fix: type checking

.github/workflows/tests.yml

@@ -19,13 +19,13 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v4
         with:
-          python-version: "3.11.9"
+          python-version: "3.10"
 
       - name: Install Requirements
         run: |
-          set -e
           pip install poetry
+          poetry lock &&
           poetry install
 
       - name: Run tests
-        run: poetry run pytest
+        run: poetry run pytest tests

.gitignore

@@ -11,8 +11,4 @@ chroma.sqlite3
 old_en.json
 db/
 test.py
-rc-tests/*
-*.pkl
-temp/*
-.vscode/*
-crew_tasks_output.json
+rc-tests/*

README.md

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

docs/core-concepts/Agents.md

@@ -16,24 +16,24 @@ description: What are crewAI Agents and how to use them.
 
 ## Agent Attributes
 
-| 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`.                                                                                                                                                                  |
+| 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`.                                                                                                                                                                  |
 
 ## Creating an Agent
 
@@ -97,53 +97,5 @@ agent = Agent(
     )
 ```
 
-## Bring your Third Party Agents
-!!! note "Extend your Third Party Agents like LlamaIndex, Langchain, Autogen or fully custom agents using the the crewai's BaseAgent class."
-
-    BaseAgent includes attributes and methods required to integrate with your crews to run and delegate tasks to other agents within your own crew.
-
-    CrewAI is a universal multi agent framework that allows for all agents to work together to automate tasks and solve problems.
-
-
-```py
-from crewai import Agent, Task, Crew
-from custom_agent import CustomAgent # You need to build and extend your own agent logic with the CrewAI BaseAgent class then import it here.
-
-from langchain.agents import load_tools
-
-langchain_tools = load_tools(["google-serper"], llm=llm)
-
-agent1 = CustomAgent(
-    role="backstory agent",
-    goal="who is {input}?",
-    backstory="agent backstory",
-    verbose=True,
-)
-
-task1 = Task(
-    expected_output="a short biography of {input}",
-    description="a short biography of {input}",
-    agent=agent1,
-)
-
-agent2 = Agent(
-    role="bio agent",
-    goal="summarize the short bio for {input} and if needed do more research",
-    backstory="agent backstory",
-    verbose=True,
-)
-
-task2 = Task(
-    description="a tldr summary of the short biography",
-    expected_output="5 bullet point summary of the biography",
-    agent=agent2,
-    context=[task1],
-)
-
-my_crew = Crew(agents=[agent1, agent2], tasks=[task1, task2])
-crew = my_crew.kickoff(inputs={"input": "Mark Twain"})
-```
-
-
 ## Conclusion
 Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents, you can create sophisticated AI systems that leverage the power of collaborative intelligence.

docs/core-concepts/Crews.md

@@ -4,38 +4,36 @@ description: Understanding and utilizing crews in the crewAI framework with comp
 ---
 
 ## What is a Crew?
-
 A crew in crewAI represents a collaborative group of agents working together to achieve a set of tasks. Each crew defines the strategy for task execution, agent collaboration, and the overall workflow.
 
 ## Crew Attributes
 
-| 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.                                                                                                                                                                                                     |
-| **Planning** *(optional)*             | `planning`             |  Adds planning ability to the Crew. When activated before each Crew iteration, all Crew data is sent to an AgentPlanner that will plan the tasks and this plan will be added to each task description.
+| Attribute                   | Description                                                  |
+| :-------------------------- | :----------------------------------------------------------- |
+| **Tasks**                   | A list of tasks assigned to the crew.                        |
+| **Agents**                  | A list of agents that are part of the crew.                  |
+| **Process** *(optional)*    | The process flow (e.g., sequential, hierarchical) the crew follows. |
+| **Verbose** *(optional)*    | The verbosity level for logging during execution.            |
+| **Manager LLM** *(optional)*| The language model used by the manager agent in a hierarchical process. **Required when using a hierarchical process.** |
+| **Function Calling LLM** *(optional)* | If passed, the crew will use this LLM to do function calling for tools for all agents in the crew. Each agent can have its own LLM, which overrides the crew's LLM for function calling. |
+| **Config** *(optional)*     | Optional configuration settings for the crew, in `Json` or `Dict[str, Any]` format. |
+| **Max RPM** *(optional)*    | Maximum requests per minute the crew adheres to during execution. |
+| **Language**  *(optional)*  | Language used for the crew, defaults to English.             |
+| **Language File** *(optional)* | Path to the language file to be used for the crew.          |
+| **Memory** *(optional)*     | Utilized for storing execution memories (short-term, long-term, entity memory). |
+| **Cache** *(optional)*      | Specifies whether to use a cache for storing the results of tools' execution. |
+| **Embedder** *(optional)*   | Configuration for the embedder to be used by the crew. Mostly used by memory for now.       |
+| **Full Output** *(optional)*| Whether the crew should return the full output with all tasks outputs or just the final output. |
+| **Step Callback** *(optional)* | A function that is called after each step of every agent. This can be used to log the agent's actions or to perform other operations; it won't override the agent-specific `step_callback`. |
+| **Task Callback** *(optional)* | A function that is called after the completion of each task. Useful for monitoring or additional operations post-task execution. |
+| **Share Crew** *(optional)* | Whether you want to share the complete crew information and execution with the crewAI team to make the library better, and allow us to train models. |
+| **Output Log File** *(optional)* | Whether you want to have a file with the complete crew output and execution. You can set it using True and it will default to the folder you are currently in and it will be called logs.txt or passing a string with the full path and name of the file. |
+| **Manager Agent** *(optional)* | `manager` sets a ustom agent that will be used as a manager. |
+| **Manager Callbacks** *(optional)* | `manager_callbacks` takes a list of callback handlers to be executed by the manager agent when a hierarchical process is used. |
+| **Prompt File** *(optional)* | Path to the prompt JSON file to be used for the crew. |
 
 !!! 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.
+    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.
 
 ## Creating a Crew
 
@@ -46,12 +44,6 @@ When assembling a crew, you combine agents with complementary roles and tools, a
 ```python
 from crewai import Crew, Agent, Task, Process
 from langchain_community.tools import DuckDuckGoSearchRun
-from crewai_tools import tool
-
-@tool('DuckDuckGoSearch')
-def search(search_query: str):
-    """Search the web for information on a given topic"""
-    return DuckDuckGoSearchRun().run(search_query)
 
 # Define agents with specific roles and tools
 researcher = Agent(
@@ -62,7 +54,7 @@ researcher = Agent(
         to the business.
         You're currently working on a project to analyze the
         trends and innovations in the space of artificial intelligence.""",
-    tools=[search]
+    tools=[DuckDuckGoSearchRun()]
 )
 
 writer = Agent(
@@ -97,57 +89,6 @@ my_crew = Crew(
 )
 ```
 
-## Crew Output
-
-!!! note "Understanding Crew Outputs"
-The output of a crew in the crewAI framework is encapsulated within the `CrewOutput` class.
-This class provides a structured way to access results of the crew's execution, including various formats such as raw strings, JSON, and Pydantic models.
-The `CrewOutput` includes the results from the final task output, token usage, and individual task outputs.
-
-### Crew Output Attributes
-
-| Attribute        | Parameters     | Type                       | Description                                                                                          |
-| :--------------- | :------------- | :------------------------- | :--------------------------------------------------------------------------------------------------- |
-| **Raw**          | `raw`          | `str`                      | The raw output of the crew. This is the default format for the output.                               |
-| **Pydantic**     | `pydantic`     | `Optional[BaseModel]`      | A Pydantic model object representing the structured output of the crew.                              |
-| **JSON Dict**    | `json_dict`    | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the crew.                                               |
-| **Tasks Output** | `tasks_output` | `List[TaskOutput]`         | A list of `TaskOutput` objects, each representing the output of a task in the crew.                  |
-| **Token Usage**  | `token_usage`  | `Dict[str, Any]`           | A summary of token usage, providing insights into the language model's performance during execution. |
-
-### Crew Output Methods and Properties
-
-| Method/Property | Description                                                                                       |
-| :-------------- | :------------------------------------------------------------------------------------------------ |
-| **json**        | Returns the JSON string representation of the crew output if the output format is JSON.           |
-| **to_dict**     | Converts the JSON and Pydantic outputs to a dictionary.                                           |
-| \***\*str\*\*** | Returns the string representation of the crew output, prioritizing Pydantic, then JSON, then raw. |
-
-### Accessing Crew Outputs
-
-Once a crew has been executed, its output can be accessed through the `output` attribute of the `Crew` object. The `CrewOutput` class provides various ways to interact with and present this output.
-
-#### Example
-
-```python
-# Example crew execution
-crew = Crew(
-    agents=[research_agent, writer_agent],
-    tasks=[research_task, write_article_task],
-    verbose=2
-)
-
-result = crew.kickoff()
-
-# Accessing the crew output
-print(f"Raw Output: {crew_output.raw}")
-if crew_output.json_dict:
-    print(f"JSON Output: {json.dumps(crew_output.json_dict, indent=2)}")
-if crew_output.pydantic:
-    print(f"Pydantic Output: {crew_output.pydantic}")
-print(f"Tasks Output: {crew_output.tasks_output}")
-print(f"Token Usage: {crew_output.token_usage}")
-```
-
 ## Memory Utilization
 
 Crews can utilize memory (short-term, long-term, and entity memory) to enhance their execution and learning over time. This feature allows crews to store and recall execution memories, aiding in decision-making and task execution strategies.
@@ -182,7 +123,7 @@ result = my_crew.kickoff()
 print(result)
 ```
 
-### Different ways to Kicking Off a Crew
+### Kicking Off a Crew
 
 Once your crew is assembled, initiate the workflow with the appropriate kickoff method. CrewAI provides several methods for better control over the kickoff process: `kickoff()`, `kickoff_for_each()`, `kickoff_async()`, and `kickoff_for_each_async()`.
 
@@ -214,33 +155,4 @@ for async_result in async_results:
     print(async_result)
 ```
 
-These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs
-
-
-### Replaying from specific task:
-You can now replay from a specific task using our cli command replay.
-
-The replay feature in CrewAI allows you to replay from a specific task using the command-line interface (CLI). By running the command `crewai replay -t <task_id>`, you can specify the `task_id` for the replay process.
-
-Kickoffs will now save the latest kickoffs returned task outputs locally for you to be able to replay from.
-
-
-### Replaying from specific task Using the CLI
-To use the replay feature, follow these steps:
-
-1. Open your terminal or command prompt.
-2. Navigate to the directory where your CrewAI project is located.
-3. Run the following command:
-
-To view latest kickoff task_ids use:
-
-```shell
-crewai log-tasks-outputs
-```
-
-
-```shell
-crewai replay -t <task_id>
-```
-
-These commands let you replay from your latest kickoff tasks, still retaining context from previously executed tasks.
+These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs

docs/core-concepts/Memory.md

@@ -12,7 +12,7 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
 | Component            | Description                                                  |
 | :------------------- | :----------------------------------------------------------- |
 | **Short-Term Memory**| Temporarily stores recent interactions and outcomes, enabling agents to recall and utilize information relevant to their current context during the current executions. |
-| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remember what they did right and wrong across multiple executions |
+| **Long-Term Memory** | Preserves valuable insights and learnings from past executions, allowing agents to build and refine their knowledge over time. So Agents can remeber what they did right and wrong across multiple executions |
 | **Entity Memory**    | Captures and organizes information about entities (people, places, concepts) encountered during tasks, facilitating deeper understanding and relationship mapping. |
 | **Contextual Memory**| Maintains the context of interactions by combining `ShortTermMemory`, `LongTermMemory`, and `EntityMemory`, aiding in the coherence and relevance of agent responses over a sequence of tasks or a conversation. |
 
@@ -29,11 +29,6 @@ description: Leveraging memory systems in the crewAI framework to enhance agent
 When configuring a crew, you can enable and customize each memory component to suit the crew's objectives and the nature of tasks it will perform.
 By default, the memory system is disabled, and you can ensure it is active by setting `memory=True` in the crew configuration. The memory will use OpenAI Embeddings by default, but you can change it by setting `embedder` to a different model.
 
-The 'embedder' only applies to **Short-Term Memory** which uses Chroma for RAG using EmbedChain package.  
-The **Long-Term Memory** uses SQLLite3 to store task results.  Currently, there is no way to override these storage implementations.
-The data storage files are saved into a platform specific location found using the appdirs package 
-and the name of the project which can be overridden using the **CREWAI_STORAGE_DIR** environment variable.
-
 ### Example: Configuring Memory for a Crew
 
 ```python
@@ -166,43 +161,10 @@ my_crew = Crew(
 )
 ```
 
-### Resetting Memory
-```sh
-crewai reset_memories [OPTIONS]
-```
-
-#### Resetting Memory Options
-- **`-l, --long`**
-  - **Description:** Reset LONG TERM memory.
-  - **Type:** Flag (boolean)
-  - **Default:** False
-
-- **`-s, --short`**
-  - **Description:** Reset SHORT TERM memory.
-  - **Type:** Flag (boolean)
-  - **Default:** False
-
-- **`-e, --entities`**
-  - **Description:** Reset ENTITIES memory.
-  - **Type:** Flag (boolean)
-  - **Default:** False
-
-- **`-k, --kickoff-outputs`**
-  - **Description:** Reset LATEST KICKOFF TASK OUTPUTS.
-  - **Type:** Flag (boolean)
-  - **Default:** False
-
-- **`-a, --all`**
-  - **Description:** Reset ALL memories.
-  - **Type:** Flag (boolean)
-  - **Default:** False
-
-
-
 ## Benefits of Using crewAI's Memory System
 - **Adaptive Learning:** Crews become more efficient over time, adapting to new information and refining their approach to tasks.
 - **Enhanced Personalization:** Memory enables agents to remember user preferences and historical interactions, leading to personalized experiences.
 - **Improved Problem Solving:** Access to a rich memory store aids agents in making more informed decisions, drawing on past learnings and contextual insights.
 
 ## Getting Started
-Integrating crewAI's memory system into your projects is straightforward. By leveraging the provided memory components and configurations, you can quickly empower your agents with the ability to remember, reason, and learn from their interactions, unlocking new levels of intelligence and capability.
+Integrating crewAI's memory system into your projects is straightforward. By leveraging the provided memory components and configurations, you can quickly empower your agents with the ability to remember, reason, and learn from their interactions, unlocking new levels of intelligence and capability.

docs/core-concepts/Planning.md

@@ -1,119 +0,0 @@
----
-title: crewAI Planning
-description: Learn how to add planning to your crewAI Crew and improve their performance.
----
-
-## Introduction
-The planning feature in CrewAI allows you to add planning capability to your crew. When enabled, before each Crew iteration, all Crew information is sent to an AgentPlanner that will plan the tasks step by step, and this plan will be added to each task description.
-
-### Using the Planning Feature
-Getting started with the planning feature is very easy, the only step required is to add `planning=True` to your Crew:
-
-```python
-from crewai import Crew, Agent, Task, Process
-
-# Assemble your crew with planning capabilities
-my_crew = Crew(
-    agents=self.agents,
-    tasks=self.tasks,
-    process=Process.sequential,
-    planning=True,
-)
-```
-
-From this point on, your crew will have planning enabled, and the tasks will be planned before each iteration.
-
-### Example
-
-When running the base case example, you will see something like the following output, which represents the output of the AgentPlanner responsible for creating the step-by-step logic to add to the Agents tasks.
-
-```bash
-
-[2024-07-15 16:49:11][INFO]: Planning the crew execution
-**Step-by-Step Plan for Task Execution**
-
-**Task Number 1: Conduct a thorough research about AI LLMs**
-
-**Agent:** AI LLMs Senior Data Researcher
-
-**Agent Goal:** Uncover cutting-edge developments in AI LLMs
-
-**Task Expected Output:** A list with 10 bullet points of the most relevant information about AI LLMs
-
-**Task Tools:** None specified
-
-**Agent Tools:** None specified
-
-**Step-by-Step Plan:**
-
-1. **Define Research Scope:**
-   - Determine the specific areas of AI LLMs to focus on, such as advancements in architecture, use cases, ethical considerations, and performance metrics.
-
-2. **Identify Reliable Sources:**
-   - List reputable sources for AI research, including academic journals, industry reports, conferences (e.g., NeurIPS, ACL), AI research labs (e.g., OpenAI, Google AI), and online databases (e.g., IEEE Xplore, arXiv).
-
-3. **Collect Data:**
-   - Search for the latest papers, articles, and reports published in 2023 and early 2024.
-   - Use keywords like "Large Language Models 2024", "AI LLM advancements", "AI ethics 2024", etc.
-
-4. **Analyze Findings:**
-   - Read and summarize the key points from each source.
-   - Highlight new techniques, models, and applications introduced in the past year.
-
-5. **Organize Information:**
-   - Categorize the information into relevant topics (e.g., new architectures, ethical implications, real-world applications).
-   - Ensure each bullet point is concise but informative.
-
-6. **Create the List:**
-   - Compile the 10 most relevant pieces of information into a bullet point list.
-   - Review the list to ensure clarity and relevance.
-
-**Expected Output:**
-A list with 10 bullet points of the most relevant information about AI LLMs.
-
----
-
-**Task Number 2: Review the context you got and expand each topic into a full section for a report**
-
-**Agent:** AI LLMs Reporting Analyst
-
-**Agent Goal:** Create detailed reports based on AI LLMs data analysis and research findings
-
-**Task Expected Output:** A fully fledge report with the main topics, each with a full section of information. Formatted as markdown without '```'
-
-**Task Tools:** None specified
-
-**Agent Tools:** None specified
-
-**Step-by-Step Plan:**
-
-1. **Review the Bullet Points:**
-   - Carefully read through the list of 10 bullet points provided by the AI LLMs Senior Data Researcher.
-
-2. **Outline the Report:**
-   - Create an outline with each bullet point as a main section heading.
-   - Plan sub-sections under each main heading to cover different aspects of the topic.
-
-3. **Research Further Details:**
-   - For each bullet point, conduct additional research if necessary to gather more detailed information.
-   - Look for case studies, examples, and statistical data to support each section.
-
-4. **Write Detailed Sections:**
-   - Expand each bullet point into a comprehensive section.
-   - Ensure each section includes an introduction, detailed explanation, examples, and a conclusion.
-   - Use markdown formatting for headings, subheadings, lists, and emphasis.
-
-5. **Review and Edit:**
-   - Proofread the report for clarity, coherence, and correctness.
-   - Make sure the report flows logically from one section to the next.
-   - Format the report according to markdown standards.
-
-6. **Finalize the Report:**
-   - Ensure the report is complete with all sections expanded and detailed.
-   - Double-check formatting and make any necessary adjustments.
-
-**Expected Output:**
-A fully-fledged report with the main topics, each with a full section of information. Formatted as markdown without '```'.
-
----
-```

docs/core-concepts/Tasks.md

@@ -4,29 +4,27 @@ description: Detailed guide on managing and creating tasks within the crewAI fra
 ---
 
 ## Overview of a Task
-
 !!! note "What is a Task?"
-In the crewAI framework, tasks are specific assignments completed by agents. They provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
+    In the crewAI framework, tasks are specific assignments completed by agents. They provide all necessary details for execution, such as a description, the agent responsible, required tools, and more, facilitating a wide range of action complexities.
 
 Tasks within crewAI can be collaborative, requiring multiple agents to work together. This is managed through the task properties and orchestrated by the Crew's process, enhancing teamwork and efficiency.
 
 ## Task Attributes
 
-| 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. |
-| **Output** _(optional)_          | `output`          | The output of the task, containing the raw, JSON, and Pydantic output plus additional details.                       |
-| **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.                  |
+| 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. |
 
 ## Creating a Task
 
@@ -37,75 +35,12 @@ from crewai import Task
 
 task = Task(
     description='Find and summarize the latest and most relevant news on AI',
-    agent=sales_agent,
-    expected_output='A bullet list summary of the top 5 most important AI news',
+    agent=sales_agent
 )
 ```
 
