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

@@ -13,4 +13,5 @@ db/
 test.py
 rc-tests/*
 *.pkl
-temp/*
+temp/*
+.vscode/*

docs/core-concepts/Agents.md

@@ -16,24 +16,24 @@ 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
 

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 custom 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.

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

@@ -8,6 +8,7 @@ The training feature in CrewAI allows you to train your AI agents using the comm
 
 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.
@@ -18,7 +19,26 @@ To use the training feature, follow these steps:
 crewai train -n <n_iterations>
 ```
 
-Replace `<n_iterations>` with the desired number of training iterations. This determines how many times the agents will go through the training process.
+### 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.

docs/how-to/Sequential.md

@@ -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(
@@ -83,4 +82,4 @@ CrewAI tracks token usage across all tasks and agents. You can access these metr
 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
+4. **Use Context**: Leverage the context from previous tasks to inform subsequent ones

poetry.lock

@@ -1,5 +1,25 @@
 # This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
 
+[[package]]
+name = "agentops"
+version = "0.1.12"
+description = "Python SDK for developing AI agent evals and observability"
+optional = true
+python-versions = ">=3.7"
+files = [
+    {file = "agentops-0.1.12-py3-none-any.whl", hash = "sha256:b4b47c990638b74810cc1c38624ada162094b46e3fdd63883642a16bc5258386"},
+    {file = "agentops-0.1.12.tar.gz", hash = "sha256:c4f762482fb240fc3503907f52498f2d8d9e4f80236ee4a12bf039317a85fcd7"},
+]
+
+[package.dependencies]
+packaging = "23.2"
+psutil = "5.9.8"
+requests = "2.31.0"
+
+[package.extras]
+dev = ["pytest (==7.4.0)", "requests-mock (==1.11.0)"]
+langchain = ["langchain (>=1.19,<2.0)"]
+
 [[package]]
 name = "aiohttp"
 version = "3.9.5"
@@ -820,13 +840,13 @@ files = [
 
 [[package]]
 name = "crewai-tools"
-version = "0.4.5"
+version = "0.4.6"
 description = "Set of tools for the crewAI framework"
 optional = false
 python-versions = "<=3.13,>=3.10"
 files = [
-    {file = "crewai_tools-0.4.5-py3-none-any.whl", hash = "sha256:d970a152a69d039eb23150755d4dc9e7c6ef9176b19a80348142619518e39b17"},
-    {file = "crewai_tools-0.4.5.tar.gz", hash = "sha256:1d7763f20afd95c6be70d31f9f0e9334cb42be127c17feddce368907077a6543"},
+    {file = "crewai_tools-0.4.6-py3-none-any.whl", hash = "sha256:bfce205766da58a83233f82ed1f31f931656eb1f9c40b38f947cbf03afdf6e0d"},
+    {file = "crewai_tools-0.4.6.tar.gz", hash = "sha256:f4b1ae8b5cf7c4b53da40223eb9734129b5fb71e7a77b676909129512307bd32"},
 ]
 
 [package.dependencies]
@@ -2505,8 +2525,8 @@ files = [
 [package.dependencies]
 orjson = ">=3.9.14,<4.0.0"
 pydantic = [
-    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
     {version = ">=2.7.4,<3.0.0", markers = "python_full_version >= \"3.12.4\""},
+    {version = ">=1,<3", markers = "python_full_version < \"3.12.4\""},
 ]
 requests = ">=2,<3"
 
@@ -3777,6 +3797,34 @@ files = [
     {file = "protobuf-4.25.3.tar.gz", hash = "sha256:25b5d0b42fd000320bd7830b349e3b696435f3b329810427a6bcce6a5492cc5c"},
 ]
 
+[[package]]
+name = "psutil"
+version = "5.9.8"
+description = "Cross-platform lib for process and system monitoring in Python."
