jz088vzn1ja4/traces/e2cf380ffc8d47d28da98f136140642b?timestamp=2025-02-05T15%3A12%3A02.717Z&observation=3b32338ee6a5d9af)_
+
+## References
+
+- [Langfuse OpenTelemetry Docs](https://langfuse.com/docs/opentelemetry/get-started)

docs/how-to/portkey-observability-and-guardrails.mdx

@@ -1,211 +0,0 @@
-# Portkey Integration with CrewAI
-<img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-CrewAI.png" alt="Portkey CrewAI Header Image" width="70%" />
-
-
-[Portkey](https://portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) is a 2-line upgrade to make your CrewAI agents reliable, cost-efficient, and fast.
-
-Portkey adds 4 core production capabilities to any CrewAI agent:
-1. Routing to **200+ LLMs**
-2. Making each LLM call more robust
-3. Full-stack tracing & cost, performance analytics
-4. Real-time guardrails to enforce behavior
-
-
-
-
-
-## Getting Started
-
-1. **Install Required Packages:**
-
-```bash
-pip install -qU crewai portkey-ai
-```
-
-2. **Configure the LLM Client:**
-
-To build CrewAI Agents with Portkey, you'll need two keys:
-- **Portkey API Key**: Sign up on the [Portkey app](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai) and copy your API key
-- **Virtual Key**: Virtual Keys securely manage your LLM API keys in one place. Store your LLM provider API keys securely in Portkey's vault
-
-```python
-from crewai import LLM
-from portkey_ai import createHeaders, PORTKEY_GATEWAY_URL
-
-gpt_llm = LLM(
-    model="gpt-4",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy", # We are using Virtual key
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_VIRTUAL_KEY", # Enter your Virtual key from Portkey
-    )
-)
-```
-
-3. **Create and Run Your First Agent:**
-
-```python
-from crewai import Agent, Task, Crew
-
-# Define your agents with roles and goals
-coder = Agent(
-    role='Software developer',
-    goal='Write clear, concise code on demand',
-    backstory='An expert coder with a keen eye for software trends.',
-    llm=gpt_llm
-)
-
-# Create tasks for your agents
-task1 = Task(
-    description="Define the HTML for making a simple website with heading- Hello World! Portkey is working!",
-    expected_output="A clear and concise HTML code",
-    agent=coder
-)
-
-# Instantiate your crew
-crew = Crew(
-    agents=[coder],
-    tasks=[task1],
-)
-
-result = crew.kickoff()
-print(result)
-```
-
-
-## Key Features
-
-| Feature | Description |
-|---------|-------------|
-| 🌐 Multi-LLM Support | Access OpenAI, Anthropic, Gemini, Azure, and 250+ providers through a unified interface |
-| 🛡️ Production Reliability | Implement retries, timeouts, load balancing, and fallbacks |
-| 📊 Advanced Observability | Track 40+ metrics including costs, tokens, latency, and custom metadata |
-| 🔍 Comprehensive Logging | Debug with detailed execution traces and function call logs |
-| 🚧 Security Controls | Set budget limits and implement role-based access control |
-| 🔄 Performance Analytics | Capture and analyze feedback for continuous improvement |
-| 💾 Intelligent Caching | Reduce costs and latency with semantic or simple caching |
-
-
-## Production Features with Portkey Configs
-
-All features mentioned below are through Portkey's Config system. Portkey's Config system allows you to define routing strategies using simple JSON objects in your LLM API calls. You can create and manage Configs directly in your code or through the Portkey Dashboard. Each Config has a unique ID for easy reference.
-
-<Frame>
-    <img src="https://raw.githubusercontent.com/Portkey-AI/docs-core/refs/heads/main/images/libraries/libraries-3.avif"/>
-</Frame>
-
-
-### 1. Use 250+ LLMs
-Access various LLMs like Anthropic, Gemini, Mistral, Azure OpenAI, and more with minimal code changes. Switch between providers or use them together seamlessly. [Learn more about Universal API](https://portkey.ai/docs/product/ai-gateway/universal-api)
-
-
-Easily switch between different LLM providers:
-
-```python
-# Anthropic Configuration
-anthropic_llm = LLM(
-    model="claude-3-5-sonnet-latest",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy",
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_ANTHROPIC_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="anthropic_agent"
-    )
-)
-
-# Azure OpenAI Configuration
-azure_llm = LLM(
-    model="gpt-4",
-    base_url=PORTKEY_GATEWAY_URL,
-    api_key="dummy",
-    extra_headers=createHeaders(
-        api_key="YOUR_PORTKEY_API_KEY",
-        virtual_key="YOUR_AZURE_VIRTUAL_KEY", #You don't need provider when using Virtual keys
-        trace_id="azure_agent"
-    )
-)
-```
-
-
-### 2. Caching
-Improve response times and reduce costs with two powerful caching modes:
-- **Simple Cache**: Perfect for exact matches
-- **Semantic Cache**: Matches responses for requests that are semantically similar
-[Learn more about Caching](https://portkey.ai/docs/product/ai-gateway/cache-simple-and-semantic)
-
-```py
-config = {
-    "cache": {
-        "mode": "semantic",  # or "simple" for exact matching
-    }
-}
-```
-
-### 3. Production Reliability
-Portkey provides comprehensive reliability features:
-- **Automatic Retries**: Handle temporary failures gracefully
-- **Request Timeouts**: Prevent hanging operations
-- **Conditional Routing**: Route requests based on specific conditions
-- **Fallbacks**: Set up automatic provider failovers
-- **Load Balancing**: Distribute requests efficiently
-
-[Learn more about Reliability Features](https://portkey.ai/docs/product/ai-gateway/)
-
-
-
-### 4. Metrics
-
-Agent runs are complex. Portkey automatically logs **40+ comprehensive metrics** for your AI agents, including cost, tokens used, latency, etc. Whether you need a broad overview or granular insights into your agent runs, Portkey's customizable filters provide the metrics you need.
-
-
-- Cost per agent interaction
-- Response times and latency
-- Token usage and efficiency
-- Success/failure rates
-- Cache hit rates
-
-<img src="https://github.com/siddharthsambharia-portkey/Portkey-Product-Images/blob/main/Portkey-Dashboard.png?raw=true" width="70%" alt="Portkey Dashboard" />
-
-### 5. Detailed Logging
-Logs are essential for understanding agent behavior, diagnosing issues, and improving performance. They provide a detailed record of agent activities and tool use, which is crucial for debugging and optimizing processes.
-
-
-Access a dedicated section to view records of agent executions, including parameters, outcomes, function calls, and errors. Filter logs based on multiple parameters such as trace ID, model, tokens used, and metadata.
-
-<details>
-  <summary><b>Traces</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Traces.png" alt="Portkey Traces" width="70%" />
-</details>
-
-<details>
-  <summary><b>Logs</b></summary>
-  <img src="https://raw.githubusercontent.com/siddharthsambharia-portkey/Portkey-Product-Images/main/Portkey-Logs.png" alt="Portkey Logs" width="70%" />
-</details>
-
-### 6. Enterprise Security Features
-- Set budget limit and rate limts per Virtual Key (disposable API keys)
-- Implement role-based access control
-- Track system changes with audit logs
-- Configure data retention policies
-
-
-
-For detailed information on creating and managing Configs, visit the [Portkey documentation](https://docs.portkey.ai/product/ai-gateway/configs).
-
-## Resources
-
-- [📘 Portkey Documentation](https://docs.portkey.ai)
-- [📊 Portkey Dashboard](https://app.portkey.ai/?utm_source=crewai&utm_medium=crewai&utm_campaign=crewai)
-- [🐦 Twitter](https://twitter.com/portkeyai)
-- [💬 Discord Community](https://discord.gg/DD7vgKK299)
-
-
-
-
-
-
-
-
-

docs/how-to/portkey-observability.mdx

@@ -1,5 +1,5 @@
 ---
-title: Portkey Observability and Guardrails
+title: Agent Monitoring with Portkey
 description: How to use Portkey with CrewAI
 icon: key
 ---

docs/mint.json

@@ -103,7 +103,8 @@
         "how-to/langtrace-observability",
         "how-to/mlflow-observability",
         "how-to/openlit-observability",
-        "how-to/portkey-observability"
+        "how-to/portkey-observability",
+        "how-to/langfuse-observability"
       ]
     },
     {

docs/tools/filewritetool.mdx

@@ -8,9 +8,9 @@ icon: file-pen
 
 ## Description
 
-The `FileWriterTool` is a component of the crewai_tools package, designed to simplify the process of writing content to files. 
+The `FileWriterTool` is a component of the crewai_tools package, designed to simplify the process of writing content to files with cross-platform compatibility (Windows, Linux, macOS). 
 It is particularly useful in scenarios such as generating reports, saving logs, creating configuration files, and more. 
-This tool supports creating new directories if they don't exist, making it easier to organize your output.
+This tool handles path differences across operating systems, supports UTF-8 encoding, and automatically creates directories if they don't exist, making it easier to organize your output reliably across different platforms.
 
 ## Installation
 
@@ -43,6 +43,8 @@ print(result)
 
 ## Conclusion
 
-By integrating the `FileWriterTool` into your crews, the agents can execute the process of writing content to files and creating directories. 
-This tool is essential for tasks that require saving output data, creating structured file systems, and more. By adhering to the setup and usage guidelines provided, 
-incorporating this tool into projects is straightforward and efficient.
+By integrating the `FileWriterTool` into your crews, the agents can reliably write content to files across different operating systems. 
+This tool is essential for tasks that require saving output data, creating structured file systems, and handling cross-platform file operations. 
+It's particularly recommended for Windows users who may encounter file writing issues with standard Python file operations.
+
+By adhering to the setup and usage guidelines provided, incorporating this tool into projects is straightforward and ensures consistent file writing behavior across all platforms.

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "crewai"
-version = "0.100.1"
+version = "0.102.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
@@ -45,7 +45,7 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"
 
 [project.optional-dependencies]
-tools = ["crewai-tools>=0.32.1"]
+tools = ["crewai-tools>=0.36.0"]
 embeddings = [
     "tiktoken~=0.7.0"
 ]

src/crewai/__init__.py

@@ -14,7 +14,7 @@ warnings.filterwarnings(
     category=UserWarning,
     module="pydantic.main",
 )
-__version__ = "0.100.1"
+__version__ = "0.102.0"
 __all__ = [
     "Agent",
     "Crew",

src/crewai/agent.py

@@ -16,29 +16,20 @@ from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.task import Task
 from crewai.tools import BaseTool
 from crewai.tools.agent_tools.agent_tools import AgentTools
-from crewai.tools.base_tool import Tool
 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.
 
@@ -123,7 +114,6 @@ class Agent(BaseAgent):
 
     @model_validator(mode="after")
     def post_init_setup(self):
-        self._set_knowledge()
         self.agent_ops_agent_name = self.role
 
         self.llm = create_llm(self.llm)
@@ -143,10 +133,13 @@ class Agent(BaseAgent):
             self.cache_handler = CacheHandler()
         self.set_cache_handler(self.cache_handler)
 
-    def _set_knowledge(self):
+    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
         try:
+            if self.embedder is None and crew_embedder:
+                self.embedder = crew_embedder
+
             if self.knowledge_sources:
-                full_pattern = re.compile(r'[^a-zA-Z0-9\-_\r\n]|(\.\.)')
+                full_pattern = re.compile(r"[^a-zA-Z0-9\-_\r\n]|(\.\.)")
                 knowledge_agent_name = f"{re.sub(full_pattern, '_', self.role)}"
                 if isinstance(self.knowledge_sources, list) and all(
                     isinstance(k, BaseKnowledgeSource) for k in self.knowledge_sources
@@ -241,6 +234,15 @@ 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,
@@ -252,9 +254,25 @@ 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)
 
@@ -267,7 +285,10 @@ 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(
@@ -352,3 +351,6 @@ class BaseAgent(ABC, BaseModel):
         if not self._rpm_controller:
             self._rpm_controller = rpm_controller
             self.create_agent_executor()
+
+    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
+        pass

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/agent_builder/utilities/base_output_converter.py

@@ -31,11 +31,11 @@ class OutputConverter(BaseModel, ABC):
     )
 
     @abstractmethod
-    def to_pydantic(self, current_attempt=1):
+    def to_pydantic(self, current_attempt=1) -> BaseModel:
         """Convert text to pydantic."""
         pass
 
     @abstractmethod
-    def to_json(self, current_attempt=1):
+    def to_json(self, current_attempt=1) -> dict:
         """Convert text to json."""
         pass

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/agents/parser.py

@@ -94,6 +94,13 @@ class CrewAgentParser:
 
         elif includes_answer:
             final_answer = text.split(FINAL_ANSWER_ACTION)[-1].strip()
+            # Check whether the final answer ends with triple backticks.
+            if final_answer.endswith("```"):
+                # Count occurrences of triple backticks in the final answer.
+                count = final_answer.count("```")
+                # If count is odd then it's an unmatched trailing set; remove it.
+                if count % 2 != 0:
+                    final_answer = final_answer[:-3].rstrip()
             return AgentFinish(thought, final_answer, text)
 
         if not re.search(r"Action\s*\d*\s*:[\s]*(.*?)", text, re.DOTALL):
@@ -117,11 +124,15 @@ class CrewAgentParser:
             )
 
     def _extract_thought(self, text: str) -> str:
-        regex = r"(.*?)(?:\n\nAction|\n\nFinal Answer)"
-        thought_match = re.search(regex, text, re.DOTALL)
-        if thought_match:
-            return thought_match.group(1).strip()
-        return ""
+        thought_index = text.find("\n\nAction")
+        if thought_index == -1:
+            thought_index = text.find("\n\nFinal Answer")
+        if thought_index == -1:
+            return ""
+        thought = text[:thought_index].strip()
+        # Remove any triple backticks from the thought string
+        thought = thought.replace("```", "").strip()
+        return thought
 
     def _clean_action(self, text: str) -> str:
         """Clean action string by removing non-essential formatting characters."""

src/crewai/cli/cli.py

@@ -203,7 +203,6 @@ def install(context):
 @crewai.command()
 def run():
     """Run the Crew."""
-    click.echo("Running the Crew")
     run_crew()
 