 !!! note "Task Assignment"
-Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
-
-## Task Output
-
-!!! note "Understanding Task Outputs"
-The output of a task in the crewAI framework is encapsulated within the `TaskOutput` class. This class provides a structured way to access results of a task, including various formats such as raw strings, JSON, and Pydantic models.
-By default, the `TaskOutput` will only include the `raw` output. A `TaskOutput` will only include the `pydantic` or `json_dict` output if the original `Task` object was configured with `output_pydantic` or `output_json`, respectively.
-
-### Task Output Attributes
-
-| Attribute         | Parameters      | Type                       | Description                                                                                        |
-| :---------------- | :-------------- | :------------------------- | :------------------------------------------------------------------------------------------------- |
-| **Description**   | `description`   | `str`                      | A brief description of the task.                                                                   |
-| **Summary**       | `summary`       | `Optional[str]`            | A short summary of the task, auto-generated from the description.                                  |
-| **Raw**           | `raw`           | `str`                      | The raw output of the task. This is the default format for the output.                             |
-| **Pydantic**      | `pydantic`      | `Optional[BaseModel]`      | A Pydantic model object representing the structured output of the task.                            |
-| **JSON Dict**     | `json_dict`     | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the task.                                             |
-| **Agent**         | `agent`         | `str`                      | The agent that executed the task.                                                                  |
-| **Output Format** | `output_format` | `OutputFormat`             | The format of the task output, with options including RAW, JSON, and Pydantic. The default is RAW. |
-
-### Task Output Methods and Properties
-
-| Method/Property | Description                                                                                       |
-| :-------------- | :------------------------------------------------------------------------------------------------ |
-| **json**        | Returns the JSON string representation of the task output if the output format is JSON.           |
-| **to_dict**     | Converts the JSON and Pydantic outputs to a dictionary.                                           |
-| \***\*str\*\*** | Returns the string representation of the task output, prioritizing Pydantic, then JSON, then raw. |
-
-### Accessing Task Outputs
-
-Once a task has been executed, its output can be accessed through the `output` attribute of the `Task` object. The `TaskOutput` class provides various ways to interact with and present this output.
-
-#### Example
-
-```python
-# Example task
-task = Task(
-    description='Find and summarize the latest AI news',
-    expected_output='A bullet list summary of the top 5 most important AI news',
-    agent=research_agent,
-    tools=[search_tool]
-)
-
-# Execute the crew
-crew = Crew(
-    agents=[research_agent],
-    tasks=[task],
-    verbose=2
-)
-
-result = crew.kickoff()
-
-# Accessing the task output
-task_output = task.output
-
-print(f"Task Description: {task_output.description}")
-print(f"Task Summary: {task_output.summary}")
-print(f"Raw Output: {task_output.raw}")
-if task_output.json_dict:
-    print(f"JSON Output: {json.dumps(task_output.json_dict, indent=2)}")
-if task_output.pydantic:
-    print(f"Pydantic Output: {task_output.pydantic}")
-```
+    Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
 
 ## Integrating Tools with Tasks
 

docs/core-concepts/Tools.md

@@ -100,24 +100,16 @@ Here is a list of the available tools and their descriptions:
 
 | Tool                        | Description                                                                                   |
 | :-------------------------- | :-------------------------------------------------------------------------------------------- |
-| **BrowserbaseLoadTool**     | A tool for interacting with and extracting data from web browsers.                            |
 | **CodeDocsSearchTool**      | A RAG tool optimized for searching through code documentation and related technical documents. |
-| **CodeInterpreterTool**     | A tool for interpreting python code.                                                          |
-| **ComposioTool**            | Enables use of Composio tools.                                                                |
 | **CSVSearchTool**           | A RAG tool designed for searching within CSV files, tailored to handle structured data.       |
 | **DirectorySearchTool**     | A RAG tool for searching within directories, useful for navigating through file systems.      |
 | **DOCXSearchTool**          | A RAG tool aimed at searching within DOCX documents, ideal for processing Word files.         |
 | **DirectoryReadTool**       | Facilitates reading and processing of directory structures and their contents.                |
-| **EXASearchTool**           | A tool designed for performing exhaustive searches across various data sources.               |
 | **FileReadTool**            | Enables reading and extracting data from files, supporting various file formats.              |
-| **FirecrawlSearchTool**     | A tool to search webpages using Firecrawl and return the results.                             |
-| **FirecrawlCrawlWebsiteTool** | A tool for crawling webpages using Firecrawl.                                               |
-| **FirecrawlScrapeWebsiteTool** | A tool for scraping webpages url using Firecrawl and returning its contents.               |
 | **GithubSearchTool**        | A RAG tool for searching within GitHub repositories, useful for code and documentation search.|
 | **SerperDevTool**           | A specialized tool for development purposes, with specific functionalities under development. |
 | **TXTSearchTool**           | A RAG tool focused on searching within text (.txt) files, suitable for unstructured data.     |
 | **JSONSearchTool**          | A RAG tool designed for searching within JSON files, catering to structured data handling.     |
-| **LlamaIndexTool**          | Enables the use of LlamaIndex tools.                                                          |
 | **MDXSearchTool**           | A RAG tool tailored for searching within Markdown (MDX) files, useful for documentation.      |
 | **PDFSearchTool**           | A RAG tool aimed at searching within PDF documents, ideal for processing scanned documents.    |
 | **PGSearchTool**            | A RAG tool optimized for searching within PostgreSQL databases, suitable for database queries. |
@@ -128,6 +120,8 @@ Here is a list of the available tools and their descriptions:
 | **XMLSearchTool**           | A RAG tool designed for searching within XML files, suitable for structured data formats.      |
 | **YoutubeChannelSearchTool**| A RAG tool for searching within YouTube channels, useful for video content analysis.           |
 | **YoutubeVideoSearchTool**  | A RAG tool aimed at searching within YouTube videos, ideal for video data extraction.          |
+| **BrowserbaseTool**         | A tool for interacting with and extracting data from web browsers.                            |
+| **ExaSearchTool**           | A tool designed for performing exhaustive searches across various data sources.               |
 
 ## Creating your own Tools
 

docs/core-concepts/Training-Crew.md

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

docs/how-to/Coding-Agents.md

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

docs/how-to/Conditional-Tasks.md

@@ -1,87 +0,0 @@
----
-title: Conditional Tasks
-description: Learn how to use conditional tasks in a crewAI kickoff
----
-
-## Introduction
-
-Conditional Tasks in crewAI allow for dynamic workflow adaptation based on the outcomes of previous tasks. This powerful feature enables crews to make decisions and execute tasks selectively, enhancing the flexibility and efficiency of your AI-driven processes.
-
-```python
-from typing import List
-
-from pydantic import BaseModel
-from crewai import Agent, Crew
-from crewai.tasks.conditional_task import ConditionalTask
-from crewai.tasks.task_output import TaskOutput
-from crewai.task import Task
-from crewai_tools import SerperDevTool
-
-
-# Define a condition function for the conditional task
-# if false task will be skipped, true, then execute task
-def is_data_missing(output: TaskOutput) -> bool:
-    return len(output.pydantic.events) < 10: # this will skip this task
-
-# Define the agents
-data_fetcher_agent = Agent(
-    role="Data Fetcher",
-    goal="Fetch data online using Serper tool",
-    backstory="Backstory 1",
-    verbose=True,
-    tools=[SerperDevTool()],
-)
-
-data_processor_agent = Agent(
-    role="Data Processor",
-    goal="Process fetched data",
-    backstory="Backstory 2",
-    verbose=True,
-)
-
-summary_generator_agent = Agent(
-    role="Summary Generator",
-    goal="Generate summary from fetched data",
-    backstory="Backstory 3",
-    verbose=True,
-)
-
-
-class EventOutput(BaseModel):
-    events: List[str]
-
-
-task1 = Task(
-    description="Fetch data about events in San Francisco using Serper tool",
-    expected_output="List of 10 things to do in SF this week",
-    agent=data_fetcher_agent,
-    output_pydantic=EventOutput,
-)
-
-conditional_task = ConditionalTask(
-    description="""
-        Check if data is missing. If we have less than 10 events,
-        fetch more events using Serper tool so that
-        we have a total of 10 events in SF this week..
-        """,
-    expected_output="List of 10 Things to do in SF this week ",
-    condition=is_data_missing,
-    agent=data_processor_agent,
-)
-
-task3 = Task(
-    description="Generate summary of events in San Francisco from fetched data",
-    expected_output="summary_generated",
-    agent=summary_generator_agent,
-)
-
-# Create a crew with the tasks
-crew = Crew(
-    agents=[data_fetcher_agent, data_processor_agent, summary_generator_agent],
-    tasks=[task1, conditional_task, task3],
-    verbose=2,
-)
-
-result = crew.kickoff()
-print("results", result)
-```

docs/how-to/Create-Custom-Tools.md

@@ -51,7 +51,7 @@ To optimize tool performance with caching, define custom caching strategies usin
 @tool("Tool with Caching")
 def cached_tool(argument: str) -> str:
     """Tool functionality description."""
-    return "Cacheable result"
+    return "Cachable result"
 
 def my_cache_strategy(arguments: dict, result: str) -> bool:
     # Define custom caching logic

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

@@ -1,10 +1,11 @@
 ---
 title: Assembling and Activating Your CrewAI Team
-description: A comprehensive guide to creating a dynamic CrewAI team for your projects, with updated functionalities including verbose mode, memory capabilities, asynchronous execution, output customization, language model configuration, code execution, integration with third-party agents, and improved task management.
+description: A comprehensive guide to creating a dynamic CrewAI team for your projects, with updated functionalities including verbose mode, memory capabilities, asynchronous execution, output customization, language model configuration, and more.
+
 ---
 
 ## Introduction
-Embark on your CrewAI journey by setting up your environment and initiating your AI crew with the latest features. This guide ensures a smooth start, incorporating all recent updates for an enhanced experience, including code execution capabilities, integration with third-party agents, and advanced task management.
+Embark on your CrewAI journey by setting up your environment and initiating your AI crew with the latest features. This guide ensures a smooth start, incorporating all recent updates for an enhanced experience.
 
 ## Step 0: Installation
 Install CrewAI and any necessary packages for your project. CrewAI is compatible with Python >=3.10,<=3.13.
@@ -15,53 +16,46 @@ pip install 'crewai[tools]'
 ```
 
 ## Step 1: Assemble Your Agents
-Define your agents with distinct roles, backstories, and enhanced capabilities. The Agent class now supports a wide range of attributes for fine-tuned control over agent behavior and interactions, including code execution and integration with third-party agents.
+Define your agents with distinct roles, backstories, and enhanced capabilities like verbose mode, memory usage, and the ability to set specific agents as managers. These elements add depth and guide their task execution and interaction within the crew.
 
 ```python
 import os
-from langchain.llms import OpenAI
+os.environ["SERPER_API_KEY"] = "Your Key"  # serper.dev API key
+os.environ["OPENAI_API_KEY"] = "Your Key"
+
 from crewai import Agent
-from crewai_tools import SerperDevTool, BrowserbaseLoadTool, EXASearchTool
-
-os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
-os.environ["SERPER_API_KEY"] = "Your Serper Key"
-os.environ["BROWSERBASE_API_KEY"] = "Your BrowserBase Key"
-os.environ["BROWSERBASE_PROJECT_ID"] = "Your BrowserBase Project Id"
-
+from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
 search_tool = SerperDevTool()
-browser_tool = BrowserbaseLoadTool()
-exa_search_tool = EXASearchTool()
+browser_tool = BrowserbaseTool()
+exa_search_tool = ExaSearchTool()
 
-# Creating a senior researcher agent with advanced configurations
+# Creating a senior researcher agent with memory and verbose mode
 researcher = Agent(
-    role='Senior Researcher',
-    goal='Uncover groundbreaking technologies in {topic}',
-    backstory=("Driven by curiosity, you're at the forefront of innovation, "
-               "eager to explore and share knowledge that could change the world."),
-    memory=True,
-    verbose=True,
-    allow_delegation=False,
-    tools=[search_tool, browser_tool],
-    allow_code_execution=False,  # New attribute for enabling code execution
-    max_iter=15,  # Maximum number of iterations for task execution
-    max_rpm=100,  # Maximum requests per minute
-    max_execution_time=3600,  # Maximum execution time in seconds
-    system_template="Your custom system template here",  # Custom system template
-    prompt_template="Your custom prompt template here",  # Custom prompt template
-    response_template="Your custom response template here",  # Custom response template
+  role='Senior Researcher',
+  goal='Uncover groundbreaking technologies in {topic}',
+  verbose=True,
+  memory=True,
+  backstory=(
+    "Driven by curiosity, you're at the forefront of"
+    "innovation, eager to explore and share knowledge that could change"
+    "the world."
+  ),
+  tools=[search_tool, browser_tool],
 )
 
-# Creating a writer agent with custom tools and specific configurations
+# Creating a writer agent with custom tools and delegation capability
 writer = Agent(
-    role='Writer',
-    goal='Narrate compelling tech stories about {topic}',
-    backstory=("With a flair for simplifying complex topics, you craft engaging "
-               "narratives that captivate and educate, bringing new discoveries to light."),
-    verbose=True,
-    allow_delegation=False,
-    memory=True,
-    tools=[exa_search_tool],
-    function_calling_llm=OpenAI(model_name="gpt-3.5-turbo"),  # Separate LLM for function calling
+  role='Writer',
+  goal='Narrate compelling tech stories about {topic}',
+  verbose=True,
+  memory=True,
+  backstory=(
+    "With a flair for simplifying complex topics, you craft"
+    "engaging narratives that captivate and educate, bringing new"
+    "discoveries to light in an accessible manner."
+  ),
+  tools=[exa_search_tool],
+  allow_delegation=False
 )
 
 # Setting a specific manager agent
@@ -70,15 +64,73 @@ manager = Agent(
   goal='Ensure the smooth operation and coordination of the team',
   verbose=True,
   backstory=(
-    "As a seasoned project manager, you excel in organizing "
+    "As a seasoned project manager, you excel in organizing"
     "tasks, managing timelines, and ensuring the team stays on track."
-  ),
-  allow_code_execution=True,  # Enable code execution for the manager
+  )
 )
 ```
 
-### New Agent Attributes and Features
+## Step 2: Define the Tasks
+Detail the specific objectives for your agents, including new features for asynchronous execution and output customization. These tasks ensure a targeted approach to their roles.
 
-1. `allow_code_execution`: Enable or disable code execution capabilities for the agent (default is False).
-2. `max_execution_time`: Set a maximum execution time (in seconds) for the agent to complete a task.
-3. `function_calling_llm`: Specify a separate language model for function calling.
+```python
+from crewai import Task
+
+# Research task
+research_task = Task(
+  description=(
+    "Identify the next big trend in {topic}."
+    "Focus on identifying pros and cons and the overall narrative."
+    "Your final report should clearly articulate the key points,"
+    "its market opportunities, and potential risks."
+  ),
+  expected_output='A comprehensive 3 paragraphs long report on the latest AI trends.',
+  tools=[search_tool],
+  agent=researcher,
+  callback="research_callback",  # Example of task callback
+  human_input=True
+)
+
+# Writing task with language model configuration
+write_task = Task(
+  description=(
+    "Compose an insightful article on {topic}."
+    "Focus on the latest trends and how it's impacting the industry."
+    "This article should be easy to understand, engaging, and positive."
+  ),
+  expected_output='A 4 paragraph article on {topic} advancements formatted as markdown.',
+  tools=[exa_search_tool],
+  agent=writer,
+  output_file='new-blog-post.md',  # Example of output customization
+)
+```
+
+## Step 3: Form the Crew
+Combine your agents into a crew, setting the workflow process they'll follow to accomplish the tasks. Now with options to configure language models for enhanced interaction and additional configurations for optimizing performance, such as creating directories when saving files.
+
+```python
+from crewai import Crew, Process
+
+# Forming the tech-focused crew with some enhanced configurations
+crew = Crew(
+  agents=[researcher, writer],
+  tasks=[research_task, write_task],
+  process=Process.sequential,  # Optional: Sequential task execution is default
+  memory=True,
+  cache=True,
+  max_rpm=100,
+  manager_agent=manager
+)
+```
+
+## Step 4: Kick It Off
+Initiate the process with your enhanced crew ready. Observe as your agents collaborate, leveraging their new capabilities for a successful project outcome. Input variables will be interpolated into the agents and tasks for a personalized approach.
+
+```python
+# Starting the task execution process with enhanced feedback
+result = crew.kickoff(inputs={'topic': 'AI in healthcare'})
+print(result)
+```
+
+## Conclusion
+Building and activating a crew in CrewAI has evolved with new functionalities. By incorporating verbose mode, memory capabilities, asynchronous task execution, output customization, language model configuration, and enhanced crew configurations, your AI team is more equipped than ever to tackle challenges efficiently. The depth of agent backstories and the precision of their objectives enrich collaboration, leading to successful project outcomes. This guide aims to provide you with a clear and detailed understanding of setting up and utilizing the CrewAI framework to its full potential.

docs/how-to/Force-Tool-Ouput-as-Result.md

@@ -1,31 +0,0 @@
----
-title: Forcing Tool Output as Result
-description: Learn how to force tool output as the result in of an Agent's task in crewAI.
----
-
-## Introduction
-In CrewAI, you can force the output of a tool as the result of an agent's task. This feature is useful when you want to ensure that the tool output is captured and returned as the task result, and avoid the agent modifying the output during the task execution.
-
-## Forcing Tool Output as Result
-To force the tool output as the result of an agent's task, you can set the `force_tool_output` parameter to `True` when creating the task. This parameter ensures that the tool output is captured and returned as the task result, without any modifications by the agent.
-
-Here's an example of how to force the tool output as the result of an agent's task:
-
-```python
-# ...
-# Define a custom tool that returns the result as the answer
-coding_agent =Agent(
-        role="Data Scientist",
-        goal="Product amazing resports on AI",
-        backstory="You work with data and AI",
-        tools=[MyCustomTool(result_as_answer=True)],
-    )
-# ...
-```
-
-### Workflow in Action
-
-1. **Task Execution**: The agent executes the task using the tool provided.
-2. **Tool Output**: The tool generates the output, which is captured as the task result.
-3. **Agent Interaction**: The agent my reflect and take learnings from the tool but the output is not modified.
-4. **Result Return**: The tool output is returned as the task result without any modifications.

docs/how-to/Kickoff-async.md

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

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

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

docs/how-to/LLM-Connections.md

@@ -1,18 +1,16 @@
 ---
 title: Connect CrewAI to LLMs
-description: Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs), including detailed class attributes, methods, and configuration options.
+description: Comprehensive guide on integrating CrewAI with various Large Language Models (LLMs), including detailed class attributes and methods.
 ---
 
 ## Connect CrewAI to LLMs
-
 !!! note "Default LLM"
-    By default, CrewAI uses OpenAI's GPT-4 model (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4o") for language processing. You can configure your agents to use a different model or API as described in this guide.
+    By default, CrewAI uses OpenAI's GPT-4 model for language processing. You can configure your agents to use a different model or API. This guide shows how to connect your agents to various LLMs through environment variables and direct instantiation.
 
 CrewAI offers flexibility in connecting to various LLMs, including local models via [Ollama](https://ollama.ai) and different APIs like Azure. It's compatible with all [LangChain LLM](https://python.langchain.com/docs/integrations/llms/) components, enabling diverse integrations for tailored AI solutions.
 
 ## CrewAI Agent Overview
-
-The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's a comprehensive overview of the Agent class attributes and methods:
+The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's an updated overview reflecting the latest codebase changes:
 
 - **Attributes**:
     - `role`: Defines the agent's role within the solution.
@@ -52,24 +50,54 @@ Ollama is preferred for local LLM integration, offering customization and privac
 ### Setting Up Ollama
 - **Environment Variables Configuration**: To integrate Ollama, set the following environment variables:
 ```sh
-OPENAI_API_BASE='http://localhost:11434'
-OPENAI_MODEL_NAME='llama2'  # Adjust based on available model
+OPENAI_API_BASE='http://localhost:11434/v1'
+OPENAI_MODEL_NAME='openhermes'  # Adjust based on available model
 OPENAI_API_KEY=''
 ```
 
 ## Ollama Integration (ex. for using Llama 2 locally)
-1. [Download Ollama](https://ollama.com/download).   
-2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.   
-3. Enjoy your free Llama2 model that powered up by excellent agents from crewai.   
+1. [Download Ollama](https://ollama.com/download).
+2. After setting up the Ollama, Pull the Llama2 by typing following lines into the terminal ```ollama pull llama2```.
+3. Create a ModelFile similar the one below in your project directory.
 ```
+FROM llama2
+
+# Set parameters
+
+PARAMETER temperature 0.8
+PARAMETER stop Result
+
+# Sets a custom system message to specify the behavior of the chat assistant
+
+# Leaving it blank for now.
+
+SYSTEM """"""
+```
+4. Create a script to get the base model, which in our case is llama2, and create a model on top of that with ModelFile above. PS: this will be ".sh" file.
+```
+#!/bin/zsh
+
+# variables
+model_name="llama2"
+custom_model_name="crewai-llama2"
+
+#get the base model
+ollama pull $model_name
+
+#create the model file
+ollama create $custom_model_name -f ./Llama2ModelFile
+```
+5. Go into the directory where the script file and ModelFile is located and run the script.
+6. Enjoy your free Llama2 model that is powered up by excellent agents from CrewAI.
+```python
 from crewai import Agent, Task, Crew
-from langchain.llms import Ollama
+from langchain_openai import ChatOpenAI
 import os
 os.environ["OPENAI_API_KEY"] = "NA"
 
