TYPO

* fixed bug for manager overriding task agent and then added pydanic valditors to sequential when no agent is added to task

* better test and fixed task.agent logic

* fixed tests and better validator message

* added validator for async_execution true in tasks whenever in hierarchical run

.github/workflows/tests.yml

@@ -23,8 +23,8 @@ jobs:
 
       - name: Install Requirements
         run: |
+          set -e
           pip install poetry
-          poetry lock &&
           poetry install
 
       - name: Run tests

.gitignore

@@ -11,4 +11,7 @@ chroma.sqlite3
 old_en.json
 db/
 test.py
-rc-tests/*
+rc-tests/*
+*.pkl
+temp/*
+.vscode/*

README.md

@@ -127,6 +127,7 @@ crew = Crew(
   agents=[researcher, writer],
   tasks=[task1, task2],
   verbose=2, # You can set it to 1 or 2 to different logging levels
+  process = Process.sequential
 )
 
 # Get your crew to work!
@@ -195,6 +196,7 @@ Please refer to the [Connect crewAI to LLMs](https://docs.crewai.com/how-to/LLM-
 
 **CrewAI's Advantage**: CrewAI is built with production in mind. It offers the flexibility of Autogen's conversational agents and the structured process approach of ChatDev, but without the rigidity. CrewAI's processes are designed to be dynamic and adaptable, fitting seamlessly into both development and production workflows.
 
+
 ## Contribution
 
 CrewAI is open-source and we welcome contributions. If you're looking to contribute, please:

docs/core-concepts/Agents.md

@@ -16,24 +16,25 @@ description: What are crewAI Agents and how to use them.
 
 ## Agent Attributes
 
-| Attribute                  | Description                                                                                                                                                                                                                                    |
-| :------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| **Role**                   | Defines the agent's function within the crew. It determines the kind of tasks the agent is best suited for.                                                                                                                                    |
-| **Goal**                   | The individual objective that the agent aims to achieve. It guides the agent's decision-making process.                                                                                                                                        |
-| **Backstory**              | Provides context to the agent's role and goal, enriching the interaction and collaboration dynamics.                                                                                                                                           |
-| **LLM** *(optional)*       | Represents the language model that will run the agent. It dynamically fetches the model name from the `OPENAI_MODEL_NAME` environment variable, defaulting to "gpt-4" if not specified.                                                         |
-| **Tools** *(optional)*     | Set of capabilities or functions that the agent can use to perform tasks. Expected to be instances of custom classes compatible with the agent's execution environment. Tools are initialized with a default value of an empty list.             |
-| **Function Calling LLM** *(optional)* | Specifies the language model that will handle the tool calling for this agent, overriding the crew function calling LLM if passed. Default is `None`.                                                                                          |
-| **Max Iter** *(optional)*  | `max_iter` is the maximum number of iterations the agent can perform before being forced to give its best answer. Default is `25`.                                                                                                                           |
-| **Max RPM** *(optional)*   | `max_rpm` is Tte maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`.                                                                               |
-| **Max Execution Time** *(optional)*   | `max_execution_time` is the Maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time.                                                                     |
-| **Verbose** *(optional)*   | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`.                                                                                              |
-| **Allow Delegation** *(optional)* | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `True`.                                                                                                       |
-| **Step Callback** *(optional)* | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`.                                                               |
-| **Cache** *(optional)*     | Indicates if the agent should use a cache for tool usage. Default is `True`.                                                                                                                                                                  |
-| **System Template** *(optional)*     | Specifies the system format for the agent. Default is `None`.                                                                                                                                                                  |
-| **Prompt Template** *(optional)*     | Specifies the prompt format for the agent. Default is `None`.                                                                                                                                                                  |
-| **Response Template** *(optional)*     | Specifies the response format for the agent. Default is `None`.                                                                                                                                                                  |
+| Attribute                  | Parameter  | Description                                                                                                                                                                                                                                    |
+| :------------------------- | :---- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Role**                   | `role`  | Defines the agent's function within the crew. It determines the kind of tasks the agent is best suited for.                                                                                                                                    |
+| **Goal**                   | `goal`  | The individual objective that the agent aims to achieve. It guides the agent's decision-making process.                                                                                                                                        |
+| **Backstory**              | `backstory`  | Provides context to the agent's role and goal, enriching the interaction and collaboration dynamics.                                                                                                                                           |
+| **LLM** *(optional)*       | `llm`  | Represents the language model that will run the agent. It dynamically fetches the model name from the `OPENAI_MODEL_NAME` environment variable, defaulting to "gpt-4" if not specified.                                                         |
+| **Tools** *(optional)*     | `tools`  | Set of capabilities or functions that the agent can use to perform tasks. Expected to be instances of custom classes compatible with the agent's execution environment. Tools are initialized with a default value of an empty list.             |
+| **Function Calling LLM** *(optional)* | `function_calling_llm`  | Specifies the language model that will handle the tool calling for this agent, overriding the crew function calling LLM if passed. Default is `None`.                                                                                          |
+| **Max Iter** *(optional)*  | `max_iter` | Max Iter is the maximum number of iterations the agent can perform before being forced to give its best answer. Default is `25`.                                                                                                                           |
+| **Max RPM** *(optional)*   | `max_rpm`  | Max RPM is the maximum number of requests per minute the agent can perform to avoid rate limits. It's optional and can be left unspecified, with a default value of `None`.                                                                               |
+| **Max Execution Time** *(optional)*   | `max_execution_time`  | Max Execution Time is the Maximum execution time for an agent to execute a task. It's optional and can be left unspecified, with a default value of `None`, meaning no max execution time.                                                                     |
+| **Verbose** *(optional)*   | `verbose`  | Setting this to `True` configures the internal logger to provide detailed execution logs, aiding in debugging and monitoring. Default is `False`.                                                                                              |
+| **Allow Delegation** *(optional)* | `allow_delegation`  | Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent. Default is `True`.                                                                                                       |
+| **Step Callback** *(optional)* | `step_callback`  | A function that is called after each step of the agent. This can be used to log the agent's actions or to perform other operations. It will overwrite the crew `step_callback`.                                                               |
+| **Cache** *(optional)*     | `cache`  | Indicates if the agent should use a cache for tool usage. Default is `True`.                                                                                                                                                                  |
+| **System Template** *(optional)*     | `system_template`  | Specifies the system format for the agent. Default is `None`.                                                                                                                                                                  |
+| **Prompt Template** *(optional)*     | `prompt_template`  | Specifies the prompt format for the agent. Default is `None`.                                                                                                                                                                  |
+| **Response Template** *(optional)*     | `response_template`  | Specifies the response format for the agent. Default is `None`.                                                                                                                                                                  |
+
 ## Creating an Agent
 
 !!! note "Agent Interaction"
@@ -96,5 +97,53 @@ agent = Agent(
     )
 ```
 
+## Bring your Third Party Agents
+!!! note "Extend your Third Party Agents like LlamaIndex, Langchain, Autogen or fully custom agents using the the crewai's BaseAgent class."
+
+    BaseAgent includes attributes and methods required to integrate with your crews to run and delegate tasks to other agents within your own crew.
+
+    CrewAI is a universal multi agent framework that allows for all agents to work together to automate tasks and solve problems.
+
+
+```py
+from crewai import Agent, Task, Crew
+from custom_agent import CustomAgent # You need to build and extend your own agent logic with the CrewAI BaseAgent class then import it here.
+
+from langchain.agents import load_tools
+
+langchain_tools = load_tools(["google-serper"], llm=llm)
+
+agent1 = CustomAgent(
+    role="backstory agent",
+    goal="who is {input}?",
+    backstory="agent backstory",
+    verbose=True,
+)
+
+task1 = Task(
+    expected_output="a short biography of {input}",
+    description="a short biography of {input}",
+    agent=agent1,
+)
+
+agent2 = Agent(
+    role="bio agent",
+    goal="summarize the short bio for {input} and if needed do more research",
+    backstory="agent backstory",
+    verbose=True,
+)
+
+task2 = Task(
+    description="a tldr summary of the short biography",
+    expected_output="5 bullet point summary of the biography",
+    agent=agent2,
+    context=[task1],
+)
+
+my_crew = Crew(agents=[agent1, agent2], tasks=[task1, task2])
+crew = my_crew.kickoff(inputs={"input": "Mark Twain"})
+```
+
+
 ## Conclusion
-Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents, you can create sophisticated AI systems that leverage the power of collaborative intelligence.
+Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents, you can create sophisticated AI systems that leverage the power of collaborative intelligence.

docs/core-concepts/Crews.md

@@ -8,29 +8,29 @@ A crew in crewAI represents a collaborative group of agents working together to
 
 ## Crew Attributes
 
-| Attribute                   | Description                                                  |
-| :-------------------------- | :----------------------------------------------------------- |
-| **Tasks**                   | A list of tasks assigned to the crew.                        |
-| **Agents**                  | A list of agents that are part of the crew.                  |
-| **Process** *(optional)*    | The process flow (e.g., sequential, hierarchical) the crew follows. |
-| **Verbose** *(optional)*    | The verbosity level for logging during execution.            |
-| **Manager LLM** *(optional)*| The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
-| **Function Calling LLM** *(optional)* | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
-| **Config** *(optional)*     | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
-| **Max RPM** *(optional)*    | Maximum requests per minute the crew adheres to during execution. |
-| **Language**  *(optional)*  | Language used for the crew, defaults to English.             |
-| **Language File** *(optional)* | Path to the language file to be used for the crew.          |
-| **Memory** *(optional)*     | Utilized for storing execution memories (short-term, long-term, entity memory). |
-| **Cache** *(optional)*      | Specifies whether to use a cache for storing the results of tools' execution. |
-| **Embedder** *(optional)*   | Configuration for the embedder to be used by the crew. Mostly used by memory for now.       |
-| **Full Output** *(optional)*| Whether the crew should return the full output with all tasks outputs or just the final output. |
-| **Step Callback** *(optional)* | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
-| **Task Callback** *(optional)* | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
-| **Share Crew** *(optional)* | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
-| **Output Log File** *(optional)* | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
-| **Manager Agent** *(optional)* | `manager` sets a ustom agent that will be used as a manager. |
-| **Manager Callbacks** *(optional)* | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
-| **Prompt File** *(optional)* | Path to the prompt JSON file to be used for the crew. |
+| Attribute                   | Parameters          | Description                                                                                              |
+| :-------------------------- | :------------------ | :------------------------------------------------------------------------------------------------------- |
+| **Tasks**                   | `tasks`               | A list of tasks assigned to the crew.                                                                    |
+| **Agents**                  | `agents`              | A list of agents that are part of the crew.                                                              |
+| **Process** *(optional)*    | `process`             | The process flow (e.g., sequential, hierarchical) the crew follows.                                      |
+| **Verbose** *(optional)*    | `verbose`             | The verbosity level for logging during execution.                                                        |
+| **Manager LLM** *(optional)*| `manager_llm`         | The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
+| **Function Calling LLM** *(optional)* | `function_calling_llm` | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
+| **Config** *(optional)*     | `config`              | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format.                       |
+| **Max RPM** *(optional)*    | `max_rpm`             | Maximum requests per minute the crew adheres to during execution.                                         |
+| **Language**  *(optional)*  | `language`            | Language used for the crew, defaults to English.                                                          |
+| **Language File** *(optional)* | `language_file`       | Path to the language file to be used for the crew.                                                        |
+| **Memory** *(optional)*     | `memory`              | Utilized for storing execution memories (short-term, long-term, entity memory).                           |
+| **Cache** *(optional)*      | `cache`               | Specifies whether to use a cache for storing the results of tools' execution.                             |
+| **Embedder** *(optional)*   | `embedder`            | Configuration for the embedder to be used by the crew. Mostly used by memory for now.                     |
+| **Full Output** *(optional)*| `full_output`         | Whether the crew should return the full output with all tasks outputs or just the final output.           |
+| **Step Callback** *(optional)* | `step_callback`       | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
+| **Task Callback** *(optional)* | `task_callback`       | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
+| **Share Crew** *(optional)* | `share_crew`          | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
+| **Output Log File** *(optional)* | `output_log_file`    | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
+| **Manager Agent** *(optional)* | `manager_agent`      | `manager` sets a custom agent that will be used as a manager.                                             |
+| **Manager Callbacks** *(optional)* | `manager_callbacks` | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
+| **Prompt File** *(optional)* | `prompt_file`         | Path to the prompt JSON file to be used for the crew.                                                     |
 
 !!! note "Crew Max RPM"
     The `max_rpm` attribute sets the maximum number of requests per minute the crew can perform to avoid rate limits and will override individual agents' `max_rpm` settings if you set it.
@@ -123,7 +123,7 @@ result = my_crew.kickoff()
 print(result)
 ```
 
-### Kicking Off a Crew
+### Different wayt to Kicking Off a Crew
 
 Once your crew is assembled, initiate the workflow with the appropriate kickoff method. CrewAI provides several methods for better control over the kickoff process: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
 
@@ -138,18 +138,21 @@ result = my_crew.kickoff()
 print(result)
 
 # Example of using kickoff_for_each
-results = my_crew.kickoff_for_each()
+inputs_array = [{'topic': 'AI in healthcare'}, {'topic': 'AI in finance'}]
+results = my_crew.kickoff_for_each(inputs=inputs_array)
 for result in results:
     print(result)
 
 # Example of using kickoff_async
-async_result = my_crew.kickoff_async()
+inputs = {'topic': 'AI in healthcare'}
+async_result = my_crew.kickoff_async(inputs=inputs)
 print(async_result)
 
 # Example of using kickoff_for_each_async
-async_results = my_crew.kickoff_for_each_async()
+inputs_array = [{'topic': 'AI in healthcare'}, {'topic': 'AI in finance'}]
+async_results = my_crew.kickoff_for_each_async(inputs=inputs_array)
 for async_result in async_results:
     print(async_result)
 ```
 
-These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs
+These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs

docs/core-concepts/Tasks.md

@@ -11,20 +11,20 @@ Tasks within crewAI can be collaborative, requiring multiple agents to work toge
 
 ## Task Attributes
 
-| Attribute              | Description                                                                                   |
-| :----------------------| :-------------------------------------------------------------------------------------------- |
-| **Description**        | A clear, concise statement of what the task entails.                                          |
-| **Agent**              | The agent responsible for the task, assigned either directly or by the crew's process.        |
-| **Expected Output**    | A detailed description of what the task's completion looks like.                              |
-| **Tools** *(optional)* | The functions or capabilities the agent can utilize to perform the task.                      |
-| **Async Execution** *(optional)* | If set, the task executes asynchronously, allowing progression without waiting for completion.|
-| **Context**  *(optional)* | Specifies tasks whose outputs are used as context for this task.                              |
-| **Config** *(optional)* | Additional configuration details for the agent executing the task, allowing further customization. |
-| **Output JSON**  *(optional)* | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set.         |
-| **Output Pydantic**  *(optional)* | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
-| **Output File**  *(optional)* | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
-| **Callback**  *(optional)* | A Python callable that is executed with the task's output upon completion.                    |
-| **Human Input** *(optional)* | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
+| Attribute              | Parameters           | Description                                                                                   |
+| :----------------------| :------------------- | :-------------------------------------------------------------------------------------------- |
+| **Description**        | `description`          | A clear, concise statement of what the task entails.                                          |
+| **Agent**              | `agent`                | The agent responsible for the task, assigned either directly or by the crew's process.        |
+| **Expected Output**    | `expected_output`      | A detailed description of what the task's completion looks like.                              |
+| **Tools** *(optional)* | `tools`                | The functions or capabilities the agent can utilize to perform the task.                      |
+| **Async Execution** *(optional)* | `async_execution`      | If set, the task executes asynchronously, allowing progression without waiting for completion.|
+| **Context**  *(optional)* | `context`              | Specifies tasks whose outputs are used as context for this task.                              |
+| **Config** *(optional)* | `config`               | Additional configuration details for the agent executing the task, allowing further customization. |
+| **Output JSON**  *(optional)* | `output_json`          | Outputs a JSON object, requiring an OpenAI client. Only one output format can be set.         |
+| **Output Pydantic**  *(optional)* | `output_pydantic`      | Outputs a Pydantic model object, requiring an OpenAI client. Only one output format can be set. |
+| **Output File**  *(optional)* | `output_file`          | Saves the task output to a file. If used with `Output JSON` or `Output Pydantic`, specifies how the output is saved. |
+| **Callback**  *(optional)* | `callback`             | A Python callable that is executed with the task's output upon completion.                    |
+| **Human Input** *(optional)* | `human_input`         | Indicates if the task requires human feedback at the end, useful for tasks needing human oversight. |
 
 ## Creating a Task
 

docs/core-concepts/Training-Crew.md

@@ -0,0 +1,53 @@
+---
+title: crewAI Train
+description: Learn how to train your crewAI agents by giving them feedback early on and get consistent results.
+---
+
+## Introduction
+The training feature in CrewAI allows you to train your AI agents using the command-line interface (CLI). By running the command `crewai train -n <n_iterations>`, you can specify the number of iterations for the training process.
+
+During training, CrewAI utilizes techniques to optimize the performance of your agents along with human feedback. This helps the agents improve their understanding, decision-making, and problem-solving abilities.
+
+### Training Your Crew Using the CLI
+To use the training feature, follow these steps:
+
+1. Open your terminal or command prompt.
+2. Navigate to the directory where your CrewAI project is located.
+3. Run the following command:
+
+```shell
+crewai train -n <n_iterations>
+```
+
+### Training Your Crew Programmatically
+To train your crew programmatically, use the following steps:
+
+1. Define the number of iterations for training.
+2. Specify the input parameters for the training process.
+3. Execute the training command within a try-except block to handle potential errors.
+
+```python
+    n_iterations = 2
+    inputs = {"topic": "CrewAI Training"}
+
+    try:
+        YourCrewName_Crew().crew().train(n_iterations= n_iterations, inputs=inputs)
+
+    except Exception as e:
+        raise Exception(f"An error occurred while training the crew: {e}")
+```
+
+!!! note "Replace `<n_iterations>` with the desired number of training iterations. This determines how many times the agents will go through the training process."
+
+
+### Key Points to Note:
+- **Positive Integer Requirement:** Ensure that the number of iterations (`n_iterations`) is a positive integer. The code will raise a `ValueError` if this condition is not met.
+- **Error Handling:** The code handles subprocess errors and unexpected exceptions, providing error messages to the user.
+
+It is important to note that the training process may take some time, depending on the complexity of your agents and will also require your feedback on each iteration.
+
+Once the training is complete, your agents will be equipped with enhanced capabilities and knowledge, ready to tackle complex tasks and provide more consistent and valuable insights.
+
+Remember to regularly update and retrain your agents to ensure they stay up-to-date with the latest information and advancements in the field.
+
+Happy training with CrewAI!

docs/how-to/Coding-Agents.md

@@ -0,0 +1,76 @@
+---
+title: Coding Agents
+description: Learn how to enable your crewAI Agents to write and execute code, and explore advanced features for enhanced functionality.
+---
+
+## Introduction
+
+crewAI Agents now have the powerful ability to write and execute code, significantly enhancing their problem-solving capabilities. This feature is particularly useful for tasks that require computational or programmatic solutions.
+
+## Enabling Code Execution
+
+To enable code execution for an agent, set the `allow_code_execution` parameter to `True` when creating the agent. Here's an example:
+
+```python
+from crewai import Agent
+
+coding_agent = Agent(
+    role="Senior Python Developer",
+    goal="Craft well-designed and thought-out code",
+    backstory="You are a senior Python developer with extensive experience in software architecture and best practices.",
+    allow_code_execution=True
+)
+```
+
+## Important Considerations
+
+1. **Model Selection**: It is strongly recommended to use more capable models like Claude 3.5 Sonnet and GPT-4 when enabling code execution. These models have a better understanding of programming concepts and are more likely to generate correct and efficient code.
+
+2. **Error Handling**: The code execution feature includes error handling. If executed code raises an exception, the agent will receive the error message and can attempt to correct the code or provide alternative solutions.
+
+3. **Dependencies**: To use the code execution feature, you need to install the `crewai_tools` package. If not installed, the agent will log an info message: "Coding tools not available. Install crewai_tools."
+
+## Code Execution Process
+
+When an agent with code execution enabled encounters a task requiring programming:
+
+1. The agent analyzes the task and determines that code execution is necessary.
+2. It formulates the Python code needed to solve the problem.
+3. The code is sent to the internal code execution tool (`CodeInterpreterTool`).
+4. The tool executes the code in a controlled environment and returns the result.
+5. The agent interprets the result and incorporates it into its response or uses it for further problem-solving.
+
+## Example Usage
+
+Here's a detailed example of creating an agent with code execution capabilities and using it in a task:
+
+```python
+from crewai import Agent, Task, Crew
+
+# Create an agent with code execution enabled
+coding_agent = Agent(
+    role="Python Data Analyst",
+    goal="Analyze data and provide insights using Python",
+    backstory="You are an experienced data analyst with strong Python skills.",
+    allow_code_execution=True
+)
+
+# Create a task that requires code execution
+data_analysis_task = Task(
+    description="Analyze the given dataset and calculate the average age of participants.",
+    agent=coding_agent
+)
+
+# Create a crew and add the task
+analysis_crew = Crew(
+    agents=[coding_agent],
+    tasks=[data_analysis_task]
+)
+
+# Execute the crew
+result = analysis_crew.kickoff()
+
+print(result)
+```
+
+In this example, the `coding_agent` can write and execute Python code to perform data analysis tasks.

docs/how-to/Creating-a-Crew-and-kick-it-off.md

@@ -1,11 +1,10 @@
 ---
 title: Assembling and Activating Your CrewAI Team
-description: A comprehensive guide to creating a dynamic CrewAI team for your projects, with updated functionalities including verbose mode, memory capabilities, asynchronous execution, output customization, language model configuration, and more.
-
+description: A comprehensive guide to creating a dynamic CrewAI team for your projects, with updated functionalities including verbose mode, memory capabilities, asynchronous execution, output customization, language model configuration, code execution, integration with third-party agents, and improved task management.
 ---
 
 ## Introduction
-Embark on your CrewAI journey by setting up your environment and initiating your AI crew with the latest features. This guide ensures a smooth start, incorporating all recent updates for an enhanced experience.
+Embark on your CrewAI journey by setting up your environment and initiating your AI crew with the latest features. This guide ensures a smooth start, incorporating all recent updates for an enhanced experience, including code execution capabilities, integration with third-party agents, and advanced task management.
 
 ## Step 0: Installation
 Install CrewAI and any necessary packages for your project. CrewAI is compatible with Python >=3.10,<=3.13.
@@ -16,46 +15,51 @@ pip install 'crewai[tools]'
 ```
 