 

src/crewai/cli/constants.py

@@ -216,10 +216,43 @@ MODELS = {
         "watsonx/ibm/granite-3-8b-instruct",
     ],
     "bedrock": [
+        "bedrock/us.amazon.nova-pro-v1:0",
+        "bedrock/us.amazon.nova-micro-v1:0",
+        "bedrock/us.amazon.nova-lite-v1:0",
+        "bedrock/us.anthropic.claude-3-5-sonnet-20240620-v1:0",
+        "bedrock/us.anthropic.claude-3-5-haiku-20241022-v1:0",
+        "bedrock/us.anthropic.claude-3-5-sonnet-20241022-v2:0",
+        "bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0",
+        "bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0",
+        "bedrock/us.anthropic.claude-3-opus-20240229-v1:0",
+        "bedrock/us.anthropic.claude-3-haiku-20240307-v1:0",
+        "bedrock/us.meta.llama3-2-11b-instruct-v1:0",
+        "bedrock/us.meta.llama3-2-3b-instruct-v1:0",
+        "bedrock/us.meta.llama3-2-90b-instruct-v1:0",
+        "bedrock/us.meta.llama3-2-1b-instruct-v1:0",
+        "bedrock/us.meta.llama3-1-8b-instruct-v1:0",
+        "bedrock/us.meta.llama3-1-70b-instruct-v1:0",
+        "bedrock/us.meta.llama3-3-70b-instruct-v1:0",
+        "bedrock/us.meta.llama3-1-405b-instruct-v1:0",
+        "bedrock/eu.anthropic.claude-3-5-sonnet-20240620-v1:0",
+        "bedrock/eu.anthropic.claude-3-sonnet-20240229-v1:0",
+        "bedrock/eu.anthropic.claude-3-haiku-20240307-v1:0",
+        "bedrock/eu.meta.llama3-2-3b-instruct-v1:0",
+        "bedrock/eu.meta.llama3-2-1b-instruct-v1:0",
+        "bedrock/apac.anthropic.claude-3-5-sonnet-20240620-v1:0",
+        "bedrock/apac.anthropic.claude-3-5-sonnet-20241022-v2:0",
+        "bedrock/apac.anthropic.claude-3-sonnet-20240229-v1:0",
+        "bedrock/apac.anthropic.claude-3-haiku-20240307-v1:0",
+        "bedrock/amazon.nova-pro-v1:0",
+        "bedrock/amazon.nova-micro-v1:0",
+        "bedrock/amazon.nova-lite-v1:0",
         "bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0",
+        "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0",
+        "bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
+        "bedrock/anthropic.claude-3-7-sonnet-20250219-v1:0",
         "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
-        "bedrock/anthropic.claude-3-haiku-20240307-v1:0",
         "bedrock/anthropic.claude-3-opus-20240229-v1:0",
+        "bedrock/anthropic.claude-3-haiku-20240307-v1:0",
         "bedrock/anthropic.claude-v2:1",
         "bedrock/anthropic.claude-v2",
         "bedrock/anthropic.claude-instant-v1",
@@ -234,8 +267,6 @@ MODELS = {
         "bedrock/ai21.j2-mid-v1",
         "bedrock/ai21.j2-ultra-v1",
         "bedrock/ai21.jamba-instruct-v1:0",
-        "bedrock/meta.llama2-13b-chat-v1",
-        "bedrock/meta.llama2-70b-chat-v1",
         "bedrock/mistral.mistral-7b-instruct-v0:2",
         "bedrock/mistral.mixtral-8x7b-instruct-v0:1",
     ],

src/crewai/cli/reset_memories_command.py

@@ -3,11 +3,6 @@ import subprocess
 import click
 
 from crewai.cli.utils import get_crew
-from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
-from crewai.memory.entity.entity_memory import EntityMemory
-from crewai.memory.long_term.long_term_memory import LongTermMemory
-from crewai.memory.short_term.short_term_memory import ShortTermMemory
-from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
 
 def reset_memories_command(

src/crewai/cli/run_crew.py

@@ -1,4 +1,6 @@
 import subprocess
+from enum import Enum
+from typing import List, Optional
 
 import click
 from packaging import version
@@ -7,16 +9,24 @@ from crewai.cli.utils import read_toml
 from crewai.cli.version import get_crewai_version
 
 
+class CrewType(Enum):
+    STANDARD = "standard"
+    FLOW = "flow"
+
+
 def run_crew() -> None:
     """
-    Run the crew by running a command in the UV environment.
+    Run the crew or flow by running a command in the UV environment.
+
+    Starting from version 0.103.0, this command can be used to run both
+    standard crews and flows. For flows, it detects the type from pyproject.toml
+    and automatically runs the appropriate command.
     """
-    command = ["uv", "run", "run_crew"]
     crewai_version = get_crewai_version()
     min_required_version = "0.71.0"
-
     pyproject_data = read_toml()
 
+    # Check for legacy poetry configuration
     if pyproject_data.get("tool", {}).get("poetry") and (
         version.parse(crewai_version) < version.parse(min_required_version)
     ):
@@ -26,18 +36,54 @@ def run_crew() -> None:
             fg="red",
         )
 
+    # Determine crew type
+    is_flow = pyproject_data.get("tool", {}).get("crewai", {}).get("type") == "flow"
+    crew_type = CrewType.FLOW if is_flow else CrewType.STANDARD
+
+    # Display appropriate message
+    click.echo(f"Running the {'Flow' if is_flow else 'Crew'}")
+
+    # Execute the appropriate command
+    execute_command(crew_type)
+
+
+def execute_command(crew_type: CrewType) -> None:
+    """
+    Execute the appropriate command based on crew type.
+
+    Args:
+        crew_type: The type of crew to run
+    """
+    command = ["uv", "run", "kickoff" if crew_type == CrewType.FLOW else "run_crew"]
+
     try:
         subprocess.run(command, capture_output=False, text=True, check=True)
 
     except subprocess.CalledProcessError as e:
-        click.echo(f"An error occurred while running the crew: {e}", err=True)
-        click.echo(e.output, err=True, nl=True)
-
-        if pyproject_data.get("tool", {}).get("poetry"):
-            click.secho(
-                "It's possible that you are using an old version of crewAI that uses poetry, please run `crewai update` to update your pyproject.toml to use uv.",
-                fg="yellow",
-            )
+        handle_error(e, crew_type)
 
     except Exception as e:
         click.echo(f"An unexpected error occurred: {e}", err=True)
+
+
+def handle_error(error: subprocess.CalledProcessError, crew_type: CrewType) -> None:
+    """
+    Handle subprocess errors with appropriate messaging.
+
+    Args:
+        error: The subprocess error that occurred
+        crew_type: The type of crew that was being run
+    """
+    entity_type = "flow" if crew_type == CrewType.FLOW else "crew"
+    click.echo(f"An error occurred while running the {entity_type}: {error}", err=True)
+
+    if error.output:
+        click.echo(error.output, err=True, nl=True)
+
+    pyproject_data = read_toml()
+    if pyproject_data.get("tool", {}).get("poetry"):
+        click.secho(
+            "It's possible that you are using an old version of crewAI that uses poetry, "
+            "please run `crewai update` to update your pyproject.toml to use uv.",
+            fg="yellow",
+        )

src/crewai/cli/templates/crew/main.py

@@ -56,7 +56,8 @@ def test():
     Test the crew execution and returns the results.
     """
     inputs = {
-        "topic": "AI LLMs"
+        "topic": "AI LLMs",
+        "current_year": str(datetime.now().year)
     }
     try:
         {{crew_name}}().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)

src/crewai/cli/templates/crew/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.1,<1.0.0"
+    "crewai[tools]>=0.102.0,<1.0.0"
 ]
 
 [project.scripts]

src/crewai/cli/templates/flow/README.md

@@ -30,13 +30,13 @@ crewai install
 
 ## Running the Project
 
-To kickstart your crew of AI agents and begin task execution, run this from the root folder of your project:
+To kickstart your flow and begin execution, run this from the root folder of your project:
 
 ```bash
 crewai run
 ```
 
-This command initializes the {{name}} Crew, assembling the agents and assigning them tasks as defined in your configuration.
+This command initializes the {{name}} Flow as defined in your configuration.
 
 This example, unmodified, will run the create a `report.md` file with the output of a research on LLMs in the root folder.
 

src/crewai/cli/templates/flow/pyproject.toml

@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.1,<1.0.0",
+    "crewai[tools]>=0.102.0,<1.0.0",
 ]
 
 [project.scripts]

src/crewai/cli/templates/tool/pyproject.toml

@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.13"
 dependencies = [
-    "crewai[tools]>=0.100.1"
+    "crewai[tools]>=0.102.0"
 ]
 
 [tool.crewai]

src/crewai/cli/utils.py

@@ -257,11 +257,11 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
         import os
 
         for root, _, files in os.walk("."):
-            if "crew.py" in files:
-                crew_path = os.path.join(root, "crew.py")
+            if crew_path in files:
+                crew_os_path = os.path.join(root, crew_path)
                 try:
                     spec = importlib.util.spec_from_file_location(
-                        "crew_module", crew_path
+                        "crew_module", crew_os_path
                     )
                     if not spec or not spec.loader:
                         continue
@@ -273,9 +273,11 @@ def get_crew(crew_path: str = "crew.py", require: bool = False) -> Crew | None:
                         for attr_name in dir(module):
                             attr = getattr(module, attr_name)
                             try:
-                                if callable(attr) and hasattr(attr, "crew"):
-                                    crew_instance = attr().crew()
-                                    return crew_instance
+                                if isinstance(attr, Crew) and hasattr(attr, "kickoff"):
+                                    print(
+                                        f"Found valid crew object in attribute '{attr_name}' at {crew_os_path}."
+                                    )
+                                    return attr
 
                             except Exception as e:
                                 print(f"Error processing attribute {attr_name}: {e}")

src/crewai/crew.py

@@ -1,7 +1,6 @@
 import asyncio
 import json
 import re
-import sys
 import uuid
 import warnings
 from concurrent.futures import Future
@@ -36,7 +35,6 @@ from crewai.process import Process
 from crewai.task import Task
 from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
-from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools.agent_tools import AgentTools
 from crewai.tools.base_tool import Tool
 from crewai.types.usage_metrics import UsageMetrics
@@ -44,6 +42,18 @@ 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 +63,6 @@ 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")
 
 
@@ -252,8 +256,6 @@ class Crew(BaseModel):
         if self.function_calling_llm and not isinstance(self.function_calling_llm, LLM):
             self.function_calling_llm = create_llm(self.function_calling_llm)
 
-        self._telemetry = Telemetry()
-        self._telemetry.set_tracer()
         return self
 
     @model_validator(mode="after")
@@ -276,12 +278,26 @@ class Crew(BaseModel):
                 if self.entity_memory
                 else EntityMemory(crew=self, embedder_config=self.embedder)
             )
-            if hasattr(self, "memory_config") and self.memory_config is not None:
-                self._user_memory = (
-                    self.user_memory if self.user_memory else UserMemory(crew=self)
-                )
+            if (
+                self.memory_config and "user_memory" in self.memory_config
+            ):  # Check for user_memory in config
+                user_memory_config = self.memory_config["user_memory"]
+                if isinstance(
+                    user_memory_config, UserMemory
+                ):  # Check if it is already an instance
+                    self._user_memory = user_memory_config
+                elif isinstance(
+                    user_memory_config, dict
+                ):  # Check if it's a configuration dict
+                    self._user_memory = UserMemory(
+                        crew=self, **user_memory_config
+                    )  # Initialize with config
+                else:
+                    raise TypeError(
+                        "user_memory must be a UserMemory instance or a configuration dictionary"
+                    )
             else:
-                self._user_memory = None
+                self._user_memory = None  # No user memory if not in config
         return self
 
     @model_validator(mode="after")
@@ -381,6 +397,22 @@ class Crew(BaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def validate_must_have_non_conditional_task(self) -> "Crew":
+        """Ensure that a crew has at least one non-conditional task."""
+        if not self.tasks:
+            return self
+        non_conditional_count = sum(
+            1 for task in self.tasks if not isinstance(task, ConditionalTask)
+        )
+        if non_conditional_count == 0:
+            raise PydanticCustomError(
+                "only_conditional_tasks",
+                "Crew must include at least one non-conditional task",
+                {},
+            )
+        return self
+
     @model_validator(mode="after")
     def validate_first_task(self) -> "Crew":
         """Ensure the first task is not a ConditionalTask."""
@@ -440,7 +472,6 @@ class Crew(BaseModel):
                         )
         return self
 
-
     @property
     def key(self) -> str:
         source = [agent.key for agent in self.agents] + [
@@ -493,10 +524,19 @@ 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)
@@ -511,7 +551,20 @@ 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()
@@ -521,60 +574,71 @@ 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]
+                agent.set_knowledge(crew_embedder=self.embedder)
+                # 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."""
@@ -743,6 +807,7 @@ class Crew(BaseModel):
                     task, task_outputs, futures, task_index, was_replayed
                 )
                 if skipped_task_output:
+                    task_outputs.append(skipped_task_output)
                     continue
 
             if task.async_execution:
@@ -766,7 +831,7 @@ class Crew(BaseModel):
                     context=context,
                     tools=tools_for_task,
                 )
-                task_outputs = [task_output]
+                task_outputs.append(task_output)
                 self._process_task_result(task, task_output)
                 self._store_execution_log(task, task_output, task_index, was_replayed)
 
@@ -787,7 +852,7 @@ class Crew(BaseModel):
             task_outputs = self._process_async_tasks(futures, was_replayed)
             futures.clear()
 
-        previous_output = task_outputs[task_index - 1] if task_outputs else None
+        previous_output = task_outputs[-1] if task_outputs else None
         if previous_output is not None and not task.should_execute(previous_output):
             self._logger.log(
                 "debug",
@@ -909,20 +974,29 @@ class Crew(BaseModel):
             )
 
     def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
-        if len(task_outputs) != 1:
-            raise ValueError(
-                "Something went wrong. Kickoff should return only one task output."
-            )
-        final_task_output = task_outputs[0]
+        if not task_outputs:
+            raise ValueError("No task outputs available to create crew output.")
+
+        # Filter out empty outputs and get the last valid one as the main output
+        valid_outputs = [t for t in task_outputs if t.raw]
+        if not valid_outputs:
+            raise ValueError("No valid task outputs available to create crew output.")
+        final_task_output = valid_outputs[-1]
+
         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,
             json_dict=final_task_output.json_dict,
-            tasks_output=[task.output for task in self.tasks if task.output],
+            tasks_output=task_outputs,
             token_usage=token_usage,
         )
 
@@ -1037,7 +1111,6 @@ class Crew(BaseModel):
             "_short_term_memory",
             "_long_term_memory",
             "_entity_memory",
-            "_telemetry",
             "agents",
             "tasks",
             "knowledge_sources",
@@ -1103,13 +1176,6 @@ 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."""
@@ -1127,25 +1193,45 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        openai_model_name: Optional[str] = None,
+        eval_llm: Union[str, InstanceOf[LLM]],
         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.")
 
-        self._test_execution_span = test_crew._telemetry.test_execution_span(
-            test_crew,
-            n_iterations,
-            inputs,
-            openai_model_name,  # type: ignore[arg-type]
-        )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+            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]
 
-        for i in range(1, n_iterations + 1):
-            evaluator.set_iteration(i)
-            test_crew.kickoff(inputs=inputs)
+            for i in range(1, n_iterations + 1):
+                evaluator.set_iteration(i)
+                test_crew.kickoff(inputs=inputs)
 
-        evaluator.print_crew_evaluation_result()
+            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)})"
@@ -1187,11 +1273,11 @@ class Crew(BaseModel):
     def _reset_all_memories(self) -> None:
         """Reset all available memory systems."""
         memory_systems = [
-            ("short term", self._short_term_memory),
-            ("entity", self._entity_memory),
-            ("long term", self._long_term_memory),
-            ("task output", self._task_output_handler),
-            ("knowledge", self.knowledge),
+            ("short term", getattr(self, "_short_term_memory", None)),
+            ("entity", getattr(self, "_entity_memory", None)),
+            ("long term", getattr(self, "_long_term_memory", None)),
+            ("task output", getattr(self, "_task_output_handler", None)),
+            ("knowledge", getattr(self, "knowledge", None)),
         ]
 
         for name, system in memory_systems:

src/crewai/flow/flow.py

@@ -1,4 +1,5 @@
 import asyncio
+import copy
 import inspect
 import logging
 from typing import (
@@ -16,19 +17,21 @@ 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.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__)
@@ -394,7 +397,6 @@ class FlowMeta(type):
                 or hasattr(attr_value, "__trigger_methods__")
                 or hasattr(attr_value, "__is_router__")
             ):
-
                 # Register start methods
                 if hasattr(attr_value, "__is_start_method__"):
                     start_methods.append(attr_name)
@@ -427,7 +429,6 @@ 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] = []
@@ -435,7 +436,6 @@ 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
@@ -469,7 +469,13 @@ 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):
@@ -569,6 +575,9 @@ class Flow(Generic[T], metaclass=FlowMeta):
             f"Initial state must be dict or BaseModel, got {type(self.initial_state)}"
         )
 
+    def _copy_state(self) -> T:
+        return copy.deepcopy(self._state)
+
     @property
     def state(self) -> T:
         return self._state
@@ -700,16 +709,34 @@ class Flow(Generic[T], metaclass=FlowMeta):
             raise TypeError(f"State must be dict or BaseModel, got {type(self._state)}")
 
     def kickoff(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
-        """Start the flow execution.
+        """
+        Start the flow execution in a synchronous context.
+
+        This method wraps kickoff_async so that all state initialization and event
+        emission is handled in the asynchronous method.
+        """
+
+        async def run_flow():
+            return await self.kickoff_async(inputs)
+
+        return asyncio.run(run_flow())
+
+    async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
+        """
+        Start the flow execution asynchronously.
+
+        This method performs state restoration (if an 'id' is provided and persistence is available)
+        and updates the flow state with any additional inputs. It then emits the FlowStartedEvent,
+        logs the flow startup, and executes all start methods. Once completed, it emits the
+        FlowFinishedEvent and returns the final output.
 