+optional = true
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*"
+files = [
+    {file = "psutil-5.9.8-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:26bd09967ae00920df88e0352a91cff1a78f8d69b3ecabbfe733610c0af486c8"},
+    {file = "psutil-5.9.8-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:05806de88103b25903dff19bb6692bd2e714ccf9e668d050d144012055cbca73"},
+    {file = "psutil-5.9.8-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:611052c4bc70432ec770d5d54f64206aa7203a101ec273a0cd82418c86503bb7"},
+    {file = "psutil-5.9.8-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:50187900d73c1381ba1454cf40308c2bf6f34268518b3f36a9b663ca87e65e36"},
+    {file = "psutil-5.9.8-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:02615ed8c5ea222323408ceba16c60e99c3f91639b07da6373fb7e6539abc56d"},
+    {file = "psutil-5.9.8-cp27-none-win32.whl", hash = "sha256:36f435891adb138ed3c9e58c6af3e2e6ca9ac2f365efe1f9cfef2794e6c93b4e"},
+    {file = "psutil-5.9.8-cp27-none-win_amd64.whl", hash = "sha256:bd1184ceb3f87651a67b2708d4c3338e9b10c5df903f2e3776b62303b26cb631"},
+    {file = "psutil-5.9.8-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:aee678c8720623dc456fa20659af736241f575d79429a0e5e9cf88ae0605cc81"},
+    {file = "psutil-5.9.8-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8cb6403ce6d8e047495a701dc7c5bd788add903f8986d523e3e20b98b733e421"},
+    {file = "psutil-5.9.8-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d06016f7f8625a1825ba3732081d77c94589dca78b7a3fc072194851e88461a4"},
+    {file = "psutil-5.9.8-cp36-cp36m-win32.whl", hash = "sha256:7d79560ad97af658a0f6adfef8b834b53f64746d45b403f225b85c5c2c140eee"},
+    {file = "psutil-5.9.8-cp36-cp36m-win_amd64.whl", hash = "sha256:27cc40c3493bb10de1be4b3f07cae4c010ce715290a5be22b98493509c6299e2"},
+    {file = "psutil-5.9.8-cp37-abi3-win32.whl", hash = "sha256:bc56c2a1b0d15aa3eaa5a60c9f3f8e3e565303b465dbf57a1b730e7a2b9844e0"},
+    {file = "psutil-5.9.8-cp37-abi3-win_amd64.whl", hash = "sha256:8db4c1b57507eef143a15a6884ca10f7c73876cdf5d51e713151c1236a0e68cf"},
+    {file = "psutil-5.9.8-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:d16bbddf0693323b8c6123dd804100241da461e41d6e332fb0ba6058f630f8c8"},
+    {file = "psutil-5.9.8.tar.gz", hash = "sha256:6be126e3225486dff286a8fb9a06246a5253f4c7c53b475ea5f5ac934e64194c"},
+]
+
+[package.extras]
+test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
+
 [[package]]
 name = "pulsar-client"
 version = "3.5.0"
@@ -3934,8 +3982,8 @@ files = [
 annotated-types = ">=0.4.0"
 pydantic-core = "2.20.0"
 typing-extensions = [
-    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
     {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
+    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
 ]
 
 [package.extras]
@@ -4588,13 +4636,13 @@ files = [
 
 [[package]]
 name = "requests"
-version = "2.32.3"
+version = "2.31.0"
 description = "Python HTTP for Humans."
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.7"
 files = [
-    {file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
-    {file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
+    {file = "requests-2.31.0-py3-none-any.whl", hash = "sha256:58cd2187c01e70e6e26505bca751777aa9f2ee0b7f4300988b709f44e013003f"},
+    {file = "requests-2.31.0.tar.gz", hash = "sha256:942c5a758f98d790eaed1a29cb6eefc7ffb0d1cf7af05c3d2791656dbd6ad1e1"},
 ]
 
 [package.dependencies]
@@ -6028,9 +6076,10 @@ doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "rst.linke
 test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools", "jaraco.test", "more-itertools", "pytest (>=6,!=8.1.*)", "pytest-checkdocs (>=2.4)", "pytest-cov", "pytest-enabler (>=2.2)", "pytest-ignore-flaky", "pytest-mypy", "pytest-ruff (>=0.2.1)"]
 
 [extras]
+agentops = ["agentops"]
 tools = ["crewai-tools"]
 
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<=3.13"
-content-hash = "d4ea0d71723ecc2bad629c387dd786b6a96c553b1e3e298516fdfcd2059d1019"
+content-hash = "e605a254f66369bdf6dbdad36f7bd58d7d97377ea37c151cccc7f48ef9f96f55"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.35.7"
+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"
@@ -21,15 +21,17 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.4.5", optional = true }
+crewai-tools = { version = "^0.4.6", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
 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 = "^0.4.5"
+crewai-tools = "^0.4.6"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"
@@ -60,4 +62,4 @@ exclude = ["cli/templates/main.py", "cli/templates/crew.py"]
 
 [build-system]
 requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+build-backend = "poetry.core.masonry.api"

src/crewai/agent.py

@@ -7,19 +7,31 @@ 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 Field, InstanceOf, model_validator
 
 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.tools.agent_tools import AgentTools
-from crewai.utilities import Prompts, Converter
+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.agents.agent_builder.base_agent import BaseAgent
 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
+
+
+@track_agent()
 class Agent(BaseAgent):
     """Represents an agent in a system.