 ## Step 1: Assemble Your Agents
-Define your agents with distinct roles, backstories, and enhanced capabilities like verbose mode, memory usage, and the ability to set specific agents as managers. These elements add depth and guide their task execution and interaction within the crew.
+Define your agents with distinct roles, backstories, and enhanced capabilities. The Agent class now supports a wide range of attributes for fine-tuned control over agent behavior and interactions, including code execution and integration with third-party agents.
 
 ```python
 import os
-os.environ["SERPER_API_KEY"] = "Your Key"  # serper.dev API key
-os.environ["OPENAI_API_KEY"] = "Your Key"
-
+from langchain.llms import OpenAI
 from crewai import Agent
 from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
+
+os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
+os.environ["SERPER_API_KEY"] = "Your Serper Key"
+
 search_tool = SerperDevTool()
 browser_tool = BrowserbaseTool()
 exa_search_tool = ExaSearchTool()
 
-# Creating a senior researcher agent with memory and verbose mode
+# Creating a senior researcher agent with advanced configurations
 researcher = Agent(
-  role='Senior Researcher',
-  goal='Uncover groundbreaking technologies in {topic}',
-  verbose=True,
-  memory=True,
-  backstory=(
-    "Driven by curiosity, you're at the forefront of"
-    "innovation, eager to explore and share knowledge that could change"
-    "the world."
-  ),
-  tools=[search_tool, browser_tool],
+    role='Senior Researcher',
+    goal='Uncover groundbreaking technologies in {topic}',
+    backstory=("Driven by curiosity, you're at the forefront of innovation, "
+               "eager to explore and share knowledge that could change the world."),
+    memory=True,
+    verbose=True,
+    allow_delegation=False,
+    tools=[search_tool, browser_tool],
+    allow_code_execution=False,  # New attribute for enabling code execution
+    max_iter=15,  # Maximum number of iterations for task execution
+    max_rpm=100,  # Maximum requests per minute
+    max_execution_time=3600,  # Maximum execution time in seconds
+    system_template="Your custom system template here",  # Custom system template
+    prompt_template="Your custom prompt template here",  # Custom prompt template
+    response_template="Your custom response template here",  # Custom response template
 )
 
-# Creating a writer agent with custom tools and delegation capability
+# Creating a writer agent with custom tools and specific configurations
 writer = Agent(
-  role='Writer',
-  goal='Narrate compelling tech stories about {topic}',
-  verbose=True,
-  memory=True,
-  backstory=(
-    "With a flair for simplifying complex topics, you craft"
-    "engaging narratives that captivate and educate, bringing new"
-    "discoveries to light in an accessible manner."
-  ),
-  tools=[exa_search_tool],
-  allow_delegation=False
+    role='Writer',
+    goal='Narrate compelling tech stories about {topic}',
+    backstory=("With a flair for simplifying complex topics, you craft engaging "
+               "narratives that captivate and educate, bringing new discoveries to light."),
+    verbose=True,
+    allow_delegation=False,
+    memory=True,
+    tools=[exa_search_tool],
+    function_calling_llm=OpenAI(model_name="gpt-3.5-turbo"),  # Separate LLM for function calling
 )
 
 # Setting a specific manager agent
@@ -64,73 +68,16 @@ manager = Agent(
   goal='Ensure the smooth operation and coordination of the team',
   verbose=True,
   backstory=(
-    "As a seasoned project manager, you excel in organizing"
+    "As a seasoned project manager, you excel in organizing "
     "tasks, managing timelines, and ensuring the team stays on track."
-  )
-)
-```
-
-## Step 2: Define the Tasks
-Detail the specific objectives for your agents, including new features for asynchronous execution and output customization. These tasks ensure a targeted approach to their roles.
-
-```python
-from crewai import Task
-
-# Research task
-research_task = Task(
-  description=(
-    "Identify the next big trend in {topic}."
-    "Focus on identifying pros and cons and the overall narrative."
-    "Your final report should clearly articulate the key points,"
-    "its market opportunities, and potential risks."
   ),
-  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
-  tools=[search_tool],
-  agent=researcher,
-  callback="research_callback",  # Example of task callback
-  human_input=True
-)
-
-# Writing task with language model configuration
-write_task = Task(
-  description=(
-    "Compose an insightful article on {topic}."
-    "Focus on the latest trends and how it's impacting the industry."
-    "This article should be easy to understand, engaging, and positive."
-  ),
-  expected_output='A 4 paragraph article on {topic} advancements formatted as markdown.',
-  tools=[exa_search_tool],
-  agent=writer,
-  output_file='new-blog-post.md',  # Example of output customization
+  allow_code_execution=True,  # Enable code execution for the manager
 )
 ```
 
-## Step 3: Form the Crew
-Combine your agents into a crew, setting the workflow process they'll follow to accomplish the tasks. Now with options to configure language models for enhanced interaction and additional configurations for optimizing performance, such as creating directories when saving files.
+### New Agent Attributes and Features
 
-```python
-from crewai import Crew, Process
-
-# Forming the tech-focused crew with some enhanced configurations
-crew = Crew(
-  agents=[researcher, writer],
-  tasks=[research_task, write_task],
-  process=Process.sequential,  # Optional: Sequential task execution is default
-  memory=True,
-  cache=True,
-  max_rpm=100,
-  manager_agent=manager
-)
-```
-
-## Step 4: Kick It Off
-Initiate the process with your enhanced crew ready. Observe as your agents collaborate, leveraging their new capabilities for a successful project outcome. Input variables will be interpolated into the agents and tasks for a personalized approach.
-
-```python
-# Starting the task execution process with enhanced feedback
-result = crew.kickoff(inputs={'topic': 'AI in healthcare'})
-print(result)
-```
-
-## Conclusion
-Building and activating a crew in CrewAI has evolved with new functionalities. By incorporating verbose mode, memory capabilities, asynchronous task execution, output customization, language model configuration, and enhanced crew configurations, your AI team is more equipped than ever to tackle challenges efficiently. The depth of agent backstories and the precision of their objectives enrich collaboration, leading to successful project outcomes. This guide aims to provide you with a clear and detailed understanding of setting up and utilizing the CrewAI framework to its full potential.
+1. `allow_code_execution`: Enable or disable code execution capabilities for the agent (default is False).
+2. `max_execution_time`: Set a maximum execution time (in seconds) for the agent to complete a task.
+3. `function_calling_llm`: Specify a separate language model for function calling.
+4

docs/how-to/Kickoff-async.md

@@ -0,0 +1,40 @@
+---
+title: Kickoff Async
+description: Kickoff a Crew Asynchronously
+---
+
+## Introduction
+CrewAI provides the ability to kickoff a crew asynchronously, allowing you to start the crew execution in a non-blocking manner. This feature is particularly useful when you want to run multiple crews concurrently or when you need to perform other tasks while the crew is executing.
+
+## Asynchronous Crew Execution
+To kickoff a crew asynchronously, use the `kickoff_async()` method. This method initiates the crew execution in a separate thread, allowing the main thread to continue executing other tasks.
+
+Here's an example of how to kickoff a crew asynchronously:
+
+```python
+from crewai import Crew, Agent, Task
+
+# Create an agent with code execution enabled
+coding_agent = Agent(
+    role="Python Data Analyst",
+    goal="Analyze data and provide insights using Python",
+    backstory="You are an experienced data analyst with strong Python skills.",
+    allow_code_execution=True
+)
+
+# 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
+)
+
+# Create a crew and add the task
+analysis_crew = Crew(
+    agents=[coding_agent],
+    tasks=[data_analysis_task]
+)
+
+# Execute the crew
+result = analysis_crew.kickoff_async(inputs={"ages": [25, 30, 35, 40, 45]})
+```
+

docs/how-to/Kickoff-for-each.md

@@ -0,0 +1,45 @@
+---
+title: Kickoff For Each
+description: Kickoff a Crew for a List
+---
+
+## Introduction
+CrewAI provides the ability to kickoff a crew for each item in a list, allowing you to execute the crew for each item in the list. This feature is particularly useful when you need to perform the same set of tasks for multiple items.
+
+## Kicking Off a Crew for Each Item
+To kickoff a crew for each item in a list, use the `kickoff_for_each()` method. This method executes the crew for each item in the list, allowing you to process multiple items efficiently.
+
+Here's an example of how to kickoff a crew for each item in a list:
+
+```python
+from crewai import Crew, Agent, Task
+
+# Create an agent with code execution enabled
+coding_agent = Agent(
+    role="Python Data Analyst",
+    goal="Analyze data and provide insights using Python",
+    backstory="You are an experienced data analyst with strong Python skills.",
+    allow_code_execution=True
+)
+
+# 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
+)
+
+# Create a crew and add the task
+analysis_crew = Crew(
+    agents=[coding_agent],
+    tasks=[data_analysis_task]
+)
+
+datasets = [
+  { "ages": [25, 30, 35, 40, 45] },
+  { "ages": [20, 25, 30, 35, 40] },
+  { "ages": [30, 35, 40, 45, 50] }
+]
+
+# Execute the crew
+result = analysis_crew.kickoff_for_each(inputs=datasets)
+```

docs/how-to/LLM-Connections.md

@@ -1,16 +1,18 @@
 ---
 title: Connect CrewAI to LLMs
-description: Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs), including detailed class attributes and methods.
+description: Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs), including detailed class attributes, methods, and configuration options.
 ---
 
 ## Connect CrewAI to LLMs
+
 !!! note "Default LLM"
-    By default, CrewAI uses OpenAI's GPT-4 model for language processing. You can configure your agents to use a different model or API. This guide shows how to connect your agents to various LLMs through environment variables and direct instantiation.
+    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
 
 CrewAI offers flexibility in connecting to various LLMs, including local models via [Ollama](https://ollama.ai) and different APIs like Azure. It's compatible with all [LangChain LLM](https://python.langchain.com/docs/integrations/llms/) components, enabling diverse integrations for tailored AI solutions.
 
 ## CrewAI Agent Overview
-The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's an updated overview reflecting the latest codebase changes:
+
+The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's a comprehensive overview of the Agent class attributes and methods:
 
 - **Attributes**:
     - `role`: Defines the agent's role within the solution.
@@ -50,54 +52,24 @@ Ollama is preferred for local LLM integration, offering customization and privac
 ### Setting Up Ollama
 - **Environment Variables Configuration**: To integrate Ollama, set the following environment variables:
 ```sh
-OPENAI_API_BASE='http://localhost:11434/v1'
-OPENAI_MODEL_NAME='openhermes'  # Adjust based on available model
+OPENAI_API_BASE='http://localhost:11434'
+OPENAI_MODEL_NAME='llama2'  # Adjust based on available model
 OPENAI_API_KEY=''
 ```
 
 ## Ollama Integration (ex. for using Llama 2 locally)
-1. [Download Ollama](https://ollama.com/download).
-2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.
-3. Create a ModelFile similar the one below in your project directory.
+1. [Download Ollama](https://ollama.com/download).   
+2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.   
+3. Enjoy your free Llama2 model that powered up by excellent agents from crewai.   
 ```
-FROM llama2
-
-# Set parameters
-
-PARAMETER temperature 0.8
-PARAMETER stop Result
-
-# Sets a custom system message to specify the behavior of the chat assistant
-
-# Leaving it blank for now.
-
-SYSTEM """"""
-```
-4. Create a script to get the base model, which in our case is llama2, and create a model on top of that with ModelFile above. PS: this will be ".sh" file.
-```
-#!/bin/zsh
-
-# variables
-model_name="llama2"
-custom_model_name="crewai-llama2"
-
-#get the base model
-ollama pull $model_name
-
-#create the model file
-ollama create $custom_model_name -f ./Llama2ModelFile
-```
-5. Go into the directory where the script file and ModelFile is located and run the script.
-6. Enjoy your free Llama2 model that is powered up by excellent agents from CrewAI.
-```python
 from crewai import Agent, Task, Crew
-from langchain_openai import ChatOpenAI
+from langchain.llms import Ollama
 import os
 os.environ["OPENAI_API_KEY"] = "NA"
 
-llm = ChatOpenAI(
-    model = "crewai-llama2",
-    base_url = "http://localhost:11434/v1")
+llm = Ollama(
+    model = "llama2",
+    base_url = "http://localhost:11434")
 
 general_agent = Agent(role = "Math Professor",
                       goal = """Provide the solution to the students that are asking mathematical questions and give them the answer.""",

docs/how-to/Langtrace-Observability.md

@@ -1,44 +1,89 @@
 ---
 title: CrewAI Agent Monitoring with Langtrace
-description: How to monitor cost, latency, and performance of CrewAI Agents using Langtrace.
+description: How to monitor cost, latency, and performance of CrewAI Agents using Langtrace, an external observability tool.
 ---
 
 # Langtrace Overview
-Langtrace is an open-source tool that helps you set up observability and evaluations for LLMs, LLM frameworks, and VectorDB. With Langtrace, you can get deep visibility into the cost, latency, and performance of your CrewAI Agents. Additionally, you can log the hyperparameters and monitor for any performance regressions and set up a process to continuously improve your Agents.
+
+Langtrace is an open-source, external tool that helps you set up observability and evaluations for Large Language Models (LLMs), LLM frameworks, and Vector Databases. While not built directly into CrewAI, Langtrace can be used alongside CrewAI to gain deep visibility into the cost, latency, and performance of your CrewAI Agents. This integration allows you to log hyperparameters, monitor performance regressions, and establish a process for continuous improvement of your Agents.
 
 ## Setup Instructions
 
-1. Sign up for [Langtrace](https://langtrace.ai/) by going to [https://langtrace.ai/signup](https://langtrace.ai/signup).
+1. Sign up for [Langtrace](https://langtrace.ai/) by visiting [https://langtrace.ai/signup](https://langtrace.ai/signup).
 2. Create a project and generate an API key.
-3. Install Langtrace in your code using the following commands.
-**Note**: For detailed instructions on integrating Langtrace, you can check out the official docs from [here](https://docs.langtrace.ai/supported-integrations/llm-frameworks/crewai).
+3. Install Langtrace in your CrewAI project using the following commands:
 
-```
+```bash
 # Install the SDK
 pip install langtrace-python-sdk
-
-# Import it into your project
-from langtrace_python_sdk import langtrace # Must precede any llm module imports
-langtrace.init(api_key = '<LANGTRACE_API_KEY>')
 ```
 
-### Features
-- **LLM Token and Cost tracking**
-- **Trace graph showing detailed execution steps with latency and logs**
-- **Dataset curation using manual annotation**
-- **Prompt versioning and management**
-- **Prompt Playground with comparison views between models**
-- **Testing and Evaluations**
+## Using Langtrace with CrewAI
 
-![Langtrace Cost and Usage Tracking](..%2Fassets%2Fcrewai-langtrace-stats.png)
-![Langtrace Span Graph and Logs Dashboard](..%2Fassets%2Fcrewai-langtrace-spans.png)
+To integrate Langtrace with your CrewAI project, follow these steps:
 
-#### Extra links
+1. Import and initialize Langtrace at the beginning of your script, before any CrewAI imports:
 
-<a href="https://x.com/langtrace_ai">🐦 Twitter</a>
-<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
-<a href="https://discord.com/invite/EaSATwtr4t">📢 Discord</a>
-<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
-<a href="https://langtrace.ai/">🖇 Website</a>
-<span>&nbsp;&nbsp;•&nbsp;&nbsp;</span>
-<a href="https://docs.langtrace.ai/introduction">📙 Documentation</a>
+```python
+from langtrace_python_sdk import langtrace
+langtrace.init(api_key='<LANGTRACE_API_KEY>')
+
+# Now import CrewAI modules
+from crewai import Agent, Task, Crew
+```
+
+2. Create your CrewAI agents and tasks as usual.
+
+3. Use Langtrace's tracking functions to monitor your CrewAI operations. For example:
+
+```python
+with langtrace.trace("CrewAI Task Execution"):
+    result = crew.kickoff()
+```
+
+### Features and Their Application to CrewAI
+
+1. **LLM Token and Cost Tracking**
+   - Monitor the token usage and associated costs for each CrewAI agent interaction.
+   - Example:
+     ```python
+     with langtrace.trace("Agent Interaction"):
+         agent_response = agent.execute(task)
+     ```
+
+2. **Trace Graph for Execution Steps**
+   - Visualize the execution flow of your CrewAI tasks, including latency and logs.
+   - Useful for identifying bottlenecks in your agent workflows.
+
+3. **Dataset Curation with Manual Annotation**
+   - Create datasets from your CrewAI task outputs for future training or evaluation.
+   - Example:
+     ```python
+     langtrace.log_dataset_item(task_input, agent_output, {"task_type": "research"})
+     ```
+
+4. **Prompt Versioning and Management**
+   - Keep track of different versions of prompts used in your CrewAI agents.
+   - Useful for A/B testing and optimizing agent performance.
+
+5. **Prompt Playground with Model Comparisons**
+   - Test and compare different prompts and models for your CrewAI agents before deployment.
+
+6. **Testing and Evaluations**
+   - Set up automated tests for your CrewAI agents and tasks.
+   - Example:
+     ```python
+     langtrace.evaluate(agent_output, expected_output, "accuracy")
+     ```
+
+## Monitoring New CrewAI Features
+
+CrewAI has introduced several new features that can be monitored using Langtrace:
+
+1. **Code Execution**: Monitor the performance and output of code executed by agents.
+   ```python
+   with langtrace.trace("Agent Code Execution"):
+       code_output = agent.execute_code(code_snippet)
+   ```
+
+2. **Third-party Agent Integration**: Track interactions with LlamaIndex, LangChain, and Autogen agents.

docs/how-to/Sequential.md

@@ -15,7 +15,7 @@ The sequential process ensures tasks are executed one after the other, following
 - **Easy Monitoring**: Facilitates easy tracking of task completion and project progress.
 
 ## Implementing the Sequential Process
-Assemble your crew and define tasks in the order they need to be executed.
+To use the sequential process, assemble your crew and define tasks in the order they need to be executed.
 
 ```python
 from crewai import Crew, Process, Agent, Task
@@ -37,10 +37,9 @@ writer = Agent(
   backstory='A skilled writer with a talent for crafting compelling narratives'
 )
 
-# Define the tasks in sequence
-research_task = Task(description='Gather relevant data...', agent=researcher)
-analysis_task = Task(description='Analyze the data...', agent=analyst)
-writing_task = Task(description='Compose the report...', agent=writer)
+research_task = Task(description='Gather relevant data...', agent=researcher, expected_output='Raw Data')
+analysis_task = Task(description='Analyze the data...', agent=analyst, expected_output='Data Insights')
+writing_task = Task(description='Compose the report...', agent=writer, expected_output='Final Report')
 
 # Form the crew with a sequential process
 report_crew = Crew(
@@ -48,6 +47,9 @@ report_crew = Crew(
   tasks=[research_task, analysis_task, writing_task],
   process=Process.sequential
 )
+
+# Execute the crew
+result = report_crew.kickoff()
 ```
 
 ### Workflow in Action
@@ -55,5 +57,29 @@ report_crew = Crew(
 2. **Subsequent Tasks**: Agents pick up their tasks based on the process type, with outcomes of preceding tasks or manager directives guiding their execution.
 3. **Completion**: The process concludes once the final task is executed, leading to project completion.
 
-## Conclusion
-The sequential and hierarchical processes in CrewAI offer clear, adaptable paths for task execution. They are well-suited for projects requiring logical progression and dynamic decision-making, ensuring each step is completed effectively, thereby facilitating a cohesive final product.
+## Advanced Features
+
+### Task Delegation
+In sequential processes, if an agent has `allow_delegation` set to `True`, they can delegate tasks to other agents in the crew. This feature is automatically set up when there are multiple agents in the crew.
+
+### Asynchronous Execution
+Tasks can be executed asynchronously, allowing for parallel processing when appropriate. To create an asynchronous task, set `async_execution=True` when defining the task.
+
+### Memory and Caching
+CrewAI supports both memory and caching features:
+- **Memory**: Enable by setting `memory=True` when creating the Crew. This allows agents to retain information across tasks.
+- **Caching**: By default, caching is enabled. Set `cache=False` to disable it.
+
+### Callbacks
+You can set callbacks at both the task and step level:
+- `task_callback`: Executed after each task completion.
+- `step_callback`: Executed after each step in an agent's execution.
+
+### Usage Metrics
+CrewAI tracks token usage across all tasks and agents. You can access these metrics after execution.
+
+## Best Practices for Sequential Processes
+1. **Order Matters**: Arrange tasks in a logical sequence where each task builds upon the previous one.
+2. **Clear Task Descriptions**: Provide detailed descriptions for each task to guide the agents effectively.
+3. **Appropriate Agent Selection**: Match agents' skills and roles to the requirements of each task.
+4. **Use Context**: Leverage the context from previous tasks to inform subsequent ones

docs/how-to/Your-Own-Manager-Agent.md

@@ -1,12 +1,12 @@
 ---
-title: Ability to Set a Specific Agent as Manager in CrewAI
-description: Introducing the ability to set a specific agent as a manager instead of having CrewAI create one automatically.
+title: Setting a Specific Agent as Manager in CrewAI
+description: Learn how to set a custom agent as the manager in CrewAI, providing more control over task management and coordination.
 
 ---
 
-# Ability to Set a Specific Agent as Manager in CrewAI
+# Setting a Specific Agent as Manager in CrewAI
 
-CrewAI now allows users to set a specific agent as the manager of the crew, providing more control over the management and coordination of tasks. This feature enables the customization of the managerial role to better fit the project's requirements.
+CrewAI allows users to set a specific agent as the manager of the crew, providing more control over the management and coordination of tasks. This feature enables the customization of the managerial role to better fit your project's requirements.
 