         Args:
-            inputs: Optional dictionary containing input values and potentially a state ID to restore
-        """
-        # Handle state restoration if ID is provided in inputs
-        if inputs and "id" in inputs and self._persistence is not None:
-            restore_uuid = inputs["id"]
-            stored_state = self._persistence.load_state(restore_uuid)
+            inputs: Optional dictionary containing input values and/or a state ID for restoration.
 
+        Returns:
+            The final output from the flow, which is the result of the last executed method.
+        """
+        if inputs:
             # Override the id in the state if it exists in inputs
             if "id" in inputs:
                 if isinstance(self._state, dict):
@@ -717,29 +744,33 @@ class Flow(Generic[T], metaclass=FlowMeta):
                 elif isinstance(self._state, BaseModel):
                     setattr(self._state, "id", inputs["id"])
 
-            if stored_state:
-                self._log_flow_event(
-                    f"Loading flow state from memory for UUID: {restore_uuid}",
-                    color="yellow",
-                )
-                # Restore the state
-                self._restore_state(stored_state)
-            else:
-                self._log_flow_event(
-                    f"No flow state found for UUID: {restore_uuid}", color="red"
-                )
+            # If persistence is enabled, attempt to restore the stored state using the provided id.
+            if "id" in inputs and self._persistence is not None:
+                restore_uuid = inputs["id"]
+                stored_state = self._persistence.load_state(restore_uuid)
+                if stored_state:
+                    self._log_flow_event(
+                        f"Loading flow state from memory for UUID: {restore_uuid}",
+                        color="yellow",
+                    )
+                    self._restore_state(stored_state)
+                else:
+                    self._log_flow_event(
+                        f"No flow state found for UUID: {restore_uuid}", color="red"
+                    )
 
-            # Apply any additional inputs after restoration
+            # Update state with any additional inputs (ignoring the 'id' key)
             filtered_inputs = {k: v for k, v in inputs.items() if k != "id"}
             if filtered_inputs:
                 self._initialize_state(filtered_inputs)
 
-        # Start flow execution
-        self.event_emitter.send(
+        # Emit FlowStartedEvent and log the start of the flow.
+        crewai_event_bus.emit(
             self,
-            event=FlowStartedEvent(
+            FlowStartedEvent(
                 type="flow_started",
                 flow_name=self.__class__.__name__,
+                inputs=inputs,
             ),
         )
         self._log_flow_event(
@@ -749,16 +780,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         if inputs is not None and "id" not in inputs:
             self._initialize_state(inputs)
 
-        return asyncio.run(self.kickoff_async())
-
-    async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = None) -> Any:
-        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
@@ -767,14 +788,15 @@ 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,
             ),
         )
+
         return final_output
 
     async def _execute_start_method(self, start_method_name: str) -> None:
@@ -803,16 +825,55 @@ class Flow(Generic[T], metaclass=FlowMeta):
     async def _execute_method(
         self, method_name: str, method: Callable, *args: Any, **kwargs: Any
     ) -> Any:
-        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
-        )
-        return result
+        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
+            )
+
+            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:
         """
@@ -833,35 +894,45 @@ class Flow(Generic[T], metaclass=FlowMeta):
         Notes
         -----
         - Routers are executed sequentially to maintain flow control
-        - Each router's result becomes the new trigger_method
+        - Each router's result becomes a new trigger_method
         - Normal listeners are executed in parallel for efficiency
         - Listeners can receive the trigger method's result as a parameter
         """
         # First, handle routers repeatedly until no router triggers anymore
+        router_results = []
+        current_trigger = trigger_method
+
         while True:
             routers_triggered = self._find_triggered_methods(
-                trigger_method, router_only=True
+                current_trigger, router_only=True
             )
             if not routers_triggered:
                 break
+
             for router_name in routers_triggered:
                 await self._execute_single_listener(router_name, result)
                 # After executing router, the router's result is the path
-                # The last router executed sets the trigger_method
-                # The router result is the last element in self._method_outputs
-                trigger_method = self._method_outputs[-1]
+                router_result = self._method_outputs[-1]
+                if router_result:  # Only add non-None results
+                    router_results.append(router_result)
+                current_trigger = (
+                    router_result  # Update for next iteration of router chain
+                )
 
-        # Now that no more routers are triggered by current trigger_method,
-        # execute normal listeners
-        listeners_triggered = self._find_triggered_methods(
-            trigger_method, router_only=False
-        )
-        if listeners_triggered:
-            tasks = [
-                self._execute_single_listener(listener_name, result)
-                for listener_name in listeners_triggered
-            ]
-            await asyncio.gather(*tasks)
+        # Now execute normal listeners for all router results and the original trigger
+        all_triggers = [trigger_method] + router_results
+
+        for current_trigger in all_triggers:
+            if current_trigger:  # Skip None results
+                listeners_triggered = self._find_triggered_methods(
+                    current_trigger, router_only=False
+                )
+                if listeners_triggered:
+                    tasks = [
+                        self._execute_single_listener(listener_name, result)
+                        for listener_name in listeners_triggered
+                    ]
+                    await asyncio.gather(*tasks)
 
     def _find_triggered_methods(
         self, trigger_method: str, router_only: bool
@@ -951,15 +1022,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
         try:
             method = self._methods[listener_name]
 
-            self.event_emitter.send(
-                self,
-                event=MethodExecutionStartedEvent(
-                    type="method_execution_started",
-                    method_name=listener_name,
-                    flow_name=self.__class__.__name__,
-                ),
-            )
-
             sig = inspect.signature(method)
             params = list(sig.parameters.values())
             method_params = [p for p in params if p.name != "self"]
@@ -971,15 +1033,6 @@ class Flow(Generic[T], metaclass=FlowMeta):
             else:
                 listener_result = await self._execute_method(listener_name, method)
 
-            self.event_emitter.send(
-                self,
-                event=MethodExecutionFinishedEvent(
-                    type="method_execution_finished",
-                    method_name=listener_name,
-                    flow_name=self.__class__.__name__,
-                ),
-            )
-
             # Execute listeners (and possibly routers) of this listener
             await self._execute_listeners(listener_name, listener_result)
 
@@ -1018,7 +1071,11 @@ 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

@@ -1,33 +0,0 @@
-from dataclasses import dataclass, field
-from datetime import datetime
-from typing import Any, Optional
-
-
-@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):
-    pass
-
-
-@dataclass
-class MethodExecutionStartedEvent(Event):
-    method_name: str
-
-
-@dataclass
-class MethodExecutionFinishedEvent(Event):
-    method_name: str
-
-
-@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/persistence/sqlite.py

@@ -4,7 +4,7 @@ SQLite-based implementation of flow state persistence.
 
 import json
 import sqlite3
-from datetime import datetime
+from datetime import datetime, timezone
 from pathlib import Path
 from typing import Any, Dict, Optional, Union
 
@@ -34,6 +34,7 @@ class SQLiteFlowPersistence(FlowPersistence):
             ValueError: If db_path is invalid
         """
         from crewai.utilities.paths import db_storage_path
+
         # Get path from argument or default location
         path = db_path or str(Path(db_storage_path()) / "flow_states.db")
 
@@ -46,7 +47,8 @@ class SQLiteFlowPersistence(FlowPersistence):
     def init_db(self) -> None:
         """Create the necessary tables if they don't exist."""
         with sqlite3.connect(self.db_path) as conn:
-            conn.execute("""
+            conn.execute(
+                """
             CREATE TABLE IF NOT EXISTS flow_states (
                 id INTEGER PRIMARY KEY AUTOINCREMENT,
                 flow_uuid TEXT NOT NULL,
@@ -54,12 +56,15 @@ class SQLiteFlowPersistence(FlowPersistence):
                 timestamp DATETIME NOT NULL,
                 state_json TEXT NOT NULL
             )
-            """)
+            """
+            )
             # Add index for faster UUID lookups
-            conn.execute("""
+            conn.execute(
+                """
             CREATE INDEX IF NOT EXISTS idx_flow_states_uuid
             ON flow_states(flow_uuid)
-            """)
+            """
+            )
 
     def save_state(
         self,
@@ -85,19 +90,22 @@ class SQLiteFlowPersistence(FlowPersistence):
             )
 
         with sqlite3.connect(self.db_path) as conn:
-            conn.execute("""
+            conn.execute(
+                """
             INSERT INTO flow_states (
                 flow_uuid,
                 method_name,
                 timestamp,
                 state_json
             ) VALUES (?, ?, ?, ?)
-            """, (
-                flow_uuid,
-                method_name,
-                datetime.utcnow().isoformat(),
-                json.dumps(state_dict),
-            ))
+            """,
+                (
+                    flow_uuid,
+                    method_name,
+                    datetime.now(timezone.utc).isoformat(),
+                    json.dumps(state_dict),
+                ),
+            )
 
     def load_state(self, flow_uuid: str) -> Optional[Dict[str, Any]]:
         """Load the most recent state for a given flow UUID.
@@ -109,13 +117,16 @@ class SQLiteFlowPersistence(FlowPersistence):
             The most recent state as a dictionary, or None if no state exists
         """
         with sqlite3.connect(self.db_path) as conn:
-            cursor = conn.execute("""
+            cursor = conn.execute(
+                """
             SELECT state_json
             FROM flow_states
             WHERE flow_uuid = ?
             ORDER BY id DESC
             LIMIT 1
-            """, (flow_uuid,))
+            """,
+                (flow_uuid,),
+            )
             row = cursor.fetchone()
 
         if row:

src/crewai/flow/state_utils.py

@@ -0,0 +1,91 @@
+import json
+from datetime import date, datetime
+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, 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
+    that can be safely serialized to JSON. To prevent infinite recursion with
+    circular references, the conversion is limited to a depth of 5 levels.
+
+    Args:
+        flow: The Flow object whose state needs to be exported
+
+    Returns:
+        dict[str, Any]: The transformed state using JSON-compatible Python
+            types.
+    """
+    result = to_serializable(flow._state)
+    assert isinstance(result, dict)
+    return result
+
+
+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)
+
+    if isinstance(obj, (str, int, float, bool, type(None))):
+        return obj
+    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]
+    elif isinstance(obj, dict):
+        return {
+            _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)
+    else:
+        return repr(obj)
+
+
+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/flow/utils.py

@@ -16,7 +16,8 @@ Example
 import ast
 import inspect
 import textwrap
-from typing import Any, Dict, List, Optional, Set, Union
+from collections import defaultdict, deque
+from typing import Any, Deque, Dict, List, Optional, Set, Union
 
 
 def get_possible_return_constants(function: Any) -> Optional[List[str]]:
@@ -118,7 +119,7 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
     - Processes router paths separately
     """
     levels: Dict[str, int] = {}
-    queue: List[str] = []
+    queue: Deque[str] = deque()
     visited: Set[str] = set()
     pending_and_listeners: Dict[str, Set[str]] = {}
 
@@ -128,28 +129,35 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
             levels[method_name] = 0
             queue.append(method_name)
 
+    # Precompute listener dependencies
+    or_listeners = defaultdict(list)
+    and_listeners = defaultdict(set)
+    for listener_name, (condition_type, trigger_methods) in flow._listeners.items():
+        if condition_type == "OR":
+            for method in trigger_methods:
+                or_listeners[method].append(listener_name)
+        elif condition_type == "AND":
+            and_listeners[listener_name] = set(trigger_methods)
+
     # Breadth-first traversal to assign levels
     while queue:
-        current = queue.pop(0)
+        current = queue.popleft()
         current_level = levels[current]
         visited.add(current)
 
-        for listener_name, (condition_type, trigger_methods) in flow._listeners.items():
-            if condition_type == "OR":
-                if current in trigger_methods:
-                    if (
-                        listener_name not in levels
-                        or levels[listener_name] > current_level + 1
-                    ):
-                        levels[listener_name] = current_level + 1
-                        if listener_name not in visited:
-                            queue.append(listener_name)
-            elif condition_type == "AND":
+        for listener_name in or_listeners[current]:
+            if listener_name not in levels or levels[listener_name] > current_level + 1:
+                levels[listener_name] = current_level + 1
+                if listener_name not in visited:
+                    queue.append(listener_name)
+
+        for listener_name, required_methods in and_listeners.items():
+            if current in required_methods:
                 if listener_name not in pending_and_listeners:
                     pending_and_listeners[listener_name] = set()
-                if current in trigger_methods:
-                    pending_and_listeners[listener_name].add(current)
-                if set(trigger_methods) == pending_and_listeners[listener_name]:
+                pending_and_listeners[listener_name].add(current)
+
+                if required_methods == pending_and_listeners[listener_name]:
                     if (
                         listener_name not in levels
                         or levels[listener_name] > current_level + 1
@@ -159,22 +167,7 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
                             queue.append(listener_name)
 
         # Handle router connections
-        if current in flow._routers:
-            router_method_name = current
-            paths = flow._router_paths.get(router_method_name, [])
-            for path in paths:
-                for listener_name, (
-                    condition_type,
-                    trigger_methods,
-                ) in flow._listeners.items():
-                    if path in trigger_methods:
-                        if (
-                            listener_name not in levels
-                            or levels[listener_name] > current_level + 1
-                        ):
-                            levels[listener_name] = current_level + 1
-                            if listener_name not in visited:
-                                queue.append(listener_name)
+        process_router_paths(flow, current, current_level, levels, queue)
 
     return levels
 
@@ -227,10 +220,7 @@ def build_ancestor_dict(flow: Any) -> Dict[str, Set[str]]:
 
 
 def dfs_ancestors(
-    node: str,
-    ancestors: Dict[str, Set[str]],
-    visited: Set[str],
-    flow: Any
+    node: str, ancestors: Dict[str, Set[str]], visited: Set[str], flow: Any
 ) -> None:
     """
     Perform depth-first search to build ancestor relationships.
@@ -274,7 +264,9 @@ def dfs_ancestors(
                     dfs_ancestors(listener_name, ancestors, visited, flow)
 
 
-def is_ancestor(node: str, ancestor_candidate: str, ancestors: Dict[str, Set[str]]) -> bool:
+def is_ancestor(
+    node: str, ancestor_candidate: str, ancestors: Dict[str, Set[str]]
+) -> bool:
     """
     Check if one node is an ancestor of another.
 