-llm = Ollama(
-    model = "llama2",
-    base_url = "http://localhost:11434")
+llm = ChatOpenAI(
+    model = "crewai-llama2",
+    base_url = "http://localhost:11434/v1")
 
 general_agent = Agent(role = "Math Professor",
                       goal = """Provide the solution to the students that are asking mathematical questions and give them the answer.""",
@@ -127,7 +155,7 @@ llm = HuggingFaceHub(
 ```
 
 ## OpenAI Compatible API Endpoints
-Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
+Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, and Mistral AI.
 
 ### Configuration Examples
 #### FastChat
@@ -144,13 +172,6 @@ OPENAI_API_BASE="http://localhost:1234/v1"
 OPENAI_API_KEY="lm-studio"
 ```
 
-#### Groq API
-```sh
-OPENAI_API_KEY=your-groq-api-key
-OPENAI_MODEL_NAME='llama3-8b-8192'
-OPENAI_API_BASE=https://api.groq.com/openai/v1
-```
-
 #### Mistral API
 ```sh
 OPENAI_API_KEY=your-mistral-api-key
@@ -218,4 +239,4 @@ azure_agent = Agent(
 ```
 
 ## Conclusion
-Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.
+Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

docs/how-to/Langtrace-Observability.md

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

docs/how-to/Replay-tasks-from-latest-Crew-Kickoff.md

@@ -1,49 +0,0 @@
----
-title: Replay Tasks from Latest Crew Kickoff
-description: Replay tasks from the latest crew.kickoff(...)
----
-
-## Introduction
-CrewAI provides the ability to replay from a task specified from the latest crew kickoff. This feature is particularly useful when you've finished a kickoff and may want to retry certain tasks or don't need to refetch data over and your agents already have the context saved from the kickoff execution so you just need to replay the tasks you want to.
-
-## Note:
-You must run `crew.kickoff()` before you can replay a task. Currently, only the latest kickoff is supported, so if you use `kickoff_for_each`, it will only allow you to replay from the most recent crew run.
-
-Here's an example of how to replay from a task:
-
-### Replaying from specific task Using the CLI
-To use the replay feature, follow these steps:
-
-1. Open your terminal or command prompt.
-2. Navigate to the directory where your CrewAI project is located.
-3. Run the following command:
-
-To view latest kickoff task_ids use:
-```shell
-crewai log-tasks-outputs
-```
-
-Once you have your task_id to replay from use:
-```shell
-crewai replay -t <task_id>
-```
-
-
-### Replaying from a task Programmatically
-To replay from a task programmatically, use the following steps:
-
-1. Specify the task_id and input parameters for the replay process.
-2. Execute the replay command within a try-except block to handle potential errors.
-
-```python
-   def replay():
-    """
-    Replay the crew execution from a specific task.
-    """
-    task_id = '<task_id>'
-    inputs = {"topic": "CrewAI Training"} # this is optional, you can pass in the inputs you want to replay otherwise uses the previous kickoffs inputs
-    try:
-        YourCrewName_Crew().crew().replay(task_id=task_id, inputs=inputs)
-
-    except Exception as e:
-        raise Exception(f"An error occurred while replaying the crew: {e}")

docs/how-to/Sequential.md

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

docs/how-to/Start-a-New-CrewAI-Project.md

@@ -1,206 +0,0 @@
----
-title: Starting a New CrewAI Project
-description: A comprehensive guide to starting a new CrewAI project, including the latest updates and project setup methods.
----
-
-# Starting Your CrewAI Project
-
-Welcome to the ultimate guide for starting a new CrewAI project. This document will walk you through the steps to create, customize, and run your CrewAI project, ensuring you have everything you need to get started.
-
-## Prerequisites
-
-We assume you have already installed CrewAI. If not, please refer to the [installation guide](https://docs.crewai.com/how-to/Installing-CrewAI/) to install CrewAI and its dependencies.
-
-## Creating a New Project
-
-To create a new project, run the following CLI command:
-
-```shell
-$ crewai create <project_name>
-```
-
-This command will create a new project folder with the following structure:
-
-```shell
-my_project/
-├── .gitignore
-├── pyproject.toml
-├── README.md
-└── src/
-    └── my_project/
-        ├── __init__.py
-        ├── main.py
-        ├── crew.py
-        ├── tools/
-        │   ├── custom_tool.py
-        │   └── __init__.py
-        └── config/
-            ├── agents.yaml
-            └── tasks.yaml
-```
-
-You can now start developing your project by editing the files in the `src/my_project` folder. The `main.py` file is the entry point of your project, and the `crew.py` file is where you define your agents and tasks.
-
-## Customizing Your Project
-
-To customize your project, you can:
-- Modify `src/my_project/config/agents.yaml` to define your agents.
-- Modify `src/my_project/config/tasks.yaml` to define your tasks.
-- Modify `src/my_project/crew.py` to add your own logic, tools, and specific arguments.
-- Modify `src/my_project/main.py` to add custom inputs for your agents and tasks.
-- Add your environment variables into the `.env` file.
-
-### Example: Defining Agents and Tasks
-
-#### agents.yaml
-
-```yaml
-researcher:
-  role: >
-    Job Candidate Researcher
-  goal: >
-    Find potential candidates for the job
-  backstory: >
-    You are adept at finding the right candidates by exploring various online
-    resources. Your skill in identifying suitable candidates ensures the best
-    match for job positions.
-```
-
-#### tasks.yaml
-
-```yaml
-research_candidates_task:
-  description: >
-    Conduct thorough research to find potential candidates for the specified job.
-    Utilize various online resources and databases to gather a comprehensive list of potential candidates.
-    Ensure that the candidates meet the job requirements provided.
-
-    Job Requirements:
-    {job_requirements}
-  expected_output: >
-    A list of 10 potential candidates with their contact information and brief profiles highlighting their suitability.
-  agent: researcher # THIS NEEDS TO MATCH THE AGENT NAME IN THE AGENTS.YAML FILE AND THE AGENT DEFINED IN THE Crew.PY FILE
-  context: # THESE NEED TO MATCH THE TASK NAMES DEFINED ABOVE AND THE TASKS.YAML FILE AND THE TASK DEFINED IN THE Crew.PY FILE
-    - researcher
-```
-
-### Referencing Variables:
-Your defined functions with the same name will be used. For example, you can reference the agent for specific tasks from task.yaml file. Ensure your annotated agent and function name is the same otherwise your task wont recognize the reference properly.
-
-#### Example References
-agent.yaml
-```yaml
-email_summarizer:
-    role: >
-      Email Summarizer
-    goal: >
-      Summarize emails into a concise and clear summary
-    backstory: >
-      You will create a 5 bullet point summary of the report
-    llm: mixtal_llm
-```
-
-task.yaml
-```yaml
-email_summarizer_task:
-    description: >
-      Summarize the email into a 5 bullet point summary
-    expected_output: >
-      A 5 bullet point summary of the email
-    agent: email_summarizer
-    context:
-      - reporting_task
-      - research_task
-```
-
-Use the annotations are used to properly reference the agent and task in the crew.py file.
-
-### Annotations include:
-* @agent
-* @task
-* @crew
-* @llm
-* @tool
-* @callback
-* @output_json
-* @output_pydantic
-* @cache_handler
-
-
-crew.py
-```py
-...
-    @llm
-    def mixtal_llm(self):
-        return ChatGroq(temperature=0, model_name="mixtral-8x7b-32768")
-
-    @agent
-    def email_summarizer(self) -> Agent:
-        return Agent(
-            config=self.agents_config["email_summarizer"],
-        )
-    ## ...other tasks defined
-    @task
-    def email_summarizer_task(self) -> Task:
-        return Task(
-            config=self.tasks_config["email_summarizer_task"],
-        )
-...
-```
-
-
-
-## Installing Dependencies
-
-To install the dependencies for your project, you can use Poetry. First, navigate to your project directory:
-
-```shell
-$ cd my_project
-$ poetry lock
-$ poetry install
-```
-
-This will install the dependencies specified in the `pyproject.toml` file.
-
-## Interpolating Variables
-
-Any variable interpolated in your `agents.yaml` and `tasks.yaml` files like `{variable}` will be replaced by the value of the variable in the `main.py` file.
-
-#### agents.yaml
-
-```yaml
-research_task:
-  description: >
-    Conduct a thorough research about the customer and competitors in the context
-    of {customer_domain}.
-    Make sure you find any interesting and relevant information given the
-    current year is 2024.
-  expected_output: >
-    A complete report on the customer and their customers and competitors,
-    including their demographics, preferences, market positioning and audience engagement.
-```
-
-#### main.py
-
-```python
-# main.py
-def run():
-    inputs = {
-        "customer_domain": "crewai.com"
-    }
-    MyProjectCrew(inputs).crew().kickoff(inputs=inputs)
-```
-
-## Running Your Project
-
-To run your project, use the following command:
-
-```shell
-$ poetry run my_project
-```
-
-This will initialize your crew of AI agents and begin task execution as defined in your configuration in the `main.py` file.
-
-## Deploying Your Project
-
-The easiest way to deploy your crew is through [CrewAI+](https://www.crewai.com/crewaiplus), where you can deploy your crew in a few clicks.

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

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

docs/index.md

@@ -33,31 +33,16 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Crews
                 </a>
             </li>
-            <li>
-                <a href="./core-concepts/Training-Crew">
-                    Training
-                </a>
-            </li>
             <li>
                 <a href="./core-concepts/Memory">
                     Memory
                 </a>
             </li>
-            <li>
-                <a href="./core-concepts/Planning">
-                    Planning
-                </a>
-            </li>
         </ul>
     </div>
     <div style="width:30%">
         <h2>How-To Guides</h2>
         <ul>
-            <li>
-                <a href="./how-to/Start-a-New-CrewAI-Project">
-                    Starting Your crewAI Project
-                </a>
-            </li>
             <li>
                 <a href="./how-to/Installing-CrewAI">
                     Installing crewAI
@@ -93,51 +78,16 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Customizing Agents
                 </a>
             </li>
-            <li>
-                <a href="./how-to/Coding-Agents">
-                    Coding Agents
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Force-Tool-Ouput-as-Result">
-                    Forcing Tool Output as Result
-                </a>
-            </li>
             <li>
                 <a href="./how-to/Human-Input-on-Execution">
                     Human Input on Execution
                 </a>
             </li>
-            <li>
-                <a href="./how-to/Kickoff-async">
-                    Kickoff a Crew Asynchronously
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Kickoff-for-each">
-                    Kickoff a Crew for a List
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Replay-tasks-from-latest-Crew-Kickoff">
-                    Replay from a Task
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Conditional-Tasks">
-                    Conditional Tasks
-                </a>
-            </li>
             <li>
                 <a href="./how-to/AgentOps-Observability">
                     Agent Monitoring with AgentOps
                 </a>
             </li>
-            <li>
-                <a href="./how-to/Langtrace-Observability">
-                    Agent Monitoring with LangTrace
-                </a>
-            </li>
         </ul>
     </div>
     <div style="width:30%">

docs/tools/CodeInterpreterTool.md

@@ -20,7 +20,6 @@ pip install 'crewai[tools]'
 Remember that when using this tool, the code must be generated by the Agent itself. The code must be a Python3 code. And it will take some time for the first time to run because it needs to build the Docker image.
 
 ```python
-from crewai import Agent
 from crewai_tools import CodeInterpreterTool
 
 Agent(
@@ -28,14 +27,3 @@ Agent(
     tools=[CodeInterpreterTool()],
 )
 ```
-
-We also provide a simple way to use it directly from the Agent.
-
-```python
-from crewai import Agent
-
-agent = Agent(
-    ...
-    allow_code_execution=True,
-)
-```

docs/tools/ComposioTool.md

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

docs/tools/GitHubSearchTool.md

@@ -4,7 +4,7 @@
     We are still working on improving tools, so there might be unexpected behavior or changes in the future.
 
 ## Description
-The GithubSearchTool is a Retrieval-Augmented Generation (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
+The GithubSearchTool is a Read, Append, and Generate (RAG) tool specifically designed for conducting semantic searches within GitHub repositories. Utilizing advanced semantic search capabilities, it sifts through code, pull requests, issues, and repositories, making it an essential tool for developers, researchers, or anyone in need of precise information from GitHub.
 
 ## Installation
 To use the GithubSearchTool, first ensure the crewai_tools package is installed in your Python environment:

docs/tools/MDXSearchTool.md

@@ -4,7 +4,7 @@
     The MDXSearchTool is in continuous development. Features may be added or removed, and functionality could change unpredictably as we refine the tool.
 
 ## Description
-The MDX Search Tool is a component of the `crewai_tools` package aimed at facilitating advanced markdown language extraction. It enables users to effectively search and extract relevant information from MD files using query-based searches. This tool is invaluable for data analysis, information management, and research tasks, streamlining the process of finding specific information within large document collections.
+The MDX Search Tool is a component of the `crewai_tools` package aimed at facilitating advanced market data extraction. This tool is invaluable for researchers and analysts seeking quick access to market insights, especially within the AI sector. It simplifies the task of acquiring, interpreting, and organizing market data by interfacing with various data sources.
 
 ## Installation
 Before using the MDX Search Tool, ensure the `crewai_tools` package is installed. If it is not, you can install it with the following command:
@@ -59,4 +59,4 @@ tool = MDXSearchTool(
         ),
     )
 )
-```
+```