 ## Using the `manager_agent` Attribute
 
@@ -23,46 +23,65 @@ from crewai import Agent, Task, Crew, Process
 # Define your agents
 researcher = Agent(
     role="Researcher",
-    goal="Make the best research and analysis on content about AI and AI agents",
-    backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+    goal="Conduct thorough research and analysis on AI and AI agents",
+    backstory="You're an expert researcher, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently researching for a new client.",
     allow_delegation=False,
 )
 
 writer = Agent(
     role="Senior Writer",
-    goal="Write the best content about AI and AI agents.",
-    backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
+    goal="Create compelling content about AI and AI agents",
+    backstory="You're a senior writer, specialized in technology, software engineering, AI, and startups. You work as a freelancer and are currently writing content for a new client.",
     allow_delegation=False,
 )
 
 # Define your task
 task = Task(
-    description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
-    expected_output="5 bullet points with a paragraph for each idea.",
+    description="Generate a list of 5 interesting ideas for an article, then write one captivating paragraph for each idea that showcases the potential of a full article on this topic. Return the list of ideas with their paragraphs and your notes.",
+    expected_output="5 bullet points, each with a paragraph and accompanying notes.",
 )
 
 # Define the manager agent
 manager = Agent(
-    role="Manager",
-    goal="Manage the crew and ensure the tasks are completed efficiently.",
-    backstory="You're an experienced manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
-    allow_delegation=False,
+    role="Project Manager",
+    goal="Efficiently manage the crew and ensure high-quality task completion",
+    backstory="You're an experienced project manager, skilled in overseeing complex projects and guiding teams to success. Your role is to coordinate the efforts of the crew members, ensuring that each task is completed on time and to the highest standard.",
+    allow_delegation=True,
 )
 
 # Instantiate your crew with a custom manager
 crew = Crew(
     agents=[researcher, writer],
-    process=Process.hierarchical,
-    manager_agent=manager,
     tasks=[task],
+    manager_agent=manager,
+    process=Process.hierarchical,
 )
 
-# Get your crew to work!
-crew.kickoff()
+# Start the crew's work
+result = crew.kickoff()
 ```
 
 ## Benefits of a Custom Manager Agent
 
-- **Enhanced Control**: Allows for a more tailored management approach, fitting the specific needs of the project.
-- **Improved Coordination**: Ensures that the tasks are efficiently coordinated and managed by an experienced agent.
-- **Customizable Management**: Provides the flexibility to define managerial roles and responsibilities that align with the project's goals.
+- **Enhanced Control**: Tailor the management approach to fit the specific needs of your project.
+- **Improved Coordination**: Ensure efficient task coordination and management by an experienced agent.
+- **Customizable Management**: Define managerial roles and responsibilities that align with your project's goals.
+
+## Setting a Manager LLM
+
+If you're using the hierarchical process and don't want to set a custom manager agent, you can specify the language model for the manager:
+
+```python
+from langchain_openai import ChatOpenAI
+
+manager_llm = ChatOpenAI(model_name="gpt-4")
+
+crew = Crew(
+    agents=[researcher, writer],
+    tasks=[task],
+    process=Process.hierarchical,
+    manager_llm=manager_llm
+)
+```
+
+Note: Either `manager_agent` or `manager_llm` must be set when using the hierarchical process.

docs/index.md

@@ -33,6 +33,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Crews
                 </a>
             </li>
+            <li>
+                <a href="./core-concepts/Training-Crew">
+                    Training
+                </a>
+            </li>
             <li>
                 <a href="./core-concepts/Memory">
                     Memory
@@ -78,16 +83,36 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Customizing Agents
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Coding-Agents">
+                    Coding Agents
+                </a>
+            </li>
             <li>
                 <a href="./how-to/Human-Input-on-Execution">
                     Human Input on Execution
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Kickoff-async">
+                    Kickoff a Crew Asynchronously
+                </a>
+            </li>
+            <li>
+                <a href="./how-to/Kickoff-for-each">
+                    Kickoff a Crew for a List
+                </a>
+            </li>
             <li>
                 <a href="./how-to/AgentOps-Observability">
                     Agent Monitoring with AgentOps
                 </a>
             </li>
+            <li>
+                <a href="./how-to/Langtrace-Observability">
+                    Agent Monitoring with LangTrace
+                </a>
+            </li>
         </ul>
     </div>
     <div style="width:30%">

docs/tools/CodeInterpreterTool.md

@@ -0,0 +1,41 @@
+# CodeInterpreterTool
+
+## Description
+This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code.
+
+It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions.
+
+## Requirements
+
+- Docker
+
+## Installation
+Install the crewai_tools package
+```shell
+pip install 'crewai[tools]'
+```
+
+## Example
+
+Remember that when using this tool, the code must be generated by the Agent itself. The code must be a Python3 code. And it will take some time for the first time to run because it needs to build the Docker image.
+
+```python
+from crewai import Agent
+from crewai_tools import CodeInterpreterTool
+
+Agent(
+    ...
+    tools=[CodeInterpreterTool()],
+)
+```
+
+We also provide a simple way to use it directly from the Agent.
+
+```python
+from crewai import Agent
+
+agent = Agent(
+    ...
+    allow_code_execution=True,
+)
+```

docs/tools/ComposioTool.md

@@ -0,0 +1,72 @@
+# ComposioTool Documentation
+
+## Description
+
+This tools is a wrapper around the composio toolset and gives your agent access to a wide variety of tools from the composio SDK.
+
+## Installation
+
+To incorporate this tool into your project, follow the installation instructions below:
+
+```shell
+pip install composio-core
+pip install 'crewai[tools]'
+```
+
+after the installation is complete, either run `composio login` or export your composio API key as `COMPOSIO_API_KEY`.
+
+## Example
+
+The following example demonstrates how to initialize the tool and execute a github action:
+
+1. Initialize toolset
+
+```python
+from composio import App
+from crewai_tools import ComposioTool
+from crewai import Agent, Task
+
+
+tools = [ComposioTool.from_action(action=Action.GITHUB_ACTIVITY_STAR_REPO_FOR_AUTHENTICATED_USER)]
+```
+
+If you don't know what action you want to use, use `from_app` and `tags` filter to get relevant actions
+
+```python
+tools = ComposioTool.from_app(App.GITHUB, tags=["important"])
+```
+
+or use `use_case` to search relevant actions
+
+```python
+tools = ComposioTool.from_app(App.GITHUB, use_case="Star a github repository")
+```
+
+2. Define agent
+
+```python
+crewai_agent = Agent(
+    role="Github Agent",
+    goal="You take action on Github using Github APIs",
+    backstory=(
+        "You are AI agent that is responsible for taking actions on Github "
+        "on users behalf. You need to take action on Github using Github APIs"
+    ),
+    verbose=True,
+    tools=tools,
+)
+```
+
+3. Execute task
+
+```python
+task = Task(
+    description="Star a repo ComposioHQ/composio on GitHub",
+    agent=crewai_agent,
+    expected_output="if the star happened",
+)
+
+task.execute()
+```
+
+* More detailed list of tools can be found [here](https://app.composio.dev)

docs/tools/PDFSearchTool.md

@@ -29,7 +29,7 @@ tool = PDFSearchTool(pdf='path/to/your/document.pdf')
 ```
 
 ## Arguments
-- `pdf`: **Optinal** The PDF path for the search. Can be provided at initialization or within the `run` method's arguments. If provided at initialization, the tool confines its search to the specified document.
+- `pdf`: **Optional** The PDF path for the search. Can be provided at initialization or within the `run` method's arguments. If provided at initialization, the tool confines its search to the specified document.
 
 ## Custom model and embeddings
 

mkdocs.yml

@@ -126,6 +126,7 @@ nav:
     - Processes: 'core-concepts/Processes.md'
     - Crews: 'core-concepts/Crews.md'
     - Collaboration: 'core-concepts/Collaboration.md'
+    - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
@@ -138,12 +139,17 @@ nav:
     - Create your own Manager Agent: 'how-to/Your-Own-Manager-Agent.md'
     - Connecting to any LLM: 'how-to/LLM-Connections.md'
     - Customizing Agents: 'how-to/Customizing-Agents.md'
+    - Coding Agents: 'how-to/Coding-Agents.md'
     - Human Input on Execution: 'how-to/Human-Input-on-Execution.md'
+    - Kickoff a Crew Asynchronously: 'how-to/Kickoff-async.md'
+    - Kickoff a Crew for a List: 'how-to/Kickoff-for-each.md'
     - Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
     - Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
   - Tools Docs:
     - Google Serper Search: 'tools/SerperDevTool.md'
     - Browserbase Web Loader: 'tools/BrowserbaseLoadTool.md'
+    - Composio Tools: 'tools/ComposioTool.md'
+    - Code Interpreter: 'tools/CodeInterpreterTool.md'
     - Scrape Website: 'tools/ScrapeWebsiteTool.md'
     - Directory Read: 'tools/DirectoryReadTool.md'
     - Exa Serch Web Loader: 'tools/EXASearchTool.md'

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.32.2"
+version = "0.35.8"
 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."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -14,22 +14,24 @@ Repository = "https://github.com/joaomdmoura/crewai"
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
 pydantic = "^2.4.2"
-langchain = "^0.1.10"
+langchain = ">=0.1.4,<0.2.0"
 openai = "^1.13.3"
 opentelemetry-api = "^1.22.0"
 opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.3.0", optional = true }
+crewai-tools = { version = "^0.4.6", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
-embedchain = "0.1.109"
 appdirs = "^1.4.4"
 jsonref = "^1.1.0"
+agentops = { version = "^0.1.9", optional = true }
+embedchain = "^0.1.113"
 
 [tool.poetry.extras]
 tools = ["crewai-tools"]
+agentops = ["agentops"]
 
 [tool.poetry.group.dev.dependencies]
 isort = "^5.13.2"
@@ -43,7 +45,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.3.0"
+crewai-tools = "^0.4.6"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"

src/crewai/__init__.py

@@ -2,3 +2,5 @@ from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.process import Process
 from crewai.task import Task
+
+__all__ = ["Agent", "Crew", "Process", "Task"]

src/crewai/agent.py

@@ -1,7 +1,5 @@
-from copy import deepcopy
 import os
-import uuid
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Any, List, Optional, Tuple
 
 from langchain.agents.agent import RunnableAgent
 from langchain.agents.tools import tool as LangChainTool
@@ -9,25 +7,32 @@ from langchain.tools.render import render_text_description
 from langchain_core.agents import AgentAction
 from langchain_core.callbacks import BaseCallbackHandler
 from langchain_openai import ChatOpenAI
-from pydantic import (
-    UUID4,
-    BaseModel,
-    ConfigDict,
-    Field,
-    InstanceOf,
-    PrivateAttr,
-    field_validator,
-    model_validator,
-)
-from pydantic_core import PydanticCustomError
+from pydantic import Field, InstanceOf, model_validator
 
-from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser, ToolsHandler
+from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.memory.contextual.contextual_memory import ContextualMemory
-from crewai.utilities import I18N, Logger, Prompts, RPMController
-from crewai.utilities.token_counter_callback import TokenCalcHandler, TokenProcess
+from crewai.tools.agent_tools import AgentTools
+from crewai.utilities import Converter, Prompts
+from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
+from crewai.utilities.token_counter_callback import TokenCalcHandler
+from crewai.utilities.training_handler import CrewTrainingHandler
+
+agentops = None
+try:
+    import agentops
+    from agentops import track_agent
+except ImportError:
+
+    def track_agent():
+        def noop(f):
+            return f
+
+        return noop
 
 
-class Agent(BaseModel):
+@track_agent()
+class Agent(BaseAgent):
     """Represents an agent in a system.
 
     Each agent has a role, a goal, a backstory, and an optional language model (llm).
@@ -51,58 +56,12 @@ class Agent(BaseModel):
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
     """
 
-    __hash__ = object.__hash__  # type: ignore
-    _logger: Logger = PrivateAttr()
-    _rpm_controller: RPMController = PrivateAttr(default=None)
-    _request_within_rpm_limit: Any = PrivateAttr(default=None)
-    _token_process: TokenProcess = TokenProcess()
-
-    formatting_errors: int = 0
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-    id: UUID4 = Field(
-        default_factory=uuid.uuid4,
-        frozen=True,
-        description="Unique identifier for the object, not set by user.",
-    )
-    role: str = Field(description="Role of the agent")
-    goal: str = Field(description="Objective of the agent")
-    backstory: str = Field(description="Backstory of the agent")
-    cache: bool = Field(
-        default=True,
-        description="Whether the agent should use a cache for tool usage.",
-    )
-    config: Optional[Dict[str, Any]] = Field(
-        description="Configuration for the agent",
-        default=None,
-    )
-    max_rpm: Optional[int] = Field(
-        default=None,
-        description="Maximum number of requests per minute for the agent execution to be respected.",
-    )
-    verbose: bool = Field(
-        default=False, description="Verbose mode for the Agent Execution"
-    )
-    allow_delegation: bool = Field(
-        default=True, description="Allow delegation of tasks to agents"
-    )
-    tools: Optional[List[Any]] = Field(
-        default_factory=list, description="Tools at agents disposal"
-    )
-    max_iter: Optional[int] = Field(
-        default=25, description="Maximum iterations for an agent to execute a task"
-    )
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
-    agent_executor: InstanceOf[CrewAgentExecutor] = Field(
-        default=None, description="An instance of the CrewAgentExecutor class."
-    )
-    crew: Any = Field(
-        default=None, description="Crew to which the agent belongs.")
-    tools_handler: InstanceOf[ToolsHandler] = Field(
-        default=None, description="An instance of the ToolsHandler class."
-    )
+    agent_ops_agent_name: str = None
+    agent_ops_agent_id: str = None
     cache_handler: InstanceOf[CacheHandler] = Field(
         default=None, description="An instance of the CacheHandler class."
     )
@@ -110,8 +69,6 @@ class Agent(BaseModel):
         default=None,
         description="Callback to be executed after each step of the agent execution.",
     )
-    i18n: I18N = Field(
-        default=I18N(), description="Internationalization settings.")
     llm: Any = Field(
         default_factory=lambda: ChatOpenAI(
             model=os.environ.get("OPENAI_MODEL_NAME", "gpt-4o")
@@ -133,47 +90,20 @@ class Agent(BaseModel):
     response_template: Optional[str] = Field(
         default=None, description="Response format for the agent."
     )
-
-    _original_role: str | None = None
-    _original_goal: str | None = None
-    _original_backstory: str | None = None
+    allow_code_execution: Optional[bool] = Field(
+        default=False, description="Enable code execution for the agent."
+    )
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
         super().__init__(**config, **data)
-
-    @field_validator("id", mode="before")
-    @classmethod
-    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
-        if v:
-            raise PydanticCustomError(
-                "may_not_set_field", "This field is not to be set by the user.", {}
-            )
-
-    @model_validator(mode="after")
-    def set_attributes_based_on_config(self) -> "Agent":
-        """Set attributes based on the agent configuration."""
-        if self.config:
-            for key, value in self.config.items():
-                setattr(self, key, value)
-        return self
-
-    @model_validator(mode="after")
-    def set_private_attrs(self):
-        """Set private attributes."""
-        self._logger = Logger(self.verbose)
-        if self.max_rpm and not self._rpm_controller:
-            self._rpm_controller = RPMController(
-                max_rpm=self.max_rpm, logger=self._logger
-            )
-        return self
+        __pydantic_self__.agent_ops_agent_name = __pydantic_self__.role
 
     @model_validator(mode="after")
     def set_agent_executor(self) -> "Agent":
-        """set agent executor is set."""
+        """Ensure agent executor and token process are set."""
         if hasattr(self.llm, "model_name"):
-            token_handler = TokenCalcHandler(
-                self.llm.model_name, self._token_process)
+            token_handler = TokenCalcHandler(self.llm.model_name, self._token_process)
 
             # Ensure self.llm.callbacks is a list
             if not isinstance(self.llm.callbacks, list):
@@ -185,6 +115,12 @@ class Agent(BaseModel):
             ):
                 self.llm.callbacks.append(token_handler)
 
+            if agentops and not any(
+                isinstance(handler, agentops.LangchainCallbackHandler) for handler in self.llm.callbacks
+            ):
+                agentops.stop_instrumenting()
+                self.llm.callbacks.append(agentops.LangchainCallbackHandler())
+
         if not self.agent_executor:
             if not self.cache_handler:
                 self.cache_handler = CacheHandler()
@@ -230,16 +166,19 @@ class Agent(BaseModel):
 
         tools = tools or self.tools
         # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
-        parsed_tools = self._parse_tools(tools)
-
+        parsed_tools = self._parse_tools(tools or [])
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
         self.agent_executor.task = task
 
-        self.agent_executor.tools_description = render_text_description(
-            parsed_tools)
+        self.agent_executor.tools_description = render_text_description(parsed_tools)
         self.agent_executor.tools_names = self.__tools_names(parsed_tools)
 
+        if self.crew and self.crew._train:
+            task_prompt = self._training_handler(task_prompt=task_prompt)
+        else:
+            task_prompt = self._use_trained_data(task_prompt=task_prompt)
+
         result = self.agent_executor.invoke(
             {
                 "input": task_prompt,
@@ -247,33 +186,22 @@ class Agent(BaseModel):
                 "tools": self.agent_executor.tools_description,
             }
         )["output"]
-
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
-
         return result
 
-    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
-        """Set the cache handler for the agent.
-
-        Args:
-            cache_handler: An instance of the CacheHandler class.
-        """
-        self.tools_handler = ToolsHandler()
-        if self.cache:
-            self.cache_handler = cache_handler
-            self.tools_handler.cache = cache_handler
-        self.create_agent_executor()
-
-    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
-        """Set the rpm controller for the agent.
-
-        Args:
-            rpm_controller: An instance of the RPMController class.
-        """
-        if not self._rpm_controller:
-            self._rpm_controller = rpm_controller
-            self.create_agent_executor()
+    def format_log_to_str(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        observation_prefix: str = "Observation: ",
+        llm_prefix: str = "",
+    ) -> str:
+        """Construct the scratchpad that lets the agent continue its thought process."""
+        thoughts = ""
+        for action, observation in intermediate_steps:
+            thoughts += action.log
+            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
+        return thoughts
 
     def create_agent_executor(self, tools=None) -> None:
         """Create an agent executor for the agent.
@@ -329,77 +257,42 @@ class Agent(BaseModel):
         )
 
         stop_words = [self.i18n.slice("observation")]
+
         if self.response_template:
             stop_words.append(
                 self.response_template.split("{{ .Response }}")[1].strip()
             )
 
         bind = self.llm.bind(stop=stop_words)
-        inner_agent = agent_args | execution_prompt | bind | CrewAgentParser(
-            agent=self)
+
+        inner_agent = agent_args | execution_prompt | bind | CrewAgentParser(agent=self)
         self.agent_executor = CrewAgentExecutor(
             agent=RunnableAgent(runnable=inner_agent), **executor_args
         )
 
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
-        """Interpolate inputs into the agent description and backstory."""
-        if self._original_role is None:
-            self._original_role = self.role
-        if self._original_goal is None:
-            self._original_goal = self.goal
-        if self._original_backstory is None:
-            self._original_backstory = self.backstory
+    def get_delegation_tools(self, agents: List[BaseAgent]):
+        agent_tools = AgentTools(agents=agents)
+        tools = agent_tools.tools()
+        return tools
 
-        if inputs:
-            self.role = self._original_role.format(**inputs)
-            self.goal = self._original_goal.format(**inputs)
-            self.backstory = self._original_backstory.format(**inputs)
+    def get_code_execution_tools(self):
+        try:
+            from crewai_tools import CodeInterpreterTool
 
-    def increment_formatting_errors(self) -> None:
-        """Count the formatting errors of the agent."""
-        self.formatting_errors += 1
+            return [CodeInterpreterTool()]
+        except ModuleNotFoundError:
+            self._logger.log(
+                "info", "Coding tools not available. Install crewai_tools. "
+            )
 
-    def format_log_to_str(
-        self,
-        intermediate_steps: List[Tuple[AgentAction, str]],
-        observation_prefix: str = "Observation: ",
-        llm_prefix: str = "",
-    ) -> str:
-        """Construct the scratchpad that lets the agent continue its thought process."""
-        thoughts = ""
-        for action, observation in intermediate_steps:
-            thoughts += action.log
-            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
-        return thoughts
-    
-    def copy(self):
-        """Create a deep copy of the Agent."""
-        exclude = {
-            "id",
-            "_logger",
-            "_rpm_controller",
-            "_request_within_rpm_limit",
-            "_token_process",      
-            "agent_executor",  
-            "tools",
-            "tools_handler",
-            "cache_handler",
-        }
+    def get_output_converter(self, llm, text, model, instructions):
+        return Converter(llm=llm, text=text, model=model, instructions=instructions)
 
-        copied_data = self.model_dump(exclude=exclude)
-        copied_data = {k: v for k, v in copied_data.items() if v is not None}
-
-        copied_agent = Agent(**copied_data)
-        copied_agent.tools = deepcopy(self.tools)
-
-        return copied_agent
-
-    # type: ignore # Function "langchain_core.tools.tool" is not valid as a type
     def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:
         """Parse tools to be used for the task."""
-        # tentatively try to import from crewai_tools import BaseTool as CrewAITool
         tools_list = []
         try:
+            # tentatively try to import from crewai_tools import BaseTool as CrewAITool
             from crewai_tools import BaseTool as CrewAITool
 
             for tool in tools:
@@ -408,10 +301,35 @@ class Agent(BaseModel):
                 else:
                     tools_list.append(tool)
         except ModuleNotFoundError:
+            tools_list = []
             for tool in tools:
                 tools_list.append(tool)
         return tools_list
 