@@ -339,7 +331,9 @@ def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:
     return parent_children
 
 
-def get_child_index(parent: str, child: str, parent_children: Dict[str, List[str]]) -> int:
+def get_child_index(
+    parent: str, child: str, parent_children: Dict[str, List[str]]
+) -> int:
     """
     Get the index of a child node in its parent's sorted children list.
 
@@ -360,3 +354,23 @@ def get_child_index(parent: str, child: str, parent_children: Dict[str, List[str
     children = parent_children.get(parent, [])
     children.sort()
     return children.index(child)
+
+
+def process_router_paths(flow, current, current_level, levels, queue):
+    """
+    Handle the router connections for the current node.
+    """
+    if current in flow._routers:
+        paths = flow._router_paths.get(current, [])
+        for path in paths:
+            for listener_name, (
+                condition_type,
+                trigger_methods,
+            ) in flow._listeners.items():
+                if path in trigger_methods:
+                    if (
+                        listener_name not in levels
+                        or levels[listener_name] > current_level + 1
+                    ):
+                        levels[listener_name] = current_level + 1
+                        queue.append(listener_name)

src/crewai/knowledge/source/excel_knowledge_source.py

@@ -1,28 +1,138 @@
 from pathlib import Path
-from typing import Dict, List
+from typing import Dict, Iterator, List, Optional, Union
+from urllib.parse import urlparse
 
-from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource
+from pydantic import Field, field_validator
+
+from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.utilities.constants import KNOWLEDGE_DIRECTORY
+from crewai.utilities.logger import Logger
 
 
-class ExcelKnowledgeSource(BaseFileKnowledgeSource):
+class ExcelKnowledgeSource(BaseKnowledgeSource):
     """A knowledge source that stores and queries Excel file content using embeddings."""
 
-    def load_content(self) -> Dict[Path, str]:
-        """Load and preprocess Excel file content."""
-        pd = self._import_dependencies()
+    # override content to be a dict of file paths to sheet names to csv content
 
+    _logger: Logger = Logger(verbose=True)
+
+    file_path: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default=None,
+        description="[Deprecated] The path to the file. Use file_paths instead.",
+    )
+    file_paths: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+        default_factory=list, description="The path to the file"
+    )
+    chunks: List[str] = Field(default_factory=list)
+    content: Dict[Path, Dict[str, str]] = Field(default_factory=dict)
+    safe_file_paths: List[Path] = Field(default_factory=list)
+
+    @field_validator("file_path", "file_paths", mode="before")
+    def validate_file_path(cls, v, info):
+        """Validate that at least one of file_path or file_paths is provided."""
+        # Single check if both are None, O(1) instead of nested conditions
+        if (
+            v is None
+            and info.data.get(
+                "file_path" if info.field_name == "file_paths" else "file_paths"
+            )
+            is None
+        ):
+            raise ValueError("Either file_path or file_paths must be provided")
+        return v
+
+    def _process_file_paths(self) -> List[Path]:
+        """Convert file_path to a list of Path objects."""
+
+        if hasattr(self, "file_path") and self.file_path is not None:
+            self._logger.log(
+                "warning",
+                "The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
+                color="yellow",
+            )
+            self.file_paths = self.file_path
+
+        if self.file_paths is None:
+            raise ValueError("Your source must be provided with a file_paths: []")
+
+        # Convert single path to list
+        path_list: List[Union[Path, str]] = (
+            [self.file_paths]
+            if isinstance(self.file_paths, (str, Path))
+            else list(self.file_paths)
+            if isinstance(self.file_paths, list)
+            else []
+        )
+
+        if not path_list:
+            raise ValueError(
+                "file_path/file_paths must be a Path, str, or a list of these types"
+            )
+
+        return [self.convert_to_path(path) for path in path_list]
+
+    def validate_content(self):
+        """Validate the paths."""
+        for path in self.safe_file_paths:
+            if not path.exists():
+                self._logger.log(
+                    "error",
+                    f"File not found: {path}. Try adding sources to the knowledge directory. If it's inside the knowledge directory, use the relative path.",
+                    color="red",
+                )
+                raise FileNotFoundError(f"File not found: {path}")
+            if not path.is_file():
+                self._logger.log(
+                    "error",
+                    f"Path is not a file: {path}",
+                    color="red",
+                )
+
+    def model_post_init(self, _) -> None:
+        if self.file_path:
+            self._logger.log(
+                "warning",
+                "The 'file_path' attribute is deprecated and will be removed in a future version. Please use 'file_paths' instead.",
+                color="yellow",
+            )
+            self.file_paths = self.file_path
+        self.safe_file_paths = self._process_file_paths()
+        self.validate_content()
+        self.content = self._load_content()
+
+    def _load_content(self) -> Dict[Path, Dict[str, str]]:
+        """Load and preprocess Excel file content from multiple sheets.
+
+        Each sheet's content is converted to CSV format and stored.
+
+        Returns:
+            Dict[Path, Dict[str, str]]: A mapping of file paths to their respective sheet contents.
+
+        Raises:
+            ImportError: If required dependencies are missing.
+            FileNotFoundError: If the specified Excel file cannot be opened.
+        """
+        pd = self._import_dependencies()
         content_dict = {}
         for file_path in self.safe_file_paths:
             file_path = self.convert_to_path(file_path)
-            df = pd.read_excel(file_path)
-            content = df.to_csv(index=False)
-            content_dict[file_path] = content
+            with pd.ExcelFile(file_path) as xl:
+                sheet_dict = {
+                    str(sheet_name): str(
+                        pd.read_excel(xl, sheet_name).to_csv(index=False)
+                    )
+                    for sheet_name in xl.sheet_names
+                }
+            content_dict[file_path] = sheet_dict
         return content_dict
 
+    def convert_to_path(self, path: Union[Path, str]) -> Path:
+        """Convert a path to a Path object."""
+        return Path(KNOWLEDGE_DIRECTORY + "/" + path) if isinstance(path, str) else path
+
     def _import_dependencies(self):
         """Dynamically import dependencies."""
         try:
-            import openpyxl  # noqa
             import pandas as pd
 
             return pd
@@ -38,10 +148,14 @@ class ExcelKnowledgeSource(BaseFileKnowledgeSource):
         and save the embeddings.
         """
         # Convert dictionary values to a single string if content is a dictionary
-        if isinstance(self.content, dict):
-            content_str = "\n".join(str(value) for value in self.content.values())
-        else:
-            content_str = str(self.content)
+        # Updated to account for .xlsx workbooks with multiple tabs/sheets
+        content_str = ""
+        for value in self.content.values():
+            if isinstance(value, dict):
+                for sheet_value in value.values():
+                    content_str += str(sheet_value) + "\n"
+            else:
+                content_str += str(value) + "\n"
 
         new_chunks = self._chunk_text(content_str)
         self.chunks.extend(new_chunks)

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

@@ -10,14 +10,23 @@ from typing import Any, Dict, List, Literal, Optional, Type, Union, cast
 from dotenv import load_dotenv
 from pydantic import BaseModel
 
+from crewai.utilities.events.llm_events import (
+    LLMCallCompletedEvent,
+    LLMCallFailedEvent,
+    LLMCallStartedEvent,
+    LLMCallType,
+)
+from crewai.utilities.events.tool_usage_events import ToolExecutionErrorEvent
+
 with warnings.catch_warnings():
     warnings.simplefilter("ignore", UserWarning)
     import litellm
-    from litellm import Choices, get_supported_openai_params
+    from litellm import Choices
     from litellm.types.utils import ModelResponse
-    from litellm.utils import supports_response_schema
+    from litellm.utils import get_supported_openai_params, supports_response_schema
 
 
+from crewai.utilities.events import crewai_event_bus
 from crewai.utilities.exceptions.context_window_exceeding_exception import (
     LLMContextLengthExceededException,
 )
@@ -55,6 +64,7 @@ LLM_CONTEXT_WINDOW_SIZES = {
     "gpt-4-turbo": 128000,
     "o1-preview": 128000,
     "o1-mini": 128000,
+    "o3-mini": 200000,  # Based on official o3-mini specifications
     # gemini
     "gemini-2.0-flash": 1048576,
     "gemini-1.5-pro": 2097152,
@@ -164,6 +174,7 @@ class LLM:
         self.context_window_size = 0
         self.reasoning_effort = reasoning_effort
         self.additional_params = kwargs
+        self.is_anthropic = self._is_anthropic_model(model)
 
         litellm.drop_params = True
 
@@ -178,43 +189,72 @@ class LLM:
         self.set_callbacks(callbacks)
         self.set_env_callbacks()
 
+    def _is_anthropic_model(self, model: str) -> bool:
+        """Determine if the model is from Anthropic provider.
+
+        Args:
+            model: The model identifier string.
+
+        Returns:
+            bool: True if the model is from Anthropic, False otherwise.
+        """
+        ANTHROPIC_PREFIXES = ("anthropic/", "claude-", "claude/")
+        return any(prefix in model.lower() for prefix in ANTHROPIC_PREFIXES)
+
     def call(
         self,
         messages: Union[str, List[Dict[str, str]]],
         tools: Optional[List[dict]] = None,
         callbacks: Optional[List[Any]] = None,
         available_functions: Optional[Dict[str, Any]] = None,
-    ) -> str:
-        """
-        High-level llm call method that:
-          1) Accepts either a string or a list of messages
-          2) Converts string input to the required message format
-          3) Calls litellm.completion
-          4) Handles function/tool calls if any
-          5) Returns the final text response or tool result
+    ) -> Union[str, Any]:
+        """High-level LLM call method.
 
-        Parameters:
-        - messages (Union[str, List[Dict[str, str]]]): The input messages for the LLM.
-          - If a string is provided, it will be converted into a message list with a single entry.
-          - If a list of dictionaries is provided, each dictionary should have 'role' and 'content' keys.
-        - tools (Optional[List[dict]]): A list of tool schemas for function calling.
-        - callbacks (Optional[List[Any]]): A list of callback functions to be executed.
-        - available_functions (Optional[Dict[str, Any]]): A dictionary mapping function names to actual Python functions.
+        Args:
+            messages: Input messages for the LLM.
+                     Can be a string or list of message dictionaries.
+                     If string, it will be converted to a single user message.
+                     If list, each dict must have 'role' and 'content' keys.
+            tools: Optional list of tool schemas for function calling.
+                  Each tool should define its name, description, and parameters.
+            callbacks: Optional list of callback functions to be executed
+                      during and after the LLM call.
+            available_functions: Optional dict mapping function names to callables
+                               that can be invoked by the LLM.
 
         Returns:
-        - str: The final text response from the LLM or the result of a tool function call.
+            Union[str, Any]: Either a text response from the LLM (str) or
+                           the result of a tool function call (Any).
+
+        Raises:
+            TypeError: If messages format is invalid
+            ValueError: If response format is not supported
+            LLMContextLengthExceededException: If input exceeds model's context limit
 
         Examples:
-        ---------
-        # Example 1: Using a string input
-        response = llm.call("Return the name of a random city in the world.")
-        print(response)
+            # Example 1: Simple string input
+            >>> response = llm.call("Return the name of a random city.")
+            >>> print(response)
+            "Paris"
 
-        # Example 2: Using a list of messages
-        messages = [{"role": "user", "content": "What is the capital of France?"}]
-        response = llm.call(messages)
-        print(response)
+            # Example 2: Message list with system and user messages
+            >>> messages = [
+            ...     {"role": "system", "content": "You are a geography expert"},
+            ...     {"role": "user", "content": "What is France's capital?"}
+            ... ]
+            >>> response = llm.call(messages)
+            >>> print(response)
+            "The capital of France is Paris."
         """
+        crewai_event_bus.emit(
+            self,
+            event=LLMCallStartedEvent(
+                messages=messages,
+                tools=tools,
+                callbacks=callbacks,
+                available_functions=available_functions,
+            ),
+        )
         # Validate parameters before proceeding with the call.
         self._validate_call_params()
 
@@ -233,10 +273,13 @@ class LLM:
                 self.set_callbacks(callbacks)
 
             try:
-                # --- 1) Prepare the parameters for the completion call
+                # --- 1) Format messages according to provider requirements
+                formatted_messages = self._format_messages_for_provider(messages)
+
+                # --- 2) Prepare the parameters for the completion call
                 params = {
                     "model": self.model,
-                    "messages": messages,
+                    "messages": formatted_messages,
                     "timeout": self.timeout,
                     "temperature": self.temperature,
                     "top_p": self.top_p,
@@ -286,6 +329,7 @@ class LLM:
 
                 # --- 4) If no tool calls, return the text response
                 if not tool_calls or not available_functions:
+                    self._handle_emit_call_events(text_response, LLMCallType.LLM_CALL)
                     return text_response
 
                 # --- 5) Handle the tool call
@@ -303,12 +347,28 @@ class LLM:
                     try:
                         # Call the actual tool function
                         result = fn(**function_args)
+                        self._handle_emit_call_events(result, LLMCallType.TOOL_CALL)
                         return result
 
                     except Exception as e:
                         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),
+                            ),
+                        )
+                        crewai_event_bus.emit(
+                            self,
+                            event=LLMCallFailedEvent(
+                                error=f"Tool execution error: {str(e)}"
+                            ),
+                        )
                         return text_response
 
                 else:
@@ -318,12 +378,64 @@ class LLM:
                     return text_response
 
             except Exception as e:
+                crewai_event_bus.emit(
+                    self,
+                    event=LLMCallFailedEvent(error=str(e)),
+                )
                 if not LLMContextLengthExceededException(
                     str(e)
                 )._is_context_limit_error(str(e)):
                     logging.error(f"LiteLLM call failed: {str(e)}")
                 raise
 
+    def _handle_emit_call_events(self, response: Any, call_type: LLMCallType):
+        """Handle the events for the LLM call.
+
+        Args:
+            response (str): The response from the LLM call.
+            call_type (str): The type of call, either "tool_call" or "llm_call".
+        """
+        crewai_event_bus.emit(
+            self,
+            event=LLMCallCompletedEvent(response=response, call_type=call_type),
+        )
+
+    def _format_messages_for_provider(
+        self, messages: List[Dict[str, str]]
+    ) -> List[Dict[str, str]]:
+        """Format messages according to provider requirements.
+
+        Args:
+            messages: List of message dictionaries with 'role' and 'content' keys.
+                     Can be empty or None.
+
+        Returns:
+            List of formatted messages according to provider requirements.
+            For Anthropic models, ensures first message has 'user' role.
+
+        Raises:
+            TypeError: If messages is None or contains invalid message format.
+        """
+        if messages is None:
+            raise TypeError("Messages cannot be None")
+
+        # Validate message format first
+        for msg in messages:
+            if not isinstance(msg, dict) or "role" not in msg or "content" not in msg:
+                raise TypeError(
+                    "Invalid message format. Each message must be a dict with 'role' and 'content' keys"
+                )
+
+        if not self.is_anthropic:
+            return messages
+
+        # Anthropic requires messages to start with 'user' role
+        if not messages or messages[0]["role"] == "system":
+            # If first message is system or empty, add a placeholder user message
+            return [{"role": "user", "content": "."}, *messages]
+
+        return messages
+
     def _get_custom_llm_provider(self) -> str:
         """
         Derives the custom_llm_provider from the model string.
@@ -357,7 +469,7 @@ class LLM:
     def supports_function_calling(self) -> bool:
         try:
             params = get_supported_openai_params(model=self.model)
-            return "response_format" in params
+            return params is not None and "tools" in params
         except Exception as e:
             logging.error(f"Failed to get supported params: {str(e)}")
             return False
@@ -365,7 +477,7 @@ class LLM:
     def supports_stop_words(self) -> bool:
         try:
             params = get_supported_openai_params(model=self.model)
-            return "stop" in params
+            return params is not None and "stop" in params
         except Exception as e:
             logging.error(f"Failed to get supported params: {str(e)}")
             return False
@@ -374,10 +486,23 @@ class LLM:
         """
         Returns the context window size, using 75% of the maximum to avoid
         cutting off messages mid-thread.
+
+        Raises:
+            ValueError: If a model's context window size is outside valid bounds (1024-2097152)
         """
         if self.context_window_size != 0:
             return self.context_window_size
 