 
@@ -48,6 +60,8 @@ class Agent(BaseAgent):
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
+    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."
     )
@@ -76,7 +90,6 @@ class Agent(BaseAgent):
     response_template: Optional[str] = Field(
         default=None, description="Response format for the agent."
     )
-
     allow_code_execution: Optional[bool] = Field(
         default=False, description="Enable code execution for the agent."
     )
@@ -84,10 +97,11 @@ class Agent(BaseAgent):
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
         super().__init__(**config, **data)
+        __pydantic_self__.agent_ops_agent_name = __pydantic_self__.role
 
     @model_validator(mode="after")
     def set_agent_executor(self) -> "Agent":
-        """Ensure agent executor and token process 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)
 
@@ -101,6 +115,12 @@ class Agent(BaseAgent):
             ):
                 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()

src/crewai/agents/agent_builder/base_agent.py

@@ -1,22 +1,26 @@
-from copy import deepcopy
 import uuid
-from typing import Any, Dict, List, Optional
 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,
-    ConfigDict,
-    PrivateAttr,
 )
 from pydantic_core import PydanticCustomError
 
-from crewai.utilities import I18N, RPMController, Logger
-from crewai.agents import CacheHandler, ToolsHandler
-from crewai.utilities.token_counter_callback import TokenProcess
+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):
@@ -187,6 +191,31 @@ class BaseAgent(ABC, BaseModel):
         """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:
@@ -216,35 +245,6 @@ class BaseAgent(ABC, BaseModel):
     def increment_formatting_errors(self) -> None:
         self.formatting_errors += 1
 
-    def copy(self):
-        exclude = {
-            "id",
-            "_logger",
-            "_rpm_controller",
-            "_request_within_rpm_limit",
-            "token_process",
-            "agent_executor",
-            "tools",
-            "tools_handler",
-            "cache_handler",
-            "crew",
-            "llm",
-        }
-
-        copied_data = self.model_dump(exclude=exclude, exclude_unset=True)
-        copied_agent = self.__class__(**copied_data)
-
-        # Copy mutable attributes separately
-        copied_agent.tools = deepcopy(self.tools)
-        copied_agent.config = deepcopy(self.config)
-
-        # Preserve original values for interpolation
-        copied_agent._original_role = self._original_role
-        copied_agent._original_goal = self._original_goal
-        copied_agent._original_backstory = self._original_backstory
-
-        return copied_agent
-
     def set_rpm_controller(self, rpm_controller: RPMController) -> None:
         """Set the rpm controller for the agent.
 

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -1,65 +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 "Action: Delegate work to coworker" not in output.log
+            and self.crew._long_term_memory
+            and self.crew._entity_memory
+            and self.task
+            and self.crew_agent
         ):
-            memory = ShortTermMemoryItem(
-                data=output.log,
-                agent=self.crew_agent.role,
-                metadata={
-                    "observation": self.task.description,
-                },
-            )
-            self.crew._short_term_memory.save(memory)
+            try:
+                ltm_agent = TaskEvaluator(self.crew_agent)
+                evaluation = ltm_agent.evaluate(self.task, output.log)
 
-    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
 
-            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]),
+                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._entity_memory.save(entity_memory)
+                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:
-        """Get human input."""
+        """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_output_converter_base.py

@@ -27,7 +27,7 @@ class OutputConverter(BaseModel, ABC):
     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(
+    max_attempts: Optional[int] = Field(
         description="Max number of attemps to try to get the output formated.",
         default=3,
     )

src/crewai/agents/executor.py

@@ -1,6 +1,14 @@
 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
@@ -11,13 +19,15 @@ from langchain_core.exceptions import OutputParserException
 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.agent_builder.base_agent_executor_mixin import (
+    CrewAgentExecutorMixin,
+)
 
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
-from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
 from crewai.utilities.training_handler import CrewTrainingHandler
+from crewai.utilities import I18N
 
 
 class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):

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 = "^0.35.7" }
+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 (
@@ -31,6 +31,11 @@ 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):
     """
@@ -219,6 +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."