+    def _training_handler(self, task_prompt: str) -> str:
+        """Handle training data for the agent task prompt to improve output on Training."""
+        if data := CrewTrainingHandler(TRAINING_DATA_FILE).load():
+            agent_id = str(self.id)
+
+            if data.get(agent_id):
+                human_feedbacks = [
+                    i["human_feedback"] for i in data.get(agent_id, {}).values()
+                ]
+                task_prompt += "You MUST follow these feedbacks: \n " + "\n - ".join(
+                    human_feedbacks
+                )
+
+        return task_prompt
+
+    def _use_trained_data(self, task_prompt: str) -> str:
+        """Use trained data for the agent task prompt to improve output."""
+        if data := CrewTrainingHandler(TRAINED_AGENTS_DATA_FILE).load():
+            if trained_data_output := data.get(self.role):
+                task_prompt += "You MUST follow these feedbacks: \n " + "\n - ".join(
+                    trained_data_output["suggestions"]
+                )
+        return task_prompt
+
     @staticmethod
     def __tools_names(tools) -> str:
         return ", ".join([t.name for t in tools])

src/crewai/agents/agent_builder/base_agent.py

@@ -0,0 +1,256 @@
+import uuid
+from abc import ABC, abstractmethod
+from copy import copy as shallow_copy
+from typing import Any, Dict, List, Optional, TypeVar
+
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    PrivateAttr,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
+
+from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
+from crewai.agents.cache.cache_handler import CacheHandler
+from crewai.agents.tools_handler import ToolsHandler
+from crewai.utilities import I18N, Logger, RPMController
+
+T = TypeVar("T", bound="BaseAgent")
+
+
+class BaseAgent(ABC, BaseModel):
+    """Abstract Base Class for all third party agents compatible with CrewAI.
+
+    Attributes:
+        id (UUID4): Unique identifier for the agent.
+        role (str): Role of the agent.
+        goal (str): Objective of the agent.
+        backstory (str): Backstory of the agent.
+        cache (bool): Whether the agent should use a cache for tool usage.
+        config (Optional[Dict[str, Any]]): Configuration for the agent.
+        verbose (bool): Verbose mode for the Agent Execution.
+        max_rpm (Optional[int]): Maximum number of requests per minute for the agent execution.
+        allow_delegation (bool): Allow delegation of tasks to agents.
+        tools (Optional[List[Any]]): Tools at the agent's disposal.
+        max_iter (Optional[int]): Maximum iterations for an agent to execute a task.
+        agent_executor (InstanceOf): An instance of the CrewAgentExecutor class.
+        llm (Any): Language model that will run the agent.
+        crew (Any): Crew to which the agent belongs.
+        i18n (I18N): Internationalization settings.
+        cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
+        tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
+
+
+    Methods:
+        execute_task(task: Any, context: Optional[str] = None, tools: Optional[List[Any]] = None) -> str:
+            Abstract method to execute a task.
+        create_agent_executor(tools=None) -> None:
+            Abstract method to create an agent executor.
+        _parse_tools(tools: List[Any]) -> List[Any]:
+            Abstract method to parse tools.
+        get_delegation_tools(agents: List["BaseAgent"]):
+            Abstract method to set the agents task tools for handling delegation and question asking to other agents in crew.
+        get_output_converter(llm, model, instructions):
+            Abstract method to get the converter class for the agent to create json/pydantic outputs.
+        interpolate_inputs(inputs: Dict[str, Any]) -> None:
+            Interpolate inputs into the agent description and backstory.
+        set_cache_handler(cache_handler: CacheHandler) -> None:
+            Set the cache handler for the agent.
+        increment_formatting_errors() -> None:
+            Increment formatting errors.
+        copy() -> "BaseAgent":
+            Create a copy of the agent.
+        set_rpm_controller(rpm_controller: RPMController) -> None:
+            Set the rpm controller for the agent.
+        set_private_attrs() -> "BaseAgent":
+            Set private attributes.
+    """
+
+    __hash__ = object.__hash__  # type: ignore
+    _logger: Logger = PrivateAttr()
+    _rpm_controller: RPMController = PrivateAttr(default=None)
+    _request_within_rpm_limit: Any = PrivateAttr(default=None)
+    formatting_errors: int = 0
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
+    role: str = Field(description="Role of the agent")
+    goal: str = Field(description="Objective of the agent")
+    backstory: str = Field(description="Backstory of the agent")
+    cache: bool = Field(
+        default=True, description="Whether the agent should use a cache for tool usage."
+    )
+    config: Optional[Dict[str, Any]] = Field(
+        description="Configuration for the agent", default=None
+    )
+    verbose: bool = Field(
+        default=False, description="Verbose mode for the Agent Execution"
+    )
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the agent execution to be respected.",
+    )
+    allow_delegation: bool = Field(
+        default=True, description="Allow delegation of tasks to agents"
+    )
+    tools: Optional[List[Any]] = Field(
+        default_factory=list, description="Tools at agents' disposal"
+    )
+    max_iter: Optional[int] = Field(
+        default=25, description="Maximum iterations for an agent to execute a task"
+    )
+    agent_executor: InstanceOf = Field(
+        default=None, description="An instance of the CrewAgentExecutor class."
+    )
+    llm: Any = Field(
+        default=None, description="Language model that will run the agent."
+    )
+    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
+    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
+    cache_handler: InstanceOf[CacheHandler] = Field(
+        default=None, description="An instance of the CacheHandler class."
+    )
+    tools_handler: InstanceOf[ToolsHandler] = Field(
+        default=None, description="An instance of the ToolsHandler class."
+    )
+
+    _original_role: str | None = None
+    _original_goal: str | None = None
+    _original_backstory: str | None = None
+    _token_process: TokenProcess = TokenProcess()
+
+    def __init__(__pydantic_self__, **data):
+        config = data.pop("config", {})
+        super().__init__(**config, **data)
+
+    @model_validator(mode="after")
+    def set_config_attributes(self):
+        if self.config:
+            for key, value in self.config.items():
+                setattr(self, key, value)
+        return self
+
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "This field is not to be set by the user.", {}
+            )
+
+    @model_validator(mode="after")
+    def set_attributes_based_on_config(self) -> "BaseAgent":
+        """Set attributes based on the agent configuration."""
+        if self.config:
+            for key, value in self.config.items():
+                setattr(self, key, value)
+        return self
+
+    @model_validator(mode="after")
+    def set_private_attrs(self):
+        """Set private attributes."""
+        self._logger = Logger(self.verbose)
+        if self.max_rpm and not self._rpm_controller:
+            self._rpm_controller = RPMController(
+                max_rpm=self.max_rpm, logger=self._logger
+            )
+        if not self._token_process:
+            self._token_process = TokenProcess()
+        return self
+
+    @abstractmethod
+    def execute_task(
+        self,
+        task: Any,
+        context: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
+    ) -> str:
+        pass
+
+    @abstractmethod
+    def create_agent_executor(self, tools=None) -> None:
+        pass
+
+    @abstractmethod
+    def _parse_tools(self, tools: List[Any]) -> List[Any]:
+        pass
+
+    @abstractmethod
+    def get_delegation_tools(self, agents: List["BaseAgent"]):
+        """Set the task tools that init BaseAgenTools class."""
+        pass
+
+    @abstractmethod
+    def get_output_converter(
+        self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
+    ):
+        """Get the converter class for the agent to create json/pydantic outputs."""
+        pass
+
+    def copy(self: T) -> T:
+        """Create a deep copy of the Agent."""
+        exclude = {
+            "id",
+            "_logger",
+            "_rpm_controller",
+            "_request_within_rpm_limit",
+            "_token_process",
+            "agent_executor",
+            "tools",
+            "tools_handler",
+            "cache_handler",
+            "llm",
+        }
+
+        # Copy llm and clear callbacks
+        existing_llm = shallow_copy(self.llm)
+        existing_llm.callbacks = []
+        copied_data = self.model_dump(exclude=exclude)
+        copied_data = {k: v for k, v in copied_data.items() if v is not None}
+
+        copied_agent = type(self)(**copied_data, llm=existing_llm, tools=self.tools)
+
+        return copied_agent
+
+    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
+        """Interpolate inputs into the agent description and backstory."""
+        if self._original_role is None:
+            self._original_role = self.role
+        if self._original_goal is None:
+            self._original_goal = self.goal
+        if self._original_backstory is None:
+            self._original_backstory = self.backstory
+
+        if inputs:
+            self.role = self._original_role.format(**inputs)
+            self.goal = self._original_goal.format(**inputs)
+            self.backstory = self._original_backstory.format(**inputs)
+
+    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
+        """Set the cache handler for the agent.
+
+        Args:
+            cache_handler: An instance of the CacheHandler class.
+        """
+        self.tools_handler = ToolsHandler()
+        if self.cache:
+            self.cache_handler = cache_handler
+            self.tools_handler.cache = cache_handler
+        self.create_agent_executor()
+
+    def increment_formatting_errors(self) -> None:
+        self.formatting_errors += 1
+
+    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
+        """Set the rpm controller for the agent.
+
+        Args:
+            rpm_controller: An instance of the RPMController class.
+        """
+        if not self._rpm_controller:
+            self._rpm_controller = rpm_controller
+            self.create_agent_executor()

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -0,0 +1,109 @@
+import time
+from typing import TYPE_CHECKING, Optional
+
+from crewai.memory.entity.entity_memory_item import EntityMemoryItem
+from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
+from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
+from crewai.utilities.converter import ConverterError
+from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
+from crewai.utilities import I18N
+
+
+if TYPE_CHECKING:
+    from crewai.crew import Crew
+    from crewai.task import Task
+    from crewai.agents.agent_builder.base_agent import BaseAgent
+
+
+class CrewAgentExecutorMixin:
+    crew: Optional["Crew"]
+    crew_agent: Optional["BaseAgent"]
+    task: Optional["Task"]
+    iterations: int
+    force_answer_max_iterations: int
+    have_forced_answer: bool
+    _i18n: I18N
+
+    def _should_force_answer(self) -> bool:
+        """Determine if a forced answer is required based on iteration count."""
+        return (
+            self.iterations == self.force_answer_max_iterations
+        ) and not self.have_forced_answer
+
+    def _create_short_term_memory(self, output) -> None:
+        """Create and save a short-term memory item if conditions are met."""
+        if (
+            self.crew
+            and self.crew_agent
+            and self.task
+            and "Action: Delegate work to coworker" not in output.log
+        ):
+            try:
+                memory = ShortTermMemoryItem(
+                    data=output.log,
+                    agent=self.crew_agent.role,
+                    metadata={
+                        "observation": self.task.description,
+                    },
+                )
+                if (
+                    hasattr(self.crew, "_short_term_memory")
+                    and self.crew._short_term_memory
+                ):
+                    self.crew._short_term_memory.save(memory)
+            except Exception as e:
+                print(f"Failed to add to short term memory: {e}")
+                pass
+
+    def _create_long_term_memory(self, output) -> None:
+        """Create and save long-term and entity memory items based on evaluation."""
+        if (
+            self.crew
+            and self.crew.memory
+            and self.crew._long_term_memory
+            and self.crew._entity_memory
+            and self.task
+            and self.crew_agent
+        ):
+            try:
+                ltm_agent = TaskEvaluator(self.crew_agent)
+                evaluation = ltm_agent.evaluate(self.task, output.log)
+
+                if isinstance(evaluation, ConverterError):
+                    return
+
+                long_term_memory = LongTermMemoryItem(
+                    task=self.task.description,
+                    agent=self.crew_agent.role,
+                    quality=evaluation.quality,
+                    datetime=str(time.time()),
+                    expected_output=self.task.expected_output,
+                    metadata={
+                        "suggestions": evaluation.suggestions,
+                        "quality": evaluation.quality,
+                    },
+                )
+                self.crew._long_term_memory.save(long_term_memory)
+
+                for entity in evaluation.entities:
+                    entity_memory = EntityMemoryItem(
+                        name=entity.name,
+                        type=entity.type,
+                        description=entity.description,
+                        relationships="\n".join(
+                            [f"- {r}" for r in entity.relationships]
+                        ),
+                    )
+                    self.crew._entity_memory.save(entity_memory)
+            except AttributeError as e:
+                print(f"Missing attributes for long term memory: {e}")
+                pass
+            except Exception as e:
+                print(f"Failed to add to long term memory: {e}")
+                pass
+
+    def _ask_human_input(self, final_answer: dict) -> str:
+        """Prompt human input for final decision making."""
+        return input(
+            self._i18n.slice("getting_input").format(final_answer=final_answer)
+        )

src/crewai/agents/agent_builder/utilities/base_agent_tool.py

@@ -0,0 +1,81 @@
+from abc import ABC, abstractmethod
+from typing import List, Optional, Union
+from pydantic import BaseModel, Field
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.task import Task
+from crewai.utilities import I18N
+
+
+class BaseAgentTools(BaseModel, ABC):
+    """Default tools around agent delegation"""
+
+    agents: List[BaseAgent] = Field(description="List of agents in this crew.")
+    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
+
+    @abstractmethod
+    def tools(self):
+        pass
+
+    def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
+        if coworker:
+            is_list = coworker.startswith("[") and coworker.endswith("]")
+            if is_list:
+                coworker = coworker[1:-1].split(",")[0]
+        return coworker
+
+    def delegate_work(
+        self, task: str, context: str, coworker: Optional[str] = None, **kwargs
+    ):
+        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
+        coworker = self._get_coworker(coworker, **kwargs)
+        return self._execute(coworker, task, context)
+
+    def ask_question(
+        self, question: str, context: str, coworker: Optional[str] = None, **kwargs
+    ):
+        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
+        coworker = self._get_coworker(coworker, **kwargs)
+        return self._execute(coworker, question, context)
+
+    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
+        """Execute the command."""
+        try:
+            if agent is None:
+                agent = ""
+
+            # It is important to remove the quotes from the agent name.
+            # The reason we have to do this is because less-powerful LLM's
+            # have difficulty producing valid JSON.
+            # As a result, we end up with invalid JSON that is truncated like this:
+            # {"task": "....", "coworker": "....
+            # when it should look like this:
+            # {"task": "....", "coworker": "...."}
+            agent_name = agent.casefold().replace('"', "").replace("\n", "")
+
+            agent = [
+                available_agent
+                for available_agent in self.agents
+                if available_agent.role.casefold().replace("\n", "") == agent_name
+            ]
+        except Exception as _:
+            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+                coworkers="\n".join(
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
+            )
+
+        if not agent:
+            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+                coworkers="\n".join(
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
+            )
+
+        agent = agent[0]
+        task = Task(
+            description=task,
+            agent=agent,
+            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
+        )
+        return agent.execute_task(task, context)

src/crewai/agents/agent_builder/utilities/base_output_converter_base.py

@@ -0,0 +1,48 @@
+from abc import ABC, abstractmethod
+from typing import Any, Optional
+
+
+from pydantic import BaseModel, Field, PrivateAttr
+
+
+class OutputConverter(BaseModel, ABC):
+    """
+    Abstract base class for converting task results into structured formats.
+
+    This class provides a framework for converting unstructured text into
+    either Pydantic models or JSON, tailored for specific agent requirements.
+    It uses a language model to interpret and structure the input text based
+    on given instructions.
+
+    Attributes:
+        text (str): The input text to be converted.
+        llm (Any): The language model used for conversion.
+        model (Any): The target model for structuring the output.
+        instructions (str): Specific instructions for the conversion process.
+        max_attempts (int): Maximum number of conversion attempts (default: 3).
+    """
+
+    _is_gpt: bool = PrivateAttr(default=True)
+    text: str = Field(description="Text to be converted.")
+    llm: Any = Field(description="The language model to be used to convert the text.")
+    model: Any = Field(description="The model to be used to convert the text.")
+    instructions: str = Field(description="Conversion instructions to the LLM.")
+    max_attempts: Optional[int] = Field(
+        description="Max number of attemps to try to get the output formated.",
+        default=3,
+    )
+
+    @abstractmethod
+    def to_pydantic(self, current_attempt=1):
+        """Convert text to pydantic."""
+        pass
+
+    @abstractmethod
+    def to_json(self, current_attempt=1):
+        """Convert text to json."""
+        pass
+
+    @abstractmethod
+    def _is_gpt(self, llm):
+        """Return if llm provided is of gpt from openai."""
+        pass

src/crewai/agents/agent_builder/utilities/base_token_process.py

@@ -0,0 +1,27 @@
+from typing import Any, Dict
+
+
+class TokenProcess:
+    total_tokens: int = 0
+    prompt_tokens: int = 0
+    completion_tokens: int = 0
+    successful_requests: int = 0
+
+    def sum_prompt_tokens(self, tokens: int):
+        self.prompt_tokens = self.prompt_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_completion_tokens(self, tokens: int):
+        self.completion_tokens = self.completion_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_successful_requests(self, requests: int):
+        self.successful_requests = self.successful_requests + requests
+
+    def get_summary(self) -> Dict[str, Any]:
+        return {
+            "total_tokens": self.total_tokens,
+            "prompt_tokens": self.prompt_tokens,
+            "completion_tokens": self.completion_tokens,
+            "successful_requests": self.successful_requests,
+        }

src/crewai/agents/executor.py

@@ -1,28 +1,36 @@
 import threading
 import time
-from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+from typing import (
+    Any,
+    Dict,
+    Iterator,
+    List,
+    Optional,
+    Tuple,
+    Union,
+)
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain_core.agents import AgentAction, AgentFinish, AgentStep
 from langchain_core.exceptions import OutputParserException
-from langchain_core.pydantic_v1 import root_validator
+
 from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
+from crewai.agents.agent_builder.base_agent_executor_mixin import (
+    CrewAgentExecutorMixin,
+)
 
 from crewai.agents.tools_handler import ToolsHandler
-from crewai.memory.entity.entity_memory_item import EntityMemoryItem
-from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
-from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
+from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.training_handler import CrewTrainingHandler
 from crewai.utilities import I18N
-from crewai.utilities.converter import ConverterError
-from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 
 
-class CrewAgentExecutor(AgentExecutor):
+class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     _i18n: I18N = I18N()
     should_ask_for_human_input: bool = False
     llm: Any = None
@@ -44,61 +52,6 @@ class CrewAgentExecutor(AgentExecutor):
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
 
-    @root_validator()
-    def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
-        values["force_answer_max_iterations"] = values["max_iterations"] - 2
-        return values
-
-    def _should_force_answer(self) -> bool:
-        return (
-            self.iterations == self.force_answer_max_iterations
-        ) and not self.have_forced_answer
-
-    def _create_short_term_memory(self, output) -> None:
-        if (
-            self.crew
-            and self.crew.memory
-            and "Action: Delegate work to coworker" not in output.log
-        ):
-            memory = ShortTermMemoryItem(
-                data=output.log,
-                agent=self.crew_agent.role,
-                metadata={
-                    "observation": self.task.description,
-                },
-            )
-            self.crew._short_term_memory.save(memory)
-
-    def _create_long_term_memory(self, output) -> None:
-        if self.crew and self.crew.memory:
-            ltm_agent = TaskEvaluator(self.crew_agent)
-            evaluation = ltm_agent.evaluate(self.task, output.log)
-
-            if isinstance(evaluation, ConverterError):
-                return
-
-            long_term_memory = LongTermMemoryItem(
-                task=self.task.description,
-                agent=self.crew_agent.role,
-                quality=evaluation.quality,
-                datetime=str(time.time()),
-                expected_output=self.task.expected_output,
-                metadata={
-                    "suggestions": evaluation.suggestions,
-                    "quality": evaluation.quality,
-                },
-            )
-            self.crew._long_term_memory.save(long_term_memory)
-
-            for entity in evaluation.entities:
-                entity_memory = EntityMemoryItem(
-                    name=entity.name,
-                    type=entity.type,
-                    description=entity.description,
-                    relationships="\n".join([f"- {r}" for r in entity.relationships]),
-                )
-                self.crew._entity_memory.save(entity_memory)
-
     def _call(
         self,
         inputs: Dict[str, str],
@@ -246,12 +199,17 @@ class CrewAgentExecutor(AgentExecutor):
         # If the tool chosen is the finishing tool, then we end and return.
         if isinstance(output, AgentFinish):
             if self.should_ask_for_human_input:
+                human_feedback = self._ask_human_input(output.return_values["output"])
+
+                if self.crew and self.crew._train:
+                    self._handle_crew_training_output(output, human_feedback)
+
                 # Making sure we only ask for it once, so disabling for the next thought loop
                 self.should_ask_for_human_input = False
-                human_feedback = self._ask_human_input(output.return_values["output"])
                 action = AgentAction(
                     tool="Human Input", tool_input=human_feedback, log=output.log
                 )
+
                 yield AgentStep(
                     action=action,
                     observation=self._i18n.slice("human_feedback").format(
@@ -261,6 +219,9 @@ class CrewAgentExecutor(AgentExecutor):
                 return
 
             else:
+                if self.crew and self.crew._train:
+                    self._handle_crew_training_output(output)
+
                 yield output
                 return
 
@@ -300,8 +261,30 @@ class CrewAgentExecutor(AgentExecutor):
                     )
             yield AgentStep(action=agent_action, observation=observation)
 
-    def _ask_human_input(self, final_answer: dict) -> str:
-        """Get human input."""
-        return input(
-            self._i18n.slice("getting_input").format(final_answer=final_answer)
-        )
+    def _handle_crew_training_output(
+        self, output: AgentFinish, human_feedback: str | None = None
+    ) -> None:
+        """Function to handle the process of the training data."""
+        agent_id = str(self.crew_agent.id)
+
+        if (
+            CrewTrainingHandler(TRAINING_DATA_FILE).load()
+            and not self.should_ask_for_human_input
+        ):
+            training_data = CrewTrainingHandler(TRAINING_DATA_FILE).load()
+            if training_data.get(agent_id):
+                training_data[agent_id][self.crew._train_iteration][
+                    "improved_output"
+                ] = output.return_values["output"]
+                CrewTrainingHandler(TRAINING_DATA_FILE).save(training_data)
+
+        if self.should_ask_for_human_input and human_feedback is not None:
+            training_data = {
+                "initial_output": output.return_values["output"],
+                "human_feedback": human_feedback,
+                "agent": agent_id,
+                "agent_role": self.crew_agent.role,
+            }
+            CrewTrainingHandler(TRAINING_DATA_FILE).append(
+                self.crew._train_iteration, agent_id, training_data
+            )

src/crewai/cli/templates/main.py

@@ -15,8 +15,9 @@ def train():
     """
     Train the crew for a given number of iterations.
     """
+    inputs = {"topic": "AI LLMs"}
     try:
-        {{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]))
+        {{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]), inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while training the crew: {e}")

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.32.2" }
+crewai = { extras = ["tools"], version = "^0.35.8" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -1,7 +1,7 @@
 import asyncio
 import json
 import uuid
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Union, Tuple
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
@@ -18,6 +18,7 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
@@ -27,6 +28,13 @@ from crewai.task import Task
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
+from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
+from crewai.utilities.training_handler import CrewTrainingHandler
+
+try:
+    import agentops
+except ImportError:
+    agentops = None
 
 
 class Crew(BaseModel):
@@ -63,11 +71,13 @@ class Crew(BaseModel):
     _short_term_memory: Optional[InstanceOf[ShortTermMemory]] = PrivateAttr()
     _long_term_memory: Optional[InstanceOf[LongTermMemory]] = PrivateAttr()
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
+    _train: Optional[bool] = PrivateAttr(default=False)
+    _train_iteration: Optional[int] = PrivateAttr()
 
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
-    agents: List[Agent] = Field(default_factory=list)
+    agents: List[BaseAgent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
     verbose: Union[int, bool] = Field(default=0)
     memory: bool = Field(
@@ -89,7 +99,7 @@ class Crew(BaseModel):
     manager_llm: Optional[Any] = Field(
         description="Language model that will run the agent.", default=None
     )
-    manager_agent: Optional[Any] = Field(
+    manager_agent: Optional[BaseAgent] = Field(
         description="Custom agent that will be used as manager.", default=None
     )
     manager_callbacks: Optional[List[InstanceOf[BaseCallbackHandler]]] = Field(
@@ -214,6 +224,33 @@ class Crew(BaseModel):
                     agent.set_rpm_controller(self._rpm_controller)
         return self
 
+    @model_validator(mode="after")
+    def validate_tasks(self):
+        if self.process == Process.sequential:
+            for task in self.tasks:
+                if task.agent is None:
+                    raise PydanticCustomError(
+                        "missing_agent_in_task",
+                        f"Sequential process error: Agent is missing in the task with the following description: {task.description}",  # type: ignore Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
+                        {},
+                    )
+
+        return self
+
+    @model_validator(mode="after")
+    def check_tasks_in_hierarchical_process_not_async(self):
+        """Validates that the tasks in hierarchical process are not flagged with async_execution."""
+        if self.process == Process.hierarchical:
+            for task in self.tasks:
+                if task.async_execution:
+                    raise PydanticCustomError(
+                        "async_execution_in_hierarchical_process",
+                        "Hierarchical process error: Tasks cannot be flagged with async_execution.",
+                        {},
+                    )
+
+        return self
+
     def _setup_from_config(self):
         assert self.config is not None, "Config should not be None."
 