+        MIN_CONTEXT = 1024
+        MAX_CONTEXT = 2097152  # Current max from gemini-1.5-pro
+
+        # Validate all context window sizes
+        for key, value in LLM_CONTEXT_WINDOW_SIZES.items():
+            if value < MIN_CONTEXT or value > MAX_CONTEXT:
+                raise ValueError(
+                    f"Context window for {key} must be between {MIN_CONTEXT} and {MAX_CONTEXT}"
+                )
+
         self.context_window_size = int(
             DEFAULT_CONTEXT_WINDOW_SIZE * CONTEXT_WINDOW_USAGE_RATIO
         )

src/crewai/memory/entity/entity_memory.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional
+from typing import Optional
 
 from pydantic import PrivateAttr
 

src/crewai/memory/memory.py

@@ -1,15 +1,15 @@
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel
 
-from crewai.memory.storage.rag_storage import RAGStorage
-
 
 class Memory(BaseModel):
     """
     Base class for memory, now supporting agent tags and generic metadata.
     """
 
+    embedder_config: Optional[Dict[str, Any]] = None
+
     storage: Any
 
     def __init__(self, storage: Any, **data: Any):

src/crewai/memory/storage/base_rag_storage.py

@@ -13,7 +13,7 @@ class BaseRAGStorage(ABC):
         self,
         type: str,
         allow_reset: bool = True,
-        embedder_config: Optional[Any] = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
         crew: Any = None,
     ):
         self.type = type

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.
@@ -674,19 +678,32 @@ class Task(BaseModel):
             return OutputFormat.PYDANTIC
         return OutputFormat.RAW
 
-    def _save_file(self, result: Any) -> None:
+    def _save_file(self, result: Union[Dict, str, Any]) -> None:
         """Save task output to a file.
 
+        Note:
+            For cross-platform file writing, especially on Windows, consider using FileWriterTool
+            from the crewai_tools package:
+                pip install 'crewai[tools]'
+                from crewai_tools import FileWriterTool
+
         Args:
             result: The result to save to the file. Can be a dict or any stringifiable object.
 
         Raises:
             ValueError: If output_file is not set
-            RuntimeError: If there is an error writing to the file
+            RuntimeError: If there is an error writing to the file. For cross-platform
+                compatibility, especially on Windows, use FileWriterTool from crewai_tools
+                package.
         """
         if self.output_file is None:
             raise ValueError("output_file is not set.")
 
+        FILEWRITER_RECOMMENDATION = (
+            "For cross-platform file writing, especially on Windows, "
+            "use FileWriterTool from crewai_tools package."
+        )
+
         try:
             resolved_path = Path(self.output_file).expanduser().resolve()
             directory = resolved_path.parent
@@ -702,7 +719,11 @@ class Task(BaseModel):
                 else:
                     file.write(str(result))
         except (OSError, IOError) as e:
-            raise RuntimeError(f"Failed to save output file: {e}")
+            raise RuntimeError(
+                "\n".join(
+                    [f"Failed to save output file: {e}", FILEWRITER_RECOMMENDATION]
+                )
+            )
         return None
 
     def __repr__(self):

src/crewai/tools/tool_usage.py

@@ -10,20 +10,21 @@ 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",
@@ -136,7 +137,6 @@ 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(
@@ -212,10 +212,6 @@ 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:
@@ -231,9 +227,6 @@ 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,
@@ -308,14 +301,33 @@ 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."""
@@ -451,18 +463,33 @@ 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
@@ -476,7 +503,7 @@ 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."
   },
@@ -40,8 +39,8 @@
     "validation_error": "### Previous attempt failed validation: {guardrail_result_error}\n\n\n### Previous result:\n{task_output}\n\n\nTry again, making sure to address the validation error."
   },
   "tools": {
-    "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolute everything you know, don't reference things but instead explain them.",
-    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolute everything you know, don't reference things but instead explain them.",
+    "delegate_work": "Delegate a specific task to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the task you want them to do, and ALL necessary context to execute the task, they know nothing about the task, so share absolutely everything you know, don't reference things but instead explain them.",
+    "ask_question": "Ask a specific question to one of the following coworkers: {coworkers}\nThe input to this tool should be the coworker, the question you have for them, and ALL necessary context to ask the question properly, they know nothing about the question, so share absolutely everything you know, don't reference things but instead explain them.",
     "add_image": {
       "name": "Add image to content",
       "description": "See image to understand its content, you can optionally ask a question about the image",

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/converter.py

@@ -20,11 +20,11 @@ class ConverterError(Exception):
 class Converter(OutputConverter):
     """Class that converts text into either pydantic or json."""
 
-    def to_pydantic(self, current_attempt=1):
+    def to_pydantic(self, current_attempt=1) -> BaseModel:
         """Convert text to pydantic."""
         try:
             if self.llm.supports_function_calling():
-                return self._create_instructor().to_pydantic()
+                result = self._create_instructor().to_pydantic()
             else:
                 response = self.llm.call(
                     [
@@ -32,18 +32,40 @@ class Converter(OutputConverter):
                         {"role": "user", "content": self.text},
                     ]
                 )
-                return self.model.model_validate_json(response)
+                try:
+                    # Try to directly validate the response JSON
+                    result = self.model.model_validate_json(response)
+                except ValidationError:
+                    # If direct validation fails, attempt to extract valid JSON
+                    result = handle_partial_json(response, self.model, False, None)
+                    # Ensure result is a BaseModel instance
+                    if not isinstance(result, BaseModel):
+                        if isinstance(result, dict):
+                            result = self.model.parse_obj(result)
+                        elif isinstance(result, str):
+                            try:
+                                parsed = json.loads(result)
+                                result = self.model.parse_obj(parsed)
+                            except Exception as parse_err:
+                                raise ConverterError(
+                                    f"Failed to convert partial JSON result into Pydantic: {parse_err}"
+                                )
+                        else:
+                            raise ConverterError(
+                                "handle_partial_json returned an unexpected type."
+                            )
+            return result
         except ValidationError as e:
             if current_attempt < self.max_attempts:
                 return self.to_pydantic(current_attempt + 1)
             raise ConverterError(
-                f"Failed to convert text into a Pydantic model due to the following validation error: {e}"
+                f"Failed to convert text into a Pydantic model due to validation error: {e}"
             )
         except Exception as e:
             if current_attempt < self.max_attempts:
                 return self.to_pydantic(current_attempt + 1)
             raise ConverterError(
-                f"Failed to convert text into a Pydantic model due to the following error: {e}"
+                f"Failed to convert text into a Pydantic model due to error: {e}"
             )
 
     def to_json(self, current_attempt=1):
@@ -197,11 +219,15 @@ def get_conversion_instructions(model: Type[BaseModel], llm: Any) -> str:
     if llm.supports_function_calling():
         model_schema = PydanticSchemaParser(model=model).get_schema()
         instructions += (
-            f"\n\nThe JSON should follow this schema:\n```json\n{model_schema}\n```"
+            f"\n\nOutput ONLY the valid JSON and nothing else.\n\n"
+            f"The JSON must follow this schema exactly:\n```json\n{model_schema}\n```"
         )
     else:
         model_description = generate_model_description(model)
-        instructions += f"\n\nThe JSON should follow this format:\n{model_description}"
+        instructions += (
+            f"\n\nOutput ONLY the valid JSON and nothing else.\n\n"
+            f"The JSON must follow this format exactly:\n{model_description}"
+        )
     return instructions
 
 

src/crewai/utilities/embedding_configurator.py

@@ -1,5 +1,5 @@
 import os
-from typing import Any, Dict, cast
+from typing import Any, Dict, Optional, cast
 
 from chromadb import Documents, EmbeddingFunction, Embeddings
 from chromadb.api.types import validate_embedding_function
@@ -18,11 +18,12 @@ class EmbeddingConfigurator:
             "bedrock": self._configure_bedrock,
             "huggingface": self._configure_huggingface,
             "watson": self._configure_watson,
+            "custom": self._configure_custom,
         }
 
     def configure_embedder(
         self,
-        embedder_config: Dict[str, Any] | None = None,
+        embedder_config: Optional[Dict[str, Any]] = None,
     ) -> EmbeddingFunction:
         """Configures and returns an embedding function based on the provided config."""
         if embedder_config is None:
@@ -30,20 +31,19 @@ class EmbeddingConfigurator:
 
         provider = embedder_config.get("provider")
         config = embedder_config.get("config", {})
-        model_name = config.get("model")
-
-        if isinstance(provider, EmbeddingFunction):
-            try:
-                validate_embedding_function(provider)
-                return provider
-            except Exception as e:
-                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+        model_name = config.get("model") if provider != "custom" else None
 
         if provider not in self.embedding_functions:
             raise Exception(
                 f"Unsupported embedding provider: {provider}, supported providers: {list(self.embedding_functions.keys())}"
             )
-        return self.embedding_functions[provider](config, model_name)
+
+        embedding_function = self.embedding_functions[provider]
+        return (
+            embedding_function(config)
+            if provider == "custom"
+            else embedding_function(config, model_name)
+        )
 
     @staticmethod
     def _create_default_embedding_function():
@@ -64,6 +64,13 @@ class EmbeddingConfigurator:
         return OpenAIEmbeddingFunction(
             api_key=config.get("api_key") or os.getenv("OPENAI_API_KEY"),
             model_name=model_name,
+            api_base=config.get("api_base", None),
+            api_type=config.get("api_type", None),
+            api_version=config.get("api_version", None),
+            default_headers=config.get("default_headers", None),
+            dimensions=config.get("dimensions", None),
+            deployment_id=config.get("deployment_id", None),
+            organization_id=config.get("organization_id", None),
         )
 
     @staticmethod
@@ -78,6 +85,10 @@ class EmbeddingConfigurator:
             api_type=config.get("api_type", "azure"),
             api_version=config.get("api_version"),
             model_name=model_name,
+            default_headers=config.get("default_headers"),
+            dimensions=config.get("dimensions"),
+            deployment_id=config.get("deployment_id"),
+            organization_id=config.get("organization_id"),
         )
 
     @staticmethod
@@ -100,6 +111,8 @@ class EmbeddingConfigurator:
         return GoogleVertexEmbeddingFunction(
             model_name=model_name,
             api_key=config.get("api_key"),
+            project_id=config.get("project_id"),
+            region=config.get("region"),
         )
 
     @staticmethod
@@ -111,6 +124,7 @@ class EmbeddingConfigurator:
         return GoogleGenerativeAiEmbeddingFunction(
             model_name=model_name,
             api_key=config.get("api_key"),
+            task_type=config.get("task_type"),
         )
 
     @staticmethod
@@ -195,3 +209,28 @@ class EmbeddingConfigurator:
                     raise e
 
         return WatsonEmbeddingFunction()
+
+    @staticmethod
+    def _configure_custom(config):
+        custom_embedder = config.get("embedder")
+        if isinstance(custom_embedder, EmbeddingFunction):
+            try:
+                validate_embedding_function(custom_embedder)
+                return custom_embedder
+            except Exception as e:
+                raise ValueError(f"Invalid custom embedding function: {str(e)}")
+        elif callable(custom_embedder):
+            try:
+                instance = custom_embedder()
+                if isinstance(instance, EmbeddingFunction):
+                    validate_embedding_function(instance)
+                    return instance
+                raise ValueError(
+                    "Custom embedder does not create an EmbeddingFunction instance"
+                )
+            except Exception as e:
+                raise ValueError(f"Error instantiating custom embedder: {str(e)}")
+        else:
+            raise ValueError(
+                "Custom embedder must be an instance of `EmbeddingFunction` or a callable that creates one"
+            )

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,11 +1,12 @@
 from collections import defaultdict
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, InstanceOf
 from rich.box import HEAVY_EDGE
 from rich.console import Console
 from rich.table import Table
 
 from crewai.agent import Agent
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
@@ -23,7 +24,7 @@ class CrewEvaluator:
 
     Attributes:
         crew (Crew): The crew of agents to evaluate.
-        openai_model_name (str): The model to use for evaluating the performance of the agents (for now ONLY OpenAI accepted).
+        eval_llm (LLM): Language model instance to use for evaluations
         tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
         iteration (int): The current iteration of the evaluation.
     """
@@ -32,9 +33,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, eval_llm: InstanceOf[LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = eval_llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +52,7 @@ class CrewEvaluator:
             ),
             backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
             verbose=False,
-            llm=self.openai_model_name,
+            llm=self.llm,
         )
 
     def _evaluation_task(
@@ -181,7 +182,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task.execution_duration,
-                self.openai_model_name,
+                self.llm.model,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(

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 +1,41 @@
+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,
+)
+from .llm_events import LLMCallCompletedEvent, LLMCallFailedEvent, LLMCallStartedEvent
+
+# 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 +1,288 @@
+from typing import Any, Dict
+
+from pydantic import Field, PrivateAttr
+
+from crewai.task import Task
+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 crewai.utilities.events.llm_events import (
+    LLMCallCompletedEvent,
+    LLMCallFailedEvent,
+    LLMCallStartedEvent,
+)
+
+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)
+    execution_spans: Dict[Task, Any] = Field(default_factory=dict)
+
+    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.execution_spans = {}
+            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, {source.id}",
+                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, {source.id}",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewKickoffFailedEvent)
+        def on_crew_failed(source, event: CrewKickoffFailedEvent):
+            self.logger.log(
+                f"❌ Crew '{event.crew_name}' failed, {source.id}",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(CrewTestStartedEvent)
+        def on_crew_test_started(source, event: CrewTestStartedEvent):
+            cloned_crew = source.copy()
+            self._telemetry.test_execution_span(
+                cloned_crew,
+                event.n_iterations,
+                event.inputs,
+                event.eval_llm or "",
+            )
+            self.logger.log(
+                f"🚀 Crew '{event.crew_name}' started test, {source.id}",
+                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):
+            span = self._telemetry.task_started(crew=source.agent.crew, task=source)
+            self.execution_spans[source] = span
+
+            self.logger.log(
+                f"📋 Task started: {source.description}",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(TaskCompletedEvent)
+        def on_task_completed(source, event: TaskCompletedEvent):
+            span = self.execution_spans.get(source)
+            if span:
+                self._telemetry.task_ended(span, source, source.agent.crew)
+            self.logger.log(
+                f"✅ Task completed: {source.description}",
+                event.timestamp,
+            )
+            self.execution_spans[source] = None
+
+        @crewai_event_bus.on(TaskFailedEvent)
+        def on_task_failed(source, event: TaskFailedEvent):
+            span = self.execution_spans.get(source)
+            if span:
+                if source.agent and source.agent.crew:
+                    self._telemetry.task_ended(span, source, source.agent.crew)
+                self.execution_spans[source] = 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(event.flow_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(
+                event.flow_name, list(source._methods.keys())
+            )
+            self.logger.log(
+                f"🤖 Flow Started: '{event.flow_name}', {source.flow_id}",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(FlowFinishedEvent)
+        def on_flow_finished(source, event: FlowFinishedEvent):
+            self.logger.log(
+                f"👍 Flow Finished: '{event.flow_name}', {source.flow_id}",
+                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,
+                #
+            )
+
+        # ----------- LLM EVENTS -----------
+
+        @crewai_event_bus.on(LLMCallStartedEvent)
+        def on_llm_call_started(source, event: LLMCallStartedEvent):
+            self.logger.log(
+                f"🤖 LLM Call Started",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(LLMCallCompletedEvent)
+        def on_llm_call_completed(source, event: LLMCallCompletedEvent):
+            self.logger.log(
+                f"✅ LLM Call Completed",
+                event.timestamp,
+            )
+
+        @crewai_event_bus.on(LLMCallFailedEvent)
+        def on_llm_call_failed(source, event: LLMCallFailedEvent):
+            self.logger.log(
+                f"❌ LLM Call Failed: '{event.error}'",
+                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/llm_events.py