docs/tools/TXTSearchTool.md

@@ -31,7 +31,7 @@ tool = TXTSearchTool(txt='path/to/text/file.txt')
 ```
 
 ## Arguments
-- `txt` (str): **Optional**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
+- `txt` (str): **Optinal**. The path to the text file you want to search. This argument is only required if the tool was not initialized with a specific text file; otherwise, the search will be conducted within the initially provided text file.
 
 ## Custom model and embeddings
 

mkdocs.yml

@@ -126,13 +126,10 @@ nav:
     - Processes: 'core-concepts/Processes.md'
     - Crews: 'core-concepts/Crews.md'
     - Collaboration: 'core-concepts/Collaboration.md'
-    - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
-    - Planning: 'core-concepts/Planning.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
   - How to Guides:
-    - Starting Your crewAI Project: 'how-to/Start-a-New-CrewAI-Project.md'
     - Installing CrewAI: 'how-to/Installing-CrewAI.md'
     - Getting Started: 'how-to/Creating-a-Crew-and-kick-it-off.md'
     - Create Custom Tools: 'how-to/Create-Custom-Tools.md'
@@ -141,20 +138,12 @@ nav:
     - Create your own Manager Agent: 'how-to/Your-Own-Manager-Agent.md'
     - Connecting to any LLM: 'how-to/LLM-Connections.md'
     - Customizing Agents: 'how-to/Customizing-Agents.md'
-    - Coding Agents: 'how-to/Coding-Agents.md'
-    - Forcing Tool Output as Result: 'how-to/Force-Tool-Ouput-as-Result.md'
     - Human Input on Execution: 'how-to/Human-Input-on-Execution.md'
-    - Kickoff a Crew Asynchronously: 'how-to/Kickoff-async.md'
-    - Kickoff a Crew for a List: 'how-to/Kickoff-for-each.md'
-    - Replay from a specific task from a kickoff: 'how-to/Replay-tasks-from-latest-Crew-Kickoff.md'
-    - Conditional Tasks: 'how-to/Conditional-Tasks.md'
     - Agent Monitoring with AgentOps: 'how-to/AgentOps-Observability.md'
     - Agent Monitoring with LangTrace: 'how-to/Langtrace-Observability.md'
   - Tools Docs:
     - Google Serper Search: 'tools/SerperDevTool.md'
     - Browserbase Web Loader: 'tools/BrowserbaseLoadTool.md'
-    - Composio Tools: 'tools/ComposioTool.md'
-    - Code Interpreter: 'tools/CodeInterpreterTool.md'
     - Scrape Website: 'tools/ScrapeWebsiteTool.md'
     - Directory Read: 'tools/DirectoryReadTool.md'
     - Exa Serch Web Loader: 'tools/EXASearchTool.md'
@@ -183,7 +172,6 @@ nav:
     - Landing Page Generator: https://github.com/joaomdmoura/crewAI-examples/tree/main/landing_page_generator"
     - Prepare for meetings: https://github.com/joaomdmoura/crewAI-examples/tree/main/prep-for-a-meeting"
   - Telemetry: 'telemetry/Telemetry.md'
-  - Change Log: 'https://github.com/crewAIInc/crewAI/releases'
 
 extra_css:
   - stylesheets/output.css

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.41.1"
+version = "0.32.2"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -14,25 +14,22 @@ Repository = "https://github.com/joaomdmoura/crewai"
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
 pydantic = "^2.4.2"
-langchain = ">0.2,<=0.3"
+langchain = "^0.1.10"
 openai = "^1.13.3"
 opentelemetry-api = "^1.22.0"
 opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.4.26", optional = true }
+crewai-tools = { version = "^0.3.0", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
+embedchain = "0.1.109"
 appdirs = "^1.4.4"
 jsonref = "^1.1.0"
-agentops = { version = "^0.3.0", optional = true }
-embedchain = "^0.1.114"
-json-repair = "^0.25.2"
 
 [tool.poetry.extras]
 tools = ["crewai-tools"]
-agentops = ["agentops"]
 
 [tool.poetry.group.dev.dependencies]
 isort = "^5.13.2"
@@ -46,7 +43,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.4.26"
+crewai-tools = "^0.3.0"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"

src/crewai/__init__.py

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

src/crewai/agent.py

@@ -1,39 +1,35 @@
 import os
-from inspect import signature
-from typing import Any, List, Optional, Tuple
+import uuid
+from copy import deepcopy
+from typing import Any, Dict, List, Optional, Tuple
 
 from langchain.agents.agent import RunnableAgent
-from langchain.agents.tools import BaseTool
 from langchain.agents.tools import tool as LangChainTool
+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, PrivateAttr, model_validator
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    PrivateAttr,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
 
-from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
-from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser, ToolsHandler
 from crewai.memory.contextual.contextual_memory import ContextualMemory
-from crewai.tools.agent_tools import AgentTools
-from crewai.utilities import Converter, Prompts
+from crewai.utilities import I18N, Logger, Prompts, RPMController
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
-from crewai.utilities.token_counter_callback import TokenCalcHandler
+from crewai.utilities.token_counter_callback import TokenCalcHandler, TokenProcess
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-agentops = None
-try:
-    import agentops  # type: ignore # Name "agentops" already defined on line 21
-    from agentops import track_agent
-except ImportError:
 
-    def track_agent():
-        def noop(f):
-            return f
-
-        return noop
-
-
-@track_agent()
-class Agent(BaseAgent):
+class Agent(BaseModel):
     """Represents an agent in a system.
 
     Each agent has a role, a goal, a backstory, and an optional language model (llm).
@@ -55,17 +51,59 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
-            allow_code_execution: Enable code execution for the agent.
-            max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
     """
 
-    _times_executed: int = PrivateAttr(default=0)
+    __hash__ = object.__hash__  # type: ignore
+    _logger: Logger = PrivateAttr()
+    _rpm_controller: RPMController = PrivateAttr(default=None)
+    _request_within_rpm_limit: Any = PrivateAttr(default=None)
+    _token_process: TokenProcess = TokenProcess()
+
+    formatting_errors: int = 0
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
+    role: str = Field(description="Role of the agent")
+    goal: str = Field(description="Objective of the agent")
+    backstory: str = Field(description="Backstory of the agent")
+    cache: bool = Field(
+        default=True,
+        description="Whether the agent should use a cache for tool usage.",
+    )
+    config: Optional[Dict[str, Any]] = Field(
+        description="Configuration for the agent",
+        default=None,
+    )
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the agent execution to be respected.",
+    )
+    verbose: bool = Field(
+        default=False, description="Verbose mode for the Agent Execution"
+    )
+    allow_delegation: bool = Field(
+        default=True, description="Allow delegation of tasks to agents"
+    )
+    tools: Optional[List[Any]] = Field(
+        default_factory=list, description="Tools at agents disposal"
+    )
+    max_iter: Optional[int] = Field(
+        default=25, description="Maximum iterations for an agent to execute a task"
+    )
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
-    agent_ops_agent_name: str = None  # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
-    agent_ops_agent_id: str = None  # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
+    agent_executor: InstanceOf[CrewAgentExecutor] = Field(
+        default=None, description="An instance of the CrewAgentExecutor class."
+    )
+    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
+    tools_handler: InstanceOf[ToolsHandler] = Field(
+        default=None, description="An instance of the ToolsHandler class."
+    )
     cache_handler: InstanceOf[CacheHandler] = Field(
         default=None, description="An instance of the CacheHandler class."
     )
@@ -73,6 +111,7 @@ class Agent(BaseAgent):
         default=None,
         description="Callback to be executed after each step of the agent execution.",
     )
+    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
     llm: Any = Field(
         default_factory=lambda: ChatOpenAI(
             model=os.environ.get("OPENAI_MODEL_NAME", "gpt-4o")
@@ -94,25 +133,47 @@ class Agent(BaseAgent):
     response_template: Optional[str] = Field(
         default=None, description="Response format for the agent."
     )
-    tools_results: Optional[List[Any]] = Field(
-        default=[], description="Results of the tools used by the agent."
-    )
     allow_code_execution: Optional[bool] = Field(
         default=False, description="Enable code execution for the agent."
     )
-    max_retry_limit: int = Field(
-        default=2,
-        description="Maximum number of retries for an agent to execute a task when an error occurs.",
-    )
+
+    _original_role: str | None = None
+    _original_goal: str | None = None
+    _original_backstory: str | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
         super().__init__(**config, **data)
-        __pydantic_self__.agent_ops_agent_name = __pydantic_self__.role
+
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "This field is not to be set by the user.", {}
+            )
+
+    @model_validator(mode="after")
+    def set_attributes_based_on_config(self) -> "Agent":
+        """Set attributes based on the agent configuration."""
+        if self.config:
+            for key, value in self.config.items():
+                setattr(self, key, value)
+        return self
+
+    @model_validator(mode="after")
+    def set_private_attrs(self):
+        """Set private attributes."""
+        self._logger = Logger(self.verbose)
+        if self.max_rpm and not self._rpm_controller:
+            self._rpm_controller = RPMController(
+                max_rpm=self.max_rpm, logger=self._logger
+            )
+        return self
 
     @model_validator(mode="after")
     def set_agent_executor(self) -> "Agent":
-        """Ensure agent executor and token process are set."""
+        """set agent executor is set."""
         if hasattr(self.llm, "model_name"):
             token_handler = TokenCalcHandler(self.llm.model_name, self._token_process)
 
@@ -126,13 +187,6 @@ 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()
@@ -175,15 +229,15 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-        tools = tools or self.tools or []
-        parsed_tools = self._parse_tools(tools)
+        tools = tools or self.tools
+
+        parsed_tools = self._parse_tools(tools)  # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
+
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
         self.agent_executor.task = task
 
-        self.agent_executor.tools_description = self._render_text_description_and_args(
-            parsed_tools
-        )
+        self.agent_executor.tools_description = render_text_description(parsed_tools)
         self.agent_executor.tools_names = self.__tools_names(parsed_tools)
 
         if self.crew and self.crew._train:
@@ -191,44 +245,40 @@ class Agent(BaseAgent):
         else:
             task_prompt = self._use_trained_data(task_prompt=task_prompt)
 
-        try:
-            result = self.agent_executor.invoke(
-                {
-                    "input": task_prompt,
-                    "tool_names": self.agent_executor.tools_names,
-                    "tools": self.agent_executor.tools_description,
-                }
-            )["output"]
-        except Exception as e:
-            self._times_executed += 1
-            if self._times_executed > self.max_retry_limit:
-                raise e
-            result = self.execute_task(task, context, tools)
+        result = self.agent_executor.invoke(
+            {
+                "input": task_prompt,
+                "tool_names": self.agent_executor.tools_names,
+                "tools": self.agent_executor.tools_description,
+            }
+        )["output"]
 
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
 
-        # If there was any tool in self.tools_results that had result_as_answer
-        # set to True, return the results of the last tool that had
-        # result_as_answer set to True
-        for tool_result in self.tools_results:  # type: ignore # Item "None" of "list[Any] | None" has no attribute "__iter__" (not iterable)
-            if tool_result.get("result_as_answer", False):
-                result = tool_result["result"]
-
         return result
 
-    def format_log_to_str(
-        self,
-        intermediate_steps: List[Tuple[AgentAction, str]],
-        observation_prefix: str = "Observation: ",
-        llm_prefix: str = "",
-    ) -> str:
-        """Construct the scratchpad that lets the agent continue its thought process."""
-        thoughts = ""
-        for action, observation in intermediate_steps:
-            thoughts += action.log
-            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
-        return thoughts
+    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
+        """Set the cache handler for the agent.
+
+        Args:
+            cache_handler: An instance of the CacheHandler class.
+        """
+        self.tools_handler = ToolsHandler()
+        if self.cache:
+            self.cache_handler = cache_handler
+            self.tools_handler.cache = cache_handler
+        self.create_agent_executor()
+
+    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
+        """Set the rpm controller for the agent.
+
+        Args:
+            rpm_controller: An instance of the RPMController class.
+        """
+        if not self._rpm_controller:
+            self._rpm_controller = rpm_controller
+            self.create_agent_executor()
 
     def create_agent_executor(self, tools=None) -> None:
         """Create an agent executor for the agent.
@@ -236,7 +286,7 @@ class Agent(BaseAgent):
         Returns:
             An instance of the CrewAgentExecutor class.
         """
-        tools = tools or self.tools or []
+        tools = tools or self.tools
 
         agent_args = {
             "input": lambda x: x["input"],
@@ -284,42 +334,75 @@ class Agent(BaseAgent):
         )
 
         stop_words = [self.i18n.slice("observation")]
-
         if self.response_template:
             stop_words.append(
                 self.response_template.split("{{ .Response }}")[1].strip()
             )
 
         bind = self.llm.bind(stop=stop_words)
-
         inner_agent = agent_args | execution_prompt | bind | CrewAgentParser(agent=self)
         self.agent_executor = CrewAgentExecutor(
             agent=RunnableAgent(runnable=inner_agent), **executor_args
         )
 
-    def get_delegation_tools(self, agents: List[BaseAgent]):
-        agent_tools = AgentTools(agents=agents)
-        tools = agent_tools.tools()
-        return tools
+    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
+        """Interpolate inputs into the agent description and backstory."""
+        if self._original_role is None:
+            self._original_role = self.role
+        if self._original_goal is None:
+            self._original_goal = self.goal
+        if self._original_backstory is None:
+            self._original_backstory = self.backstory
 
-    def get_code_execution_tools(self):
-        try:
-            from crewai_tools import CodeInterpreterTool
+        if inputs:
+            self.role = self._original_role.format(**inputs)
+            self.goal = self._original_goal.format(**inputs)
+            self.backstory = self._original_backstory.format(**inputs)
 
-            return [CodeInterpreterTool()]
-        except ModuleNotFoundError:
-            self._logger.log(
-                "info", "Coding tools not available. Install crewai_tools. "
-            )
+    def increment_formatting_errors(self) -> None:
+        """Count the formatting errors of the agent."""
+        self.formatting_errors += 1
 
-    def get_output_converter(self, llm, text, model, instructions):
-        return Converter(llm=llm, text=text, model=model, instructions=instructions)
+    def format_log_to_str(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        observation_prefix: str = "Observation: ",
+        llm_prefix: str = "",
+    ) -> str:
+        """Construct the scratchpad that lets the agent continue its thought process."""
+        thoughts = ""
+        for action, observation in intermediate_steps:
+            thoughts += action.log
+            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
+        return thoughts
+
+    def copy(self):
+        """Create a deep copy of the Agent."""
+        exclude = {
+            "id",
+            "_logger",
+            "_rpm_controller",
+            "_request_within_rpm_limit",
+            "_token_process",
+            "agent_executor",
+            "tools",
+            "tools_handler",
+            "cache_handler",
+        }
+
+        copied_data = self.model_dump(exclude=exclude)
+        copied_data = {k: v for k, v in copied_data.items() if v is not None}
+
+        copied_agent = Agent(**copied_data)
+        copied_agent.tools = deepcopy(self.tools)
+
+        return copied_agent
 
     def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:  # type: ignore # Function "langchain_core.tools.tool" is not valid as a type
         """Parse tools to be used for the task."""
+        # tentatively try to import from crewai_tools import BaseTool as CrewAITool
         tools_list = []
         try:
-            # tentatively try to import from crewai_tools import BaseTool as CrewAITool
             from crewai_tools import BaseTool as CrewAITool
 
             for tool in tools:
@@ -327,11 +410,15 @@ class Agent(BaseAgent):
                     tools_list.append(tool.to_langchain())
                 else:
                     tools_list.append(tool)
+
+            if self.allow_code_execution:
+                from crewai_tools.code_interpreter_tool import CodeInterpreterTool
+
+                tools_list.append(CodeInterpreterTool)
+
         except ModuleNotFoundError:
-            tools_list = []
             for tool in tools:
                 tools_list.append(tool)
-
         return tools_list
 
     def _training_handler(self, task_prompt: str) -> str:
@@ -358,52 +445,6 @@ class Agent(BaseAgent):
                 )
         return task_prompt
 
-    def _render_text_description(self, tools: List[BaseTool]) -> str:
-        """Render the tool name and description in plain text.
-
-        Output will be in the format of:
-
-        .. code-block:: markdown
-
-            search: This tool is used for search
-            calculator: This tool is used for math
-        """
-        description = "\n".join(
-            [
-                f"Tool name: {tool.name}\nTool description:\n{tool.description}"
-                for tool in tools
-            ]
-        )
-
-        return description
-
-    def _render_text_description_and_args(self, tools: List[BaseTool]) -> str:
-        """Render the tool name, description, and args in plain text.
-
-        Output will be in the format of:
-
-        .. code-block:: markdown
-
-            search: This tool is used for search, args: {"query": {"type": "string"}}
-            calculator: This tool is used for math, \
-    args: {"expression": {"type": "string"}}
-        """
-        tool_strings = []
-        for tool in tools:
-            args_schema = str(tool.args)
-            if hasattr(tool, "func") and tool.func:
-                sig = signature(tool.func)
-                description = (
-                    f"Tool Name: {tool.name}{sig}\nTool Description: {tool.description}"
-                )
-            else:
-                description = (
-                    f"Tool Name: {tool.name}\nTool Description: {tool.description}"
-                )
-            tool_strings.append(f"{description}\nTool Arguments: {args_schema}")
-
-        return "\n".join(tool_strings)
-
     @staticmethod
     def __tools_names(tools) -> str:
         return ", ".join([t.name for t in tools])

src/crewai/agents/agent_builder/base_agent.py

@@ -1,262 +0,0 @@
-import uuid
-from abc import ABC, abstractmethod
-from copy import copy as shallow_copy
-from hashlib import md5
-from typing import Any, Dict, List, Optional, TypeVar
-
-from pydantic import (
-    UUID4,
-    BaseModel,
-    ConfigDict,
-    Field,
-    InstanceOf,
-    PrivateAttr,
-    field_validator,
-    model_validator,
-)
-from pydantic_core import PydanticCustomError
-
-from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
-from crewai.agents.cache.cache_handler import CacheHandler
-from crewai.agents.tools_handler import ToolsHandler
-from crewai.utilities import I18N, Logger, RPMController
-
-T = TypeVar("T", bound="BaseAgent")
-
-
-class BaseAgent(ABC, BaseModel):
-    """Abstract Base Class for all third party agents compatible with CrewAI.
-
-    Attributes:
-        id (UUID4): Unique identifier for the agent.
-        role (str): Role of the agent.
-        goal (str): Objective of the agent.
-        backstory (str): Backstory of the agent.
-        cache (bool): Whether the agent should use a cache for tool usage.
-        config (Optional[Dict[str, Any]]): Configuration for the agent.
-        verbose (bool): Verbose mode for the Agent Execution.
-        max_rpm (Optional[int]): Maximum number of requests per minute for the agent execution.
-        allow_delegation (bool): Allow delegation of tasks to agents.
-        tools (Optional[List[Any]]): Tools at the agent's disposal.
-        max_iter (Optional[int]): Maximum iterations for an agent to execute a task.
-        agent_executor (InstanceOf): An instance of the CrewAgentExecutor class.
-        llm (Any): Language model that will run the agent.
-        crew (Any): Crew to which the agent belongs.
-        i18n (I18N): Internationalization settings.
-        cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
-        tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
-
-
-    Methods:
-        execute_task(task: Any, context: Optional[str] = None, tools: Optional[List[Any]] = None) -> str:
-            Abstract method to execute a task.
-        create_agent_executor(tools=None) -> None:
-            Abstract method to create an agent executor.
-        _parse_tools(tools: List[Any]) -> List[Any]:
-            Abstract method to parse tools.
-        get_delegation_tools(agents: List["BaseAgent"]):
-            Abstract method to set the agents task tools for handling delegation and question asking to other agents in crew.
-        get_output_converter(llm, model, instructions):
-            Abstract method to get the converter class for the agent to create json/pydantic outputs.
-        interpolate_inputs(inputs: Dict[str, Any]) -> None:
-            Interpolate inputs into the agent description and backstory.
-        set_cache_handler(cache_handler: CacheHandler) -> None:
-            Set the cache handler for the agent.
-        increment_formatting_errors() -> None:
-            Increment formatting errors.
-        copy() -> "BaseAgent":
-            Create a copy of the agent.
-        set_rpm_controller(rpm_controller: RPMController) -> None:
-            Set the rpm controller for the agent.
-        set_private_attrs() -> "BaseAgent":
-            Set private attributes.
-    """
-
-    __hash__ = object.__hash__  # type: ignore
-    _logger: Logger = PrivateAttr()
-    _rpm_controller: RPMController = PrivateAttr(default=None)
-    _request_within_rpm_limit: Any = PrivateAttr(default=None)
-    formatting_errors: int = 0
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
-    role: str = Field(description="Role of the agent")
-    goal: str = Field(description="Objective of the agent")
-    backstory: str = Field(description="Backstory of the agent")
-    cache: bool = Field(
-        default=True, description="Whether the agent should use a cache for tool usage."
-    )
-    config: Optional[Dict[str, Any]] = Field(
-        description="Configuration for the agent", default=None
-    )
-    verbose: bool = Field(
-        default=False, description="Verbose mode for the Agent Execution"
-    )
-    max_rpm: Optional[int] = Field(
-        default=None,
-        description="Maximum number of requests per minute for the agent execution to be respected.",
-    )
-    allow_delegation: bool = Field(
-        default=True, description="Allow delegation of tasks to agents"
-    )
-    tools: Optional[List[Any]] = Field(
-        default_factory=list, description="Tools at agents' disposal"
-    )
-    max_iter: Optional[int] = Field(
-        default=25, description="Maximum iterations for an agent to execute a task"
-    )
-    agent_executor: InstanceOf = Field(
-        default=None, description="An instance of the CrewAgentExecutor class."
-    )
-    llm: Any = Field(
-        default=None, description="Language model that will run the agent."
-    )
-    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-    cache_handler: InstanceOf[CacheHandler] = Field(
-        default=None, description="An instance of the CacheHandler class."
-    )
-    tools_handler: InstanceOf[ToolsHandler] = Field(
-        default=None, description="An instance of the ToolsHandler class."
-    )
-
-    _original_role: str | None = None
-    _original_goal: str | None = None
-    _original_backstory: str | None = None
-    _token_process: TokenProcess = TokenProcess()
-
-    def __init__(__pydantic_self__, **data):
-        config = data.pop("config", {})
-        super().__init__(**config, **data)
-
-    @model_validator(mode="after")
-    def set_config_attributes(self):
-        if self.config:
-            for key, value in self.config.items():
-                setattr(self, key, value)
-        return self
-
-    @field_validator("id", mode="before")
-    @classmethod
-    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
-        if v:
-            raise PydanticCustomError(
-                "may_not_set_field", "This field is not to be set by the user.", {}
-            )
-
-    @model_validator(mode="after")
-    def set_attributes_based_on_config(self) -> "BaseAgent":
-        """Set attributes based on the agent configuration."""
-        if self.config:
-            for key, value in self.config.items():
-                setattr(self, key, value)
-        return self
-
-    @model_validator(mode="after")
-    def set_private_attrs(self):
-        """Set private attributes."""
-        self._logger = Logger(self.verbose)
-        if self.max_rpm and not self._rpm_controller:
-            self._rpm_controller = RPMController(