@@ -242,12 +279,41 @@ class Crew(BaseModel):
         del task_config["agent"]
         return Task(**task_config, agent=task_agent)
 
+    def _setup_for_training(self) -> None:
+        """Sets up the crew for training."""
+        self._train = True
+
+        for task in self.tasks:
+            task.human_input = True
+
+        for agent in self.agents:
+            agent.allow_delegation = False
+
+    def train(self, n_iterations: int, inputs: Optional[Dict[str, Any]] = {}) -> None:
+        """Trains the crew for a given number of iterations."""
+        self._setup_for_training()
+
+        for n_iteration in range(n_iterations):
+            self._train_iteration = n_iteration
+            self.kickoff(inputs=inputs)
+
+        training_data = CrewTrainingHandler("training_data.pkl").load()
+
+        for agent in self.agents:
+            result = TaskEvaluator(agent).evaluate_training_data(
+                training_data=training_data, agent_id=str(agent.id)
+            )
+
+            CrewTrainingHandler("trained_agents_data.pkl").save_trained_data(
+                agent_id=str(agent.role), trained_data=result.model_dump()
+            )
+
     def kickoff(
         self,
         inputs: Optional[Dict[str, Any]] = {},
     ) -> Union[str, Dict[str, Any]]:
         """Starts the crew to work on its assigned tasks."""
-        self._execution_span = self._telemetry.crew_execution_span(self)
+        self._execution_span = self._telemetry.crew_execution_span(self, inputs)
         # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
         self._interpolate_inputs(inputs)
         self._set_tasks_callbacks()
@@ -255,11 +321,17 @@ class Crew(BaseModel):
         i18n = I18N(prompt_file=self.prompt_file)
 
         for agent in self.agents:
+            # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
             agent.i18n = i18n
-            agent.crew = self
-
+            # 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:
                 agent.function_calling_llm = self.function_calling_llm
+
+            if agent.allow_code_execution:
+                agent.tools += agent.get_code_execution_tools()
+
             if not agent.step_callback:
                 agent.step_callback = self.step_callback
 
@@ -270,39 +342,46 @@ class Crew(BaseModel):
         if self.process == Process.sequential:
             result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            # type: ignore # Unpacking a string is disallowed
             result, manager_metrics = self._run_hierarchical_process()
-            # type: ignore # Cannot determine type of "manager_metrics"
             metrics.append(manager_metrics)
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
             )
+        metrics += [agent._token_process.get_summary() for agent in self.agents]
 
-        metrics = metrics + [
-            agent._token_process.get_summary() for agent in self.agents
-        ]
         self.usage_metrics = {
             key: sum([m[key] for m in metrics if m is not None]) for key in metrics[0]
         }
 
         return result
 
-    def kickoff_for_each(self, inputs: List[Dict[str, Any]]) -> List:
+    def kickoff_for_each(
+        self, inputs: List[Dict[str, Any]]
+    ) -> List[Union[str, Dict[str, Any]]]:
         """Executes the Crew's workflow for each input in the list and aggregates results."""
         results = []
 
+        # Initialize the parent crew's usage metrics
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
+
         for input_data in inputs:
             crew = self.copy()
 
-            for task in crew.tasks:
-                task.interpolate_inputs(input_data)
-            for agent in crew.agents:
-                agent.interpolate_inputs(input_data)
+            output = crew.kickoff(inputs=input_data)
+
+            if crew.usage_metrics:
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
 
-            output = crew.kickoff()
             results.append(output)
 
+        self.usage_metrics = total_usage_metrics
         return results
 
     async def kickoff_async(
@@ -312,36 +391,44 @@ class Crew(BaseModel):
         return await asyncio.to_thread(self.kickoff, inputs)
 
     async def kickoff_for_each_async(self, inputs: List[Dict]) -> List[Any]:
-        async def run_crew(input_data):
-            crew = self.copy()
+        crew_copies = [self.copy() for _ in inputs]
 
-            for task in crew.tasks:
-                task.interpolate_inputs(input_data)
-            for agent in crew.agents:
-                agent.interpolate_inputs(input_data)
+        async def run_crew(crew, input_data):
+            return await crew.kickoff_async(inputs=input_data)
 
-            return await crew.kickoff_async()
-
-        tasks = [asyncio.create_task(run_crew(input_data)) for input_data in inputs]
+        tasks = [
+            asyncio.create_task(run_crew(crew_copies[i], inputs[i]))
+            for i in range(len(inputs))
+        ]
 
         results = await asyncio.gather(*tasks)
 
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
+        for crew in crew_copies:
+            if crew.usage_metrics:
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += crew.usage_metrics.get(key, 0)
+
+        self.usage_metrics = total_usage_metrics
+
         return results
 
-    def train(self, n_iterations: int) -> None:
-        # TODO: Implement training
-        pass
-
-    def _run_sequential_process(self) -> Union[str, Dict[str, Any]]:
+    def _run_sequential_process(self) -> str:
         """Executes tasks sequentially and returns the final output."""
         task_output = ""
+
         for task in self.tasks:
             if task.agent.allow_delegation:  # type: ignore #  Item "None" of "Agent | None" has no attribute "allow_delegation"
                 agents_for_delegation = [
                     agent for agent in self.agents if agent != task.agent
                 ]
                 if len(self.agents) > 1 and len(agents_for_delegation) > 0:
-                    task.tools += AgentTools(agents=agents_for_delegation).tools()
+                    task.tools += task.agent.get_delegation_tools(agents_for_delegation)
 
             role = task.agent.role if task.agent is not None else "None"
             self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
@@ -353,7 +440,6 @@ class Crew(BaseModel):
                 self._file_handler.log(
                     agent=role, task=task.description, status="started"
                 )
-
             output = task.execute(context=task_output)
 
             if not task.async_execution:
@@ -366,21 +452,24 @@ class Crew(BaseModel):
                 self._file_handler.log(agent=role, task=task_output, status="completed")
 
         self._finish_execution(task_output)
-        # type: ignore # Item "None" of "Agent | None" has no attribute "_token_process"
-        token_usage = task.agent._token_process.get_summary()
+
+        token_usage = self.calculate_usage_metrics()
+
         # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
         return self._format_output(task_output, token_usage)
 
-    def _run_hierarchical_process(self) -> Union[str, Dict[str, Any]]:
+    def _run_hierarchical_process(
+        self,
+    ) -> Tuple[Union[str, Dict[str, Any]], Dict[str, Any]]:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
 
         i18n = I18N(prompt_file=self.prompt_file)
         if self.manager_agent is not None:
             self.manager_agent.allow_delegation = True
             manager = self.manager_agent
-            if len(manager.tools) > 0:
+            if manager.tools is not None and len(manager.tools) > 0:
                 raise Exception("Manager agent should not have tools")
-            manager.tools = AgentTools(agents=self.agents).tools()
+            manager.tools = self.manager_agent.get_delegation_tools(self.agents)
         else:
             manager = Agent(
                 role=i18n.retrieve("hierarchical_manager_agent", "role"),
@@ -388,10 +477,12 @@ class Crew(BaseModel):
                 backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
                 tools=AgentTools(agents=self.agents).tools(),
                 llm=self.manager_llm,
-                verbose=True,
+                verbose=self.verbose,
             )
+            self.manager_agent = manager
 
         task_output = ""
+
         for task in self.tasks:
             self._logger.log("debug", f"Working Agent: {manager.role}")
             self._logger.log("info", f"Starting Task: {task.description}")
@@ -401,23 +492,26 @@ class Crew(BaseModel):
                     agent=manager.role, task=task.description, status="started"
                 )
 
+            if task.agent:
+                manager.tools = task.agent.get_delegation_tools([task.agent])
+            else:
+                manager.tools = manager.get_delegation_tools(self.agents)
             task_output = task.execute(
                 agent=manager, context=task_output, tools=manager.tools
             )
 
             self._logger.log("debug", f"[{manager.role}] Task output: {task_output}")
-
             if self.output_log_file:
                 self._file_handler.log(
                     agent=manager.role, task=task_output, status="completed"
                 )
 
         self._finish_execution(task_output)
+
         # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
-        manager_token_usage = manager._token_process.get_summary()
-        return self._format_output(
-            task_output, manager_token_usage
-        ), manager_token_usage
+        token_usage = self.calculate_usage_metrics()
+
+        return self._format_output(task_output, token_usage), token_usage
 
     def copy(self):
         """Create a deep copy of the Crew."""
@@ -432,12 +526,13 @@ class Crew(BaseModel):
             "_short_term_memory",
             "_long_term_memory",
             "_entity_memory",
+            "_telemetry",
             "agents",
             "tasks",
         }
 
         cloned_agents = [agent.copy() for agent in self.agents]
-        cloned_tasks = [task.copy() for task in self.tasks]
+        cloned_tasks = [task.copy(cloned_agents) for task in self.tasks]
 
         copied_data = self.model_dump(exclude=exclude)
         copied_data = {k: v for k, v in copied_data.items() if v is not None}
@@ -465,15 +560,17 @@ class Crew(BaseModel):
             for task in self.tasks
         ]
         # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
-        [agent.interpolate_inputs(inputs) for agent in self.agents]
+        for agent in self.agents:
+            agent.interpolate_inputs(inputs)
 
     def _format_output(
-        self, output: str, token_usage: Optional[Dict[str, Any]]
+        self, output: str, token_usage: Optional[Dict[str, Any]] = None
     ) -> Union[str, Dict[str, Any]]:
         """
         Formats the output of the crew execution.
         If full_output is True, then returned data type will be a dictionary else returned outputs are string
         """
+
         if self.full_output:
             return {  # type: ignore # Incompatible return value type (got "dict[str, Sequence[str | TaskOutput | None]]", expected "str")
                 "final_output": output,
@@ -486,7 +583,34 @@ class Crew(BaseModel):
     def _finish_execution(self, output) -> None:
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
+        if agentops:
+            agentops.end_session(
+                end_state="Success",
+                end_state_reason="Finished Execution"
+            )
         self._telemetry.end_crew(self, output)
 
+    def calculate_usage_metrics(self) -> Dict[str, int]:
+        """Calculates and returns the usage metrics."""
+        total_usage_metrics = {
+            "total_tokens": 0,
+            "prompt_tokens": 0,
+            "completion_tokens": 0,
+            "successful_requests": 0,
+        }
+
+        for agent in self.agents:
+            if hasattr(agent, "_token_process"):
+                token_sum = agent._token_process.get_summary()
+                for key in total_usage_metrics:
+                    total_usage_metrics[key] += token_sum.get(key, 0)
+
+        if self.manager_agent and hasattr(self.manager_agent, "_token_process"):
+            token_sum = self.manager_agent._token_process.get_summary()
+            for key in total_usage_metrics:
+                total_usage_metrics[key] += token_sum.get(key, 0)
+
+        return total_usage_metrics
+
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/task.py

@@ -1,17 +1,21 @@
-from copy import deepcopy
 import os
 import re
 import threading
 import uuid
-from typing import Any, Dict, List, Optional, Type
+from copy import copy
+from typing import Any, Dict, List, Optional, Type, Union
 
 from langchain_openai import ChatOpenAI
+from opentelemetry.trace import Span
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
 
-from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.task_output import TaskOutput
-from crewai.utilities import I18N, Converter, ConverterError, Printer
+from crewai.telemetry.telemetry import Telemetry
+from crewai.utilities.converter import ConverterError
+from crewai.utilities.i18n import I18N
+from crewai.utilities.printer import Printer
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
@@ -42,7 +46,6 @@ class Task(BaseModel):
     tools_errors: int = 0
     delegations: int = 0
     i18n: I18N = I18N()
-    thread: Optional[threading.Thread] = None
     prompt_context: Optional[str] = None
     description: str = Field(description="Description of the actual task.")
     expected_output: str = Field(
@@ -55,7 +58,7 @@ class Task(BaseModel):
     callback: Optional[Any] = Field(
         description="Callback to be executed after the task is completed.", default=None
     )
-    agent: Optional[Agent] = Field(
+    agent: Optional[BaseAgent] = Field(
         description="Agent responsible for execution the task.", default=None
     )
     context: Optional[List["Task"]] = Field(
@@ -95,8 +98,11 @@ class Task(BaseModel):
         default=False,
     )
 
+    _telemetry: Telemetry
+    _execution_span: Span | None = None
     _original_description: str | None = None
     _original_expected_output: str | None = None
+    _thread: threading.Thread | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -118,6 +124,12 @@ class Task(BaseModel):
             return value[1:]
         return value
 
+    @model_validator(mode="after")
+    def set_private_attrs(self) -> "Task":
+        """Set private attributes."""
+        self._telemetry = Telemetry()
+        return self
+
     @model_validator(mode="after")
     def set_attributes_based_on_config(self) -> "Task":
         """Set attributes based on the agent configuration."""
@@ -145,9 +157,21 @@ class Task(BaseModel):
             )
         return self
 
+    def wait_for_completion(self) -> str | BaseModel:
+        """Wait for asynchronous task completion and return the output."""
+        assert self.async_execution, "Task is not set to be executed asynchronously."
+
+        if self._thread:
+            self._thread.join()
+            self._thread = None
+
+        assert self.output, "Task output is not set."
+
+        return self.output.exported_output
+
     def execute(  # type: ignore # Missing return statement
         self,
-        agent: Agent | None = None,
+        agent: BaseAgent | None = None,
         context: Optional[str] = None,
         tools: Optional[List[Any]] = None,
     ) -> str:
@@ -157,6 +181,8 @@ class Task(BaseModel):
             Output of the task.
         """
 
+        self._execution_span = self._telemetry.task_started(self)
+
         agent = agent or self.agent
         if not agent:
             raise Exception(
@@ -168,8 +194,8 @@ class Task(BaseModel):
             context = []
             for task in self.context:
                 if task.async_execution:
-                    task.thread.join()  # type: ignore # Item "None" of "Thread | None" has no attribute "join"
-                if task and task.output:
+                    task.wait_for_completion()
+                if task.output:
                     # type: ignore # Item "str" of "str | None" has no attribute "append"
                     context.append(task.output.raw_output)
             # type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
@@ -179,10 +205,10 @@ class Task(BaseModel):
         tools = tools or self.tools
 
         if self.async_execution:
-            self.thread = threading.Thread(
+            self._thread = threading.Thread(
                 target=self._execute, args=(agent, self, context, tools)
             )
-            self.thread.start()
+            self._thread.start()
         else:
             result = self._execute(
                 task=self,
@@ -192,15 +218,15 @@ class Task(BaseModel):
             )
             return result
 
-    def _execute(self, agent, task, context, tools):
+    def _execute(self, agent: "BaseAgent", task, context, tools):
         result = agent.execute_task(
             task=task,
             context=context,
             tools=tools,
         )
-
         exported_output = self._export_output(result)
 
+        # type: ignore # the responses are usually str but need to figure out a more elegant solution here
         self.output = TaskOutput(
             description=self.description,
             exported_output=exported_output,
@@ -211,6 +237,10 @@ class Task(BaseModel):
         if self.callback:
             self.callback(self.output)
 
+        if self._execution_span:
+            self._telemetry.task_ended(self._execution_span, self)
+            self._execution_span = None
+
         return exported_output
 
     def prompt(self) -> str:
@@ -246,7 +276,7 @@ class Task(BaseModel):
         """Increment the delegations counter."""
         self.delegations += 1
 
-    def copy(self):
+    def copy(self, agents: Optional[List["BaseAgent"]] = None) -> "Task":
         """Create a deep copy of the Task."""
         exclude = {
             "id",
@@ -261,8 +291,12 @@ class Task(BaseModel):
         cloned_context = (
             [task.copy() for task in self.context] if self.context else None
         )
-        cloned_agent = self.agent.copy() if self.agent else None
-        cloned_tools = deepcopy(self.tools) if self.tools else None
+
+        def get_agent_by_role(role: str) -> Union["BaseAgent", None]:
+            return next((agent for agent in agents if agent.role == role), None)
+
+        cloned_agent = get_agent_by_role(self.agent.role) if self.agent else None
+        cloned_tools = copy(self.tools) if self.tools else []
 
         copied_task = Task(
             **copied_data,
@@ -270,6 +304,7 @@ class Task(BaseModel):
             agent=cloned_agent,
             tools=cloned_tools,
         )
+
         return copied_task
 
     def _export_output(self, result: str) -> Any:
@@ -301,15 +336,14 @@ class Task(BaseModel):
                     except Exception:
                         pass
 
-            # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_llm"
-            llm = self.agent.function_calling_llm or self.agent.llm
-
+            # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
+            llm = getattr(self.agent, "function_calling_llm", None) or self.agent.llm
             if not self._is_gpt(llm):
                 # type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
                 model_schema = PydanticSchemaParser(model=model).get_schema()
                 instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
-            converter = Converter(
+            converter = self.agent.get_output_converter(
                 llm=llm, text=result, model=model, instructions=instructions
             )
 
@@ -328,7 +362,9 @@ class Task(BaseModel):
         if self.output_file:
             content = (
                 # type: ignore # "str" has no attribute "json"
-                exported_result if not self.output_pydantic else exported_result.json()
+                exported_result
+                if not self.output_pydantic
+                else exported_result.model_dump_json()
             )
             self._save_file(content)
 

src/crewai/telemetry/telemetry.py

@@ -1,8 +1,10 @@
+from __future__ import annotations
+
 import asyncio
 import json
 import os
 import platform
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 import pkg_resources
 from opentelemetry import trace
@@ -10,7 +12,11 @@ from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExport
 from opentelemetry.sdk.resources import SERVICE_NAME, Resource
 from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
-from opentelemetry.trace import Status, StatusCode
+from opentelemetry.trace import Span, Status, StatusCode
+
+if TYPE_CHECKING:
+    from crewai.crew import Crew
+    from crewai.task import Task
 
 
 class Telemetry:
@@ -88,9 +94,6 @@ class Telemetry:
                 self._add_attribute(span, "python_version", platform.python_version())
                 self._add_attribute(span, "crew_id", str(crew.id))
                 self._add_attribute(span, "crew_process", crew.process)
-                self._add_attribute(
-                    span, "crew_language", crew.prompt_file if crew.i18n else "None"
-                )
                 self._add_attribute(span, "crew_memory", crew.memory)
                 self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
                 self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
@@ -102,6 +105,8 @@ class Telemetry:
                             {
                                 "id": str(agent.id),
                                 "role": agent.role,
+                                "goal": agent.goal,
+                                "backstory": agent.backstory,
                                 "verbose?": agent.verbose,
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
@@ -123,8 +128,16 @@ class Telemetry:
                         [
                             {
                                 "id": str(task.id),
+                                "description": task.description,
+                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
+                                "human_input?": task.human_input,
                                 "agent_role": task.agent.role if task.agent else "None",
+                                "context": (
+                                    [task.description for task in task.context]
+                                    if task.context
+                                    else None
+                                ),
                                 "tools_names": [
                                     tool.name.casefold() for tool in task.tools
                                 ],
@@ -143,6 +156,38 @@ class Telemetry:
             except Exception:
                 pass
 
+    def task_started(self, task: Task) -> Span | None:
+        """Records task started in a crew."""
+        if self.ready:
+            try:
+                tracer = trace.get_tracer("crewai.telemetry")
+                span = tracer.start_span("Task Execution")
+
+                self._add_attribute(span, "task_id", str(task.id))
+                self._add_attribute(span, "formatted_description", task.description)
+                self._add_attribute(
+                    span, "formatted_expected_output", task.expected_output
+                )
+
+                return span
+            except Exception:
+                pass
+
+        return None
+
+    def task_ended(self, span: Span, task: Task):
+        """Records task execution in a crew."""
+        if self.ready:
+            try:
+                self._add_attribute(
+                    span, "output", task.output.raw_output if task.output else ""
+                )
+
+                span.set_status(Status(StatusCode.OK))
+                span.end()
+            except Exception:
+                pass
+
     def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
         """Records the repeated usage 'error' of a tool by an agent."""
         if self.ready:
@@ -207,7 +252,7 @@ class Telemetry:
             except Exception:
                 pass
 
-    def crew_execution_span(self, crew):
+    def crew_execution_span(self, crew: Crew, inputs: dict[str, Any] | None):
         """Records the complete execution of a crew.
         This is only collected if the user has opted-in to share the crew.
         """
@@ -221,6 +266,7 @@ class Telemetry:
                     pkg_resources.get_distribution("crewai").version,
                 )
                 self._add_attribute(span, "crew_id", str(crew.id))
+                self._add_attribute(span, "inputs", json.dumps(inputs))
                 self._add_attribute(
                     span,
                     "crew_agents",
@@ -238,7 +284,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools
+                                    tool.name.casefold() for tool in agent.tools or []
                                 ],
                             }
                             for agent in crew.agents
@@ -253,16 +299,17 @@ class Telemetry:
                             {
                                 "id": str(task.id),
                                 "description": task.description,
+                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
-                                "output": task.expected_output,
+                                "human_input?": task.human_input,
                                 "agent_role": task.agent.role if task.agent else "None",
                                 "context": (
                                     [task.description for task in task.context]
                                     if task.context
-                                    else "None"
+                                    else None
                                 ),
                                 "tools_names": [
-                                    tool.name.casefold() for tool in task.tools
+                                    tool.name.casefold() for tool in task.tools or []
                                 ],
                             }
                             for task in crew.tasks

src/crewai/tools/agent_tools.py

@@ -1,106 +1,25 @@
-from typing import List, Union
-
 from langchain.tools import StructuredTool
-from pydantic import BaseModel, Field
 
-from crewai.agent import Agent
-from crewai.task import Task
-from crewai.utilities import I18N
+from crewai.agents.agent_builder.utilities.base_agent_tool import BaseAgentTools
 
 
-class AgentTools(BaseModel):
+class AgentTools(BaseAgentTools):
     """Default tools around agent delegation"""
 
-    agents: List[Agent] = Field(description="List of agents in this crew.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-
     def tools(self):
+        coworkers = f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
         tools = [
             StructuredTool.from_function(
                 func=self.delegate_work,
                 name="Delegate work to coworker",
                 description=self.i18n.tools("delegate_work").format(
-                    coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
+                    coworkers=coworkers
                 ),
             ),
             StructuredTool.from_function(
                 func=self.ask_question,
                 name="Ask question to coworker",
-                description=self.i18n.tools("ask_question").format(
-                    coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
-                ),
+                description=self.i18n.tools("ask_question").format(coworkers=coworkers),
             ),
         ]
         return tools
-
-    def delegate_work(
-        self,
-        task: str,
-        context: Union[str, None] = None,
-        coworker: Union[str, None] = None,
-        **kwargs,
-    ):
-        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
-        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
-        if coworker:
-            is_list = coworker.startswith("[") and coworker.endswith("]")
-            if is_list:
-                coworker = coworker[1:-1].split(",")[0]
-        return self._execute(coworker, task, context)
-
-    def ask_question(
-        self,
-        question: str,
-        context: Union[str, None] = None,
-        coworker: Union[str, None] = None,
-        **kwargs,
-    ):
-        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
-        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
-        if coworker:
-            is_list = coworker.startswith("[") and coworker.endswith("]")
-            if is_list:
-                coworker = coworker[1:-1].split(",")[0]
-        return self._execute(coworker, question, context)
-
-    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
-        """Execute the command."""
-        try:
-            if agent is None:
-                agent = ""
-
-            # It is important to remove the quotes from the agent name.
-            # The reason we have to do this is because less-powerful LLM's
-            # have difficulty producing valid JSON.
-            # As a result, we end up with invalid JSON that is truncated like this:
-            # {"task": "....", "coworker": "....
-            # when it should look like this:
-            # {"task": "....", "coworker": "...."}
-            agent_name = agent.casefold().replace('"', "").replace("\n", "")
-
-            agent = [
-                available_agent
-                for available_agent in self.agents
-                if available_agent.role.casefold().replace("\n", "") == agent_name
-            ]
-        except Exception as _:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        if not agent:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        agent = agent[0]
-        task = Task(
-            description=task,
-            agent=agent,
-            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
-        )
-        return agent.execute_task(task, context)

src/crewai/tools/tool_usage.py

@@ -11,6 +11,12 @@ from crewai.telemetry import Telemetry
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.utilities import I18N, Converter, ConverterError, Printer
 