@@ -0,0 +1,36 @@
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+
+from crewai.utilities.events.base_events import CrewEvent
+
+
+class LLMCallType(Enum):
+    """Type of LLM call being made"""
+
+    TOOL_CALL = "tool_call"
+    LLM_CALL = "llm_call"
+
+
+class LLMCallStartedEvent(CrewEvent):
+    """Event emitted when a LLM call starts"""
+
+    type: str = "llm_call_started"
+    messages: Union[str, List[Dict[str, str]]]
+    tools: Optional[List[dict]] = None
+    callbacks: Optional[List[Any]] = None
+    available_functions: Optional[Dict[str, Any]] = None
+
+
+class LLMCallCompletedEvent(CrewEvent):
+    """Event emitted when a LLM call completes"""
+
+    type: str = "llm_call_completed"
+    response: Any
+    call_type: LLMCallType
+
+
+class LLMCallFailedEvent(CrewEvent):
+    """Event emitted when a LLM call fails"""
+
+    error: str
+    type: str = "llm_call_failed"

src/crewai/utilities/events/task_events.py

@@ -0,0 +1,32 @@
+from typing import 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/llm_utils.py

@@ -44,6 +44,7 @@ def create_llm(
         # Extract attributes with explicit types
         model = (
             getattr(llm_value, "model_name", None)
+            or getattr(llm_value, "model", None)
             or getattr(llm_value, "deployment_name", None)
             or str(llm_value)
         )

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(

src/crewai/utilities/token_counter_callback.py

@@ -30,8 +30,14 @@ class TokenCalcHandler(CustomLogger):
                     if hasattr(usage, "prompt_tokens"):
                         self.token_cost_process.sum_prompt_tokens(usage.prompt_tokens)
                     if hasattr(usage, "completion_tokens"):
-                        self.token_cost_process.sum_completion_tokens(usage.completion_tokens)
-                    if hasattr(usage, "prompt_tokens_details") and usage.prompt_tokens_details:
+                        self.token_cost_process.sum_completion_tokens(
+                            usage.completion_tokens
+                        )
+                    if (
+                        hasattr(usage, "prompt_tokens_details")
+                        and usage.prompt_tokens_details
+                        and usage.prompt_tokens_details.cached_tokens
+                    ):
                         self.token_cost_process.sum_cached_prompt_tokens(
                             usage.prompt_tokens_details.cached_tokens
                         )

tests/agent_test.py

@@ -8,7 +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
@@ -16,9 +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():
@@ -154,15 +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"])
@@ -249,10 +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(
@@ -265,10 +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"])
@@ -983,23 +990,35 @@ 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
 
@@ -15,15 +14,24 @@ from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+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
 
@@ -49,6 +57,41 @@ writer = Agent(
 )
 
 
+def test_crew_with_only_conditional_tasks_raises_error():
+    """Test that creating a crew with only conditional tasks raises an error."""
+
+    def condition_func(task_output: TaskOutput) -> bool:
+        return True
+
+    conditional1 = ConditionalTask(
+        description="Conditional task 1",
+        expected_output="Output 1",
+        agent=researcher,
+        condition=condition_func,
+    )
+    conditional2 = ConditionalTask(
+        description="Conditional task 2",
+        expected_output="Output 2",
+        agent=researcher,
+        condition=condition_func,
+    )
+    conditional3 = ConditionalTask(
+        description="Conditional task 3",
+        expected_output="Output 3",
+        agent=researcher,
+        condition=condition_func,
+    )
+
+    with pytest.raises(
+        pydantic_core._pydantic_core.ValidationError,
+        match="Crew must include at least one non-conditional task",
+    ):
+        Crew(
+            agents=[researcher],
+            tasks=[conditional1, conditional2, conditional3],
+        )
+
+
 def test_crew_config_conditional_requirement():
     with pytest.raises(ValueError):
         Crew(process=Process.sequential)
@@ -556,12 +599,12 @@ def test_crew_with_delegating_agents_should_not_override_task_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -620,12 +663,12 @@ def test_crew_with_delegating_agents_should_not_override_agent_tools():
         _, kwargs = mock_execute_sync.call_args
         tools = kwargs["tools"]
 
-        assert any(isinstance(tool, TestTool) for tool in new_ceo.tools), (
-            "TestTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in new_ceo.tools
+        ), "TestTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in tools
+        ), "Delegation tool should be present"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -749,17 +792,17 @@ def test_task_tools_override_agent_tools_with_allow_delegation():
         used_tools = kwargs["tools"]
 
         # Confirm AnotherTestTool is present but TestTool is not
-        assert any(isinstance(tool, AnotherTestTool) for tool in used_tools), (
-            "AnotherTestTool should be present"
-        )
-        assert not any(isinstance(tool, TestTool) for tool in used_tools), (
-            "TestTool should not be present among used tools"
-        )
+        assert any(
+            isinstance(tool, AnotherTestTool) for tool in used_tools
+        ), "AnotherTestTool should be present"
+        assert not any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "TestTool should not be present among used tools"
 
         # Confirm delegation tool(s) are present
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
     # Finally, make sure the agent's original tools remain unchanged
     assert len(researcher_with_delegation.tools) == 1
@@ -790,6 +833,12 @@ def test_crew_verbose_output(capsys):
 
     crew.kickoff()
     captured = capsys.readouterr()
+
+    # Filter out event listener logs (lines starting with '[')
+    filtered_output = "\n".join(
+        line for line in captured.out.split("\n") if not line.startswith("[")
+    )
+
     expected_strings = [
         "\x1b[1m\x1b[95m# Agent:\x1b[00m \x1b[1m\x1b[92mResearcher",
         "\x1b[00m\n\x1b[95m## Task:\x1b[00m \x1b[92mResearch AI advancements.",
@@ -802,14 +851,19 @@ def test_crew_verbose_output(capsys):
     ]
 
     for expected_string in expected_strings:
-        assert expected_string in captured.out
+        assert expected_string in filtered_output
 
     # Now test with verbose set to False
     crew.verbose = False
     crew._logger = Logger(verbose=False)
     crew.kickoff()
     captured = capsys.readouterr()
-    assert captured.out == ""
+    filtered_output = "\n".join(
+        line
+        for line in captured.out.split("\n")
+        if not line.startswith("[") and line.strip() and not line.startswith("\x1b")
+    )
+    assert filtered_output == ""
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1247,9 +1301,9 @@ 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():
@@ -1560,9 +1614,9 @@ def test_code_execution_flag_adds_code_tool_upon_kickoff():
 
         # Verify that exactly one tool was used and it was a CodeInterpreterTool
         assert len(used_tools) == 1, "Should have exactly one tool"
-        assert isinstance(used_tools[0], CodeInterpreterTool), (
-            "Tool should be CodeInterpreterTool"
-        )
+        assert isinstance(
+            used_tools[0], CodeInterpreterTool
+        ), "Tool should be CodeInterpreterTool"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -1919,6 +1973,7 @@ def test_task_callback_on_crew():
 
 def test_task_callback_both_on_task_and_crew():
     from unittest.mock import MagicMock, patch
+
     mock_callback_on_task = MagicMock()
     mock_callback_on_crew = MagicMock()
 
@@ -2060,6 +2115,210 @@ def test_tools_with_custom_caching():
             assert result.raw == "3"
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_task_uses_last_output():
+    """Test that conditional tasks use the last task output for condition evaluation."""
+    task1 = Task(
+        description="First task",
+        expected_output="First output",
+        agent=researcher,
+    )
+
+    def condition_fails(task_output: TaskOutput) -> bool:
+        # This condition will never be met
+        return "never matches" in task_output.raw.lower()
+
+    def condition_succeeds(task_output: TaskOutput) -> bool:
+        # This condition will match first task's output
+        return "first success" in task_output.raw.lower()
+
+    conditional_task1 = ConditionalTask(
+        description="Second task - conditional that fails condition",
+        expected_output="Second output",
+        agent=researcher,
+        condition=condition_fails,
+    )
+
+    conditional_task2 = ConditionalTask(
+        description="Third task - conditional that succeeds using first task output",
+        expected_output="Third output",
+        agent=writer,
+        condition=condition_succeeds,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, conditional_task1, conditional_task2],
+    )
+
+    # Mock outputs for tasks
+    mock_first = TaskOutput(
+        description="First task output",
+        raw="First success output",  # Will be used by third task's condition
+        agent=researcher.role,
+    )
+    mock_third = TaskOutput(
+        description="Third task output",
+        raw="Third task executed",  # Output when condition succeeds using first task output
+        agent=writer.role,
+    )
+
+    # Set up mocks for task execution and conditional logic
+    with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
+        # First conditional fails, second succeeds
+        mock_should_execute.side_effect = [False, True]
+        with patch.object(Task, "execute_sync") as mock_execute:
+            mock_execute.side_effect = [mock_first, mock_third]
+            result = crew.kickoff()
+
+            # Verify execution behavior
+            assert mock_execute.call_count == 2  # Only first and third tasks execute
+            assert mock_should_execute.call_count == 2  # Both conditionals checked
+
+            # Verify outputs collection:
+            # First executed task output, followed by an automatically generated (skipped) output, then the conditional execution
+            assert len(result.tasks_output) == 3
+            assert (
+                result.tasks_output[0].raw == "First success output"
+            )  # First task succeeded
+            assert (
+                result.tasks_output[1].raw == ""
+            )  # Second task skipped (condition failed)
+            assert (
+                result.tasks_output[2].raw == "Third task executed"
+            )  # Third task used first task's output
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_tasks_result_collection():
+    """Test that task outputs are properly collected based on execution status."""
+    task1 = Task(
+        description="Normal task that always executes",
+        expected_output="First output",
+        agent=researcher,
+    )
+
+    def condition_never_met(task_output: TaskOutput) -> bool:
+        return "never matches" in task_output.raw.lower()
+
+    def condition_always_met(task_output: TaskOutput) -> bool:
+        return "success" in task_output.raw.lower()
+
+    task2 = ConditionalTask(
+        description="Conditional task that never executes",
+        expected_output="Second output",
+        agent=researcher,
+        condition=condition_never_met,
+    )
+
+    task3 = ConditionalTask(
+        description="Conditional task that always executes",
+        expected_output="Third output",
+        agent=writer,
+        condition=condition_always_met,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2, task3],
+    )
+
+    # Mock outputs for different execution paths
+    mock_success = TaskOutput(
+        description="Success output",
+        raw="Success output",  # Triggers third task's condition
+        agent=researcher.role,
+    )
+    mock_conditional = TaskOutput(
+        description="Conditional output",
+        raw="Conditional task executed",
+        agent=writer.role,
+    )
+
+    # Set up mocks for task execution and conditional logic
+    with patch.object(ConditionalTask, "should_execute") as mock_should_execute:
+        # First conditional fails, second succeeds
+        mock_should_execute.side_effect = [False, True]
+        with patch.object(Task, "execute_sync") as mock_execute:
+            mock_execute.side_effect = [mock_success, mock_conditional]
+            result = crew.kickoff()
+
+            # Verify execution behavior
+            assert mock_execute.call_count == 2  # Only first and third tasks execute
+            assert mock_should_execute.call_count == 2  # Both conditionals checked
+
+            # Verify task output collection:
+            # There should be three outputs: normal task, skipped conditional task (empty output),
+            # and the conditional task that executed.
+            assert len(result.tasks_output) == 3
+            assert (
+                result.tasks_output[0].raw == "Success output"
+            )  # Normal task executed
+            assert result.tasks_output[1].raw == ""  # Second task skipped
+            assert (
+                result.tasks_output[2].raw == "Conditional task executed"
+            )  # Third task executed
+
+            # Verify task output collection
+            assert len(result.tasks_output) == 3
+            assert (
+                result.tasks_output[0].raw == "Success output"
+            )  # Normal task executed
+            assert result.tasks_output[1].raw == ""  # Second task skipped
+            assert (
+                result.tasks_output[2].raw == "Conditional task executed"
+            )  # Third task executed
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_multiple_conditional_tasks():
+    """Test that having multiple conditional tasks in sequence works correctly."""
+    task1 = Task(
+        description="Initial research task",
+        expected_output="Research output",
+        agent=researcher,
+    )
+
+    def condition1(task_output: TaskOutput) -> bool:
+        return "success" in task_output.raw.lower()
+
+    def condition2(task_output: TaskOutput) -> bool:
+        return "proceed" in task_output.raw.lower()
+
+    task2 = ConditionalTask(
+        description="First conditional task",
+        expected_output="Conditional output 1",
+        agent=writer,
+        condition=condition1,
+    )
+
+    task3 = ConditionalTask(
+        description="Second conditional task",
+        expected_output="Conditional output 2",
+        agent=writer,
+        condition=condition2,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2, task3],
+    )
+
+    # Mock different task outputs to test conditional logic
+    mock_success = TaskOutput(
+        description="Mock success",
+        raw="Success and proceed output",
+        agent=researcher.role,
+    )
+
+    # Set up mocks for task execution
+    with patch.object(Task, "execute_sync", return_value=mock_success) as mock_execute:
+        result = crew.kickoff()
+        # Verify all tasks were executed (no IndexError)
+        assert mock_execute.call_count == 3
+        assert len(result.tasks_output) == 3
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_using_contextual_memory():
     from unittest.mock import patch
@@ -2328,6 +2587,16 @@ 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"
     )
@@ -2373,6 +2642,10 @@ 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(
@@ -3101,7 +3374,19 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     copy_mock.return_value = crew
 
     n_iterations = 2
-    crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
+    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
     kickoff_mock.assert_has_calls(
@@ -3110,13 +3395,17 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
 
     crew_evaluator.assert_has_calls(
         [
-            mock.call(crew, "gpt-4o-mini"),
+            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():
@@ -3178,9 +3467,9 @@ def test_fetch_inputs():
     expected_placeholders = {"role_detail", "topic", "field"}
     actual_placeholders = crew.fetch_inputs()
 
-    assert actual_placeholders == expected_placeholders, (
-        f"Expected {expected_placeholders}, but got {actual_placeholders}"
-    )
+    assert (
+        actual_placeholders == expected_placeholders
+    ), f"Expected {expected_placeholders}, but got {actual_placeholders}"
 
 
 def test_task_tools_preserve_code_execution_tools():
@@ -3253,20 +3542,20 @@ def test_task_tools_preserve_code_execution_tools():
         used_tools = kwargs["tools"]
 