 
@@ -294,16 +326,13 @@ class Crew(BaseModel):
             # 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 (
-                hasattr(agent, "function_calling_llm")
-                and not agent.function_calling_llm
-            ):
+            if not agent.function_calling_llm:
                 agent.function_calling_llm = self.function_calling_llm
 
-            if hasattr(agent, "allow_code_execution") and agent.allow_code_execution:
+            if agent.allow_code_execution:
                 agent.tools += agent.get_code_execution_tools()
 
-            if hasattr(agent, "step_callback") and not agent.step_callback:
+            if not agent.step_callback:
                 agent.step_callback = self.step_callback
 
             agent.create_agent_executor()
@@ -313,17 +342,13 @@ 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 = metrics + [
-            agent._token_process.get_summary() for agent in self.agents
-        ]
+        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]
@@ -331,21 +356,32 @@ class Crew(BaseModel):
 
         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(
@@ -355,26 +391,37 @@ 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 _run_sequential_process(self) -> str:
         """Executes tasks sequentially and returns the final output."""
         task_output = ""
-        token_usage = []
+
         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 = [
@@ -400,27 +447,27 @@ class Crew(BaseModel):
 
             role = task.agent.role if task.agent is not None else "None"
             self._logger.log("debug", f"== [{role}] Task output: {task_output}\n\n")
-            token_summ = task.agent._token_process.get_summary()
-
-            token_usage.append(token_summ)
 
             if self.output_log_file:
                 self._file_handler.log(agent=role, task=task_output, status="completed")
 
-        token_usage_formatted = self.aggregate_token_usage(token_usage)
         self._finish_execution(task_output)
 
-        # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
-        return self._format_output(task_output, token_usage_formatted)
+        token_usage = self.calculate_usage_metrics()
 
-    def _run_hierarchical_process(self) -> Union[str, Dict[str, Any]]:
+        # 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,
+    ) -> 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 = self.manager_agent.get_delegation_tools(self.agents)
         else:
@@ -432,9 +479,10 @@ class Crew(BaseModel):
                 llm=self.manager_llm,
                 verbose=self.verbose,
             )
+            self.manager_agent = manager
 
         task_output = ""
-        token_usage = []
+
         for task in self.tasks:
             self._logger.log("debug", f"Working Agent: {manager.role}")
             self._logger.log("info", f"Starting Task: {task.description}")
@@ -444,14 +492,15 @@ 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 hasattr(task, "agent._token_process"):
-                token_summ = task.agent._token_process.get_summary()
-                token_usage.append(token_summ)
             if self.output_log_file:
                 self._file_handler.log(
                     agent=manager.role, task=task_output, status="completed"
@@ -460,13 +509,9 @@ class Crew(BaseModel):
         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()
-        token_usage.append(manager_token_usage)
-        token_usage_formatted = self.aggregate_token_usage(token_usage)
+        token_usage = self.calculate_usage_metrics()
 
-        return self._format_output(
-            task_output, token_usage_formatted
-        ), manager_token_usage
+        return self._format_output(task_output, token_usage), token_usage
 
     def copy(self):
         """Create a deep copy of the Crew."""
@@ -481,12 +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}
@@ -524,6 +570,7 @@ class Crew(BaseModel):
         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,
@@ -536,13 +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)})"
-
-    def aggregate_token_usage(self, token_usage_list: List[Dict[str, Any]]):
-        return {
-            key: sum([m[key] for m in token_usage_list if m is not None])
-            for key in token_usage_list[0]
-        }

src/crewai/task.py

@@ -2,8 +2,8 @@ import os
 import re
 import threading
 import uuid
-from copy import deepcopy
-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
@@ -13,7 +13,9 @@ from pydantic_core import PydanticCustomError
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities import I18N, ConverterError, Printer
+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
 
 
@@ -216,7 +218,7 @@ 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,
@@ -274,7 +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",
@@ -289,8 +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 []
+
+        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,
@@ -298,6 +304,7 @@ class Task(BaseModel):
             agent=cloned_agent,
             tools=cloned_tools,
         )
+
         return copied_task
 
     def _export_output(self, result: str) -> Any:
@@ -329,7 +336,7 @@ class Task(BaseModel):
                     except Exception:
                         pass
 
-            # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_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]"
@@ -355,7 +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/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],
-    ) -> str:  # TODO: Fix this return type --> finecwg : I updated return type to str
+    ) -> 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 result is None: #! finecwg: if not result --> if result is None
+        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/converter.py

@@ -32,7 +32,7 @@ class Converter(OutputConverter):
             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}"
@@ -46,7 +46,7 @@ class Converter(OutputConverter):
             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.")