+agentops = None
+try:
+    import agentops
+except ImportError:
+    pass
+
 OPENAI_BIGGER_MODELS = ["gpt-4"]
 
 
@@ -98,7 +104,8 @@ class ToolUsage:
         tool_string: str,
         tool: BaseTool,
         calling: Union[ToolCalling, InstructorToolCalling],
-    ) -> None:  # TODO: Fix this return type
+    ) -> str:  # TODO: Fix this return type
+        tool_event = agentops.ToolEvent(name=calling.tool_name) if agentops else None
         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(
@@ -123,7 +130,7 @@ class ToolUsage:
                 tool=calling.tool_name, input=calling.arguments
             )
 
-        if not result:
+        if result is None:  #! finecwg: if not result --> if result is None
             try:
                 if calling.tool_name in [
                     "Delegate work to coworker",
@@ -164,6 +171,10 @@ 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:
@@ -184,6 +195,8 @@ class ToolUsage:
                 )
 
         self._printer.print(content=f"\n\n{result}\n", color="purple")
+        if agentops:
+            agentops.record(tool_event)
         self._telemetry.tool_usage(
             llm=self.function_calling_llm,
             tool_name=tool.name,
@@ -290,7 +303,7 @@ class ToolUsage:
               Example:
               {"tool_name": "tool name", "arguments": {"arg_name1": "value", "arg_name2": 2}}""",
                     ),
-                    max_attemps=1,
+                    max_attempts=1,
                 )
                 calling = converter.to_pydantic()
 

src/crewai/translations/en.json

@@ -17,7 +17,7 @@
     "task_with_context": "{task}\n\nThis is the context you're working with:\n{context}",
     "expected_output": "\nThis is the expect criteria for your final answer: {expected_output} \n you MUST return the actual complete content as the final answer, not a summary.",
     "human_feedback": "You got human feedback on your work, re-avaluate it and give a new Final Answer when ready.\n {human_feedback}",
-    "getting_input": "This is the agent final answer: {final_answer}\nPlease provide a feedback: "
+    "getting_input": "This is the agent's final answer: {final_answer}\nPlease provide feedback: "
   },
   "errors": {
     "force_final_answer": "Tool won't be use because it's time to give your final answer. Don't use tools and just your absolute BEST Final answer.",

src/crewai/utilities/__init__.py

@@ -1,9 +1,22 @@
 from .converter import Converter, ConverterError
+from .file_handler import FileHandler
 from .i18n import I18N
 from .instructor import Instructor
 from .logger import Logger
+from .parser import YamlParser
 from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
-from .fileHandler import FileHandler
-from .parser import YamlParser
+
+__all__ = [
+    "Converter",
+    "ConverterError",
+    "FileHandler",
+    "I18N",
+    "Instructor",
+    "Logger",
+    "Printer",
+    "Prompts",
+    "RPMController",
+    "YamlParser",
+]

src/crewai/utilities/constants.py

@@ -0,0 +1,2 @@
+TRAINING_DATA_FILE = "training_data.pkl"
+TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"

src/crewai/utilities/converter.py

@@ -1,9 +1,11 @@
 import json
-from typing import Any, Optional
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
-from pydantic import BaseModel, Field, PrivateAttr, model_validator
+from pydantic import model_validator
+from crewai.agents.agent_builder.utilities.base_output_converter_base import (
+    OutputConverter,
+)
 
 
 class ConverterError(Exception):
@@ -14,19 +16,9 @@ class ConverterError(Exception):
         self.message = message
 
 
-class Converter(BaseModel):
+class Converter(OutputConverter):
     """Class that converts text into either pydantic or json."""
 
-    _is_gpt: bool = PrivateAttr(default=True)
-    text: str = Field(description="Text to be converted.")
-    llm: Any = Field(description="The language model to be used to convert the text.")
-    model: Any = Field(description="The model to be used to convert the text.")
-    instructions: str = Field(description="Conversion instructions to the LLM.")
-    max_attemps: Optional[int] = Field(
-        description="Max number of attemps to try to get the output formated.",
-        default=3,
-    )
-
     @model_validator(mode="after")
     def check_llm_provider(self):
         if not self._is_gpt(self.llm):
@@ -40,7 +32,7 @@ class Converter(BaseModel):
             else:
                 return self._create_chain().invoke({})
         except Exception as e:
-            if current_attempt < self.max_attemps:
+            if current_attempt < self.max_attempts:
                 return self.to_pydantic(current_attempt + 1)
             return ConverterError(
                 f"Failed to convert text into a pydantic model due to the following error: {e}"
@@ -54,7 +46,7 @@ class Converter(BaseModel):
             else:
                 return json.dumps(self._create_chain().invoke({}).model_dump())
         except Exception:
-            if current_attempt < self.max_attemps:
+            if current_attempt < self.max_attempts:
                 return self.to_json(current_attempt + 1)
             return ConverterError("Failed to convert text into JSON.")
 
@@ -64,7 +56,7 @@ class Converter(BaseModel):
 
         inst = Instructor(
             llm=self.llm,
-            max_attemps=self.max_attemps,
+            max_attempts=self.max_attempts,
             model=self.model,
             content=self.text,
             instructions=self.instructions,

src/crewai/utilities/evaluators/task_evaluator.py

@@ -6,6 +6,17 @@ from pydantic import BaseModel, Field
 from crewai.utilities import Converter
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
+agentops = None
+try:
+    from agentops import track_agent
+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.")
@@ -26,6 +37,19 @@ class TaskEvaluation(BaseModel):
     )
 
 
+class TrainingTaskEvaluation(BaseModel):
+    suggestions: List[str] = Field(
+        description="Based on the Human Feedbacks and the comparison between Initial Outputs and Improved outputs provide action items based on human_feedback for future tasks."
+    )
+    quality: float = Field(
+        description="A score from 0 to 10 evaluating on completion, quality, and overall performance from the improved output to the initial output based on the human feedback."
+    )
+    final_summary: str = Field(
+        description="A step by step action items to improve the next Agent based on the human-feedback and improved output."
+    )
+
+
+@track_agent(name="Task Evaluator")
 class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm
@@ -59,3 +83,49 @@ class TaskEvaluator:
 
     def _is_gpt(self, llm) -> bool:
         return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
+
+    def evaluate_training_data(
+        self, training_data: dict, agent_id: str
+    ) -> TrainingTaskEvaluation:
+        """
+        Evaluate the training data based on the llm output, human feedback, and improved output.
+
+        Parameters:
+            - training_data (dict): The training data to be evaluated.
+            - agent_id (str): The ID of the agent.
+        """
+
+        output_training_data = training_data[agent_id]
+
+        final_aggregated_data = ""
+        for _, data in output_training_data.items():
+            final_aggregated_data += (
+                f"Initial Output:\n{data['initial_output']}\n\n"
+                f"Human Feedback:\n{data['human_feedback']}\n\n"
+                f"Improved Output:\n{data['improved_output']}\n\n"
+            )
+
+        evaluation_query = (
+            "Assess the quality of the training data based on the llm output, human feedback , and llm output improved result.\n\n"
+            f"{final_aggregated_data}"
+            "Please provide:\n"
+            "- Based on the Human Feedbacks and the comparison between Initial Outputs and Improved outputs provide action items based on human_feedback for future tasks\n"
+            "- A score from 0 to 10 evaluating on completion, quality, and overall performance from the improved output to the initial output based on the human feedback\n"
+        )
+        instructions = "I'm gonna convert this raw text into valid JSON."
+
+        if not self._is_gpt(self.llm):
+            model_schema = PydanticSchemaParser(
+                model=TrainingTaskEvaluation
+            ).get_schema()
+            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
+
+        converter = Converter(
+            llm=self.llm,
+            text=evaluation_query,
+            model=TrainingTaskEvaluation,
+            instructions=instructions,
+        )
+
+        pydantic_result = converter.to_pydantic()
+        return pydantic_result

src/crewai/utilities/fileHandler.py

@@ -1,20 +0,0 @@
-import os
-from datetime import datetime
-
-
-class FileHandler:
-    """take care of file operations, currently it only logs messages to a file"""
-
-    def __init__(self, file_path):
-        if isinstance(file_path, bool):
-            self._path = os.path.join(os.curdir, "logs.txt")
-        elif isinstance(file_path, str):
-            self._path = file_path
-        else:
-            raise ValueError("file_path must be either a boolean or a string.")
-
-    def log(self, **kwargs):
-        now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-        message = f"{now}: ".join([f"{key}={value}" for key, value in kwargs.items()])
-        with open(self._path, "a", encoding = 'utf-8') as file:
-            file.write(message + "\n")

src/crewai/utilities/file_handler.py

@@ -0,0 +1,69 @@
+import os
+import pickle
+from datetime import datetime
+
+
+class FileHandler:
+    """take care of file operations, currently it only logs messages to a file"""
+
+    def __init__(self, file_path):
+        if isinstance(file_path, bool):
+            self._path = os.path.join(os.curdir, "logs.txt")
+        elif isinstance(file_path, str):
+            self._path = file_path
+        else:
+            raise ValueError("file_path must be either a boolean or a string.")
+
+    def log(self, **kwargs):
+        now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        message = f"{now}: ".join([f"{key}={value}" for key, value in kwargs.items()])
+        with open(self._path, "a", encoding="utf-8") as file:
+            file.write(message + "\n")
+
+
+class PickleHandler:
+    def __init__(self, file_name: str) -> None:
+        """
+        Initialize the PickleHandler with the name of the file where data will be stored.
+        The file will be saved in the current directory.
+
+        Parameters:
+        - file_name (str): The name of the file for saving and loading data.
+        """
+        self.file_path = os.path.join(os.getcwd(), file_name)
+        self._initialize_file()
+
+    def _initialize_file(self) -> None:
+        """
+        Initialize the file with an empty dictionary if it does not exist or is empty.
+        """
+        if not os.path.exists(self.file_path) or os.path.getsize(self.file_path) == 0:
+            self.save({})  # Save an empty dictionary to initialize the file
+
+    def save(self, data) -> None:
+        """
+        Save the data to the specified file using pickle.
+
+        Parameters:
+        - data (object): The data to be saved.
+        """
+        with open(self.file_path, "wb") as file:
+            pickle.dump(data, file)
+
+    def load(self) -> dict:
+        """
+        Load the data from the specified file using pickle.
+
+        Returns:
+        - dict: The data loaded from the file.
+        """
+        if not os.path.exists(self.file_path) or os.path.getsize(self.file_path) == 0:
+            return {}  # Return an empty dictionary if the file does not exist or is empty
+
+        with open(self.file_path, "rb") as file:
+            try:
+                return pickle.load(file)
+            except EOFError:
+                return {}  # Return an empty dictionary if the file is empty or corrupted
+            except Exception:
+                raise  # Raise any other exceptions that occur during loading

src/crewai/utilities/token_counter_callback.py

@@ -4,46 +4,22 @@ import tiktoken
 from langchain.callbacks.base import BaseCallbackHandler
 from langchain.schema import LLMResult
 
-
-class TokenProcess:
-    total_tokens: int = 0
-    prompt_tokens: int = 0
-    completion_tokens: int = 0
-    successful_requests: int = 0
-
-    def sum_prompt_tokens(self, tokens: int):
-        self.prompt_tokens = self.prompt_tokens + tokens
-        self.total_tokens = self.total_tokens + tokens
-
-    def sum_completion_tokens(self, tokens: int):
-        self.completion_tokens = self.completion_tokens + tokens
-        self.total_tokens = self.total_tokens + tokens
-
-    def sum_successful_requests(self, requests: int):
-        self.successful_requests = self.successful_requests + requests
-
-    def get_summary(self) -> Dict[str, Any]:
-        return {
-            "total_tokens": self.total_tokens,
-            "prompt_tokens": self.prompt_tokens,
-            "completion_tokens": self.completion_tokens,
-            "successful_requests": self.successful_requests,
-        }
+from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
 
 
 class TokenCalcHandler(BaseCallbackHandler):
-    model: str = ""
+    model_name: str = ""
     token_cost_process: TokenProcess
 
-    def __init__(self, model, token_cost_process):
-        self.model = model
+    def __init__(self, model_name, token_cost_process):
+        self.model_name = model_name
         self.token_cost_process = token_cost_process
 
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
         try:
-            encoding = tiktoken.encoding_for_model(self.model)
+            encoding = tiktoken.encoding_for_model(self.model_name)
         except KeyError:
             encoding = tiktoken.get_encoding("cl100k_base")
 

src/crewai/utilities/training_handler.py

@@ -0,0 +1,31 @@
+from crewai.utilities.file_handler import PickleHandler
+
+
+class CrewTrainingHandler(PickleHandler):
+    def save_trained_data(self, agent_id: str, trained_data: dict) -> None:
+        """
+        Save the trained data for a specific agent.
+
+        Parameters:
+        - agent_id (str): The ID of the agent.
+        - trained_data (dict): The trained data to be saved.
+        """
+        data = self.load()
+        data[agent_id] = trained_data
+        self.save(data)
+
+    def append(self, train_iteration: int, agent_id: str, new_data) -> None:
+        """
+        Append new data to the existing pickle file.
+
+        Parameters:
+        - new_data (object): The new data to be appended.
+        """
+        data = self.load()
+
+        if agent_id in data:
+            data[agent_id][train_iteration] = new_data
+        else:
+            data[agent_id] = {train_iteration: new_data}
+
+        self.save(data)

tests/agent_test.py

@@ -1,5 +1,6 @@
 """Test Agent creation and execution basic functionality."""
 
+from unittest import mock
 from unittest.mock import patch
 
 import pytest
@@ -732,7 +733,7 @@ def test_agent_llm_uses_token_calc_handler_with_llm_has_model_name():
 
     assert len(agent1.llm.callbacks) == 1
     assert agent1.llm.callbacks[0].__class__.__name__ == "TokenCalcHandler"
-    assert agent1.llm.callbacks[0].model == "gpt-4o"
+    assert agent1.llm.callbacks[0].model_name == "gpt-4o"
     assert (
         agent1.llm.callbacks[0].token_cost_process.__class__.__name__ == "TokenProcess"
     )
@@ -842,3 +843,54 @@ Thought:
 
 """
     )
+
+
+@patch("crewai.agent.CrewTrainingHandler")
+def test_agent_training_handler(crew_training_handler):
+    task_prompt = "What is 1 + 1?"
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        verbose=True,
+    )
+    crew_training_handler().load.return_value = {
+        f"{str(agent.id)}": {"0": {"human_feedback": "good"}}
+    }
+
+    result = agent._training_handler(task_prompt=task_prompt)
+
+    assert result == "What is 1 + 1?You MUST follow these feedbacks: \n good"
+
+    crew_training_handler.assert_has_calls(
+        [mock.call(), mock.call("training_data.pkl"), mock.call().load()]
+    )
+
+
+@patch("crewai.agent.CrewTrainingHandler")
+def test_agent_use_trained_data(crew_training_handler):
+    task_prompt = "What is 1 + 1?"
+    agent = Agent(
+        role="researcher",
+        goal="test goal",
+        backstory="test backstory",
+        verbose=True,
+    )
+    crew_training_handler().load.return_value = {
+        agent.role: {
+            "suggestions": [
+                "The result of the math operatio must be right.",
+                "Result must be better than 1.",
+            ]
+        }
+    }
+
+    result = agent._use_trained_data(task_prompt=task_prompt)
+
+    assert (
+        result == "What is 1 + 1?You MUST follow these feedbacks: \n "
+        "The result of the math operatio must be right.\n - Result must be better than 1."
+    )
+    crew_training_handler.assert_has_calls(
+        [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
+    )

tests/cassettes/test_crew_async_kickoff_for_each_full_ouput.yaml

@@ -0,0 +1,585 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are dog Researcher. You have a lot of experience
+      with dog.\nYour personal goal is: Express hot takes on dog.To 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: my best complete final answer to the task.\nYour
+      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!\nCurrent
+      Task: Give me an analysis around dog.\n\nThis is the expect criteria for your
+      final answer: 1 bullet point about dog that''s under 15 words. \n you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '951'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.34.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.34.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Dogs"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        incredibly"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        loyal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        creatures"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        make"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        excellent"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        companions"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGly5pkMQFPEoB5vefeCguR5lZg5","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 89c8b85b1adac009-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 01 Jul 2024 19:14:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=EKr3m8uVLAQymRGlOvcrrYSniXqH.I6nlooc.HtxR58-1719861278-1.0.1.1-ShT9PH0Sv.qvbXjw_BhtziPUPaOIFBxlzXEIk_MXnfJ5PxggSkkaN25IKMZglSd3N2X.U2pWvFwywNQXiXlRnQ;
+        path=/; expires=Mon, 01-Jul-24 19:44:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=NdoJw5c7TqrbsjEH.ABD06WhM3d1BUh2BfsxOwuclSY-1719861278155-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '110'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '16000000'
+      x-ratelimit-remaining-requests:
+      - '9998'
+      x-ratelimit-remaining-tokens:
+      - '15999741'
+      x-ratelimit-reset-requests:
+      - 11ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_266fff38f6e0a997187154e25d6615e8
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are apple Researcher. You have a lot of
+      experience with apple.\nYour personal goal is: Express hot takes on apple.To
+      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: my best complete final answer to
+      the task.\nYour 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!\nCurrent Task: Give me an analysis around apple.\n\nThis is the expect criteria
+      for your final answer: 1 bullet point about apple that''s under 15 words. \n
+      you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '961'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.34.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.34.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Apple''s"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        ecosystem"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        fosters"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        seamless"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        integration"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        but"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        limit"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        user"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        flexibility"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        choice"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyTsxWJNVf7aQLLtKEYroHrIXk","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 89c8b85b19501351-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 01 Jul 2024 19:14:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=R2LwekshY1B9Z5rF_RyOforiY4rLQreEXx6gOzhnZCI-1719861278-1.0.1.1-y_WShmsjsavKJEOt9Yw8nwjv05e4WdVaZGu8pYcS4z0wF9heVD.0C9W2aQodYxaWIQvkXiPm7y93ma7WCxUdBQ;
+        path=/; expires=Mon, 01-Jul-24 19:44:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=TLDVkWpa_eP62.b4QTrhowr4J_DsXwMZ2nGDaWD4ebU-1719861278245-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '99'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '16000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '15999780'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_39f52bd8b06ab4ada2c16853345eb6dc
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are cat Researcher. You have a lot of experience
+      with cat.\nYour personal goal is: Express hot takes on cat.To 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: my best complete final answer to the task.\nYour
+      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!\nCurrent
+      Task: Give me an analysis around cat.\n\nThis is the expect criteria for your
+      final answer: 1 bullet point about cat that''s under 15 words. \n you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '951'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.34.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.34.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Cats"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        natural"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        hunters"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        with"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        unique"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        personalities"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        strong"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        territorial"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        instincts"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGlyAPhJWtbWCzqHs7gAID5K4T0X","object":"chat.completion.chunk","created":1719861278,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 89c8b85b1fde4546-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 01 Jul 2024 19:14:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=KdRY51WYOZSedMQIfG_vPmrPdO67._RkSjV0nq.khUk-1719861278-1.0.1.1-r0uJtNVxaGm2OCkQliG.tsX3vekPCDQb2IET3ywu41Igu1Qfz01rhz_WlvKIllsZlXIyd6rvHT7NxLo.UOtD7Q;
+        path=/; expires=Mon, 01-Jul-24 19:44:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Qqu1FBant56uM9Al0JmDl7QMk9cRcojzFUt8volvWPo-1719861278308-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      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
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '16000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '15999783'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_a0c6e5796af340d6720b9cfd55df703e
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_crew_full_ouput.yaml