         # Verify all expected tools are present
-        assert any(isinstance(tool, TestTool) for tool in used_tools), (
-            "Task's TestTool should be present"
-        )
-        assert any(isinstance(tool, CodeInterpreterTool) for tool in used_tools), (
-            "CodeInterpreterTool should be present"
-        )
-        assert any("delegate" in tool.name.lower() for tool in used_tools), (
-            "Delegation tool should be present"
-        )
+        assert any(
+            isinstance(tool, TestTool) for tool in used_tools
+        ), "Task's TestTool should be present"
+        assert any(
+            isinstance(tool, CodeInterpreterTool) for tool in used_tools
+        ), "CodeInterpreterTool should be present"
+        assert any(
+            "delegate" in tool.name.lower() for tool in used_tools
+        ), "Delegation tool should be present"
 
         # Verify the total number of tools (TestTool + CodeInterpreter + 2 delegation tools)
-        assert len(used_tools) == 4, (
-            "Should have TestTool, CodeInterpreter, and 2 delegation tools"
-        )
+        assert (
+            len(used_tools) == 4
+        ), "Should have TestTool, CodeInterpreter, and 2 delegation tools"
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -3310,9 +3599,9 @@ def test_multimodal_flag_adds_multimodal_tools():
         used_tools = kwargs["tools"]
 
         # Check that the multimodal tool was added
-        assert any(isinstance(tool, AddImageTool) for tool in used_tools), (
-            "AddImageTool should be present when agent is multimodal"
-        )
+        assert any(
+            isinstance(tool, AddImageTool) for tool in used_tools
+        ), "AddImageTool should be present when agent is multimodal"
 
         # Verify we have exactly one tool (just the AddImageTool)
         assert len(used_tools) == 1, "Should only have the AddImageTool"
@@ -3538,9 +3827,9 @@ def test_crew_guardrail_feedback_in_context():
     assert len(execution_contexts) > 1, "Task should have been executed multiple times"
 
     # Verify that the second execution included the guardrail feedback
-    assert "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1], (
-        "Guardrail feedback should be included in retry context"
-    )
+    assert (
+        "Output must contain the keyword 'IMPORTANT'" in execution_contexts[1]
+    ), "Guardrail feedback should be included in retry context"
 
     # Verify final output meets guardrail requirements
     assert "IMPORTANT" in result.raw, "Final output should contain required keyword"

tests/flow/test_state_utils.py

@@ -0,0 +1,150 @@
+from datetime import date, datetime
+from typing import List
+from unittest.mock import Mock
+
+import pytest
+from pydantic import BaseModel
+
+from crewai.flow import Flow
+from crewai.flow.state_utils import export_state, to_string
+
+
+class Address(BaseModel):
+    street: str
+    city: str
+    country: str
+
+
+class Person(BaseModel):
+    name: str
+    age: int
+    address: Address
+    birthday: date
+    skills: List[str]
+
+
+@pytest.fixture
+def mock_flow():
+    def create_flow(state):
+        flow = Mock(spec=Flow)
+        flow._state = state
+        return flow
+
+    return create_flow
+
+
+@pytest.mark.parametrize(
+    "test_input,expected",
+    [
+        ({"text": "hello world"}, {"text": "hello world"}),
+        ({"number": 42}, {"number": 42}),
+        ({"decimal": 3.14}, {"decimal": 3.14}),
+        ({"flag": True}, {"flag": True}),
+        ({"empty": None}, {"empty": None}),
+        ({"list": [1, 2, 3]}, {"list": [1, 2, 3]}),
+        ({"tuple": (1, 2, 3)}, {"tuple": [1, 2, 3]}),
+        ({"set": {1, 2, 3}}, {"set": [1, 2, 3]}),
+        ({"nested": [1, [2, 3], {4, 5}]}, {"nested": [1, [2, 3], [4, 5]]}),
+    ],
+)
+def test_basic_serialization(mock_flow, test_input, expected):
+    flow = mock_flow(test_input)
+    result = export_state(flow)
+    assert result == expected
+
+
+@pytest.mark.parametrize(
+    "input_date,expected",
+    [
+        (date(2024, 1, 1), "2024-01-01"),
+        (datetime(2024, 1, 1, 12, 30), "2024-01-01T12:30:00"),
+    ],
+)
+def test_temporal_serialization(mock_flow, input_date, expected):
+    flow = mock_flow({"date": input_date})
+    result = export_state(flow)
+    assert result["date"] == expected
+
+
+@pytest.mark.parametrize(
+    "key,value,expected_key_type",
+    [
+        (("tuple", "key"), "value", str),
+        (None, "value", str),
+        (123, "value", str),
+        ("normal", "value", str),
+    ],
+)
+def test_dictionary_key_serialization(mock_flow, key, value, expected_key_type):
+    flow = mock_flow({key: value})
+    result = export_state(flow)
+    assert len(result) == 1
+    result_key = next(iter(result.keys()))
+    assert isinstance(result_key, expected_key_type)
+    assert result[result_key] == value
+
+
+@pytest.mark.parametrize(
+    "callable_obj,expected_in_result",
+    [
+        (lambda x: x * 2, "lambda"),
+        (str.upper, "upper"),
+    ],
+)
+def test_callable_serialization(mock_flow, callable_obj, expected_in_result):
+    flow = mock_flow({"func": callable_obj})
+    result = export_state(flow)
+    assert isinstance(result["func"], str)
+    assert expected_in_result in result["func"].lower()
+
+
+def test_pydantic_model_serialization(mock_flow):
+    address = Address(street="123 Main St", city="Tech City", country="Pythonia")
+
+    person = Person(
+        name="John Doe",
+        age=30,
+        address=address,
+        birthday=date(1994, 1, 1),
+        skills=["Python", "Testing"],
+    )
+
+    flow = mock_flow(
+        {
+            "single_model": address,
+            "nested_model": person,
+            "model_list": [address, address],
+            "model_dict": {"home": address},
+        }
+    )
+
+    result = export_state(flow)
+    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):
+    """Test max depth handling with a deeply nested structure"""
+
+    def create_nested(depth):
+        if depth == 0:
+            return "value"
+        return {"next": create_nested(depth - 1)}
+
+    deep_structure = create_nested(10)
+    flow = mock_flow(deep_structure)
+    result = export_state(flow)
+
+    assert result == {
+        "next": {
+            "next": {
+                "next": {
+                    "next": {
+                        "next": "{'next': {'next': {'next': {'next': {'next': 'value'}}}}}"
+                    }
+                }
+            }
+        }
+    }

tests/flow_test.py

@@ -1,11 +1,20 @@
 """Test Flow creation and execution basic functionality."""
 
 import asyncio
+from datetime import datetime
 
 import pytest
 from pydantic import BaseModel
 
 from crewai.flow.flow import Flow, and_, listen, or_, router, start
+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():
@@ -398,3 +407,351 @@ def test_router_with_multiple_conditions():
 
     # final_step should run after router_and
     assert execution_order.index("log_final_step") > execution_order.index("router_and")
+
+
+def test_unstructured_flow_event_emission():
+    """Test that the correct events are emitted during unstructured flow
+    execution with all fields validated."""
+
+    class PoemFlow(Flow):
+        @start()
+        def prepare_flower(self):
+            self.state["flower"] = "roses"
+            return "foo"
+
+        @start()
+        def prepare_color(self):
+            self.state["color"] = "red"
+            return "bar"
+
+        @listen(prepare_color)
+        def write_first_sentence(self):
+            return f"{self.state['flower']} are {self.state['color']}"
+
+        @listen(write_first_sentence)
+        def finish_poem(self, first_sentence):
+            separator = self.state.get("separator", "\n")
+            return separator.join([first_sentence, "violets are blue"])
+
+        @listen(finish_poem)
+        def save_poem_to_database(self):
+            # A method without args/kwargs to ensure events are sent correctly
+            return "roses are red\nviolets are blue"
+
+    flow = PoemFlow()
+    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)
+
+    # 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"] == ", "
+
+    assert received_events[1].method_name == "prepare_flower"
+    assert received_events[1].params == {}
+    assert "flower" not in received_events[1].state
+
+    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 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 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 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(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():
+    """Test that the correct events are emitted during structured flow
+    execution with all fields validated."""
+
+    class OnboardingState(BaseModel):
+        name: str = ""
+        sent: bool = False
+
+    class OnboardingFlow(Flow[OnboardingState]):
+        @start()
+        def user_signs_up(self):
+            self.state.sent = False
+
+        @listen(user_signs_up)
+        def send_welcome_message(self):
+            self.state.sent = True
+            return f"Welcome, {self.state.name}!"
+
+    flow = OnboardingFlow()
+    flow.kickoff(inputs={"name": "Anakin"})
+
+    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(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():
+    """Test that the correct events are emitted stateless during flow execution
+    with all fields validated."""
+
+    class StatelessFlow(Flow):
+        @start()
+        def init(self):
+            pass
+
+        @listen(init)
+        def process(self):
+            return "Deeds will not be less valiant because they are unpraised."
+
+    event_log = []
+
+    def handle_event(_, event):
+        event_log.append(event)
+
+    flow = StatelessFlow()
+    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(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(received_events[1], MethodExecutionStartedEvent)
+    assert received_events[1].method_name == "init"
+
+    assert isinstance(received_events[2], MethodExecutionFinishedEvent)
+    assert received_events[2].method_name == "init"
+
+    assert isinstance(received_events[3], MethodExecutionStartedEvent)
+    assert received_events[3].method_name == "process"
+
+    assert isinstance(received_events[4], MethodExecutionFinishedEvent)
+    assert received_events[4].method_name == "process"
+
+    assert isinstance(received_events[5], FlowFinishedEvent)
+    assert received_events[5].flow_name == "StatelessFlow"
+    assert (
+        received_events[5].result
+        == "Deeds will not be less valiant because they are unpraised."
+    )
+    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)
+
+
+def test_multiple_routers_from_same_trigger():
+    """Test that multiple routers triggered by the same method all activate their listeners."""
+    execution_order = []
+
+    class MultiRouterFlow(Flow):
+        def __init__(self):
+            super().__init__()
+            # Set diagnosed conditions to trigger all routers
+            self.state["diagnosed_conditions"] = "DHA"  # Contains D, H, and A
+
+        @start()
+        def scan_medical(self):
+            execution_order.append("scan_medical")
+            return "scan_complete"
+
+        @router(scan_medical)
+        def diagnose_conditions(self):
+            execution_order.append("diagnose_conditions")
+            return "diagnosis_complete"
+
+        @router(diagnose_conditions)
+        def diabetes_router(self):
+            execution_order.append("diabetes_router")
+            if "D" in self.state["diagnosed_conditions"]:
+                return "diabetes"
+            return None
+
+        @listen("diabetes")
+        def diabetes_analysis(self):
+            execution_order.append("diabetes_analysis")
+            return "diabetes_analysis_complete"
+
+        @router(diagnose_conditions)
+        def hypertension_router(self):
+            execution_order.append("hypertension_router")
+            if "H" in self.state["diagnosed_conditions"]:
+                return "hypertension"
+            return None
+
+        @listen("hypertension")
+        def hypertension_analysis(self):
+            execution_order.append("hypertension_analysis")
+            return "hypertension_analysis_complete"
+
+        @router(diagnose_conditions)
+        def anemia_router(self):
+            execution_order.append("anemia_router")
+            if "A" in self.state["diagnosed_conditions"]:
+                return "anemia"
+            return None
+
+        @listen("anemia")
+        def anemia_analysis(self):
+            execution_order.append("anemia_analysis")
+            return "anemia_analysis_complete"
+
+    flow = MultiRouterFlow()
+    flow.kickoff()
+
+    # Verify all methods were called
+    assert "scan_medical" in execution_order
+    assert "diagnose_conditions" in execution_order
+
+    # Verify all routers were called
+    assert "diabetes_router" in execution_order
+    assert "hypertension_router" in execution_order
+    assert "anemia_router" in execution_order
+
+    # Verify all listeners were called - this is the key test for the fix
+    assert "diabetes_analysis" in execution_order
+    assert "hypertension_analysis" in execution_order
+    assert "anemia_analysis" in execution_order
+
+    # Verify execution order constraints
+    assert execution_order.index("diagnose_conditions") > execution_order.index(
+        "scan_medical"
+    )
+
+    # All routers should execute after diagnose_conditions
+    assert execution_order.index("diabetes_router") > execution_order.index(
+        "diagnose_conditions"
+    )
+    assert execution_order.index("hypertension_router") > execution_order.index(
+        "diagnose_conditions"
+    )
+    assert execution_order.index("anemia_router") > execution_order.index(
+        "diagnose_conditions"
+    )
+
+    # All analyses should execute after their respective routers
+    assert execution_order.index("diabetes_analysis") > execution_order.index(
+        "diabetes_router"
+    )
+    assert execution_order.index("hypertension_analysis") > execution_order.index(
+        "hypertension_router"
+    )
+    assert execution_order.index("anemia_analysis") > execution_order.index(
+        "anemia_router"
+    )

tests/llm_test.py

@@ -6,8 +6,9 @@ import pytest
 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.llm import CONTEXT_WINDOW_USAGE_RATIO, LLM
+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
 
 
@@ -284,8 +285,103 @@ def test_o3_mini_reasoning_effort_medium():
     assert isinstance(result, str)
     assert "Paris" in result
 
+def test_context_window_validation():
+    """Test that context window validation works correctly."""
+    # Test valid window size
+    llm = LLM(model="o3-mini")
+    assert llm.get_context_window_size() == int(200000 * CONTEXT_WINDOW_USAGE_RATIO)
+
+    # Test invalid window size
+    with pytest.raises(ValueError) as excinfo:
+        with patch.dict(
+            "crewai.llm.LLM_CONTEXT_WINDOW_SIZES",
+            {"test-model": 500},  # Below minimum
+            clear=True,
+        ):
+            llm = LLM(model="test-model")
+            llm.get_context_window_size()
+    assert "must be between 1024 and 2097152" in str(excinfo.value)
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.fixture
+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 = [
+        ("anthropic/claude-3", True),
+        ("claude-instant", True),
+        ("claude/v1", True),
+        ("gpt-4", False),
+        ("", 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
+    formatted = anthropic_llm._format_messages_for_provider([system_message])
+    assert len(formatted) == 2
+    assert formatted[0]["role"] == "user"
+    assert formatted[0]["content"] == "."
+    assert formatted[1] == system_message
+
+    # Test when first message is already user
+    formatted = anthropic_llm._format_messages_for_provider([user_message])
+    assert len(formatted) == 1
+    assert formatted[0] == user_message
+
+    # Test with empty message list
+    formatted = anthropic_llm._format_messages_for_provider([])
+    assert len(formatted) == 1
+    assert formatted[0]["role"] == "user"
+    assert formatted[0]["content"] == "."
+
+    # Test with non-Anthropic model (should not modify messages)
+    non_anthropic_llm = LLM(model="gpt-4")
+    formatted = non_anthropic_llm._format_messages_for_provider([system_message])
+    assert len(formatted) == 1
+    assert formatted[0] == system_message
+
+
 def test_deepseek_r1_with_open_router():
     if not os.getenv("OPEN_ROUTER_API_KEY"):
         pytest.skip("OPEN_ROUTER_API_KEY not set; skipping test.")
@@ -298,3 +394,51 @@ 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_converter_with_llama3_2_model.yaml