 
@@ -56,7 +56,7 @@ class Converter(OutputConverter):
 
         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.")
@@ -38,6 +49,7 @@ class TrainingTaskEvaluation(BaseModel):
     )
 
 
+@track_agent(name="Task Evaluator")
 class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm

src/crewai/utilities/token_counter_callback.py

@@ -8,18 +8,18 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 
 
 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")
 

tests/agent_test.py

@@ -12,7 +12,6 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
 from crewai.agents.parser import CrewAgentParser
-
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController
@@ -734,7 +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"
     )

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_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_crew_kickoff_for_each_full_ouput.yaml

@@ -400126,7 +400126,7 @@ interactions:
       Content-Type:
       - application/octet-stream
       Date:
-      - Wed, 26 Jun 2024 00:47:57 GMT
+      - Sun, 23 Jun 2024 14:23:37 GMT
       ETag:
       - '0x8DC736E200CD241'
       Last-Modified:
@@ -400138,128 +400138,24 @@ interactions:
       x-ms-lease-status:
       - unlocked
       x-ms-request-id:
-      - 8134b189-f01e-002a-4362-c7d69f000000
+      - fcf86155-f01e-0015-1278-c51e3c000000
       x-ms-version:
       - '2009-09-19'
     status:
       code: 200
       message: OK
 - request:
-    body: !!binary |
-      CqIhCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS+SAKEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKTAQoQeFaYfr5OxyZaJbtlPmhykRIIyBZe8r8vT78qClRvb2wgVXNhZ2UwATmAmXe6
-      bGfcF0FgRXi6bGfcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJKHwoJdG9vbF9uYW1lEhIK
-      EGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABKTAQoQDWl8VO5eDhpC
-      8WTRhE7lIxIIjCV/tIXBg+gqClRvb2wgVXNhZ2UwATmQ09a7bGfcF0EYZNe7bGfcF0oaCg5jcmV3
-      YWlfdmVyc2lvbhIICgYwLjMyLjJKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoI
-      YXR0ZW1wdHMSAhgBegIYAYUBAAEAABKTAQoQdZyAk3NfWDJ95Rl9fwm9JBIIeOLAjtRHX8YqClRv
-      b2wgVXNhZ2UwATn4LiPAbGfcF0Hw1iPAbGfcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJK
-      HwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEA
-      ABLQAQoQ9B/WTcQbD55N9my9PwwJ/RII61GsN4ZK8lsqEFRvb2wgVXNhZ2UgRXJyb3IwATn4XSTC
-      bGfcF0F4GSXCbGfcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJKZgoDbGxtEl8KXXsibmFt
-      ZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC00LTAxMjUtcHJldmlldyIsICJ0ZW1wZXJhdHVy
-      ZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAAS0AEKEN0yjmyVck//dsMA
-      AJt7gVsSCE64+GH0u+SCKhBUb29sIFVzYWdlIEVycm9yMAE5iIgTw2xn3BdBODwUw2xn3BdKGgoO
-      Y3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySmYKA2xsbRJfCl17Im5hbWUiOiBudWxsLCAibW9kZWxf
-      bmFtZSI6ICJncHQtNC0wMTI1LXByZXZpZXciLCAidGVtcGVyYXR1cmUiOiAwLjcsICJjbGFzcyI6
-      ICJDaGF0T3BlbkFJIn16AhgBhQEAAQAAEtABChDHSt0G/EqmGlI1IdhjDtotEgj83Lu7mYSDsyoQ
-      VG9vbCBVc2FnZSBFcnJvcjABOZCYGMRsZ9wXQXBEGcRsZ9wXShoKDmNyZXdhaV92ZXJzaW9uEggK
-      BjAuMzIuMkpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTQtMDEy
-      NS1wcmV2aWV3IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIY
-      AYUBAAEAABJoChBpV7cx2tTNYorpmU9Iezq6EgjT9Wm5SX16tioQVG9vbCBVc2FnZSBFcnJvcjAB
-      ObDiWsdsZ9wXQfB+W8dsZ9wXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMnoCGAGFAQABAAAS
-      kwEKECe14QwK8YEX5k/HAyTJJOESCLC5kWxi9XjbKgpUb29sIFVzYWdlMAE5AHmbyGxn3BdBcA2c
-      yGxn3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh8KCXRvb2xfbmFtZRISChBnZXRfZmlu
-      YWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkwEKECkLzxPcPFShQTRBKOuA5VwS
-      CEXEpf9vgT0qKgpUb29sIFVzYWdlMAE5uIX9yWxn3BdBiAr+yWxn3BdKGgoOY3Jld2FpX3ZlcnNp
-      b24SCAoGMC4zMi4ySh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRz
-      EgIYAXoCGAGFAQABAAASkwEKELKxl/VCmmnFuHppNDaUdLYSCMxTFAfY7LKZKgpUb29sIFVzYWdl
-      MAE5cEBDy2xn3BdBKMlDy2xn3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh8KCXRvb2xf
-      bmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASaAoQWsd1
-      ufYSiTjFfOLUvTXiGhIIUqeG6O/KOEsqEFRvb2wgVXNhZ2UgRXJyb3IwATnonMXObGfcF0FANcbO
-      bGfcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJ6AhgBhQEAAQAAEpwBChDePaRaxJbHM9ti
-      mgjFTw4eEgiJJ6aTsD4j1CoKVG9vbCBVc2FnZTABObD+Q9FsZ9wXQSCTRNFsZ9wXShoKDmNyZXdh
-      aV92ZXJzaW9uEggKBjAuMzIuMkooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dv
-      cmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpsBChB8AxpI4Iiqli5YpSzNuAHkEgiuoKKr
-      AonvqioKVG9vbCBVc2FnZTABOQhPr9ZsZ9wXQRjzr9ZsZ9wXShoKDmNyZXdhaV92ZXJzaW9uEggK
-      BjAuMzIuMkonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0aW9uIHRvIGNvd29ya2VySg4KCGF0dGVt