@@ -1,668 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
-      personal goal is: test goalTo 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: my best complete final answer to the task.\nYour 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!\n\nThought: \n\nCurrent Task:
-      just say hi!\n\nThis is the expect criteria for your final answer: your greeting
-      \n you 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: \n"}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, br
-      connection:
-      - keep-alive
-      content-length:
-      - '868'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: 'data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        need"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        greet"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        most"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        complete"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        best"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        way"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        possible"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        hope"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        this"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        message"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        finds"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        you"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        well"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        It"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''s"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        pleasure"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        connect"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        with"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        you"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWQAjLm65fTweOAMj1MPNv86j41","object":"chat.completion.chunk","created":1709396946,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
-
-
-        data: [DONE]
-
-
-        '
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85e2c3813dc74b3a-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream
-      Date:
-      - Sat, 02 Mar 2024 16:29:06 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=JbHUHi.PhJbn_QGk.tB4mt46gFfgOY5E6S9FpR38AzY-1709396946-1.0.1.1-Yt6Pwz26qOyGpN2UGMk.iiHV7sfrPJ2nDBpwFPJ2kXjGygJLhrYHSJvnrLL6ufjynJrhtybfDFrpo4hu1MStLQ;
-        path=/; expires=Sat, 02-Mar-24 16:59:06 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=igGYT0nylGjk3GqE593NfxDZQhEjSpI4EBIKLRdO_Es-1709396946964-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '294'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299804'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 39ms
-      x-request-id:
-      - req_b7545a68924d8c2dde81405fd15da550
-    status:
-      code: 200
-      message: OK
-- request:
-    body: !!binary |
-      Cp4JCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS9QgKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRLeCAoQ7pSFzdiU1zWikuY84UhC0RII7TdRvEn9w/gqDENyZXcgQ3JlYXRlZDABOWjw
-      2CJ3/7gXQeBT2iJ3/7gXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMTYuM0oaCg5weXRob25fdmVy
-      c2lvbhIICgYzLjExLjdKMQoHY3Jld19pZBImCiQxOWIwYzkxMC05YzcwLTQyNzItOWMxNy00NWY5
-      ZjE4Nzk0ODNKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKFQoNY3Jld19sYW5ndWFnZRIE
-      CgJlbkoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAJKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRz
-      EgIYAUrLAgoLY3Jld19hZ2VudHMSuwIKuAJbeyJpZCI6ICJhOTkyYzA2Yi00MTI2LTRhNDMtYjg0
-      MS1hMzBlY2VmOGNjZGQiLCAicm9sZSI6ICJ0ZXN0IHJvbGUiLCAibWVtb3J5X2VuYWJsZWQ/Ijog
-      ZmFsc2UsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDE1LCAibWF4X3JwbSI6IG51bGws
-      ICJpMThuIjogImVuIiwgImxsbSI6ICJ7XCJuYW1lXCI6IG51bGwsIFwibW9kZWxfbmFtZVwiOiBc
-      ImdwdC00XCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5BSVwi
-      fSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJ0b29sc19uYW1lcyI6IFtdfV1KhAIK
-      CmNyZXdfdGFza3MS9QEK8gFbeyJpZCI6ICI4YjBlMjBhZC1kZDk4LTRkYzktOTI3ZC03ODc3M2U4
-      MTExODciLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJv
-      bGUiLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsiaWQiOiAiMzQzODkyYTUtNjZmZC00MzI5LThhY2Et
-      NTYxNjUxMjM2ZjNiIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAi
-      dGVzdCByb2xlIiwgInRvb2xzX25hbWVzIjogW119XUooCghwbGF0Zm9ybRIcChptYWNPUy0xNC4z
-      LWFybTY0LWFybS02NGJpdEocChBwbGF0Zm9ybV9yZWxlYXNlEggKBjIzLjMuMEobCg9wbGF0Zm9y
-      bV9zeXN0ZW0SCAoGRGFyd2luSnsKEHBsYXRmb3JtX3ZlcnNpb24SZwplRGFyd2luIEtlcm5lbCBW
-      ZXJzaW9uIDIzLjMuMDogV2VkIERlYyAyMCAyMTozMDo1OSBQU1QgMjAyMzsgcm9vdDp4bnUtMTAw
-      MDIuODEuNX43L1JFTEVBU0VfQVJNNjRfVDYwMzBKCgoEY3B1cxICGAx6AhgB
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, br
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '1185'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.23.0
-    method: POST
-    uri: http://telemetry.crewai.com:4318/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Sat, 02 Mar 2024 16:29:10 GMT
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
-      personal goal is: test goalTo 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: my best complete final answer to the task.\nYour 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!\n\nThought: \n\nCurrent Task:
-      just say hello!\n\nThis is the expect criteria for your final answer: your greeting
-      \n you MUST return the actual complete content as the final answer, not a summary.\n\nThis
-      is the context you''re working with:\nHello! I hope this message finds you well.
-      It''s a pleasure to connect with you.\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: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
-      "stream": true, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, br
-      connection:
-      - keep-alive
-      content-length:
-      - '996'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=JbHUHi.PhJbn_QGk.tB4mt46gFfgOY5E6S9FpR38AzY-1709396946-1.0.1.1-Yt6Pwz26qOyGpN2UGMk.iiHV7sfrPJ2nDBpwFPJ2kXjGygJLhrYHSJvnrLL6ufjynJrhtybfDFrpo4hu1MStLQ;
-        _cfuvid=igGYT0nylGjk3GqE593NfxDZQhEjSpI4EBIKLRdO_Es-1709396946964-0.0.1.1-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: 'data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        must"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        greet"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        recipient"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        most"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        pleasant"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        complete"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        way"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        possible"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        ensuring"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        convey"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        warmth"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        sincerity"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        while"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        also"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        mir"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"roring"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        tone"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        content"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        their"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        original"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        message"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        \n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        It"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        is"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        delight"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        receive"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        your"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        message"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        trust"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        this"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        response"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        finds"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        you"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        good"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        spirits"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        It"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''s"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        indeed"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        pleasure"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        connect"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        with"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        you"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        too"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMWS0X1Ns9ODqSffsOVkE5A8lKKU","object":"chat.completion.chunk","created":1709396948,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
-
-
-        data: [DONE]
-
-
-        '
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85e2c38f395e4b3a-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream
-      Date:
-      - Sat, 02 Mar 2024 16:29:08 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '354'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299773'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 45ms
-      x-request-id:
-      - req_b5fd5a293909548e8b3c57ba4425dd08
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_crew_full_output.yaml

@@ -0,0 +1,314 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo 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:
+      my best complete final answer to the task.\nYour 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!\nCurrent Task: just say hi!\n\nThis is
+      the expect criteria for your final answer: your greeting \n you 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:\n", "role": "user"}], "model": "gpt-4o",
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '853'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.34.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.34.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvixvu2sSTjML4oN3fsoMeTHbew","object":"chat.completion.chunk","created":1719861882,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 89c8c71ccad81823-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 01 Jul 2024 19:24:42 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=uU.2MR0L4Mv3xs4DzFlWOQLVId1dJXQBlWffhr9mqxU-1719861882-1.0.1.1-JSKN2_O9iYj8QCZjy0IGiunZxvXimz5Kzv5wQJedVua5E6WIl1UvP.wguXbK0cds7ayJReYnR8v8oAN2rmtnNQ;
+        path=/; expires=Mon, 01-Jul-24 19:54:42 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=yc5Q7WKbO5zoiGNQx86HpHNM3HeXi2HxCxw31lL_UuU-1719861882665-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '86'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '16000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '15999808'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_25d95f35048bf71e28d73fbed6576a6c
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo 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:
+      my best complete final answer to the task.\nYour 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!\nCurrent Task: just say hello!\n\nThis
+      is the expect criteria for your final answer: your greeting \n you MUST return
+      the actual complete content as the final answer, not a summary.\n\nThis is the
+      context you''re working with:\nHi!\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:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
+      "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, br
+      connection:
+      - keep-alive
+      content-length:
+      - '905'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=uU.2MR0L4Mv3xs4DzFlWOQLVId1dJXQBlWffhr9mqxU-1719861882-1.0.1.1-JSKN2_O9iYj8QCZjy0IGiunZxvXimz5Kzv5wQJedVua5E6WIl1UvP.wguXbK0cds7ayJReYnR8v8oAN2rmtnNQ;
+        _cfuvid=yc5Q7WKbO5zoiGNQx86HpHNM3HeXi2HxCxw31lL_UuU-1719861882665-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.34.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.34.0
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.3
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
+        Hello"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9gGvjRHciTPrlyXWRGu5z5C56L10c","object":"chat.completion.chunk","created":1719861883,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 89c8c7202e0f1823-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Mon, 01 Jul 2024 19:24:43 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '82'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '16000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '15999794'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_754b5067e8f56d5c1182dc0f57be0e45
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_sequential_crew_creation_tasks_without_agents.yaml

@@ -0,0 +1,146 @@
+interactions:
+- request:
+    body: !!binary |
+      CtoyCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSsTIKEgoQY3Jld2FpLnRl
+      bGVtZXRyeRJpChCqSW3lVdefwRBLNXi6Xhm8EgijxkgGOCJOMSoQVG9vbCBVc2FnZSBFcnJvcjAB
+      OQh+giEMv94XQYgthSEMv94XShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMzAuMTF6AhgBhQEAAQAA
+      EmkKEITX9xWzBQ0KqeidbMtD1zESCLEDq6L4lZGPKhBUb29sIFVzYWdlIEVycm9yMAE5OF5weAy/
+      3hdBqOZyeAy/3hdKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4zMC4xMXoCGAGFAQABAAASgAIKEPfc
+      duYrDUwkgj4RUzAtD2cSCFdOYgVbkCuLKg5UYXNrIEV4ZWN1dGlvbjABOciuqqkLv94XQcA1NNcM
+      v94XSjEKB3Rhc2tfaWQSJgokMzg2ZTBkMWQtMWVjNy00M2QzLTg3MWItNWU3ZjBiZjBkOWVmSi0K
+      FWZvcm1hdHRlZF9kZXNjcmlwdGlvbhIUChJIb3cgbXVjaCBpcyAyICsgMj9KQwoZZm9ybWF0dGVk
+      X2V4cGVjdGVkX291dHB1dBImCiRUaGUgcmVzdWx0IG9mIHRoZSBzdW0gYXMgYW4gaW50ZWdlci5K
+      DQoGb3V0cHV0EgMKATR6AhgBhQEAAQAAErYLChC8sKh5qQC3H99eVsmrP4vCEgizWQpCjdW1WSoM
+      Q3JldyBDcmVhdGVkMAE5eIbY2Qy/3hdBSILa2Qy/3hdKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4z
+      MC4xMUoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjVKMQoHY3Jld19pZBImCiQ1MjA2MDE0Zi0w
+      NDUyLTQzNjQtOWZiMS1lNWM4MzZmNmZiYmJKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxK
+      EQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251
+      bWJlcl9vZl9hZ2VudHMSAhgBStIECgtjcmV3X2FnZW50cxLCBAq/BFt7ImlkIjogIjU2OTBjOGJm
+      LWVkMzEtNGU1OC04NzBhLTE2OWM3OTQ1ODdjOSIsICJyb2xlIjogIlJlc2VhcmNoZXIiLCAiZ29h
+      bCI6ICJNYWtlIHRoZSBiZXN0IHJlc2VhcmNoIGFuZCBhbmFseXNpcyBvbiBjb250ZW50IGFib3V0
+      IEFJIGFuZCBBSSBhZ2VudHMiLCAiYmFja3N0b3J5IjogIllvdSdyZSBhbiBleHBlcnQgcmVzZWFy
+      Y2hlciwgc3BlY2lhbGl6ZWQgaW4gdGVjaG5vbG9neSwgc29mdHdhcmUgZW5naW5lZXJpbmcsIEFJ
+      IGFuZCBzdGFydHVwcy4gWW91IHdvcmsgYXMgYSBmcmVlbGFuY2VyIGFuZCBpcyBub3cgd29ya2lu
+      ZyBvbiBkb2luZyByZXNlYXJjaCBhbmQgYW5hbHlzaXMgZm9yIGEgbmV3IGN1c3RvbWVyLiIsICJ2
+      ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6
+      IG51bGwsICJsbG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNG9c
+      IiwgXCJ0ZW1wZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRl
+      bGVnYXRpb25fZW5hYmxlZD8iOiB0cnVlLCAidG9vbHNfbmFtZXMiOiBbXX1dStACCgpjcmV3X3Rh
+      c2tzEsECCr4CW3siaWQiOiAiZTE5ODM4Y2EtOGNhMi00MzhiLThiNmMtNDFmM2VlYjJmMDA1Iiwg
+      ImRlc2NyaXB0aW9uIjogIkxvb2sgYXQgdGhlIGF2YWlsYWJsZSBkYXRhIG5kIGdpdmUgbWUgYSBz
+      ZW5zZSBvbiB0aGUgdG90YWwgbnVtYmVyIG9mIHNhbGVzLiIsICJleHBlY3RlZF9vdXRwdXQiOiAi
+      VGhlIHRvdGFsIG51bWJlciBvZiBzYWxlcyBhcyBhbiBpbnRlZ2VyIiwgImFzeW5jX2V4ZWN1dGlv
+      bj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJSZXNlYXJj
+      aGVyIiwgImNvbnRleHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbXX1dSioKCHBsYXRmb3JtEh4K
+      HG1hY09TLTE0LjEuMS1hcm02NC1hcm0tNjRiaXRKHAoQcGxhdGZvcm1fcmVsZWFzZRIICgYyMy4x
+      LjBKGwoPcGxhdGZvcm1fc3lzdGVtEggKBkRhcndpbkp7ChBwbGF0Zm9ybV92ZXJzaW9uEmcKZURh
+      cndpbiBLZXJuZWwgVmVyc2lvbiAyMy4xLjA6IE1vbiBPY3QgIDkgMjE6Mjc6MjQgUERUIDIwMjM7
+      IHJvb3Q6eG51LTEwMDAyLjQxLjl+Ni9SRUxFQVNFX0FSTTY0X1Q2MDAwSgoKBGNwdXMSAhgKegIY
+      AYUBAAEAABL/CAoQ96LQBkWdya2FFyVOx27tLRIIXv2S0EgHgE4qDENyZXcgQ3JlYXRlZDABOdDJ
+      bNwMv94XQRiybtwMv94XShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMzAuMTFKGgoOcHl0aG9uX3Zl
+      cnNpb24SCAoGMy4xMS41SjEKB2NyZXdfaWQSJgokOGM5OTQzNDMtYzcyYi00MzIwLTlkNTItNzI2
+      MTlkNmNmZTc3ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQ
+      AEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIY
+      AUr+AgoLY3Jld19hZ2VudHMS7gIK6wJbeyJpZCI6ICI1YThjOGRjZS00YmQyLTQyMWEtYjUzZC1k
+      ZjE5ODEzMDFiYjEiLCAicm9sZSI6ICJSZXNlYXJjaGVyIiwgImdvYWwiOiAiQmUgc3VwZXIgZW1w
+      YXRoZXRpYy4iLCAiYmFja3N0b3J5IjogIllvdSdyZSBsb3ZlIHRvIHNleSBob3dkeS4iLCAidmVy
+      Ym9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImkxOG4iOiBu
+      dWxsLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6IFwiZ3B0LTRvXCIs
+      IFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5BSVwifSIsICJkZWxl
+      Z2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJ0b29sc19uYW1lcyI6IFtdfV1K7QEKCmNyZXdfdGFz
+      a3MS3gEK2wFbeyJpZCI6ICJmNWEwMjU3Ni1iNTYxLTRiNzQtOTNhMC0yNmYxMDc2YWI5M2MiLCAi
+      ZGVzY3JpcHRpb24iOiAic2F5IGhvd2R5IiwgImV4cGVjdGVkX291dHB1dCI6ICJIb3dkeSEiLCAi
+      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9y
+      b2xlIjogIlJlc2VhcmNoZXIiLCAiY29udGV4dCI6IG51bGwsICJ0b29sc19uYW1lcyI6IFtdfV1K
+      KgoIcGxhdGZvcm0SHgocbWFjT1MtMTQuMS4xLWFybTY0LWFybS02NGJpdEocChBwbGF0Zm9ybV9y
+      ZWxlYXNlEggKBjIzLjEuMEobCg9wbGF0Zm9ybV9zeXN0ZW0SCAoGRGFyd2luSnsKEHBsYXRmb3Jt
+      X3ZlcnNpb24SZwplRGFyd2luIEtlcm5lbCBWZXJzaW9uIDIzLjEuMDogTW9uIE9jdCAgOSAyMToy
+      NzoyNCBQRFQgMjAyMzsgcm9vdDp4bnUtMTAwMDIuNDEuOX42L1JFTEVBU0VfQVJNNjRfVDYwMDBK
+      CgoEY3B1cxICGAp6AhgBhQEAAQAAErgCChCZQqdNoQoZm/bgnzRGX2OfEgguN/7szlsLYioOVGFz
+      ayBFeGVjdXRpb24wATmwOXfcDL/eF0FoPgTeDL/eF0oxCgd0YXNrX2lkEiYKJGY1YTAyNTc2LWI1
+      NjEtNGI3NC05M2EwLTI2ZjEwNzZhYjkzY0okChVmb3JtYXR0ZWRfZGVzY3JpcHRpb24SCwoJc2F5
+      IGhvd2R5SiUKGWZvcm1hdHRlZF9leHBlY3RlZF9vdXRwdXQSCAoGSG93ZHkhSmwKBm91dHB1dBJi
+      CmBIb3dkeSEgSSBob3BlIHRoaXMgbWVzc2FnZSBmaW5kcyB5b3Ugd2VsbCBhbmQgYnJpbmdzIGEg
+      c21pbGUgdG8geW91ciBmYWNlLiBIYXZlIGEgZmFudGFzdGljIGRheSF6AhgBhQEAAQAAEv8IChBG
+      RLGvZYMTRLcpQuhEq3MREggMeXM0BUGtiSoMQ3JldyBDcmVhdGVkMAE5KKNZ4Qy/3hdBWI9b4Qy/
+      3hdKGwoOY3Jld2FpX3ZlcnNpb24SCQoHMC4zMC4xMUoaCg5weXRob25fdmVyc2lvbhIICgYzLjEx
+      LjVKMQoHY3Jld19pZBImCiQxN2Q3YmMzYi04MjE2LTQ4MWMtOGU2YS0zN2U4MDA3M2E1YmJKHAoM
+      Y3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVt
+      YmVyX29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSv4CCgtjcmV3X2Fn
+      ZW50cxLuAgrrAlt7ImlkIjogIjRiYTAzMmMzLWE1NDktNDQyMS05MjY0LTY1ZmVmODZhMTI3MiIs
+      ICJyb2xlIjogIlJlc2VhcmNoZXIiLCAiZ29hbCI6ICJCZSBzdXBlciBlbXBhdGhldGljLiIsICJi
+      YWNrc3RvcnkiOiAiWW91J3JlIGxvdmUgdG8gc2V5IGhvd2R5LiIsICJ2ZXJib3NlPyI6IGZhbHNl
+      LCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6IG51bGwsICJsbG0iOiAi
+      e1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNG9cIiwgXCJ0ZW1wZXJhdHVy
+      ZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25fZW5hYmxl
+      ZD8iOiBmYWxzZSwgInRvb2xzX25hbWVzIjogW119XUrtAQoKY3Jld190YXNrcxLeAQrbAVt7Imlk
+      IjogImJlOGZjMWNmLTVjMTYtNDQ4NS04NDZkLTlmNzkxNjcxZmE0NCIsICJkZXNjcmlwdGlvbiI6
+      ICJzYXkgaG93ZHkiLCAiZXhwZWN0ZWRfb3V0cHV0IjogIkhvd2R5ISIsICJhc3luY19leGVjdXRp
+      b24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFy
+      Y2hlciIsICJjb250ZXh0IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119XUoqCghwbGF0Zm9ybRIe
+      ChxtYWNPUy0xNC4xLjEtYXJtNjQtYXJtLTY0Yml0ShwKEHBsYXRmb3JtX3JlbGVhc2USCAoGMjMu
+      MS4wShsKD3BsYXRmb3JtX3N5c3RlbRIICgZEYXJ3aW5KewoQcGxhdGZvcm1fdmVyc2lvbhJnCmVE
+      YXJ3aW4gS2VybmVsIFZlcnNpb24gMjMuMS4wOiBNb24gT2N0ICA5IDIxOjI3OjI0IFBEVCAyMDIz
+      OyByb290OnhudS0xMDAwMi40MS45fjYvUkVMRUFTRV9BUk02NF9UNjAwMEoKCgRjcHVzEgIYCnoC
+      GAGFAQABAAAS3gEKEPaxZgbRdGE/aC7TcpTEU3USCO2gTkTtndVwKg5UYXNrIEV4ZWN1dGlvbjAB
+      OSjeZOEMv94XQXgCO+IMv94XSjEKB3Rhc2tfaWQSJgokYmU4ZmMxY2YtNWMxNi00NDg1LTg0NmQt
+      OWY3OTE2NzFmYTQ0SiQKFWZvcm1hdHRlZF9kZXNjcmlwdGlvbhILCglzYXkgaG93ZHlKJQoZZm9y
+      bWF0dGVkX2V4cGVjdGVkX291dHB1dBIICgZIb3dkeSFKEgoGb3V0cHV0EggKBkhvd2R5IXoCGAGF
+      AQABAAAS6AwKEDPpREZrHZXFHl0sOJRtgesSCBN6824xY2RxKgxDcmV3IENyZWF0ZWQwATl40Vfi
+      DL/eF0HQY1niDL/eF0obCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjMwLjExShoKDnB5dGhvbl92ZXJz
+      aW9uEggKBjMuMTEuNUoxCgdjcmV3X2lkEiYKJGU3YjFlNDdjLTM4OTQtNDUyYi1hNzRjLWZiZTU3
+      NDUxOWQxOEocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABK
+      GgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFK
+      0wQKC2NyZXdfYWdlbnRzEsMECsAEW3siaWQiOiAiYzRmZTBkOTYtNzRkMy00MTk4LWI5MDQtYWFi
+      NzBlZGMxYjQ1IiwgInJvbGUiOiAiUmVzZWFyY2hlciIsICJnb2FsIjogIk1ha2UgdGhlIGJlc3Qg
+      cmVzZWFyY2ggYW5kIGFuYWx5c2lzIG9uIGNvbnRlbnQgYWJvdXQgQUkgYW5kIEFJIGFnZW50cyIs
+      ICJiYWNrc3RvcnkiOiAiWW91J3JlIGFuIGV4cGVydCByZXNlYXJjaGVyLCBzcGVjaWFsaXplZCBp
+      biB0ZWNobm9sb2d5LCBzb2Z0d2FyZSBlbmdpbmVlcmluZywgQUkgYW5kIHN0YXJ0dXBzLiBZb3Ug
+      d29yayBhcyBhIGZyZWVsYW5jZXIgYW5kIGlzIG5vdyB3b3JraW5nIG9uIGRvaW5nIHJlc2VhcmNo
+      IGFuZCBhbmFseXNpcyBmb3IgYSBuZXcgY3VzdG9tZXIuIiwgInZlcmJvc2U/IjogZmFsc2UsICJt
+      YXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJpMThuIjogbnVsbCwgImxsbSI6ICJ7XCJu
+      YW1lXCI6IG51bGwsIFwibW9kZWxfbmFtZVwiOiBcImdwdC00b1wiLCBcInRlbXBlcmF0dXJlXCI6
+      IDAuNywgXCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlcIn0iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6
+      IGZhbHNlLCAidG9vbHNfbmFtZXMiOiBbXX1dSoEECgpjcmV3X3Rhc2tzEvIDCu8DW3siaWQiOiAi
+      YzE2NTkyZjktZDM2Yy00MDFlLWJiMTEtYzdlMGY5ODkxZjA2IiwgImRlc2NyaXB0aW9uIjogIkNv
+      bWUgdXAgd2l0aCBhIGxpc3Qgb2YgNSBpbnRlcmVzdGluZyBpZGVhcyB0byBleHBsb3JlIGZvciBh
+      biBhcnRpY2xlLCB0aGVuIHdyaXRlIG9uZSBhbWF6aW5nIHBhcmFncmFwaCBoaWdobGlnaHQgZm9y
+      IGVhY2ggaWRlYSB0aGF0IHNob3djYXNlcyBob3cgZ29vZCBhbiBhcnRpY2xlIGFib3V0IHRoaXMg
+      dG9waWMgY291bGQgYmUuIFJldHVybiB0aGUgbGlzdCBvZiBpZGVhcyB3aXRoIHRoZWlyIHBhcmFn
+      cmFwaCBhbmQgeW91ciBub3Rlcy4iLCAiZXhwZWN0ZWRfb3V0cHV0IjogIjUgYnVsbGV0IHBvaW50
+      cyB3aXRoIGEgcGFyYWdyYXBoIGZvciBlYWNoIGlkZWEuIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBm
+      YWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25lIiwgImNvbnRl
+      eHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbXX1dSioKCHBsYXRmb3JtEh4KHG1hY09TLTE0LjEu
+      MS1hcm02NC1hcm0tNjRiaXRKHAoQcGxhdGZvcm1fcmVsZWFzZRIICgYyMy4xLjBKGwoPcGxhdGZv
+      cm1fc3lzdGVtEggKBkRhcndpbkp7ChBwbGF0Zm9ybV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwg
+      VmVyc2lvbiAyMy4xLjA6IE1vbiBPY3QgIDkgMjE6Mjc6MjQgUERUIDIwMjM7IHJvb3Q6eG51LTEw
+      MDAyLjQxLjl+Ni9SRUxFQVNFX0FSTTY0X1Q2MDAwSgoKBGNwdXMSAhgKegIYAYUBAAEAAA==
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, br
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '6493'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.25.0
+    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:
+      - Wed, 03 Jul 2024 15:56:09 GMT
+    status:
+      code: 200
+      message: OK
+version: 1

tests/crew_test.py

@@ -1,6 +1,8 @@
 """Test Agent creation and execution basic functionality."""
 