-                max_rpm=self.max_rpm, logger=self._logger
-            )
-        if not self._token_process:
-            self._token_process = TokenProcess()
-        return self
-
-    @property
-    def key(self):
-        source = [self.role, self.goal, self.backstory]
-        return md5("|".join(source).encode()).hexdigest()
-
-    @abstractmethod
-    def execute_task(
-        self,
-        task: Any,
-        context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
-    ) -> str:
-        pass
-
-    @abstractmethod
-    def create_agent_executor(self, tools=None) -> None:
-        pass
-
-    @abstractmethod
-    def _parse_tools(self, tools: List[Any]) -> List[Any]:
-        pass
-
-    @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[Any]:
-        """Set the task tools that init BaseAgenTools class."""
-        pass
-
-    @abstractmethod
-    def get_output_converter(
-        self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
-    ):
-        """Get the converter class for the agent to create json/pydantic outputs."""
-        pass
-
-    def copy(self: T) -> T:  # type: ignore # Signature of "copy" incompatible with supertype "BaseModel"
-        """Create a deep copy of the Agent."""
-        exclude = {
-            "id",
-            "_logger",
-            "_rpm_controller",
-            "_request_within_rpm_limit",
-            "_token_process",
-            "agent_executor",
-            "tools",
-            "tools_handler",
-            "cache_handler",
-            "llm",
-        }
-
-        # Copy llm and clear callbacks
-        existing_llm = shallow_copy(self.llm)
-        existing_llm.callbacks = []
-        copied_data = self.model_dump(exclude=exclude)
-        copied_data = {k: v for k, v in copied_data.items() if v is not None}
-
-        copied_agent = type(self)(**copied_data, llm=existing_llm, tools=self.tools)
-
-        return copied_agent
-
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
-        """Interpolate inputs into the agent description and backstory."""
-        if self._original_role is None:
-            self._original_role = self.role
-        if self._original_goal is None:
-            self._original_goal = self.goal
-        if self._original_backstory is None:
-            self._original_backstory = self.backstory
-
-        if inputs:
-            self.role = self._original_role.format(**inputs)
-            self.goal = self._original_goal.format(**inputs)
-            self.backstory = self._original_backstory.format(**inputs)
-
-    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
-        """Set the cache handler for the agent.
-
-        Args:
-            cache_handler: An instance of the CacheHandler class.
-        """
-        self.tools_handler = ToolsHandler()
-        if self.cache:
-            self.cache_handler = cache_handler
-            self.tools_handler.cache = cache_handler
-        self.create_agent_executor()
-
-    def increment_formatting_errors(self) -> None:
-        self.formatting_errors += 1
-
-    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
-        """Set the rpm controller for the agent.
-
-        Args:
-            rpm_controller: An instance of the RPMController class.
-        """
-        if not self._rpm_controller:
-            self._rpm_controller = rpm_controller
-            self.create_agent_executor()

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

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

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

@@ -1,86 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List, Optional, Union
-
-from pydantic import BaseModel, Field
-
-from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.task import Task
-from crewai.utilities import I18N
-
-
-class BaseAgentTools(BaseModel, ABC):
-    """Default tools around agent delegation"""
-
-    agents: List[BaseAgent] = Field(description="List of agents in this crew.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-
-    @abstractmethod
-    def tools(self):
-        pass
-
-    def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
-        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
-        if coworker:
-            is_list = coworker.startswith("[") and coworker.endswith("]")
-            if is_list:
-                coworker = coworker[1:-1].split(",")[0]
-
-        return coworker
-
-    def delegate_work(
-        self, task: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, task, context)
-
-    def ask_question(
-        self, question: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, question, context)
-
-    def _execute(
-        self, agent_name: Union[str, None], task: str, context: Union[str, None]
-    ):
-        """Execute the command."""
-        try:
-            if agent_name is None:
-                agent_name = ""
-
-            # It is important to remove the quotes from the agent name.
-            # The reason we have to do this is because less-powerful LLM's
-            # have difficulty producing valid JSON.
-            # As a result, we end up with invalid JSON that is truncated like this:
-            # {"task": "....", "coworker": "....
-            # when it should look like this:
-            # {"task": "....", "coworker": "...."}
-            agent_name = agent_name.casefold().replace('"', "").replace("\n", "")
-
-            agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[BaseAgent]", variable has type "str | None")
-                available_agent
-                for available_agent in self.agents
-                if available_agent.role.casefold().replace("\n", "") == agent_name
-            ]
-        except Exception as _:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        if not agent:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        agent = agent[0]
-        task_with_assigned_agent = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
-            description=task,
-            agent=agent,
-            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
-        )
-        return agent.execute_task(task_with_assigned_agent, context)

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

@@ -1,47 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Any, Optional
-
-from pydantic import BaseModel, Field
-
-
-class OutputConverter(BaseModel, ABC):
-    """
-    Abstract base class for converting task results into structured formats.
-
-    This class provides a framework for converting unstructured text into
-    either Pydantic models or JSON, tailored for specific agent requirements.
-    It uses a language model to interpret and structure the input text based
-    on given instructions.
-
-    Attributes:
-        text (str): The input text to be converted.
-        llm (Any): The language model used for conversion.
-        model (Any): The target model for structuring the output.
-        instructions (str): Specific instructions for the conversion process.
-        max_attempts (int): Maximum number of conversion attempts (default: 3).
-    """
-
-    text: str = Field(description="Text to be converted.")
-    llm: Any = Field(description="The language model to be used to convert the text.")
-    model: Any = Field(description="The model to be used to convert the text.")
-    instructions: str = Field(description="Conversion instructions to the LLM.")
-    max_attempts: Optional[int] = Field(
-        description="Max number of attempts to try to get the output formatted.",
-        default=3,
-    )
-
-    @abstractmethod
-    def to_pydantic(self, current_attempt=1):
-        """Convert text to pydantic."""
-        pass
-
-    @abstractmethod
-    def to_json(self, current_attempt=1):
-        """Convert text to json."""
-        pass
-
-    @property
-    @abstractmethod
-    def is_gpt(self) -> bool:
-        """Return if llm provided is of gpt from openai."""
-        pass

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

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

src/crewai/agents/executor.py

@@ -7,19 +7,24 @@ from langchain.agents.agent import ExceptionTool
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain_core.agents import AgentAction, AgentFinish, AgentStep
 from langchain_core.exceptions import OutputParserException
+from langchain_core.pydantic_v1 import root_validator
 from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
 
-from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.tools_handler import ToolsHandler
+from crewai.memory.entity.entity_memory_item import EntityMemoryItem
+from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
+from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.converter import ConverterError
+from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
-class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
+class CrewAgentExecutor(AgentExecutor):
     _i18n: I18N = I18N()
     should_ask_for_human_input: bool = False
     llm: Any = None
@@ -35,12 +40,67 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     tools_handler: Optional[InstanceOf[ToolsHandler]] = None
     max_iterations: Optional[int] = 15
     have_forced_answer: bool = False
-    force_answer_max_iterations: Optional[int] = None  # type: ignore # Incompatible types in assignment (expression has type "int | None", base class "CrewAgentExecutorMixin" defined the type as "int")
+    force_answer_max_iterations: Optional[int] = None
     step_callback: Optional[Any] = None
     system_template: Optional[str] = None
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
 
+    @root_validator()
+    def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
+        values["force_answer_max_iterations"] = values["max_iterations"] - 2
+        return values
+
+    def _should_force_answer(self) -> bool:
+        return (
+            self.iterations == self.force_answer_max_iterations
+        ) and not self.have_forced_answer
+
+    def _create_short_term_memory(self, output) -> None:
+        if (
+            self.crew
+            and self.crew.memory
+            and "Action: Delegate work to coworker" not in output.log
+        ):
+            memory = ShortTermMemoryItem(
+                data=output.log,
+                agent=self.crew_agent.role,
+                metadata={
+                    "observation": self.task.description,
+                },
+            )
+            self.crew._short_term_memory.save(memory)
+
+    def _create_long_term_memory(self, output) -> None:
+        if self.crew and self.crew.memory:
+            ltm_agent = TaskEvaluator(self.crew_agent)
+            evaluation = ltm_agent.evaluate(self.task, output.log)
+
+            if isinstance(evaluation, ConverterError):
+                return
+
+            long_term_memory = LongTermMemoryItem(
+                task=self.task.description,
+                agent=self.crew_agent.role,
+                quality=evaluation.quality,
+                datetime=str(time.time()),
+                expected_output=self.task.expected_output,
+                metadata={
+                    "suggestions": evaluation.suggestions,
+                    "quality": evaluation.quality,
+                },
+            )
+            self.crew._long_term_memory.save(long_term_memory)
+
+            for entity in evaluation.entities:
+                entity_memory = EntityMemoryItem(
+                    name=entity.name,
+                    type=entity.type,
+                    description=entity.description,
+                    relationships="\n".join([f"- {r}" for r in entity.relationships]),
+                )
+                self.crew._entity_memory.save(entity_memory)
+
     def _call(
         self,
         inputs: Dict[str, str],
@@ -232,7 +292,6 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                 tools_names=self.tools_names,
                 function_calling_llm=self.function_calling_llm,
                 task=self.task,
-                agent=self.crew_agent,
                 action=agent_action,
             )
             tool_calling = tool_usage.parse(agent_action.log)
@@ -242,8 +301,6 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             else:
                 if tool_calling.tool_name.casefold().strip() in [
                     name.casefold().strip() for name in name_to_tool_map
-                ] or tool_calling.tool_name.casefold().replace("_", " ") in [
-                    name.casefold().strip() for name in name_to_tool_map
                 ]:
                     observation = tool_usage.use(tool_calling, agent_action.log)
                 else:
@@ -253,6 +310,12 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                     )
             yield AgentStep(action=agent_action, observation=observation)
 
+    def _ask_human_input(self, final_answer: dict) -> str:
+        """Get human input."""
+        return input(
+            self._i18n.slice("getting_input").format(final_answer=final_answer)
+        )
+
     def _handle_crew_training_output(
         self, output: AgentFinish, human_feedback: str | None = None
     ) -> None:

src/crewai/agents/parser.py

@@ -1,7 +1,6 @@
 import re
 from typing import Any, Union
 
-from json_repair import repair_json
 from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain_core.agents import AgentAction, AgentFinish
 from langchain_core.exceptions import OutputParserException
@@ -49,15 +48,11 @@ class CrewAgentParser(ReActSingleInputOutputParser):
                 raise OutputParserException(
                     f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
                 )
-            action = action_match.group(1)
-            clean_action = self._clean_action(action)
-
-            action_input = action_match.group(2).strip()
-
-            tool_input = action_input.strip(" ").strip('"')
-            safe_tool_input = self._safe_repair_json(tool_input)
-
-            return AgentAction(clean_action, safe_tool_input, text)
+            action = action_match.group(1).strip()
+            action_input = action_match.group(2)
+            tool_input = action_input.strip(" ")
+            tool_input = tool_input.strip('"')
+            return AgentAction(action, tool_input, text)
 
         elif includes_answer:
             return AgentFinish(
@@ -92,30 +87,3 @@ class CrewAgentParser(ReActSingleInputOutputParser):
                 llm_output=text,
                 send_to_llm=True,
             )
-
-    def _clean_action(self, text: str) -> str:
-        """Clean action string by removing non-essential formatting characters."""
-        return re.sub(r"^\s*\*+\s*|\s*\*+\s*$", "", text).strip()
-
-    def _safe_repair_json(self, tool_input: str) -> str:
-        UNABLE_TO_REPAIR_JSON_RESULTS = ['""', "{}"]
-
-        # Skip repair if the input starts and ends with square brackets
-        # Explanation: The JSON parser has issues handling inputs that are enclosed in square brackets ('[]').
-        # These are typically valid JSON arrays or strings that do not require repair. Attempting to repair such inputs
-        # might lead to unintended alterations, such as wrapping the entire input in additional layers or modifying
-        # the structure in a way that changes its meaning. By skipping the repair for inputs that start and end with
-        # square brackets, we preserve the integrity of these valid JSON structures and avoid unnecessary modifications.
-        if tool_input.startswith("[") and tool_input.endswith("]"):
-            return tool_input
-
-        # Before repair, handle common LLM issues:
-        # 1. Replace """ with " to avoid JSON parser errors
-
-        tool_input = tool_input.replace('"""', '"')
-
-        result = repair_json(tool_input)
-        if result in UNABLE_TO_REPAIR_JSON_RESULTS:
-            return tool_input
-
-        return str(result)

src/crewai/cli/cli.py

@@ -1,14 +1,7 @@
 import click
 import pkg_resources
 
-from crewai.memory.storage.kickoff_task_outputs_storage import (
-    KickoffTaskOutputsSQLiteStorage,
-)
-
 from .create_crew import create_crew
-from .replay_from_task import replay_task_command
-from .reset_memories_command import reset_memories_command
-from .test_crew import test_crew
 from .train_crew import train_crew
 
 
@@ -55,97 +48,5 @@ def train(n_iterations: int):
     train_crew(n_iterations)
 
 
-@crewai.command()
-@click.option(
-    "-t",
-    "--task_id",
-    type=str,
-    help="Replay the crew from this task ID, including all subsequent tasks.",
-)
-def replay(task_id: str) -> None:
-    """
-    Replay the crew execution from a specific task.
-
-    Args:
-        task_id (str): The ID of the task to replay from.
-    """
-    try:
-        click.echo(f"Replaying the crew from task {task_id}")
-        replay_task_command(task_id)
-    except Exception as e:
-        click.echo(f"An error occurred while replaying: {e}", err=True)
-
-
-@crewai.command()
-def log_tasks_outputs() -> None:
-    """
-    Retrieve your latest crew.kickoff() task outputs.
-    """
-    try:
-        storage = KickoffTaskOutputsSQLiteStorage()
-        tasks = storage.load()
-
-        if not tasks:
-            click.echo(
-                "No task outputs found. Only crew kickoff task outputs are logged."
-            )
-            return
-
-        for index, task in enumerate(tasks, 1):
-            click.echo(f"Task {index}: {task['task_id']}")
-            click.echo(f"Description: {task['expected_output']}")
-            click.echo("------")
-
-    except Exception as e:
-        click.echo(f"An error occurred while logging task outputs: {e}", err=True)
-
-
-@crewai.command()
-@click.option("-l", "--long", is_flag=True, help="Reset LONG TERM memory")
-@click.option("-s", "--short", is_flag=True, help="Reset SHORT TERM memory")
-@click.option("-e", "--entities", is_flag=True, help="Reset ENTITIES memory")
-@click.option(
-    "-k",
-    "--kickoff-outputs",
-    is_flag=True,
-    help="Reset LATEST KICKOFF TASK OUTPUTS",
-)
-@click.option("-a", "--all", is_flag=True, help="Reset ALL memories")
-def reset_memories(long, short, entities, kickoff_outputs, all):
-    """
-    Reset the crew memories (long, short, entity, latest_crew_kickoff_ouputs). This will delete all the data saved.
-    """
-    try:
-        if not all and not (long or short or entities or kickoff_outputs):
-            click.echo(
-                "Please specify at least one memory type to reset using the appropriate flags."
-            )
-            return
-        reset_memories_command(long, short, entities, kickoff_outputs, all)
-    except Exception as e:
-        click.echo(f"An error occurred while resetting memories: {e}", err=True)
-
-
-@crewai.command()
-@click.option(
-    "-n",
-    "--n_iterations",
-    type=int,
-    default=3,
-    help="Number of iterations to Test the crew",
-)
-@click.option(
-    "-m",
-    "--model",
-    type=str,
-    default="gpt-4o-mini",
-    help="LLM Model to run the tests on the Crew. For now only accepting only OpenAI models.",
-)
-def test(n_iterations: int, model: str):
-    """Test the crew and evaluate the results."""
-    click.echo(f"Testing the crew for {n_iterations} iterations with model {model}")
-    test_crew(n_iterations, model)
-
-
 if __name__ == "__main__":
     crewai()

src/crewai/cli/replay_from_task.py

@@ -1,24 +0,0 @@
-import subprocess
-import click
-
-
-def replay_task_command(task_id: str) -> None:
-    """
-    Replay the crew execution from a specific task.
-
-    Args:
-      task_id (str): The ID of the task to replay from.
-    """
-    command = ["poetry", "run", "replay", task_id]
-
-    try:
-        result = subprocess.run(command, capture_output=False, text=True, check=True)
-        if result.stderr:
-            click.echo(result.stderr, err=True)
-
-    except subprocess.CalledProcessError as e:
-        click.echo(f"An error occurred while replaying the task: {e}", err=True)
-        click.echo(e.output, err=True)
-
-    except Exception as e:
-        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/cli/reset_memories_command.py

@@ -1,45 +0,0 @@
-import subprocess
-import click
-
-from crewai.memory.entity.entity_memory import EntityMemory
-from crewai.memory.long_term.long_term_memory import LongTermMemory
-from crewai.memory.short_term.short_term_memory import ShortTermMemory
-from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
-
-
-def reset_memories_command(long, short, entity, kickoff_outputs, all) -> None:
-    """
-    Replay the crew execution from a specific task.
-
-    Args:
-      task_id (str): The ID of the task to replay from.
-    """
-
-    try:
-        if all:
-            ShortTermMemory().reset()
-            EntityMemory().reset()
-            LongTermMemory().reset()
-            TaskOutputStorageHandler().reset()
-            click.echo("All memories have been reset.")
-        else:
-            if long:
-                LongTermMemory().reset()
-                click.echo("Long term memory has been reset.")
-
-            if short:
-                ShortTermMemory().reset()
-                click.echo("Short term memory has been reset.")
-            if entity:
-                EntityMemory().reset()
-                click.echo("Entity memory has been reset.")
-            if kickoff_outputs:
-                TaskOutputStorageHandler().reset()
-                click.echo("Latest Kickoff outputs stored has been reset.")
-
-    except subprocess.CalledProcessError as e:
-        click.echo(f"An error occurred while resetting the memories: {e}", err=True)
-        click.echo(e.output, err=True)
-
-    except Exception as e:
-        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/cli/templates/config/tasks.yaml

@@ -5,7 +5,6 @@ research_task:
     the current year is 2024.
   expected_output: >
     A list with 10 bullet points of the most relevant information about {topic}
-  agent: researcher
 
 reporting_task:
   description: >
@@ -13,5 +12,4 @@ reporting_task:
     Make sure the report is detailed and contains any and all relevant information.
   expected_output: >
     A fully fledge reports with the mains topics, each with a full section of information.
-    Formatted as markdown without '```'
-  agent: reporting_analyst
+    Formated as markdown with out '```'

src/crewai/cli/templates/crew.py

@@ -32,12 +32,14 @@ class {{crew_name}}Crew():
 	def research_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['research_task'],
+			agent=self.researcher()
 		)
 
 	@task
 	def reporting_task(self) -> Task:
 		return Task(
 			config=self.tasks_config['reporting_task'],
+			agent=self.reporting_analyst(),
 			output_file='report.md'
 		)
 

src/crewai/cli/templates/main.py

@@ -2,15 +2,9 @@
 import sys
 from {{folder_name}}.crew import {{crew_name}}Crew
 
-# This main file is intended to be a way for your to run your
-# crew locally, so refrain from adding necessary logic into this file.
-# Replace with inputs you want to test with, it will automatically
-# interpolate any tasks and agents information
 
 def run():
-    """
-    Run the crew.
-    """
+    # Replace with your inputs, it will automatically interpolate any tasks and agents information
     inputs = {
         'topic': 'AI LLMs'
     }
@@ -21,34 +15,9 @@ def train():
     """
     Train the crew for a given number of iterations.
     """
-    inputs = {
-        "topic": "AI LLMs"
-    }
+    inputs = {"topic": "AI LLMs"}
     try:
         {{crew_name}}Crew().crew().train(n_iterations=int(sys.argv[1]), inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while training the crew: {e}")
-
-def replay():
-    """
-    Replay the crew execution from a specific task.
-    """
-    try:
-        {{crew_name}}Crew().crew().replay(task_id=sys.argv[1])
-
-    except Exception as e:
-        raise Exception(f"An error occurred while replaying the crew: {e}")
-
-def test():
-    """
-    Test the crew execution and returns the results.
-    """
-    inputs = {
-        "topic": "AI LLMs"
-    }
-    try:
-        {{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), model=sys.argv[2], inputs=inputs)
-
-    except Exception as e:
-        raise Exception(f"An error occurred while replaying the crew: {e}")

src/crewai/cli/templates/pyproject.toml

@@ -6,13 +6,11 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.41.1" }
+crewai = { extras = ["tools"], version = "^0.32.2" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"
 train = "{{folder_name}}.main:train"
-replay = "{{folder_name}}.main:replay"
-test = "{{folder_name}}.main:test"
 
 [build-system]
 requires = ["poetry-core"]

src/crewai/cli/test_crew.py

@@ -1,30 +0,0 @@
-import subprocess
-
-import click
-
-
-def test_crew(n_iterations: int, model: str) -> None:
-    """
-    Test the crew by running a command in the Poetry environment.
-
-    Args:
-        n_iterations (int): The number of iterations to test the crew.
-        model (str): The model to test the crew with.
-    """
-    command = ["poetry", "run", "test", str(n_iterations), model]
-
-    try:
-        if n_iterations <= 0:
-            raise ValueError("The number of iterations must be a positive integer.")
-
-        result = subprocess.run(command, capture_output=False, text=True, check=True)
-
-        if result.stderr:
-            click.echo(result.stderr, err=True)
-
-    except subprocess.CalledProcessError as e:
-        click.echo(f"An error occurred while testing the crew: {e}", err=True)
-        click.echo(e.output, err=True)
-
-    except Exception as e:
-        click.echo(f"An unexpected error occurred: {e}", err=True)

src/crewai/crew.py

@@ -1,9 +1,7 @@
 import asyncio
 import json
 import uuid
-from concurrent.futures import Future
-from hashlib import md5
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, Dict, List, Optional, Union
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
@@ -20,37 +18,18 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agent import Agent
-from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
-from crewai.crews.crew_output import CrewOutput
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.process import Process
 from crewai.task import Task
-from crewai.tasks.conditional_task import ConditionalTask
-from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
 from crewai.tools.agent_tools import AgentTools
 from crewai.utilities import I18N, FileHandler, Logger, RPMController
-from crewai.utilities.constants import (
-    TRAINED_AGENTS_DATA_FILE,
-    TRAINING_DATA_FILE,
-)
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