-      cHRzEgIYAXoCGAGFAQABAAASkQEKEHWST7FZaG5Ij0kYfqRwQFISCGo4iAiKiKriKgpUb29sIFVz
-      YWdlMAE5qKLl2Wxn3BdBuEbm2Wxn3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRv
-      b2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpEBChBW
-      s1jZuOvGnPk5qZAn/3bvEghcLUd+91YchSoKVG9vbCBVc2FnZTABOVBUJttsZ9wXQfDgJttsZ9wX
-      ShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMkodCgl0b29sX25hbWUSEAoObGVhcm5fYWJvdXRf
-      QUlKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABJoChB390oxWJKggBM1q5uqyAIWEgilZ4dcV9H3
-      zyoQVG9vbCBVc2FnZSBFcnJvcjABObCnTtxsZ9wXQYAsT9xsZ9wXShoKDmNyZXdhaV92ZXJzaW9u
-      EggKBjAuMzIuMnoCGAGFAQABAAAS+QEKEGWFgsouWvCkBbw9hOp41fkSCHuQEq4LICdiKgpUb29s
-      IFVzYWdlMAE5aLsF4Wxn3BdBcIoG4Wxn3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0K
-      CXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsi
-      bmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJh
-      dHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAAS+QEKEH74JqRDD3nP
-      pYFzHXVuRBMSCOVLhi1+G6VtKgpUb29sIFVzYWdlMAE5GDRy4mxn3BdB+N9y4mxn3BdKGgoOY3Jl
-      d2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghh
-      dHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0z
-      LjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUki
-      fXoCGAGFAQABAAAS+QEKELEPPr1EMWxY9eCI/9VxYRISCBifMoJVgs46KgpUb29sIFVzYWdlMAE5
-      WMIV5Gxn3BdBOG4W5Gxn3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRvb2xfbmFt
-      ZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFtZSI6IG51
-      bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVyZSI6IDAu
-      NywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAASnAEKEIj74gWv+Pwo4caZDgnygaYS
-      CETmyodLQY8/KgpUb29sIFVzYWdlMAE5sBTAFm1n3BdBANjAFm1n3BdKGgoOY3Jld2FpX3ZlcnNp
-      b24SCAoGMC4zMi4ySigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4K
-      CGF0dGVtcHRzEgIYAXoCGAGFAQABAAASnAEKEDq45gMODvysUf5wQQf4F+0SCHZHV4/9LnhnKgpU
-      b29sIFVzYWdlMAE5EDHQIG1n3BdBwOTQIG1n3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4y
-      SigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIY
-      AXoCGAGFAQABAAASnAEKEJHNsGUrqNbXyAOQPZnty9kSCAASe0iLg1zKKgpUb29sIFVzYWdlMAE5
-      kCpPLW1n3BdBmPlPLW1n3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySigKCXRvb2xfbmFt
-      ZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS
-      jQEKEP5ZHkp/aYaAyGuu53Anw2kSCDu8tanZxniRKgpUb29sIFVzYWdlMAE5iFVHWG1n3BdBUAVI
-      WG1n3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4yShkKCXRvb2xfbmFtZRIMCgptdWx0aXBs
-      aWVySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASjQEKEFPBMl1rYMxgfMdCym2d+yUSCIu9WYA8
-      9juvKgpUb29sIFVzYWdlMAE5YK3oWW1n3BdB6D3pWW1n3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
-      MC4zMi4yShkKCXRvb2xfbmFtZRIMCgptdWx0aXBsaWVySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQAB
-      AAASaAoQCQJWjJpe1L2HUfWpwOVCVRIIb/BALasmjQEqEFRvb2wgVXNhZ2UgRXJyb3IwATmAGdJc
-      bWfcF0F4wdJcbWfcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJ6AhgBhQEAAQAAEmgKED/Z
-      tmI7I3o+4n/FgbLHhtMSCGEtw+VqWPc+KhBUb29sIFVzYWdlIEVycm9yMAE5aDyyXW1n3BdBIMWy
-      XW1n3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4yegIYAYUBAAEAAA==
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate, br
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '4261'
-      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, 26 Jun 2024 00:47:59 GMT
-    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 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",
+    body: '{"messages": [{"content": "You are {topic} Researcher. You have a lot of
+      experience with {topic}.\nYour personal goal is: Express hot takes on {topic}.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:
@@ -400269,13 +400165,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '853'
+      - '963'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.35.3
+      - OpenAI/Python 1.34.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -400285,73 +400181,116 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.35.3
+      - 1.34.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         now"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         can"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         give"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         a"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         great"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         Answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