@@ -1,14 +1,9 @@
 interactions:
 - request:
-    body: '{"model": "llama3.2:3b", "prompt": "### User:\nName: Alice Llama, Age:
-      30\n\n### System:\nProduce JSON OUTPUT ONLY! Adhere to this format {\"name\":
-      \"function_name\", \"arguments\":{\"argument_name\": \"argument_value\"}} The
-      following functions are available to you:\n{''type'': ''function'', ''function'':
-      {''name'': ''SimpleModel'', ''description'': ''Correctly extracted `SimpleModel`
-      with all the required parameters with correct types'', ''parameters'': {''properties'':
-      {''name'': {''title'': ''Name'', ''type'': ''string''}, ''age'': {''title'':
-      ''Age'', ''type'': ''integer''}}, ''required'': [''age'', ''name''], ''type'':
-      ''object''}}}\n\n\n", "options": {}, "stream": false, "format": "json"}'
+    body: '{"model": "llama3.2:3b", "prompt": "### System:\nPlease convert the following
+      text into valid JSON.\n\nOutput ONLY the valid JSON and nothing else.\n\nThe
+      JSON must follow this format exactly:\n{\n  \"name\": str,\n  \"age\": int\n}\n\n###
+      User:\nName: Alice Llama, Age: 30\n\n", "options": {"stop": []}, "stream": false}'
     headers:
       accept:
       - '*/*'
@@ -17,23 +12,23 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '657'
+      - '321'
       host:
       - localhost:11434
       user-agent:
-      - litellm/1.57.4
+      - litellm/1.60.2
     method: POST
     uri: http://localhost:11434/api/generate
   response:
-    content: '{"model":"llama3.2:3b","created_at":"2025-01-15T20:47:11.926411Z","response":"{\"name\":
-      \"SimpleModel\", \"arguments\":{\"name\": \"Alice Llama\", \"age\": 30}}","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,2724,512,678,25,30505,445,81101,11,13381,25,220,966,271,14711,744,512,1360,13677,4823,32090,27785,0,2467,6881,311,420,3645,5324,609,794,330,1723,1292,498,330,16774,23118,14819,1292,794,330,14819,3220,32075,578,2768,5865,527,2561,311,499,512,13922,1337,1232,364,1723,518,364,1723,1232,5473,609,1232,364,16778,1747,518,364,4789,1232,364,34192,398,28532,1595,16778,1747,63,449,682,279,2631,5137,449,4495,4595,518,364,14105,1232,5473,13495,1232,5473,609,1232,5473,2150,1232,364,678,518,364,1337,1232,364,928,25762,364,425,1232,5473,2150,1232,364,17166,518,364,1337,1232,364,11924,8439,2186,364,6413,1232,2570,425,518,364,609,4181,364,1337,1232,364,1735,23742,3818,128009,128006,78191,128007,271,5018,609,794,330,16778,1747,498,330,16774,23118,609,794,330,62786,445,81101,498,330,425,794,220,966,3500],"total_duration":3374470708,"load_duration":1075750500,"prompt_eval_count":167,"prompt_eval_duration":1871000000,"eval_count":24,"eval_duration":426000000}'
+    content: '{"model":"llama3.2:3b","created_at":"2025-02-21T02:57:55.059392Z","response":"{\"name\":
+      \"Alice Llama\", \"age\": 30}","done":true,"done_reason":"stop","context":[128006,9125,128007,271,38766,1303,33025,2696,25,6790,220,2366,18,271,128009,128006,882,128007,271,14711,744,512,5618,5625,279,2768,1495,1139,2764,4823,382,5207,27785,279,2764,4823,323,4400,775,382,791,4823,2011,1833,420,3645,7041,512,517,220,330,609,794,610,345,220,330,425,794,528,198,633,14711,2724,512,678,25,30505,445,81101,11,13381,25,220,966,271,128009,128006,78191,128007,271,5018,609,794,330,62786,445,81101,498,330,425,794,220,966,92],"total_duration":4675906000,"load_duration":836091458,"prompt_eval_count":82,"prompt_eval_duration":3561000000,"eval_count":15,"eval_duration":275000000}'
     headers:
       Content-Length:
-      - '1263'
+      - '761'
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Wed, 15 Jan 2025 20:47:12 GMT
+      - Fri, 21 Feb 2025 02:57:55 GMT
     http_version: HTTP/1.1
     status_code: 200
 - request:
@@ -52,7 +47,7 @@ interactions:
       host:
       - localhost:11434
       user-agent:
-      - litellm/1.57.4
+      - litellm/1.60.2
     method: POST
     uri: http://localhost:11434/api/show
   response:
@@ -228,7 +223,7 @@ interactions:
       Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
       3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
       show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
-      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      FROM llama3.2:3b\\n\\nFROM /Users/joaomoura/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
       \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
       Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
       if .Tools }}When you receive a tool call response, use the output to format
@@ -441,12 +436,12 @@ interactions:
       .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
       else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
       .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2025-02-20T18:55:09.150577031-08:00\"}"
     headers:
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Wed, 15 Jan 2025 20:47:12 GMT
+      - Fri, 21 Feb 2025 02:57:55 GMT
       Transfer-Encoding:
       - chunked
     http_version: HTTP/1.1
@@ -467,7 +462,7 @@ interactions:
       host:
       - localhost:11434
       user-agent:
-      - litellm/1.57.4
+      - litellm/1.60.2
     method: POST
     uri: http://localhost:11434/api/show
   response:
@@ -643,7 +638,7 @@ interactions:
       Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
       3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
       show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
-      FROM llama3.2:3b\\n\\nFROM /Users/brandonhancock/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
+      FROM llama3.2:3b\\n\\nFROM /Users/joaomoura/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
       \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
       Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end }}\\n{{-
       if .Tools }}When you receive a tool call response, use the output to format
@@ -856,12 +851,12 @@ interactions:
       .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{ end }}\\n{{-
       else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
       .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
-      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2024-12-31T11:53:14.529771974-05:00\"}"
+      end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":[\"en\",\"de\",\"fr\",\"it\",\"pt\",\"hi\",\"es\",\"th\"],\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":[\"facebook\",\"meta\",\"pytorch\",\"llama\",\"llama-3\",\"text-generation\"],\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"modified_at\":\"2025-02-20T18:55:09.150577031-08:00\"}"
     headers:
       Content-Type:
       - application/json; charset=utf-8
       Date:
-      - Wed, 15 Jan 2025 20:47:12 GMT
+      - Fri, 21 Feb 2025 02:57:55 GMT
       Transfer-Encoding:
       - chunked
     http_version: HTTP/1.1

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_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_crew_emits_test_kickoff_type_event.yaml

@@ -0,0 +1,236 @@
+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 expected 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:
+      - '838'
+      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-B4VsaBZ4ec4b0ab4pkqWgyxTFVVfc\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1740415556,\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_7fcd609668\"\n}\n"
+    headers:
+      CF-RAY:
+      - 9170edc5da6f230e-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 24 Feb 2025 16:45:57 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=lvRw4Nyef7N35to64fj2_kHDfbZp0KSFbwgF5chYMRI-1740415557-1.0.1.1-o5BaN1FpBwv5Wq6zIlv0rCB28lk5hVI9wZQWU3pig1jgyAKDkYzTwZ0MlSR6v6TPIX9RfepjrO3.Gk3FEmcVRw;
+        path=/; expires=Mon, 24-Feb-25 17:15:57 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=ySaVoTQvAcQyH5QoJQJDj75e5j8HwGFPOlFMAWEvXJk-1740415557302-0.0.1.1-604800000;
+        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:
+      - '721'
+      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:
+      - '149999808'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_fc3b3bcd4382cddaa3c04ce7003e4857
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "system", "content": "You are Task Execution Evaluator.
+      Evaluator agent for crew evaluation with precise capabilities to evaluate the
+      performance of the agents in the crew based on the tasks they have performed\nYour
+      personal goal is: Your goal is to evaluate the performance of the agents in
+      the crew based on the tasks they have performed using score from 1 to 10 evaluating
+      on completion, quality, and overall performance.\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:
+      Based on the task description and the expected output, compare and evaluate
+      the performance of the agents in the crew based on the Task Output they have
+      performed using score from 1 to 10 evaluating on completion, quality, and overall
+      performance.task_description: Just say hi task_expected_output: hi agent: base_agent
+      agent_goal: Just say hi Task Output: hi\n\nThis is the expected criteria for
+      your final answer: Evaluation Score from 1 to 10 based on the performance of
+      the agents on the tasks\nyou MUST return the actual complete content as the
+      final answer, not a summary.\nEnsure your final answer contains only the content
+      in the following format: {\n  \"quality\": float\n}\n\nEnsure the final output
+      does not include any code block markers like ```json or ```python.\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:
+      - '1765'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=lvRw4Nyef7N35to64fj2_kHDfbZp0KSFbwgF5chYMRI-1740415557-1.0.1.1-o5BaN1FpBwv5Wq6zIlv0rCB28lk5hVI9wZQWU3pig1jgyAKDkYzTwZ0MlSR6v6TPIX9RfepjrO3.Gk3FEmcVRw;
+        _cfuvid=ySaVoTQvAcQyH5QoJQJDj75e5j8HwGFPOlFMAWEvXJk-1740415557302-0.0.1.1-604800000
+      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-B4Vsbd9AsRaJ2exDtWnHAwC8rIjfi\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1740415557,\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: {  \\n  \\\"quality\\\": 10  \\n}  \",\n        \"refusal\": null\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 338,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 360,\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_7fcd609668\"\n}\n"
+    headers:
+      CF-RAY:
+      - 9170edd15bb5230e-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 24 Feb 2025 16:45:58 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:
+      - '860'
+      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:
+      - '149999578'
+      x-ratelimit-reset-requests:
+      - 2ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_fad452c2d10b5fc95809130912b08837
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_llm_emits_call_failed_event.yaml

@@ -0,0 +1,103 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Hello, how are you?"}], "model":
+      "gpt-4o-mini", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '102'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000;
+        __cf_bm=fU6K5KZoDmgcEuF8_yWAYKUO5fKHh6q5.wDPnna393g-1740424913-1.0.1.1-2iOaq3JVGWs439V0HxJee0IC9HdJm7dPkeJorD.AGw0YwkngRPM8rrTzn_7ht1BkbOauEezj.wPKcBz18gIYUg
+      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-B4YLA2SrC2rwdVQ3U87G5a0P5lsLw\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1740425016,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Hello! I'm just a computer program, so
+      I don't have feelings, but I'm here and ready to help you. How can I assist
+      you today?\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      13,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 43,\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_709714d124\"\n}\n"
+    headers:
+      CF-RAY:
+      - 9171d4c0ed44236e-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 24 Feb 2025 19:23:38 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:
+      - '1954'
+      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_ea2703502b8827e4297cd2a7bae9d9c8
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/utilities/cassettes/test_llm_emits_call_started_event.yaml

@@ -0,0 +1,108 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "Hello, how are you?"}], "model":
+      "gpt-4o-mini", "stop": []}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '102'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=GefCcEtb_Gem93E4a9Hvt3Xyof1YQZVJAXBb9I6pEUs-1739398417375-0.0.1.1-604800000
+      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-B4YJU8IWKGyBQtAyPDRd3SFI2flYR\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1740424912,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Hello! I'm just a computer program, so
+      I don't have feelings, but I'm here and ready to help you. How can I assist
+      you today?\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      13,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 43,\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_7fcd609668\"\n}\n"
+    headers:
+      CF-RAY:
+      - 9171d230d8ed7ae0-SJC
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Mon, 24 Feb 2025 19:21:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=fU6K5KZoDmgcEuF8_yWAYKUO5fKHh6q5.wDPnna393g-1740424913-1.0.1.1-2iOaq3JVGWs439V0HxJee0IC9HdJm7dPkeJorD.AGw0YwkngRPM8rrTzn_7ht1BkbOauEezj.wPKcBz18gIYUg;
+        path=/; expires=Mon, 24-Feb-25 19:51:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=IY8ppO70AMHr2skDSUsGh71zqHHdCQCZ3OvkPi26NBc-1740424913267-0.0.1.1-604800000;
+        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:
+      - '993'
+      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_d9c4d49185e97b1797061efc1e55d811
+    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_converter.py

@@ -1,4 +1,5 @@
 import json
+import os
 from typing import Dict, List, Optional
 from unittest.mock import MagicMock, Mock, patch
 
@@ -220,10 +221,13 @@ def test_get_conversion_instructions_gpt():
         supports_function_calling.return_value = True
         instructions = get_conversion_instructions(SimpleModel, llm)
         model_schema = PydanticSchemaParser(model=SimpleModel).get_schema()
-        assert (
-            instructions
-            == f"Please convert the following text into valid JSON.\n\nThe JSON should follow this schema:\n```json\n{model_schema}\n```"
+        expected_instructions = (
+            "Please convert the following text into valid JSON.\n\n"
+            "Output ONLY the valid JSON and nothing else.\n\n"
+            "The JSON must follow this schema exactly:\n```json\n"
+            f"{model_schema}\n```"
         )
+        assert instructions == expected_instructions
 
 
 def test_get_conversion_instructions_non_gpt():
@@ -346,12 +350,17 @@ def test_convert_with_instructions():
     assert output.age == 30
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+# Skip tests that call external APIs when running in CI/CD
+skip_external_api = pytest.mark.skipif(
+    os.getenv("CI") is not None, reason="Skipping tests that call external API in CI/CD"
+)
+
+
+@skip_external_api
+@pytest.mark.vcr(filter_headers=["authorization"], record_mode="once")
 def test_converter_with_llama3_2_model():
     llm = LLM(model="ollama/llama3.2:3b", base_url="http://localhost:11434")
-
     sample_text = "Name: Alice Llama, Age: 30"
-
     instructions = get_conversion_instructions(SimpleModel, llm)
     converter = Converter(
         llm=llm,
@@ -359,19 +368,17 @@ def test_converter_with_llama3_2_model():
         model=SimpleModel,
         instructions=instructions,
     )
-
     output = converter.to_pydantic()
-
     assert isinstance(output, SimpleModel)
     assert output.name == "Alice Llama"
     assert output.age == 30
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@skip_external_api
+@pytest.mark.vcr(filter_headers=["authorization"], record_mode="once")
 def test_converter_with_llama3_1_model():
     llm = LLM(model="ollama/llama3.1", base_url="http://localhost:11434")
     sample_text = "Name: Alice Llama, Age: 30"
-
     instructions = get_conversion_instructions(SimpleModel, llm)
     converter = Converter(
         llm=llm,
@@ -379,14 +386,19 @@ def test_converter_with_llama3_1_model():
         model=SimpleModel,
         instructions=instructions,
     )
-
     output = converter.to_pydantic()
-
     assert isinstance(output, SimpleModel)
     assert output.name == "Alice Llama"
     assert output.age == 30
 
 
+# Skip tests that call external APIs when running in CI/CD
+skip_external_api = pytest.mark.skipif(
+    os.getenv("CI") is not None, reason="Skipping tests that call external API in CI/CD"
+)
+
+
+@skip_external_api
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_converter_with_nested_model():
     llm = LLM(model="gpt-4o-mini")
@@ -563,7 +575,7 @@ def test_converter_with_ambiguous_input():
     with pytest.raises(ConverterError) as exc_info:
         output = converter.to_pydantic()
 
-    assert "validation error" in str(exc_info.value).lower()
+    assert "failed to convert text into a pydantic model" in str(exc_info.value).lower()
 
 
 # Tests for function calling support