-from crewai.utilities.formatter import (
-    aggregate_raw_outputs_from_task_outputs,
-    aggregate_raw_outputs_from_tasks,
-)
-from crewai.utilities.planning_handler import CrewPlanner
-from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
 
-try:
-    import agentops
-except ImportError:
-    agentops = None
-
 
 class Crew(BaseModel):
     """
@@ -71,10 +50,10 @@ class Crew(BaseModel):
         max_rpm: Maximum number of requests per minute for the crew execution to be respected.
         prompt_file: Path to the prompt json file to be used for the crew.
         id: A unique identifier for the crew instance.
+        full_output: Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.
         task_callback: Callback to be executed after each task for every agents execution.
         step_callback: Callback to be executed after each step for every agents execution.
         share_crew: Whether you want to share the complete crew information and execution with crewAI to make the library better, and allow us to train models.
-        planning: Plan the crew execution and add the plan to the crew.
     """
 
     __hash__ = object.__hash__  # type: ignore
@@ -88,18 +67,11 @@ class Crew(BaseModel):
     _entity_memory: Optional[InstanceOf[EntityMemory]] = PrivateAttr()
     _train: Optional[bool] = PrivateAttr(default=False)
     _train_iteration: Optional[int] = PrivateAttr()
-    _inputs: Optional[Dict[str, Any]] = PrivateAttr(default=None)
-    _logging_color: str = PrivateAttr(
-        default="bold_purple",
-    )
-    _task_output_handler: TaskOutputStorageHandler = PrivateAttr(
-        default_factory=TaskOutputStorageHandler
-    )
 
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
-    agents: List[BaseAgent] = Field(default_factory=list)
+    agents: List[Agent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
     verbose: Union[int, bool] = Field(default=0)
     memory: bool = Field(
@@ -114,10 +86,14 @@ class Crew(BaseModel):
         default=None,
         description="Metrics for the LLM usage during all tasks execution.",
     )
+    full_output: Optional[bool] = Field(
+        default=False,
+        description="Whether the crew should return the full output with all tasks outputs and token usage metrics or just the final output.",
+    )
     manager_llm: Optional[Any] = Field(
         description="Language model that will run the agent.", default=None
     )
-    manager_agent: Optional[BaseAgent] = Field(
+    manager_agent: Optional[Any] = Field(
         description="Custom agent that will be used as manager.", default=None
     )
     manager_callbacks: Optional[List[InstanceOf[BaseCallbackHandler]]] = Field(
@@ -150,18 +126,6 @@ class Crew(BaseModel):
         default=False,
         description="output_log_file",
     )
-    planning: Optional[bool] = Field(
-        default=False,
-        description="Plan the crew execution and add the plan to the crew.",
-    )
-    task_execution_output_json_files: Optional[List[str]] = Field(
-        default=None,
-        description="List of file paths for task execution JSON files.",
-    )
-    execution_logs: List[Dict[str, Any]] = Field(
-        default=[],
-        description="List of execution logs for tasks",
-    )
 
     @field_validator("id", mode="before")
     @classmethod
@@ -197,6 +161,7 @@ class Crew(BaseModel):
         self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
         self._telemetry = Telemetry()
         self._telemetry.set_tracer()
+        self._telemetry.crew_creation(self)
         return self
 
     @model_validator(mode="after")
@@ -253,120 +218,6 @@ 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
-
-    @model_validator(mode="after")
-    def validate_end_with_at_most_one_async_task(self):
-        """Validates that the crew ends with at most one asynchronous task."""
-        final_async_task_count = 0
-
-        # Traverse tasks backward
-        for task in reversed(self.tasks):
-            if task.async_execution:
-                final_async_task_count += 1
-            else:
-                break  # Stop traversing as soon as a non-async task is encountered
-
-        if final_async_task_count > 1:
-            raise PydanticCustomError(
-                "async_task_count",
-                "The crew must end with at most one asynchronous task.",
-                {},
-            )
-
-        return self
-
-    @model_validator(mode="after")
-    def validate_first_task(self) -> "Crew":
-        """Ensure the first task is not a ConditionalTask."""
-        if self.tasks and isinstance(self.tasks[0], ConditionalTask):
-            raise PydanticCustomError(
-                "invalid_first_task",
-                "The first task cannot be a ConditionalTask.",
-                {},
-            )
-        return self
-
-    @model_validator(mode="after")
-    def validate_async_tasks_not_async(self) -> "Crew":
-        """Ensure that ConditionalTask is not async."""
-        for task in self.tasks:
-            if task.async_execution and isinstance(task, ConditionalTask):
-                raise PydanticCustomError(
-                    "invalid_async_conditional_task",
-                    f"Conditional Task: {task.description} , cannot be executed asynchronously.",  # type: ignore # Argument of type "str" cannot be assigned to parameter "message_template" of type "LiteralString"
-                    {},
-                )
-        return self
-
-    @model_validator(mode="after")
-    def validate_async_task_cannot_include_sequential_async_tasks_in_context(self):
-        """
-        Validates that if a task is set to be executed asynchronously,
-        it cannot include other asynchronous tasks in its context unless
-        separated by a synchronous task.
-        """
-        for i, task in enumerate(self.tasks):
-            if task.async_execution and task.context:
-                for context_task in task.context:
-                    if context_task.async_execution:
-                        for j in range(i - 1, -1, -1):
-                            if self.tasks[j] == context_task:
-                                raise ValueError(
-                                    f"Task '{task.description}' is asynchronous and cannot include other sequential asynchronous tasks in its context."
-                                )
-                            if not self.tasks[j].async_execution:
-                                break
-        return self
-
-    @model_validator(mode="after")
-    def validate_context_no_future_tasks(self):
-        """Validates that a task's context does not include future tasks."""
-        task_indices = {id(task): i for i, task in enumerate(self.tasks)}
-
-        for task in self.tasks:
-            if task.context:
-                for context_task in task.context:
-                    if id(context_task) not in task_indices:
-                        continue  # Skip context tasks not in the main tasks list
-                    if task_indices[id(context_task)] > task_indices[id(task)]:
-                        raise ValueError(
-                            f"Task '{task.description}' has a context dependency on a future task '{context_task.description}', which is not allowed."
-                        )
-        return self
-
-    @property
-    def key(self) -> str:
-        source = [agent.key for agent in self.agents] + [
-            task.key for task in self.tasks
-        ]
-        return md5("|".join(source).encode()).hexdigest()
-
     def _setup_from_config(self):
         assert self.config is not None, "Config should not be None."
 
@@ -405,9 +256,6 @@ class Crew(BaseModel):
         for agent in self.agents:
             agent.allow_delegation = False
 
-        CrewTrainingHandler(TRAINING_DATA_FILE).initialize_file()
-        CrewTrainingHandler(TRAINED_AGENTS_DATA_FILE).initialize_file()
-
     def train(self, n_iterations: int, inputs: Optional[Dict[str, Any]] = {}) -> None:
         """Trains the crew for a given number of iterations."""
         self._setup_for_training()
@@ -416,205 +264,151 @@ class Crew(BaseModel):
             self._train_iteration = n_iteration
             self.kickoff(inputs=inputs)
 
-        training_data = CrewTrainingHandler(TRAINING_DATA_FILE).load()
+        training_data = CrewTrainingHandler("training_data.pkl").load()
 
         for agent in self.agents:
             result = TaskEvaluator(agent).evaluate_training_data(
                 training_data=training_data, agent_id=str(agent.id)
             )
 
-            CrewTrainingHandler(TRAINED_AGENTS_DATA_FILE).save_trained_data(
+            CrewTrainingHandler("trained_agents_data.pkl").save_trained_data(
                 agent_id=str(agent.role), trained_data=result.model_dump()
             )
 
     def kickoff(
         self,
-        inputs: Optional[Dict[str, Any]] = None,
-    ) -> CrewOutput:
+        inputs: Optional[Dict[str, Any]] = {},
+    ) -> Union[str, Dict[str, Any]]:
         """Starts the crew to work on its assigned tasks."""
-        self._execution_span = self._telemetry.crew_execution_span(self, inputs)
-        self._task_output_handler.reset()
-        self._logging_color = "bold_purple"
+        self._execution_span = self._telemetry.crew_execution_span(self)
 
-        if inputs is not None:
-            self._inputs = inputs
-            self._interpolate_inputs(inputs)
+        self._interpolate_inputs(inputs)  # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
         self._set_tasks_callbacks()
 
         i18n = I18N(prompt_file=self.prompt_file)
 
         for agent in self.agents:
             agent.i18n = i18n
-            # type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
-            agent.crew = self  # type: ignore[attr-defined]
-            # TODO: Create an AgentFunctionCalling protocol for future refactoring
-            if not agent.function_calling_llm:  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
-                agent.function_calling_llm = self.function_calling_llm  # type: ignore # "BaseAgent" has no attribute "function_calling_llm"
+            agent.crew = self
 
-            if agent.allow_code_execution:  # type: ignore # BaseAgent" has no attribute "allow_code_execution"
-                agent.tools += agent.get_code_execution_tools()  # type: ignore # "BaseAgent" has no attribute "get_code_execution_tools"; maybe "get_delegation_tools"?
-
-            if not agent.step_callback:  # type: ignore # "BaseAgent" has no attribute "step_callback"
-                agent.step_callback = self.step_callback  # type: ignore # "BaseAgent" has no attribute "step_callback"
+            if not agent.function_calling_llm:
+                agent.function_calling_llm = self.function_calling_llm
+            if not agent.step_callback:
+                agent.step_callback = self.step_callback
 
             agent.create_agent_executor()
 
-        if self.planning:
-            self._handle_crew_planning()
-
         metrics = []
 
         if self.process == Process.sequential:
             result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            result = self._run_hierarchical_process()
+            result, manager_metrics = self._run_hierarchical_process()  # type: ignore # Unpacking a string is disallowed
+            metrics.append(manager_metrics)  # type: ignore # Cannot determine type of "manager_metrics"
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
             )
-        metrics += [agent._token_process.get_summary() for agent in self.agents]
 
+        metrics = metrics + [
+            agent._token_process.get_summary() for agent in self.agents
+        ]
         self.usage_metrics = {
-            key: sum([m[key] for m in metrics if m is not None]) for key in metrics[0]
+            key: sum([m[key] for m in metrics if m is not None])  # type: ignore # List comprehension has incompatible type List[Any | str]; expected List[bool]
+            for key in metrics[0]
         }
 
         return result
 
-    def kickoff_for_each(self, inputs: List[Dict[str, Any]]) -> List[CrewOutput]:
+    def kickoff_for_each(self, inputs: List[Dict[str, Any]]) -> List:
         """Executes the Crew's workflow for each input in the list and aggregates results."""
-        results: List[CrewOutput] = []
-
-        # Initialize the parent crew's usage metrics
-        total_usage_metrics = {
-            "total_tokens": 0,
-            "prompt_tokens": 0,
-            "completion_tokens": 0,
-            "successful_requests": 0,
-        }
+        results = []
 
         for input_data in inputs:
             crew = self.copy()
 
-            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)
+            for task in crew.tasks:
+                task.interpolate_inputs(input_data)
+            for agent in crew.agents:
+                agent.interpolate_inputs(input_data)
 
+            output = crew.kickoff()
             results.append(output)
 
-        self.usage_metrics = total_usage_metrics
-        self._task_output_handler.reset()
         return results
 
-    async def kickoff_async(self, inputs: Optional[Dict[str, Any]] = {}) -> CrewOutput:
+    async def kickoff_async(
+        self, inputs: Optional[Dict[str, Any]] = {}
+    ) -> Union[str, Dict]:
         """Asynchronous kickoff method to start the crew execution."""
         return await asyncio.to_thread(self.kickoff, inputs)
 
-    async def kickoff_for_each_async(self, inputs: List[Dict]) -> List[CrewOutput]:
-        crew_copies = [self.copy() for _ in inputs]
+    async def kickoff_for_each_async(self, inputs: List[Dict]) -> List[Any]:
+        async def run_crew(input_data):
+            crew = self.copy()
 
-        async def run_crew(crew, input_data):
-            return await crew.kickoff_async(inputs=input_data)
+            for task in crew.tasks:
+                task.interpolate_inputs(input_data)
+            for agent in crew.agents:
+                agent.interpolate_inputs(input_data)
 
-        tasks = [
-            asyncio.create_task(run_crew(crew_copies[i], inputs[i]))
-            for i in range(len(inputs))
-        ]
-        tasks = [
-            asyncio.create_task(run_crew(crew_copies[i], inputs[i]))
-            for i in range(len(inputs))
-        ]
+            return await crew.kickoff_async()
+
+        tasks = [asyncio.create_task(run_crew(input_data)) for input_data in 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
-
-        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
-        self._task_output_handler.reset()
         return results
 
-    def _handle_crew_planning(self):
-        """Handles the Crew planning."""
-        self._logger.log("info", "Planning the crew execution")
-        result = CrewPlanner(self.tasks)._handle_crew_planning()
+    def _run_sequential_process(self) -> str:
+        """Executes tasks sequentially and returns the final output."""
+        task_output = ""
+        for task in self.tasks:
+            if task.agent.allow_delegation:  # type: ignore #  Item "None" of "Agent | None" has no attribute "allow_delegation"
+                agents_for_delegation = [
+                    agent for agent in self.agents if agent != task.agent
+                ]
+                if len(self.agents) > 1 and len(agents_for_delegation) > 0:
+                    task.tools += AgentTools(agents=agents_for_delegation).tools()
 
-        if result is not None and hasattr(result, "list_of_plans_per_task"):
-            for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
-                task.description += step_plan
-        else:
+            role = task.agent.role if task.agent is not None else "None"
+            self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
             self._logger.log(
-                "info", "Something went wrong with the planning process of the Crew"
+                "info", f"== Starting Task: {task.description}", color="bold_purple"
             )
 
-    def _store_execution_log(
-        self,
-        task: Task,
-        output: TaskOutput,
-        task_index: int,
-        was_replayed: bool = False,
-    ):
-        if self._inputs:
-            inputs = self._inputs
-        else:
-            inputs = {}
+            if self.output_log_file:
+                self._file_handler.log(
+                    agent=role, task=task.description, status="started"
+                )
 
-        log = {
-            "task": task,
-            "output": {
-                "description": output.description,
-                "summary": output.summary,
-                "raw": output.raw,
-                "pydantic": output.pydantic,
-                "json_dict": output.json_dict,
-                "output_format": output.output_format,
-                "agent": output.agent,
-            },
-            "task_index": task_index,
-            "inputs": inputs,
-            "was_replayed": was_replayed,
-        }
-        self._task_output_handler.update(task_index, log)
+            output = task.execute(context=task_output)
 
-    def _run_sequential_process(self) -> CrewOutput:
-        """Executes tasks sequentially and returns the final output."""
-        return self._execute_tasks(self.tasks)
+            if not task.async_execution:
+                task_output = output
 
-    def _run_hierarchical_process(self) -> CrewOutput:
+            role = task.agent.role if task.agent is not None else "None"
+            self._logger.log("debug", f"== [{role}] Task output: {task_output}\n\n")
+
+            if self.output_log_file:
+                self._file_handler.log(agent=role, task=task_output, status="completed")
+
+        self._finish_execution(task_output)
+
+        token_usage = task.agent._token_process.get_summary()  # type: ignore # Item "None" of "Agent | None" has no attribute "_token_process"
+
+        return self._format_output(task_output, token_usage)  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
+
+    def _run_hierarchical_process(self) -> Union[str, Dict[str, Any]]:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
-        self._create_manager_agent()
-        return self._execute_tasks(self.tasks, self.manager_agent)
 
-    def _create_manager_agent(self):
         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 manager.tools is not None and len(manager.tools) > 0:
+            if len(manager.tools) > 0:
                 raise Exception("Manager agent should not have tools")
-            manager.tools = self.manager_agent.get_delegation_tools(self.agents)
+            manager.tools = AgentTools(agents=self.agents).tools()
         else:
             manager = Agent(
                 role=i18n.retrieve("hierarchical_manager_agent", "role"),
@@ -622,267 +416,36 @@ class Crew(BaseModel):
                 backstory=i18n.retrieve("hierarchical_manager_agent", "backstory"),
                 tools=AgentTools(agents=self.agents).tools(),
                 llm=self.manager_llm,
-                verbose=self.verbose,
+                verbose=True,
             )
-            self.manager_agent = manager
 
-    def _execute_tasks(
-        self,
-        tasks: List[Task],
-        manager: Optional[BaseAgent] = None,
-        start_index: Optional[int] = 0,
-        was_replayed: bool = False,
-    ) -> CrewOutput:
-        """Executes tasks sequentially and returns the final output.
+        task_output = ""
+        for task in self.tasks:
+            self._logger.log("debug", f"Working Agent: {manager.role}")
+            self._logger.log("info", f"Starting Task: {task.description}")
 
-        Args:
-            tasks (List[Task]): List of tasks to execute
-            manager (Optional[BaseAgent], optional): Manager agent to use for delegation. Defaults to None.
-
-        Returns:
-            CrewOutput: Final output of the crew
-        """
-
-        task_outputs: List[TaskOutput] = []
-        futures: List[Tuple[Task, Future[TaskOutput], int]] = []
-        last_sync_output: Optional[TaskOutput] = None
-
-        for task_index, task in enumerate(tasks):
-            if start_index is not None and task_index < start_index:
-                if task.output:
-                    if task.async_execution:
-                        task_outputs.append(task.output)
-                    else:
-                        task_outputs = [task.output]
-                        last_sync_output = task.output
-                continue
-
-            agent_to_use = self._get_agent_to_use(task, manager)
-            if agent_to_use is None:
-                raise ValueError(
-                    f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
+            if self.output_log_file:
+                self._file_handler.log(
+                    agent=manager.role, task=task.description, status="started"
                 )
 
-            self._prepare_agent_tools(task, manager)
-            self._log_task_start(task, agent_to_use.role)
-
-            if isinstance(task, ConditionalTask):
-                skipped_task_output = self._handle_conditional_task(
-                    task, task_outputs, futures, task_index, was_replayed
-                )
-                if skipped_task_output:
-                    continue
-
-            if task.async_execution:
-                context = self._get_context(
-                    task, [last_sync_output] if last_sync_output else []
-                )
-                future = task.execute_async(
-                    agent=agent_to_use,
-                    context=context,
-                    tools=agent_to_use.tools,
-                )
-                futures.append((task, future, task_index))
-            else:
-                if futures:
-                    task_outputs = self._process_async_tasks(futures, was_replayed)
-                    futures.clear()
-
-                context = self._get_context(task, task_outputs)
-                task_output = task.execute_sync(
-                    agent=agent_to_use,
-                    context=context,
-                    tools=agent_to_use.tools,
-                )
-                task_outputs = [task_output]
-                self._process_task_result(task, task_output)
-                self._store_execution_log(task, task_output, task_index, was_replayed)
-
-        if futures:
-            task_outputs = self._process_async_tasks(futures, was_replayed)
-
-        return self._create_crew_output(task_outputs)
-
-    def _handle_conditional_task(
-        self,
-        task: ConditionalTask,
-        task_outputs: List[TaskOutput],
-        futures: List[Tuple[Task, Future[TaskOutput], int]],
-        task_index: int,
-        was_replayed: bool,
-    ) -> Optional[TaskOutput]:
-        if futures:
-            task_outputs = self._process_async_tasks(futures, was_replayed)
-            futures.clear()
-
-        previous_output = task_outputs[task_index - 1] if task_outputs else None
-        if previous_output is not None and not task.should_execute(previous_output):
-            self._logger.log(
-                "debug",
-                f"Skipping conditional task: {task.description}",
-                color="yellow",
+            task_output = task.execute(
+                agent=manager, context=task_output, tools=manager.tools
             )
-            skipped_task_output = task.get_skipped_task_output()
 
-            if not was_replayed:
-                self._store_execution_log(task, skipped_task_output, task_index)
-            return skipped_task_output
-        return None
+            self._logger.log("debug", f"[{manager.role}] Task ouptput: {task_output}")
 
-    def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
-        if self.process == Process.hierarchical:
-            if manager:
-                self._update_manager_tools(task, manager)
-            else:
-                raise ValueError("Manager agent is required for hierarchical process.")
-        elif task.agent and task.agent.allow_delegation:
-            self._add_delegation_tools(task)
-
-    def _get_agent_to_use(
-        self, task: Task, manager: Optional[BaseAgent]
-    ) -> Optional[BaseAgent]:
-        if self.process == Process.hierarchical:
-            return manager
-        return task.agent
-
-    def _add_delegation_tools(self, task: Task):
-        agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
-        if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
-            delegation_tools = task.agent.get_delegation_tools(agents_for_delegation)
-
-            # Add tools if they are not already in task.tools
-            for new_tool in delegation_tools:
-                # Find the index of the tool with the same name
-                existing_tool_index = next(
-                    (
-                        index
-                        for index, tool in enumerate(task.tools or [])
-                        if tool.name == new_tool.name
-                    ),
-                    None,
+            if self.output_log_file:
+                self._file_handler.log(
+                    agent=manager.role, task=task_output, status="completed"
                 )
-                if not task.tools:
-                    task.tools = []
 
-                if existing_tool_index is not None:
-                    # Replace the existing tool
-                    task.tools[existing_tool_index] = new_tool
-                else:
-                    # Add the new tool
-                    task.tools.append(new_tool)
+        self._finish_execution(task_output)
 
-    def _log_task_start(self, task: Task, role: str = "None"):
-        color = self._logging_color
-        self._logger.log("debug", f"== Working Agent: {role}", color=color)
-        self._logger.log("info", f"== Starting Task: {task.description}", color=color)
-        if self.output_log_file:
-            self._file_handler.log(agent=role, task=task.description, status="started")
-
-    def _update_manager_tools(self, task: Task, manager: BaseAgent):
-        if task.agent:
-            manager.tools = task.agent.get_delegation_tools([task.agent])
-        else:
-            manager.tools = manager.get_delegation_tools(self.agents)
-
-    def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
-        context = (
-            aggregate_raw_outputs_from_tasks(task.context)
-            if task.context
-            else aggregate_raw_outputs_from_task_outputs(task_outputs)
-        )
-        return context
-
-    def _process_task_result(self, task: Task, output: TaskOutput) -> None:
-        role = task.agent.role if task.agent is not None else "None"
-        self._logger.log("debug", f"== [{role}] Task output: {output}\n\n")
-        if self.output_log_file:
-            self._file_handler.log(agent=role, task=output, status="completed")
-
-    def _create_crew_output(self, task_outputs: List[TaskOutput]) -> CrewOutput:
-        if len(task_outputs) != 1:
-            raise ValueError(
-                "Something went wrong. Kickoff should return only one task output."
-            )
-        final_task_output = task_outputs[0]
-        final_string_output = final_task_output.raw
-        self._finish_execution(final_string_output)
-        token_usage = self.calculate_usage_metrics()
-
-        return CrewOutput(
-            raw=final_task_output.raw,
-            pydantic=final_task_output.pydantic,
-            json_dict=final_task_output.json_dict,
-            tasks_output=[task.output for task in self.tasks if task.output],
-            token_usage=token_usage,
-        )
-
-    def _process_async_tasks(
-        self,
-        futures: List[Tuple[Task, Future[TaskOutput], int]],
-        was_replayed: bool = False,
-    ) -> List[TaskOutput]:
-        task_outputs: List[TaskOutput] = []
-        for future_task, future, task_index in futures:
-            task_output = future.result()
-            task_outputs.append(task_output)
-            self._process_task_result(future_task, task_output)
-            self._store_execution_log(
-                future_task, task_output, task_index, was_replayed
-            )
-        return task_outputs
-
-    def _find_task_index(
-        self, task_id: str, stored_outputs: List[Any]
-    ) -> Optional[int]:
-        return next(
-            (
-                index
-                for (index, d) in enumerate(stored_outputs)
-                if d["task_id"] == str(task_id)
-            ),
-            None,
-        )
-
-    def replay(
-        self, task_id: str, inputs: Optional[Dict[str, Any]] = None
-    ) -> CrewOutput:
-        stored_outputs = self._task_output_handler.load()
-        if not stored_outputs:
-            raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
-
-        start_index = self._find_task_index(task_id, stored_outputs)
-
-        if start_index is None:
-            raise ValueError(f"Task with id {task_id} not found in the crew's tasks.")
-
-        replay_inputs = (
-            inputs if inputs is not None else stored_outputs[start_index]["inputs"]
-        )
-        self._inputs = replay_inputs
-
-        if replay_inputs:
-            self._interpolate_inputs(replay_inputs)
-
-        if self.process == Process.hierarchical:
-            self._create_manager_agent()
-
-        for i in range(start_index):
-            stored_output = stored_outputs[i][
-                "output"
-            ]  # for adding context to the task
-            task_output = TaskOutput(
-                description=stored_output["description"],
-                agent=stored_output["agent"],
-                raw=stored_output["raw"],
-                pydantic=stored_output["pydantic"],
-                json_dict=stored_output["json_dict"],
-                output_format=stored_output["output_format"],
-            )
-            self.tasks[i].output = task_output
-
-        self._logging_color = "bold_blue"
-        result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
-        return result
+        manager_token_usage = manager._token_process.get_summary()
+        return self._format_output(  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
+            task_output, manager_token_usage
+        ), manager_token_usage
 
     def copy(self):
         """Create a deep copy of the Crew."""
@@ -897,13 +460,12 @@ 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(cloned_agents) for task in self.tasks]
+        cloned_tasks = [task.copy() 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}
@@ -930,47 +492,29 @@ class Crew(BaseModel):
             )
             for task in self.tasks
         ]
-        # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
-        for agent in self.agents:
-            agent.interpolate_inputs(inputs)
 
-    def _finish_execution(self, final_string_output: str) -> None:
+        [agent.interpolate_inputs(inputs) for agent in self.agents]  # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
+
+    def _format_output(
+        self, output: str, token_usage: Optional[Dict[str, Any]]
+    ) -> Union[str, Dict[str, Any]]:
+        """
+        Formats the output of the crew execution.
+        If full_output is True, then returned data type will be a dictionary else returned outputs are string
+        """
+        if self.full_output:
+            return {  # type: ignore # Incompatible return value type (got "dict[str, Sequence[str | TaskOutput | None]]", expected "str")
+                "final_output": output,
+                "tasks_outputs": [task.output for task in self.tasks if task],
+                "usage_metrics": token_usage,
+            }
+        else:
+            return output
+
+    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, final_string_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 test(
-        self, n_iterations: int, model: str, inputs: Optional[Dict[str, Any]] = None
-    ) -> None:
-        """Test the crew with the given inputs."""
-        pass
+        self._telemetry.end_crew(self, output)
 
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/crews/__init__.py

@@ -1 +0,0 @@
-from .crew_output import CrewOutput

src/crewai/crews/crew_output.py

@@ -1,50 +0,0 @@
-import json
-from typing import Any, Dict, Optional
-
-from pydantic import BaseModel, Field
-
-from crewai.tasks.output_format import OutputFormat
-from crewai.tasks.task_output import TaskOutput
-
-
-class CrewOutput(BaseModel):
-    """Class that represents the result of a crew."""
-
-    raw: str = Field(description="Raw output of crew", default="")
-    pydantic: Optional[BaseModel] = Field(
-        description="Pydantic output of Crew", default=None
-    )
-    json_dict: Optional[Dict[str, Any]] = Field(
-        description="JSON dict output of Crew", default=None
-    )
-    tasks_output: list[TaskOutput] = Field(
-        description="Output of each task", default=[]
-    )
-    token_usage: Dict[str, Any] = Field(
-        description="Processed token summary", default={}
-    )
-
-    @property
-    def json(self) -> Optional[str]:
-        if self.tasks_output[-1].output_format != OutputFormat.JSON:
-            raise ValueError(
-                "No JSON output found in the final task. Please make sure to set the output_json property in the final task in your crew."
-            )
-
-        return json.dumps(self.json_dict)
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert json_output and pydantic_output to a dictionary."""
-        output_dict = {}
-        if self.json_dict:
-            output_dict.update(self.json_dict)
-        elif self.pydantic:
-            output_dict.update(self.pydantic.model_dump())
-        return output_dict
-
-    def __str__(self):
-        if self.pydantic:
-            return str(self.pydantic)
-        if self.json_dict:
-            return str(self.json_dict)
-        return self.raw

src/crewai/memory/entity/entity_memory.py

@@ -23,9 +23,3 @@ class EntityMemory(Memory):
         """Saves an entity item into the SQLite storage."""
         data = f"{item.name}({item.type}): {item.description}"
         super().save(data, item.metadata)
-
-    def reset(self) -> None:
-        try:
-            self.storage.reset()
-        except Exception as e:
-            raise Exception(f"An error occurred while resetting the entity memory: {e}")

src/crewai/memory/long_term/long_term_memory.py

@@ -30,6 +30,3 @@ class LongTermMemory(Memory):
 
     def search(self, task: str, latest_n: int = 3) -> Dict[str, Any]:
         return self.storage.load(task, latest_n)  # type: ignore # BUG?: "Storage" has no attribute "load"
-
-    def reset(self) -> None:
-        self.storage.reset()

src/crewai/memory/short_term/short_term_memory.py

@@ -18,16 +18,8 @@ class ShortTermMemory(Memory):
         )
         super().__init__(storage)
 
-    def save(self, item: ShortTermMemoryItem) -> None:
+    def save(self, item: ShortTermMemoryItem) -> None:  # type: ignore # BUG?: Signature of "save" incompatible with supertype "Memory"
         super().save(item.data, item.metadata, item.agent)
 
     def search(self, query: str, score_threshold: float = 0.35):
         return self.storage.search(query=query, score_threshold=score_threshold)  # type: ignore # BUG? The reference is to the parent class, but the parent class does not have this parameters
-
-    def reset(self) -> None:
-        try:
-            self.storage.reset()
-        except Exception as e:
-            raise Exception(
-                f"An error occurred while resetting the short-term memory: {e}"
-            )

src/crewai/memory/storage/interface.py

@@ -9,6 +9,3 @@ class Storage:
 
     def search(self, key: str) -> Dict[str, Any]:  # type: ignore
         pass
-
-    def reset(self) -> None:
-        pass

src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -1,166 +0,0 @@
-import json
-import sqlite3
-from typing import Any, Dict, List, Optional
-
-from crewai.task import Task
-from crewai.utilities import Printer
-from crewai.utilities.crew_json_encoder import CrewJSONEncoder
-from crewai.utilities.paths import db_storage_path
-
-
-class KickoffTaskOutputsSQLiteStorage:
-    """
-    An updated SQLite storage class for kickoff task outputs storage.
-    """
-
-    def __init__(
-        self, db_path: str = f"{db_storage_path()}/latest_kickoff_task_outputs.db"
-    ) -> None:
-        self.db_path = db_path
-        self._printer: Printer = Printer()
-        self._initialize_db()
-
-    def _initialize_db(self):
-        """
-        Initializes the SQLite database and creates LTM table
-        """
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-                cursor.execute(
-                    """
-                    CREATE TABLE IF NOT EXISTS latest_kickoff_task_outputs (
-                        task_id TEXT PRIMARY KEY,
-                        expected_output TEXT,
-                        output JSON,
-                        task_index INTEGER,
-                        inputs JSON,
-                        was_replayed BOOLEAN,
-                        timestamp DATETIME DEFAULT CURRENT_TIMESTAMP
-                    )
-                """
-                )
-
-                conn.commit()
-        except sqlite3.Error as e:
-            self._printer.print(
-                content=f"SAVING KICKOFF TASK OUTPUTS ERROR: An error occurred during database initialization: {e}",
-                color="red",
-            )
-
-    def add(
-        self,
-        task: Task,
-        output: Dict[str, Any],
-        task_index: int,
-        was_replayed: bool = False,
-        inputs: Dict[str, Any] = {},
-    ):
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-                cursor.execute(
-                    """
-                INSERT OR REPLACE INTO latest_kickoff_task_outputs
-                (task_id, expected_output, output, task_index, inputs, was_replayed)
-                VALUES (?, ?, ?, ?, ?, ?)
-            """,
-                    (
-                        str(task.id),
-                        task.expected_output,
-                        json.dumps(output, cls=CrewJSONEncoder),
-                        task_index,
-                        json.dumps(inputs),
-                        was_replayed,
-                    ),
-                )
-                conn.commit()
-        except sqlite3.Error as e:
-            self._printer.print(
-                content=f"SAVING KICKOFF TASK OUTPUTS ERROR: An error occurred during database initialization: {e}",
-                color="red",
-            )
-
-    def update(
-        self,
-        task_index: int,
-        **kwargs,
-    ):
-        """
-        Updates an existing row in the latest_kickoff_task_outputs table based on task_index.
-        """
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-
-                fields = []
-                values = []
-                for key, value in kwargs.items():
-                    fields.append(f"{key} = ?")
-                    values.append(
-                        json.dumps(value, cls=CrewJSONEncoder)
-                        if isinstance(value, dict)
-                        else value
-                    )
-
-                query = f"UPDATE latest_kickoff_task_outputs SET {', '.join(fields)} WHERE task_index = ?"
-                values.append(task_index)
-
-                cursor.execute(query, tuple(values))
-                conn.commit()
-
-                if cursor.rowcount == 0:
-                    self._printer.print(
-                        f"No row found with task_index {task_index}. No update performed.",
-                        color="red",
-                    )
-        except sqlite3.Error as e:
-            self._printer.print(f"UPDATE KICKOFF TASK OUTPUTS ERROR: {e}", color="red")
-
-    def load(self) -> Optional[List[Dict[str, Any]]]:
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-                cursor.execute("""
-                SELECT *
-                FROM latest_kickoff_task_outputs
-                ORDER BY task_index
-                """)
-
-                rows = cursor.fetchall()
-                results = []
-                for row in rows:
-                    result = {
-                        "task_id": row[0],
-                        "expected_output": row[1],
-                        "output": json.loads(row[2]),
-                        "task_index": row[3],
-                        "inputs": json.loads(row[4]),
-                        "was_replayed": row[5],
-                        "timestamp": row[6],
-                    }
-                    results.append(result)
-
-                return results
-
-        except sqlite3.Error as e:
-            self._printer.print(
-                content=f"LOADING KICKOFF TASK OUTPUTS ERROR: An error occurred while querying kickoff task outputs: {e}",
-                color="red",
-            )
-            return None
-
-    def delete_all(self):
-        """
-        Deletes all rows from the latest_kickoff_task_outputs table.
-        """
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-                cursor.execute("DELETE FROM latest_kickoff_task_outputs")
-                conn.commit()
-        except sqlite3.Error as e:
-            self._printer.print(
-                content=f"ERROR: Failed to delete all kickoff task outputs: {e}",
-                color="red",
-            )

src/crewai/memory/storage/ltm_sqlite_storage.py

@@ -103,20 +103,3 @@ class LTMSQLiteStorage:
                 color="red",
             )
         return None
-
-    def reset(
-        self,
-    ) -> None:
-        """Resets the LTM table with error handling."""
-        try:
-            with sqlite3.connect(self.db_path) as conn:
-                cursor = conn.cursor()
-                cursor.execute("DELETE FROM long_term_memories")
-                conn.commit()
-
-        except sqlite3.Error as e:
-            self._printer.print(
-                content=f"MEMORY ERROR: An error occurred while deleting all rows in LTM: {e}",
-                color="red",
-            )
-        return None

src/crewai/memory/storage/rag_storage.py

@@ -2,7 +2,6 @@ import contextlib
 import io
 import logging
 import os
-import shutil
 from typing import Any, Dict, List, Optional
 
 from embedchain import App
@@ -72,13 +71,13 @@ class RAGStorage(Storage):
 
         if embedder_config:
             config["embedder"] = embedder_config
-        self.type = type
+
         self.app = App.from_config(config=config)
         self.app.llm = FakeLLM()
         if allow_reset:
             self.app.reset()
 
-    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:  # type: ignore # BUG?: Should be save(key, value, metadata)  Signature of "save" incompatible with supertype "Storage"
         self._generate_embedding(value, metadata)
 
     def search(  # type: ignore # BUG?: Signature of "search" incompatible with supertype "Storage"
@@ -103,11 +102,3 @@ class RAGStorage(Storage):
     def _generate_embedding(self, text: str, metadata: Dict[str, Any]) -> Any:
         with suppress_logging():
             self.app.add(text, data_type="text", metadata=metadata)
-
-    def reset(self) -> None:
-        try:
-            shutil.rmtree(f"{db_storage_path()}/{self.type}")
-        except Exception as e:
-            raise Exception(
-                f"An error occurred while resetting the {self.type} memory: {e}"
-            )

src/crewai/project/__init__.py

@@ -1,25 +1,2 @@
-from .annotations import (
-    agent,
-    crew,
-    task,
-    output_json,
-    output_pydantic,
-    tool,
-    callback,
-    llm,
-    cache_handler,
-)
+from .annotations import agent, crew, task
 from .crew_base import CrewBase
-
-__all__ = [
-    "agent",
-    "crew",
-    "task",
-    "output_json",
-    "output_pydantic",
-    "tool",
-    "callback",
-    "CrewBase",
-    "llm",
-    "cache_handler",
-]

src/crewai/project/annotations.py

@@ -30,37 +30,6 @@ def agent(func):
     return func
 
 
-def llm(func):
-    func.is_llm = True
-    func = memoize(func)
-    return func
-
-
-def output_json(cls):
-    cls.is_output_json = True
-    return cls
-
-
-def output_pydantic(cls):
-    cls.is_output_pydantic = True
-    return cls
-
-
-def tool(func):
-    func.is_tool = True
-    return memoize(func)
-
-
-def callback(func):
-    func.is_callback = True
-    return memoize(func)
-
-
-def cache_handler(func):
-    func.is_cache_handler = True
-    return memoize(func)
-
-
 def crew(func):
     def wrapper(self, *args, **kwargs):
         instantiated_tasks = []

src/crewai/project/crew_base.py

@@ -1,7 +1,6 @@
 import inspect
 import os
 from pathlib import Path
-from typing import Any, Callable, Dict
 
 import yaml
 from dotenv import load_dotenv
@@ -21,6 +20,11 @@ def CrewBase(cls):
                 base_directory = Path(frame_info.filename).parent.resolve()
                 break
 
+        if base_directory is None:
+            raise Exception(
+                "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
+            )
+
         original_agents_config_path = getattr(
             cls, "agents_config", "config/agents.yaml"
         )
@@ -28,20 +32,12 @@ def CrewBase(cls):
 
         def __init__(self, *args, **kwargs):
             super().__init__(*args, **kwargs)
-
-            if self.base_directory is None:
-                raise Exception(
-                    "Unable to dynamically determine the project's base directory, you must run it from the project's root directory."
-                )
-
             self.agents_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_agents_config_path)
             )
             self.tasks_config = self.load_yaml(
                 os.path.join(self.base_directory, self.original_tasks_config_path)
             )
-            self.map_all_agent_variables()
-            self.map_all_task_variables()
 
         @staticmethod
         def load_yaml(config_path: str):
@@ -49,138 +45,4 @@ def CrewBase(cls):
                 # parsedContent = YamlParser.parse(file)  # type: ignore # Argument 1 to "parse" has incompatible type "TextIOWrapper"; expected "YamlParser"
                 return yaml.safe_load(file)
 
-        def _get_all_functions(self):
-            return {
-                name: getattr(self, name)
-                for name in dir(self)
-                if callable(getattr(self, name))
-            }
-
-        def _filter_functions(
-            self, functions: Dict[str, Callable], attribute: str
-        ) -> Dict[str, Callable]:
-            return {
-                name: func
-                for name, func in functions.items()
-                if hasattr(func, attribute)
-            }
-
-        def map_all_agent_variables(self) -> None:
-            all_functions = self._get_all_functions()
-            llms = self._filter_functions(all_functions, "is_llm")
-            tool_functions = self._filter_functions(all_functions, "is_tool")
-            cache_handler_functions = self._filter_functions(
-                all_functions, "is_cache_handler"
-            )
-            callbacks = self._filter_functions(all_functions, "is_callback")
-            agents = self._filter_functions(all_functions, "is_agent")
-
-            for agent_name, agent_info in self.agents_config.items():
-                self._map_agent_variables(
-                    agent_name,
-                    agent_info,
-                    agents,
-                    llms,
-                    tool_functions,
-                    cache_handler_functions,
-                    callbacks,
-                )
-
-        def _map_agent_variables(
-            self,
-            agent_name: str,
-            agent_info: Dict[str, Any],
-            agents: Dict[str, Callable],
-            llms: Dict[str, Callable],
-            tool_functions: Dict[str, Callable],
-            cache_handler_functions: Dict[str, Callable],
-            callbacks: Dict[str, Callable],
-        ) -> None:
-            if llm := agent_info.get("llm"):
-                self.agents_config[agent_name]["llm"] = llms[llm]()
-
-            if tools := agent_info.get("tools"):
-                self.agents_config[agent_name]["tools"] = [
-                    tool_functions[tool]() for tool in tools
-                ]
-
-            if function_calling_llm := agent_info.get("function_calling_llm"):
-                self.agents_config[agent_name]["function_calling_llm"] = agents[
-                    function_calling_llm
-                ]()
-
-            if step_callback := agent_info.get("step_callback"):
-                self.agents_config[agent_name]["step_callback"] = callbacks[
-                    step_callback
-                ]()
-
-            if cache_handler := agent_info.get("cache_handler"):
-                self.agents_config[agent_name]["cache_handler"] = (
-                    cache_handler_functions[cache_handler]()
-                )
-
-        def map_all_task_variables(self) -> None:
-            all_functions = self._get_all_functions()
-            agents = self._filter_functions(all_functions, "is_agent")
-            tasks = self._filter_functions(all_functions, "is_task")
-            output_json_functions = self._filter_functions(
-                all_functions, "is_output_json"
-            )
-            tool_functions = self._filter_functions(all_functions, "is_tool")
-            callback_functions = self._filter_functions(all_functions, "is_callback")
-            output_pydantic_functions = self._filter_functions(
-                all_functions, "is_output_pydantic"
-            )
-
-            for task_name, task_info in self.tasks_config.items():
-                self._map_task_variables(
-                    task_name,
-                    task_info,
-                    agents,
-                    tasks,
-                    output_json_functions,
-                    tool_functions,
-                    callback_functions,
-                    output_pydantic_functions,
-                )
-
-        def _map_task_variables(
-            self,
-            task_name: str,
-            task_info: Dict[str, Any],
-            agents: Dict[str, Callable],
-            tasks: Dict[str, Callable],
-            output_json_functions: Dict[str, Callable],
-            tool_functions: Dict[str, Callable],
-            callback_functions: Dict[str, Callable],
-            output_pydantic_functions: Dict[str, Callable],
-        ) -> None:
-            if context_list := task_info.get("context"):
-                self.tasks_config[task_name]["context"] = [
-                    tasks[context_task_name]() for context_task_name in context_list
-                ]
-
-            if tools := task_info.get("tools"):
-                self.tasks_config[task_name]["tools"] = [
-                    tool_functions[tool]() for tool in tools
-                ]
-
-            if agent_name := task_info.get("agent"):
-                self.tasks_config[task_name]["agent"] = agents[agent_name]()
-
-            if output_json := task_info.get("output_json"):
-                self.tasks_config[task_name]["output_json"] = output_json_functions[
-                    output_json
-                ]
-
-            if output_pydantic := task_info.get("output_pydantic"):
-                self.tasks_config[task_name]["output_pydantic"] = (
-                    output_pydantic_functions[output_pydantic]
-                )
-
-            if callbacks := task_info.get("callbacks"):
-                self.tasks_config[task_name]["callbacks"] = [
-                    callback_functions[callback]() for callback in callbacks
-                ]
-
     return WrappedClass

src/crewai/task.py

@@ -1,25 +1,17 @@
-import json
 import os
 import re
 import threading
 import uuid
-from concurrent.futures import Future
-from copy import copy
-from hashlib import md5
-from typing import Any, Dict, List, Optional, Tuple, Type, Union
+from copy import deepcopy
+from typing import Any, Dict, List, Optional, Type
 
 from langchain_openai import ChatOpenAI
-from opentelemetry.trace import Span
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
 
-from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.tasks.output_format import OutputFormat
+from crewai.agent import Agent
 from crewai.tasks.task_output import TaskOutput
-from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities.converter import Converter, ConverterError
-from crewai.utilities.i18n import I18N
-from crewai.utilities.printer import Printer
+from crewai.utilities import I18N, Converter, ConverterError, Printer
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
@@ -50,6 +42,7 @@ class Task(BaseModel):
     tools_errors: int = 0
     delegations: int = 0
     i18n: I18N = I18N()
+    thread: Optional[threading.Thread] = None
     prompt_context: Optional[str] = None
     description: str = Field(description="Description of the actual task.")
     expected_output: str = Field(
@@ -62,7 +55,7 @@ class Task(BaseModel):
     callback: Optional[Any] = Field(
         description="Callback to be executed after the task is completed.", default=None
     )
-    agent: Optional[BaseAgent] = Field(