-        Hi"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        Dogs"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7HGovGTNNv8jlZBbEHKCMAa2Sn","object":"chat.completion.chunk","created":1719362879,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        loyal"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        companions"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        enhance"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        human"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        well"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"-being"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        through"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        emotional"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        support"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIPzOXprkfuIluBhM1o1gL8lm3yu","object":"chat.completion.chunk","created":1719152619,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -400362,20 +400301,20 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8999306a3c2b97ff-SJC
+      - 8985231e8e72453b-ATL
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Wed, 26 Jun 2024 00:48:00 GMT
+      - Sun, 23 Jun 2024 14:23:39 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=cZ1tqEJHf90QH5Wpf8u5w22pMiXEVmHqh.l_FNQzPUE-1719362880-1.0.1.1-ukAMHHbJtb1dXgdiJ9rZPnK9Dr9955CracMEW21Vc4n80TvL8Aj_Ke_B7G85jBPWrNAAQ0LYFLomosxQMd_qSg;
-        path=/; expires=Wed, 26-Jun-24 01:18:00 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=eo7Wv_7IoFobCr06vVNbn6fiTV000XuWJ5mG6A5XfCI-1719152619-1.0.1.1-VWt6JrnrLWxl1Heg2Mc9q1an5j9.JHISIS2VP5qbC_YCwRn5WkI_QykzIBPo8kil7ndx45QBS0fUvVDo22tWKQ;
+        path=/; expires=Sun, 23-Jun-24 14:53:39 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=jB8ShrBkfWJf2HStRWtCrxPo9TmM70i91UOQVSXB_ik-1719362880048-0.0.1.1-604800000;
+      - _cfuvid=zHfpY3hveQ2EtdkjxmAEpZPcSMSo.R1IXEnggmqkQEI-1719152619731-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -400384,41 +400323,41 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '766'
+      - '115'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=31536000; includeSubDomains
+      - max-age=15724800; includeSubDomains
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '16000000'
+      - '12000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '15999808'
+      - '11999780'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 0s
+      - 1ms
       x-request-id:
-      - e2e310e93ef808475e7ac73c1ef60ec0
+      - req_6e1809edb78fae06d8a20ed070c6e64a
     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}'
+    body: '{"messages": [{"content": "You are {topic} Researcher. You have a lot of
+      experience with {topic}.\nYour personal goal is: Express hot takes on {topic}.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
@@ -400427,16 +400366,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '905'
+      - '963'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=cZ1tqEJHf90QH5Wpf8u5w22pMiXEVmHqh.l_FNQzPUE-1719362880-1.0.1.1-ukAMHHbJtb1dXgdiJ9rZPnK9Dr9955CracMEW21Vc4n80TvL8Aj_Ke_B7G85jBPWrNAAQ0LYFLomosxQMd_qSg;
-        _cfuvid=jB8ShrBkfWJf2HStRWtCrxPo9TmM70i91UOQVSXB_ik-1719362880048-0.0.1.1-604800000
+      - __cf_bm=eo7Wv_7IoFobCr06vVNbn6fiTV000XuWJ5mG6A5XfCI-1719152619-1.0.1.1-VWt6JrnrLWxl1Heg2Mc9q1an5j9.JHISIS2VP5qbC_YCwRn5WkI_QykzIBPo8kil7ndx45QBS0fUvVDo22tWKQ;
+        _cfuvid=zHfpY3hveQ2EtdkjxmAEpZPcSMSo.R1IXEnggmqkQEI-1719152619731-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.35.3
+      - OpenAI/Python 1.34.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -400446,73 +400385,116 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.35.3
+      - 1.34.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.12.3
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         now"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         can"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         give"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         a"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         great"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
         Answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"
-        Hello"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        Cats"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        are"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9eB7I99F3dYCupsw3MZZeCiuDZbnU","object":"chat.completion.chunk","created":1719362880,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5bf7397cd3","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        independent"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        curious"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        creatures"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        with"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        strong"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        sense"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        territory"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ0Z7g9gLoEyFe4tuHZY3zDHIxh","object":"chat.completion.chunk","created":1719152620,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -400523,13 +400505,13 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 89993072097897ff-SJC