 import json
+from unittest import mock
+from unittest.mock import patch
 
 import pydantic_core
 import pytest
@@ -155,9 +157,9 @@ def test_hierarchical_process():
         manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
         tasks=[task],
     )
-
+    result = crew.kickoff()
     assert (
-        crew.kickoff()
+        result
         == "1. 'Demystifying AI: An in-depth exploration of Artificial Intelligence for the layperson' - In this piece, we will unravel the enigma of AI, simplifying its complexities into digestible information for the everyday individual. By using relatable examples and analogies, we will journey through the neural networks and machine learning algorithms that define AI, without the jargon and convoluted explanations that often accompany such topics.\n\n2. 'The Role of AI in Startups: A Game Changer?' - Startups today are harnessing the power of AI to revolutionize their businesses. This article will delve into how AI, as an innovative force, is shaping the startup ecosystem, transforming everything from customer service to product development. We'll explore real-life case studies of startups that have leveraged AI to accelerate their growth and disrupt their respective industries.\n\n3. 'AI and Ethics: Navigating the Complex Landscape' - AI brings with it not just technological advancements, but ethical dilemmas as well. This article will engage readers in a thought-provoking discussion on the ethical implications of AI, exploring issues like bias in algorithms, privacy concerns, job displacement, and the moral responsibility of AI developers. We will also discuss potential solutions and frameworks to address these challenges.\n\n4. 'Unveiling the AI Agents: The Future of Customer Service' - AI agents are poised to reshape the customer service landscape, offering businesses the ability to provide round-the-clock support and personalized experiences. In this article, we'll dive deep into the world of AI agents, examining how they work, their benefits and limitations, and how they're set to redefine customer interactions in the digital age.\n\n5. 'From Science Fiction to Reality: AI in Everyday Life' - AI, once a concept limited to the realm of sci-fi, has now permeated our daily lives. This article will highlight the ubiquitous presence of AI, from voice assistants and recommendation algorithms, to autonomous vehicles and smart homes. We'll explore how AI, in its various forms, is transforming our everyday experiences, making the future seem a lot closer than we imagined."
     )
 
@@ -358,7 +360,7 @@ def test_api_calls_throttling(capsys):
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_full_ouput():
+def test_crew_full_output():
     agent = Agent(
         role="test role",
         goal="test goal",
@@ -381,18 +383,99 @@ def test_crew_full_ouput():
     crew = Crew(agents=[agent], tasks=[task1, task2], full_output=True)
 
     result = crew.kickoff()
+
     assert result == {
-        "final_output": "Hello! It is a delight to receive your message. I trust this response finds you in good spirits. It's indeed a pleasure to connect with you too.",
+        "final_output": "Hello!",
         "tasks_outputs": [task1.output, task2.output],
         "usage_metrics": {
-            "completion_tokens": 109,
-            "prompt_tokens": 330,
+            "total_tokens": 348,
+            "prompt_tokens": 314,
+            "completion_tokens": 34,
             "successful_requests": 2,
-            "total_tokens": 439,
         },
     }
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_kickoff_for_each_full_ouput():
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task], full_output=True)
+    results = crew.kickoff_for_each(inputs=inputs)
+
+    assert len(results) == len(inputs)
+    for result in results:
+        assert "usage_metrics" in result
+        assert isinstance(result["usage_metrics"], dict)
+
+        # Assert that all required keys are in usage_metrics and their values are not None
+        for key in [
+            "total_tokens",
+            "prompt_tokens",
+            "completion_tokens",
+            "successful_requests",
+        ]:
+            assert key in result["usage_metrics"]
+            assert result["usage_metrics"][key] > 0
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_crew_async_kickoff_for_each_full_ouput():
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task], full_output=True)
+    results = await crew.kickoff_for_each_async(inputs=inputs)
+
+    assert len(results) == len(inputs)
+    for result in results:
+        assert "usage_metrics" in result
+        assert isinstance(result["usage_metrics"], dict)
+
+        # Assert that all required keys are in usage_metrics and their values are not None
+        for key in [
+            "total_tokens",
+            "prompt_tokens",
+            "completion_tokens",
+            "successful_requests",
+        ]:
+            assert key in result["usage_metrics"]
+            # TODO: FIX THIS WHEN USAGE METRICS ARE RE-DONE
+            # assert result["usage_metrics"][key] > 0
+
+
 def test_agents_rpm_is_never_set_if_crew_max_RPM_is_not_set():
     agent = Agent(
         role="test role",
@@ -465,6 +548,262 @@ def test_async_task_execution():
                 join.assert_called()
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_kickoff_for_each_single_input():
+    """Tests if kickoff_for_each works with a single input."""
+    from unittest.mock import patch
+
+    inputs = [{"topic": "dog"}]
+    expected_outputs = ["Dogs are loyal companions and popular pets."]
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    with patch.object(Agent, "execute_task") as mock_execute_task:
+        mock_execute_task.side_effect = expected_outputs
+        crew = Crew(agents=[agent], tasks=[task])
+        results = crew.kickoff_for_each(inputs=inputs)
+
+    assert len(results) == 1
+    assert results == expected_outputs
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_kickoff_for_each_multiple_inputs():
+    """Tests if kickoff_for_each works with multiple inputs."""
+    from unittest.mock import patch
+
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+    expected_outputs = [
+        "Dogs are loyal companions and popular pets.",
+        "Cats are independent and low-maintenance pets.",
+        "Apples are a rich source of dietary fiber and vitamin C.",
+    ]
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    with patch.object(Agent, "execute_task") as mock_execute_task:
+        mock_execute_task.side_effect = expected_outputs
+        crew = Crew(agents=[agent], tasks=[task])
+        results = crew.kickoff_for_each(inputs=inputs)
+
+    assert len(results) == len(inputs)
+    for i, res in enumerate(results):
+        assert res == expected_outputs[i]
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_kickoff_for_each_empty_input():
+    """Tests if kickoff_for_each handles an empty input list."""
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+    results = crew.kickoff_for_each(inputs=[])
+    assert results == []
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_kickoff_for_each_invalid_input():
+    """Tests if kickoff_for_each raises TypeError for invalid input types."""
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+
+    with pytest.raises(TypeError):
+        # Pass a string instead of a list
+        crew.kickoff_for_each("invalid input")
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_kickoff_for_each_error_handling():
+    """Tests error handling in kickoff_for_each when kickoff raises an error."""
+    from unittest.mock import patch
+
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+    expected_outputs = [
+        "Dogs are loyal companions and popular pets.",
+        "Cats are independent and low-maintenance pets.",
+        "Apples are a rich source of dietary fiber and vitamin C.",
+    ]
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task])
+
+    with patch.object(Crew, "kickoff") as mock_kickoff:
+        mock_kickoff.side_effect = expected_outputs[:2] + [
+            Exception("Simulated kickoff error")
+        ]
+        with pytest.raises(Exception, match="Simulated kickoff error"):
+            crew.kickoff_for_each(inputs=inputs)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_kickoff_async_basic_functionality_and_output():
+    """Tests the basic functionality and output of kickoff_async."""
+    from unittest.mock import patch
+
+    inputs = {"topic": "dog"}
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    # Create the crew
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+    )
+
+    expected_output = "This is a sample output from kickoff."
+    with patch.object(Crew, "kickoff", return_value=expected_output) as mock_kickoff:
+        result = await crew.kickoff_async(inputs)
+
+        assert isinstance(result, str), "Result should be a string"
+        assert result == expected_output, "Result should match expected output"
+        mock_kickoff.assert_called_once_with(inputs)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_async_kickoff_for_each_async_basic_functionality_and_output():
+    """Tests the basic functionality and output of akickoff_for_each_async."""
+    from unittest.mock import patch
+
+    inputs = [
+        {"topic": "dog"},
+        {"topic": "cat"},
+        {"topic": "apple"},
+    ]
+
+    # Define expected outputs for each input
+    expected_outputs = [
+        "Dogs are loyal companions and popular pets.",
+        "Cats are independent and low-maintenance pets.",
+        "Apples are a rich source of dietary fiber and vitamin C.",
+    ]
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    with patch.object(
+        Crew, "kickoff_async", side_effect=expected_outputs
+    ) as mock_kickoff_async:
+        crew = Crew(agents=[agent], tasks=[task])
+
+        results = await crew.kickoff_for_each_async(inputs)
+
+        assert len(results) == len(inputs)
+        assert results == expected_outputs
+        for input_data in inputs:
+            mock_kickoff_async.assert_any_call(inputs=input_data)
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.asyncio
+async def test_async_kickoff_for_each_async_empty_input():
+    """Tests if akickoff_for_each_async handles an empty input list."""
+
+    agent = Agent(
+        role="{topic} Researcher",
+        goal="Express hot takes on {topic}.",
+        backstory="You have a lot of experience with {topic}.",
+    )
+
+    task = Task(
+        description="Give me an analysis around {topic}.",
+        expected_output="1 bullet point about {topic} that's under 15 words.",
+        agent=agent,
+    )
+
+    # Create the crew
+    crew = Crew(
+        agents=[agent],
+        tasks=[task],
+    )
+
+    # Call the function we are testing
+    results = await crew.kickoff_for_each_async([])
+
+    # Assertion
+    assert results == [], "Result should be an empty list when input is empty"
+
+
 def test_set_agents_step_callback():
     from unittest.mock import patch
 
@@ -597,6 +936,30 @@ def test_task_with_no_arguments():
     assert result == "75"
 
 
+def test_code_execution_flag_adds_code_tool_upon_kickoff():
+    from crewai_tools import CodeInterpreterTool
+
+    programmer = Agent(
+        role="Programmer",
+        goal="Write code to solve problems.",
+        backstory="You're a programmer who loves to solve problems with code.",
+        allow_delegation=False,
+        allow_code_execution=True,
+    )
+
+    task = Task(
+        description="How much is 2 + 2?",
+        expected_output="The result of the sum as an integer.",
+        agent=programmer,
+    )
+
+    crew = Crew(agents=[programmer], tasks=[task])
+    crew.kickoff()
+    assert len(programmer.tools) == 1
+    assert programmer.tools[0].__class__ == CodeInterpreterTool
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegation_is_not_enabled_if_there_are_only_one_agent():
     from unittest.mock import patch
 
@@ -614,7 +977,6 @@ def test_delegation_is_not_enabled_if_there_are_only_one_agent():
     )
 
     crew = Crew(agents=[researcher], tasks=[task])
-
     with patch.object(Task, "execute") as execute:
         execute.return_value = "ok"
         crew.kickoff()
@@ -665,6 +1027,29 @@ def test_agent_usage_metrics_are_captured_for_sequential_process():
     }
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_sequential_crew_creation_tasks_without_agents():
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        # agent=researcher, # not having an agent on the task should throw an error
+    )
+
+    # Expected Output: The sequential crew should fail to create because the task is missing an agent
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError) as exec_info:
+        Crew(
+            tasks=[task],
+            agents=[researcher],
+            process=Process.sequential,
+        )
+
+    assert exec_info.value.errors()[0]["type"] == "missing_agent_in_task"
+    assert (
+        "Agent is missing in the task with the following description"
+        in exec_info.value.errors()[0]["msg"]
+    )
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     from langchain_openai import ChatOpenAI
@@ -682,20 +1067,75 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
         agents=[agent],
         tasks=[task],
         process=Process.hierarchical,
-        manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
+        manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
     )
 
     result = crew.kickoff()
     assert result == '"Howdy!"'
-    print(crew.usage_metrics)
+
     assert crew.usage_metrics == {
-        "total_tokens": 1659,
-        "prompt_tokens": 1376,
-        "completion_tokens": 283,
-        "successful_requests": 3,
+        "total_tokens": 1927,
+        "prompt_tokens": 1557,
+        "completion_tokens": 370,
+        "successful_requests": 4,
     }
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_hierarchical_crew_creation_tasks_with_agents():
+    """
+    Agents are not required for tasks in a hierarchical process but sometimes they are still added
+    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
+    """
+    from langchain_openai import ChatOpenAI
+
+    task = Task(
+        description="Write one amazing paragraph about AI.",
+        expected_output="A single paragraph with 4 sentences.",
+        agent=writer,
+    )
+
+    crew = Crew(
+        tasks=[task],
+        agents=[writer, researcher],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(model="gpt-4o"),
+    )
+    crew.kickoff()
+    assert crew.manager_agent is not None
+    assert crew.manager_agent.tools is not None
+    assert crew.manager_agent.tools[0].description.startswith(
+        "Delegate a specific task to one of the following coworkers: [Senior Writer]"
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_hierarchical_crew_creation_tasks_without_async_execution():
+    from langchain_openai import ChatOpenAI
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        async_execution=True,  # should throw an error
+    )
+
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError) as exec_info:
+        Crew(
+            tasks=[task],
+            agents=[researcher],
+            process=Process.hierarchical,
+            manager_llm=ChatOpenAI(model="gpt-4o"),
+        )
+
+    assert (
+        exec_info.value.errors()[0]["type"] == "async_execution_in_hierarchical_process"
+    )
+    assert (
+        "Hierarchical process error: Tasks cannot be flagged with async_execution."
+        in exec_info.value.errors()[0]["msg"]
+    )
+
+
 def test_crew_inputs_interpolate_both_agents_and_tasks():
     agent = Agent(
         role="{topic} Researcher",
@@ -706,9 +1146,10 @@ def test_crew_inputs_interpolate_both_agents_and_tasks():
     task = Task(
         description="Give me an analysis around {topic}.",
         expected_output="{points} bullet points about {topic}.",
+        agent=agent,
     )
 
-    crew = Crew(agents=[agent], tasks=[task], inputs={"topic": "AI", "points": 5})
+    crew = Crew(agents=[agent], tasks=[task])
     inputs = {"topic": "AI", "points": 5}
     crew._interpolate_inputs(inputs=inputs)  # Manual call for now
 
@@ -1006,24 +1447,69 @@ def test_manager_agent_with_tools_raises_exception():
         crew.kickoff()
 
 
-def test_crew_train_success():
+@patch("crewai.crew.Crew.kickoff")
+@patch("crewai.crew.CrewTrainingHandler")
+@patch("crewai.crew.TaskEvaluator")
+def test_crew_train_success(task_evaluator, crew_training_handler, kickoff):
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
         expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
     )
 
     crew = Crew(
         agents=[researcher, writer],
         tasks=[task],
     )
+    crew.train(n_iterations=2, inputs={"topic": "AI"})
+    task_evaluator.assert_has_calls(
+        [
+            mock.call(researcher),
+            mock.call().evaluate_training_data(
+                training_data=crew_training_handler().load(),
+                agent_id=str(researcher.id),
+            ),
+            mock.call().evaluate_training_data().model_dump(),
+            mock.call(writer),
+            mock.call().evaluate_training_data(
+                training_data=crew_training_handler().load(),
+                agent_id=str(writer.id),
+            ),
+            mock.call().evaluate_training_data().model_dump(),
+        ]
+    )
 
-    crew.train(n_iterations=2)
+    crew_training_handler.assert_has_calls(
+        [
+            mock.call("training_data.pkl"),
+            mock.call().load(),
+            mock.call("trained_agents_data.pkl"),
+            mock.call().save_trained_data(
+                agent_id="Researcher",
+                trained_data=task_evaluator().evaluate_training_data().model_dump(),
+            ),
+            mock.call("trained_agents_data.pkl"),
+            mock.call().save_trained_data(
+                agent_id="Senior Writer",
+                trained_data=task_evaluator().evaluate_training_data().model_dump(),
+            ),
+            mock.call(),
+            mock.call().load(),
+            mock.call(),
+            mock.call().load(),
+        ]
+    )
+
+    kickoff.assert_has_calls(
+        [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
+    )
 
 
 def test_crew_train_error():
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article",
         expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
     )
 
     crew = Crew(
@@ -1036,3 +1522,33 @@ def test_crew_train_error():
         assert "train() missing 1 required positional argument: 'n_iterations'" in str(
             e
         )
+
+
+def test__setup_for_training():
+    researcher.allow_delegation = True
+    writer.allow_delegation = True
+    agents = [researcher, writer]
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
+    )
+
+    crew = Crew(
+        agents=agents,
+        tasks=[task],
+    )
+
+    assert crew._train is False
+    assert task.human_input is False
+
+    for agent in agents:
+        assert agent.allow_delegation is True
+
+    crew._setup_for_training()
+
+    assert crew._train is True
+    assert task.human_input is True
+
+    for agent in agents:
+        assert agent.allow_delegation is False

tests/task_test.py

@@ -1,7 +1,6 @@
 """Test Agent creation and execution basic functionality."""
 
 import json
-
 from unittest.mock import MagicMock, patch
 
 import pytest

tests/utilities/evaluators/test_task_evaluator.py

@@ -0,0 +1,64 @@
+from unittest import mock
+from unittest.mock import MagicMock, patch
+
+from crewai.utilities.evaluators.task_evaluator import (
+    TaskEvaluator,
+    TrainingTaskEvaluation,
+)
+
+
+@patch("crewai.utilities.evaluators.task_evaluator.Converter")
+def test_evaluate_training_data(converter_mock):
+    training_data = {
+        "agent_id": {
+            "data1": {
+                "initial_output": "Initial output 1",
+                "human_feedback": "Human feedback 1",
+                "improved_output": "Improved output 1",
+            },
+            "data2": {
+                "initial_output": "Initial output 2",
+                "human_feedback": "Human feedback 2",
+                "improved_output": "Improved output 2",
+            },
+        }
+    }
+    agent_id = "agent_id"
+    original_agent = MagicMock()
+    function_return_value = TrainingTaskEvaluation(
+        suggestions=[
+            "The initial output was already good, having a detailed explanation. However, the improved output "
+            "gave similar information but in a more professional manner using better vocabulary. For future tasks, "
+            "try to implement more elaborate language and precise terminology from the beginning."
+        ],
+        quality=8.0,
+        final_summary="The agent responded well initially. However, the improved output showed that there is room "
+        "for enhancement in terms of language usage, precision, and professionalism. For future tasks, the agent "
+        "should focus more on these points from the start to increase performance.",
+    )
+    converter_mock.return_value.to_pydantic.return_value = function_return_value
+    result = TaskEvaluator(original_agent=original_agent).evaluate_training_data(
+        training_data, agent_id
+    )
+
+    assert result == function_return_value
+    converter_mock.assert_has_calls(
+        [
+            mock.call(
+                llm=original_agent.llm,
+                text="Assess the quality of the training data based on the llm output, human feedback , and llm "
+                "output improved result.\n\nInitial Output:\nInitial output 1\n\nHuman Feedback:\nHuman feedback "
+                "1\n\nImproved Output:\nImproved output 1\n\nInitial Output:\nInitial output 2\n\nHuman "
+                "Feedback:\nHuman feedback 2\n\nImproved Output:\nImproved output 2\n\nPlease provide:\n- "
+                "Based on the Human Feedbacks and the comparison between Initial Outputs and Improved outputs "
+                "provide action items based on human_feedback for future tasks\n- A score from 0 to 10 evaluating "
+                "on completion, quality, and overall performance from the improved output to the initial output "
+                "based on the human feedback\n",
+                model=TrainingTaskEvaluation,
+                instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
+                "following structure, with the following keys:\n- suggestions: List[str]\n- "
+                "quality: float\n- final_summary: str",
+            ),
+            mock.call().to_pydantic(),
+        ]
+    )

tests/utilities/test_file_handler.py

@@ -0,0 +1,41 @@
+import os
+import unittest
+
+import pytest
+
+from crewai.utilities.file_handler import PickleHandler
+
+
+class TestPickleHandler(unittest.TestCase):
+    def setUp(self):
+        self.file_name = "test_data.pkl"
+        self.file_path = os.path.join(os.getcwd(), self.file_name)
+        self.handler = PickleHandler(self.file_name)
+
+    def tearDown(self):
+        if os.path.exists(self.file_path):
+            os.remove(self.file_path)
+
+    def test_initialize_file(self):
+        assert os.path.exists(self.file_path) is True
+        assert os.path.getsize(self.file_path) >= 0
+
+    def test_save_and_load(self):
+        data = {"key": "value"}
+        self.handler.save(data)
+        loaded_data = self.handler.load()
+        assert loaded_data == data
+
+    def test_load_empty_file(self):
+        loaded_data = self.handler.load()
+        assert loaded_data == {}
+
+    def test_load_corrupted_file(self):
+        with open(self.file_path, "wb") as file:
+            file.write(b"corrupted data")
+
+        with pytest.raises(Exception) as exc:
+            self.handler.load()
+
+        assert str(exc.value) == "pickle data was truncated"
+        assert "<class '_pickle.UnpicklingError'>" == str(exc.type)

tests/utilities/test_training_handler.py

@@ -0,0 +1,42 @@
+import os
+import unittest
+
+from crewai.utilities.training_handler import CrewTrainingHandler
+
+
+class TestCrewTrainingHandler(unittest.TestCase):
+    def setUp(self):
+        self.handler = CrewTrainingHandler("trained_data.pkl")
+
+    def tearDown(self):
+        os.remove("trained_data.pkl")
+        del self.handler
+
+    def test_save_trained_data(self):
+        agent_id = "agent1"
+        trained_data = {"param1": 1, "param2": 2}
+        self.handler.save_trained_data(agent_id, trained_data)
+
+        # Assert that the trained data is saved correctly
+        data = self.handler.load()
+        assert data[agent_id] == trained_data
+
+    def test_append_existing_agent(self):
+        train_iteration = 1
+        agent_id = "agent1"
+        new_data = {"param3": 3, "param4": 4}
+        self.handler.append(train_iteration, agent_id, new_data)
+
+        # Assert that the new data is appended correctly to the existing agent
+        data = self.handler.load()
+        assert data[agent_id][train_iteration] == new_data
+
+    def test_append_new_agent(self):
+        train_iteration = 1
+        agent_id = "agent2"
+        new_data = {"param5": 5, "param6": 6}
+        self.handler.append(train_iteration, agent_id, new_data)
+
+        # Assert that the new agent and data are appended correctly
+        data = self.handler.load()
+        assert data[agent_id][train_iteration] == new_data