+      - 898523253f8c453b-ATL
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Wed, 26 Jun 2024 00:48:00 GMT
+      - Sun, 23 Jun 2024 14:23:40 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -400539,26 +400521,230 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '134'
+      - '121'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=31536000; includeSubDomains
+      - max-age=15724800; includeSubDomains
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '16000000'
+      - '12000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '15999794'
+      - '11999779'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 0s
+      - 1ms
       x-request-id:
-      - 95f7e7603df593de5f778bfbd77838c9
+      - req_fcdeaba57c8c0b5c80fdaaf4f3949da3
     status:
       code: 200
       message: OK
-version: 1
+- request:
+    body: '{"messages": [{"content": "You are {topic} Researcher. You have a lot of
+      experience with {topic}.\nYour personal goal is: Express hot takes on {topic}.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:
+      - '967'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=eo7Wv_7IoFobCr06vVNbn6fiTV000XuWJ5mG6A5XfCI-1719152619-1.0.1.1-VWt6JrnrLWxl1Heg2Mc9q1an5j9.JHISIS2VP5qbC_YCwRn5WkI_QykzIBPo8kil7ndx45QBS0fUvVDo22tWKQ;
+        _cfuvid=zHfpY3hveQ2EtdkjxmAEpZPcSMSo.R1IXEnggmqkQEI-1719152619731-0.0.1.1-604800000
+      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-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        Apple"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        revolution"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"ized"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        technology"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        with"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        the"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        i"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"Phone"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        transforming"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        communication"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        media"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"
+        consumption"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9dIQ14W5gaHA4p3dYi6n7FrRBnzhN","object":"chat.completion.chunk","created":1719152621,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_5e6c71d4a8","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8985232a4e71453b-ATL
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Sun, 23 Jun 2024 14:23:41 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '108'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '12000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '11999779'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 1ms
+      x-request-id:
+      - req_d8c11c52c26f88d19413eb84f91587da
+    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

@@ -360,7 +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",
@@ -388,14 +388,94 @@ def test_crew_full_ouput():
         "final_output": "Hello!",
         "tasks_outputs": [task1.output, task2.output],
         "usage_metrics": {
-            "total_tokens": 517,
-            "prompt_tokens": 466,
-            "completion_tokens": 51,
-            "successful_requests": 3,
+            "total_tokens": 348,
+            "prompt_tokens": 314,
+            "completion_tokens": 34,
+            "successful_requests": 2,
         },
     }
 
 
+@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",
@@ -468,6 +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
 
@@ -691,6 +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
@@ -715,13 +1074,68 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     assert result == '"Howdy!"'
 
     assert crew.usage_metrics == {
-        "total_tokens": 1616,
-        "prompt_tokens": 1333,
-        "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",
@@ -732,9 +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
 
@@ -1039,6 +1454,7 @@ 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(
@@ -1093,6 +1509,7 @@ 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(
@@ -1114,6 +1531,7 @@ def test__setup_for_training():
     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(