+    agent: Optional[Agent] = Field(
         description="Agent responsible for execution the task.", default=None
     )
     context: Optional[List["Task"]] = Field(
@@ -101,16 +94,9 @@ class Task(BaseModel):
         description="Whether the task should have a human review the final answer of the agent",
         default=False,
     )
-    converter_cls: Optional[Type[Converter]] = Field(
-        description="A converter class used to export structured output",
-        default=None,
-    )
 
-    _telemetry: Telemetry
-    _execution_span: Span | None = None
     _original_description: str | None = None
     _original_expected_output: str | None = None
-    _thread: threading.Thread | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -132,12 +118,6 @@ class Task(BaseModel):
             return value[1:]
         return value
 
-    @model_validator(mode="after")
-    def set_private_attrs(self) -> "Task":
-        """Set private attributes."""
-        self._telemetry = Telemetry()
-        return self
-
     @model_validator(mode="after")
     def set_attributes_based_on_config(self) -> "Task":
         """Set attributes based on the agent configuration."""
@@ -165,102 +145,70 @@ class Task(BaseModel):
             )
         return self
 
-    def execute_sync(
+    def execute(  # type: ignore # Missing return statement
         self,
-        agent: Optional[BaseAgent] = None,
+        agent: Agent | None = None,
         context: Optional[str] = None,
         tools: Optional[List[Any]] = None,
-    ) -> TaskOutput:
-        """Execute the task synchronously."""
-        return self._execute_core(agent, context, tools)
+    ) -> str:
+        """Execute the task.
 
-    @property
-    def key(self) -> str:
-        description = self._original_description or self.description
-        expected_output = self._original_expected_output or self.expected_output
-        source = [description, expected_output]
+        Returns:
+            Output of the task.
+        """
 
-        return md5("|".join(source).encode()).hexdigest()
-
-    def execute_async(
-        self,
-        agent: BaseAgent | None = None,
-        context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
-    ) -> Future[TaskOutput]:
-        """Execute the task asynchronously."""
-        future: Future[TaskOutput] = Future()
-        threading.Thread(
-            target=self._execute_task_async, args=(agent, context, tools, future)
-        ).start()
-        return future
-
-    def _execute_task_async(
-        self,
-        agent: Optional[BaseAgent],
-        context: Optional[str],
-        tools: Optional[List[Any]],
-        future: Future[TaskOutput],
-    ) -> None:
-        """Execute the task asynchronously with context handling."""
-        result = self._execute_core(agent, context, tools)
-        future.set_result(result)
-
-    def _execute_core(
-        self,
-        agent: Optional[BaseAgent],
-        context: Optional[str],
-        tools: Optional[List[Any]],
-    ) -> TaskOutput:
-        """Run the core execution logic of the task."""
         agent = agent or self.agent
-        self.agent = agent
         if not agent:
             raise Exception(
                 f"The task '{self.description}' has no agent assigned, therefore it can't be executed directly and should be executed in a Crew using a specific process that support that, like hierarchical."
             )
 
-        self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
+        if self.context:
+            context = []  # type: ignore # Incompatible types in assignment (expression has type "list[Never]", variable has type "str | None")
+            for task in self.context:
+                if task.async_execution:
+                    task.thread.join()  # type: ignore # Item "None" of "Thread | None" has no attribute "join"
+                if task and task.output:
+                    context.append(task.output.raw_output)  # type: ignore # Item "str" of "str | None" has no attribute "append"
+            context = "\n".join(context)  # type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
 
         self.prompt_context = context
-        tools = tools or self.tools or []
+        tools = tools or self.tools
 
+        if self.async_execution:
+            self.thread = threading.Thread(
+                target=self._execute, args=(agent, self, context, tools)
+            )
+            self.thread.start()
+        else:
+            result = self._execute(
+                task=self,
+                agent=agent,
+                context=context,
+                tools=tools,
+            )
+            return result
+
+    def _execute(self, agent, task, context, tools):
         result = agent.execute_task(
-            task=self,
+            task=task,
             context=context,
             tools=tools,
         )
 
-        pydantic_output, json_output = self._export_output(result)
+        exported_output = self._export_output(result)
 
-        task_output = TaskOutput(
+        self.output = TaskOutput(
             description=self.description,
-            raw=result,
-            pydantic=pydantic_output,
-            json_dict=json_output,
+            exported_output=exported_output,
+            raw_output=result,
             agent=agent.role,
-            output_format=self._get_output_format(),
         )
-        self.output = task_output
 
         if self.callback:
             self.callback(self.output)
 
-        if self._execution_span:
-            self._telemetry.task_ended(self._execution_span, self, agent.crew)
-            self._execution_span = None
-
-        if self.output_file:
-            content = (
-                json_output
-                if json_output
-                else pydantic_output.model_dump_json()
-                if pydantic_output
-                else result
-            )
-            self._save_file(content)
-
-        return task_output
+        return exported_output
 
     def prompt(self) -> str:
         """Prompt the task.
@@ -295,7 +243,7 @@ class Task(BaseModel):
         """Increment the delegations counter."""
         self.delegations += 1
 
-    def copy(self, agents: List["BaseAgent"]) -> "Task":
+    def copy(self):
         """Create a deep copy of the Task."""
         exclude = {
             "id",
@@ -308,14 +256,10 @@ class Task(BaseModel):
         copied_data = {k: v for k, v in copied_data.items() if v is not None}
 
         cloned_context = (
-            [task.copy(agents) for task in self.context] if self.context else None
+            [task.copy() for task in self.context] if self.context else None
         )
-
-        def get_agent_by_role(role: str) -> Union["BaseAgent", None]:
-            return next((agent for agent in agents if agent.role == role), None)
-
-        cloned_agent = get_agent_by_role(self.agent.role) if self.agent else None
-        cloned_tools = copy(self.tools) if self.tools else []
+        cloned_agent = self.agent.copy() if self.agent else None
+        cloned_tools = deepcopy(self.tools) if self.tools else None
 
         copied_task = Task(
             **copied_data,
@@ -323,121 +267,63 @@ class Task(BaseModel):
             agent=cloned_agent,
             tools=cloned_tools,
         )
-
         return copied_task
 
-    def _create_converter(self, *args, **kwargs) -> Converter:
-        """Create a converter instance."""
-        if self.agent and not self.converter_cls:
-            converter = self.agent.get_output_converter(*args, **kwargs)
-        elif self.converter_cls:
-            converter = self.converter_cls(*args, **kwargs)
-
-        if not converter:
-            raise Exception("No output converter found or set.")
-
-        return converter
-
-    def _export_output(
-        self, result: str
-    ) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
-        pydantic_output: Optional[BaseModel] = None
-        json_output: Optional[Dict[str, Any]] = None
+    def _export_output(self, result: str) -> Any:
+        exported_result = result
+        instructions = "I'm gonna convert this raw text into valid JSON."
 
         if self.output_pydantic or self.output_json:
-            model_output = self._convert_to_model(result)
-            pydantic_output = (
-                model_output if isinstance(model_output, BaseModel) else None
-            )
-            if isinstance(model_output, str):
-                try:
-                    json_output = json.loads(model_output)
-                except json.JSONDecodeError:
-                    json_output = None
-            else:
-                json_output = model_output if isinstance(model_output, dict) else None
+            model = self.output_pydantic or self.output_json
 
-        return pydantic_output, json_output
-
-    def _convert_to_model(self, result: str) -> Union[dict, BaseModel, str]:
-        model = self.output_pydantic or self.output_json
-        if model is None:
-            return result
-
-        try:
-            return self._validate_model(result, model)
-        except Exception:
-            return self._handle_partial_json(result, model)
-
-    def _validate_model(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel]:
-        exported_result = model.model_validate_json(result)
-        if self.output_json:
-            return exported_result.model_dump()
-        return exported_result
-
-    def _handle_partial_json(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel, str]:
-        match = re.search(r"({.*})", result, re.DOTALL)
-        if match:
+            # try to convert task_output directly to pydantic/json
             try:
-                exported_result = model.model_validate_json(match.group(0))
+                exported_result = model.model_validate_json(result)  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
                 if self.output_json:
-                    return exported_result.model_dump()
+                    return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
                 return exported_result
             except Exception:
-                pass
+                # sometimes the response contains valid JSON in the middle of text
+                match = re.search(r"({.*})", result, re.DOTALL)
+                if match:
+                    try:
+                        exported_result = model.model_validate_json(match.group(0))  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
+                        if self.output_json:
+                            return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
+                        return exported_result
+                    except Exception:
+                        pass
 
-        return self._convert_with_instructions(result, model)
+            llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_llm"
 
-    def _convert_with_instructions(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel, str]:
-        llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "BaseAgent | None" has no attribute "function_calling_llm"
-        instructions = self._get_conversion_instructions(model, llm)
+            if not self._is_gpt(llm):
+                model_schema = PydanticSchemaParser(model=model).get_schema()  # type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
+                instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
-        converter = self._create_converter(
-            llm=llm, text=result, model=model, instructions=instructions
-        )
-        exported_result = (
-            converter.to_pydantic() if self.output_pydantic else converter.to_json()
-        )
-
-        if isinstance(exported_result, ConverterError):
-            Printer().print(
-                content=f"{exported_result.message} Using raw output instead.",
-                color="red",
+            converter = Converter(
+                llm=llm, text=result, model=model, instructions=instructions
             )
-            return result
+
+            if self.output_pydantic:
+                exported_result = converter.to_pydantic()
+            elif self.output_json:
+                exported_result = converter.to_json()
+
+            if isinstance(exported_result, ConverterError):
+                Printer().print(
+                    content=f"{exported_result.message} Using raw output instead.",
+                    color="red",
+                )
+                exported_result = result
+
+        if self.output_file:
+            content = (
+                exported_result if not self.output_pydantic else exported_result.json()  # type: ignore # "str" has no attribute "json"
+            )
+            self._save_file(content)
 
         return exported_result
 
-    def _get_output_format(self) -> OutputFormat:
-        if self.output_json:
-            return OutputFormat.JSON
-        if self.output_pydantic:
-            return OutputFormat.PYDANTIC
-        return OutputFormat.RAW
-
-    def _get_conversion_instructions(self, model: Type[BaseModel], llm: Any) -> str:
-        instructions = "I'm gonna convert this raw text into valid JSON."
-        if not self._is_gpt(llm):
-            model_schema = PydanticSchemaParser(model=model).get_schema()
-            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
-        return instructions
-
-    def _save_output(self, content: str) -> None:
-        if not self.output_file:
-            raise Exception("Output file path is not set.")
-
-        directory = os.path.dirname(self.output_file)
-        if directory and not os.path.exists(directory):
-            os.makedirs(directory)
-        with open(self.output_file, "w", encoding="utf-8") as file:
-            file.write(content)
-
     def _is_gpt(self, llm) -> bool:
         return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
 

src/crewai/tasks/__init__.py

@@ -1,4 +0,0 @@
-from crewai.tasks.output_format import OutputFormat
-from crewai.tasks.task_output import TaskOutput
-
-__all__ = ["OutputFormat", "TaskOutput"]

src/crewai/tasks/conditional_task.py

@@ -1,47 +0,0 @@
-from typing import Any, Callable
-
-from pydantic import Field
-
-from crewai.task import Task
-from crewai.tasks.output_format import OutputFormat
-from crewai.tasks.task_output import TaskOutput
-
-
-class ConditionalTask(Task):
-    """
-    A task that can be conditionally executed based on the output of another task.
-    Note: This cannot be the only task you have in your crew and cannot be the first since its needs context from the previous task.
-    """
-
-    condition: Callable[[TaskOutput], bool] = Field(
-        default=None,
-        description="Maximum number of retries for an agent to execute a task when an error occurs.",
-    )
-
-    def __init__(
-        self,
-        condition: Callable[[Any], bool],
-        **kwargs,
-    ):
-        super().__init__(**kwargs)
-        self.condition = condition
-
-    def should_execute(self, context: TaskOutput) -> bool:
-        """
-        Determines whether the conditional task should be executed based on the provided context.
-
-        Args:
-            context (Any): The context or output from the previous task that will be evaluated by the condition.
-
-        Returns:
-            bool: True if the task should be executed, False otherwise.
-        """
-        return self.condition(context)
-
-    def get_skipped_task_output(self):
-        return TaskOutput(
-            description=self.description,
-            raw="",
-            agent=self.agent.role if self.agent else "",
-            output_format=OutputFormat.RAW,
-        )

src/crewai/tasks/output_format.py

@@ -1,9 +0,0 @@
-from enum import Enum
-
-
-class OutputFormat(str, Enum):
-    """Enum that represents the output format of a task."""
-
-    JSON = "json"
-    PYDANTIC = "pydantic"
-    RAW = "raw"

src/crewai/tasks/task_output.py

@@ -1,60 +1,24 @@
-import json
-from typing import Any, Dict, Optional
+from typing import Optional, Union
 
 from pydantic import BaseModel, Field, model_validator
 
-from crewai.tasks.output_format import OutputFormat
-
 
 class TaskOutput(BaseModel):
     """Class that represents the result of a task."""
 
     description: str = Field(description="Description of the task")
     summary: Optional[str] = Field(description="Summary of the task", default=None)
-    raw: str = Field(description="Raw output of the task", default="")
-    pydantic: Optional[BaseModel] = Field(
-        description="Pydantic output of task", default=None
-    )
-    json_dict: Optional[Dict[str, Any]] = Field(
-        description="JSON dictionary of task", default=None
+    exported_output: Union[str, BaseModel] = Field(
+        description="Output of the task", default=None
     )
     agent: str = Field(description="Agent that executed the task")
-    output_format: OutputFormat = Field(
-        description="Output format of the task", default=OutputFormat.RAW
-    )
+    raw_output: str = Field(description="Result of the task")
 
     @model_validator(mode="after")
     def set_summary(self):
-        """Set the summary field based on the description."""
         excerpt = " ".join(self.description.split(" ")[:10])
         self.summary = f"{excerpt}..."
         return self
 
-    @property
-    def json(self) -> Optional[str]:
-        if self.output_format != OutputFormat.JSON:
-            raise ValueError(
-                """
-                Invalid output format requested.
-                If you would like to access the JSON output,
-                please make sure to set the output_json property for the task
-                """
-            )
-
-        return json.dumps(self.json_dict)
-
-    def to_dict(self) -> Dict[str, Any]:
-        """Convert json_output and pydantic_output to a dictionary."""
-        output_dict = {}
-        if self.json_dict:
-            output_dict.update(self.json_dict)
-        elif self.pydantic:
-            output_dict.update(self.pydantic.model_dump())
-        return output_dict
-
-    def __str__(self) -> str:
-        if self.pydantic:
-            return str(self.pydantic)
-        if self.json_dict:
-            return str(self.json_dict)
-        return self.raw
+    def result(self):
+        return self.exported_output

src/crewai/telemetry/telemetry.py

@@ -1,10 +1,8 @@
-from __future__ import annotations
-
 import asyncio
 import json
 import os
 import platform
-from typing import TYPE_CHECKING, Any
+from typing import Any
 
 import pkg_resources
 from opentelemetry import trace
@@ -12,11 +10,7 @@ from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExport
 from opentelemetry.sdk.resources import SERVICE_NAME, Resource
 from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
-from opentelemetry.trace import Span, Status, StatusCode
-
-if TYPE_CHECKING:
-    from crewai.crew import Crew
-    from crewai.task import Task
+from opentelemetry.trace import Status, StatusCode
 
 
 class Telemetry:
@@ -80,7 +74,7 @@ class Telemetry:
                 self.ready = False
                 self.trace_set = False
 
-    def crew_creation(self, crew: Crew, inputs: dict[str, Any] | None):
+    def crew_creation(self, crew):
         """Records the creation of a crew."""
         if self.ready:
             try:
@@ -92,9 +86,11 @@ class Telemetry:
                     pkg_resources.get_distribution("crewai").version,
                 )
                 self._add_attribute(span, "python_version", platform.python_version())
-                self._add_attribute(span, "crew_key", crew.key)
                 self._add_attribute(span, "crew_id", str(crew.id))
                 self._add_attribute(span, "crew_process", crew.process)
+                self._add_attribute(
+                    span, "crew_language", crew.prompt_file if crew.i18n else "None"
+                )
                 self._add_attribute(span, "crew_memory", crew.memory)
                 self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
                 self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
@@ -104,11 +100,8 @@ class Telemetry:
                     json.dumps(
                         [
                             {
-                                "key": agent.key,
                                 "id": str(agent.id),
                                 "role": agent.role,
-                                "goal": agent.goal,
-                                "backstory": agent.backstory,
                                 "verbose?": agent.verbose,
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
@@ -116,7 +109,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools or []
+                                    tool.name.casefold() for tool in agent.tools
                                 ],
                             }
                             for agent in crew.agents
@@ -129,21 +122,11 @@ class Telemetry:
                     json.dumps(
                         [
                             {
-                                "key": task.key,
                                 "id": str(task.id),
-                                "description": task.description,
-                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
-                                "human_input?": task.human_input,
                                 "agent_role": task.agent.role if task.agent else "None",
-                                "agent_key": task.agent.key if task.agent else None,
-                                "context": (
-                                    [task.description for task in task.context]
-                                    if task.context
-                                    else None
-                                ),
                                 "tools_names": [
-                                    tool.name.casefold() for tool in task.tools or []
+                                    tool.name.casefold() for tool in task.tools
                                 ],
                             }
                             for task in crew.tasks
@@ -155,71 +138,6 @@ class Telemetry:
                 self._add_attribute(span, "platform_system", platform.system())
                 self._add_attribute(span, "platform_version", platform.version())
                 self._add_attribute(span, "cpus", os.cpu_count())
-
-                if crew.share_crew:
-                    self._add_attribute(
-                        span, "crew_inputs", json.dumps(inputs) if inputs else None
-                    )
-
-                span.set_status(Status(StatusCode.OK))
-                span.end()
-            except Exception:
-                pass
-
-    def task_started(self, crew: Crew, task: Task) -> Span | None:
-        """Records task started in a crew."""
-        if self.ready:
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-
-                created_span = tracer.start_span("Task Created")
-
-                self._add_attribute(created_span, "crew_key", crew.key)
-                self._add_attribute(created_span, "crew_id", str(crew.id))
-                self._add_attribute(created_span, "task_key", task.key)
-                self._add_attribute(created_span, "task_id", str(task.id))
-
-                if crew.share_crew:
-                    self._add_attribute(
-                        created_span, "formatted_description", task.description
-                    )
-                    self._add_attribute(
-                        created_span, "formatted_expected_output", task.expected_output
-                    )
-
-                created_span.set_status(Status(StatusCode.OK))
-                created_span.end()
-
-                span = tracer.start_span("Task Execution")
-
-                self._add_attribute(span, "crew_key", crew.key)
-                self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(span, "task_key", task.key)
-                self._add_attribute(span, "task_id", str(task.id))
-
-                if crew.share_crew:
-                    self._add_attribute(span, "formatted_description", task.description)
-                    self._add_attribute(
-                        span, "formatted_expected_output", task.expected_output
-                    )
-
-                return span
-            except Exception:
-                pass
-
-        return None
-
-    def task_ended(self, span: Span, task: Task, crew: Crew):
-        """Records task execution in a crew."""
-        if self.ready:
-            try:
-                if crew.share_crew:
-                    self._add_attribute(
-                        span,
-                        "task_output",
-                        task.output.raw if task.output else "",
-                    )
-
                 span.set_status(Status(StatusCode.OK))
                 span.end()
             except Exception:
@@ -289,12 +207,10 @@ class Telemetry:
             except Exception:
                 pass
 
-    def crew_execution_span(self, crew: Crew, inputs: dict[str, Any] | None):
+    def crew_execution_span(self, crew):
         """Records the complete execution of a crew.
         This is only collected if the user has opted-in to share the crew.
         """
-        self.crew_creation(crew, inputs)
-
         if (self.ready) and (crew.share_crew):
             try:
                 tracer = trace.get_tracer("crewai.telemetry")
@@ -304,18 +220,13 @@ class Telemetry:
                     "crewai_version",
                     pkg_resources.get_distribution("crewai").version,
                 )
-                self._add_attribute(span, "crew_key", crew.key)
                 self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(
-                    span, "crew_inputs", json.dumps(inputs) if inputs else None
-                )
                 self._add_attribute(
                     span,
                     "crew_agents",
                     json.dumps(
                         [
                             {
-                                "key": agent.key,
                                 "id": str(agent.id),
                                 "role": agent.role,
                                 "goal": agent.goal,
@@ -327,7 +238,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools or []
+                                    tool.name.casefold() for tool in agent.tools
                                 ],
                             }
                             for agent in crew.agents
@@ -342,18 +253,16 @@ class Telemetry:
                             {
                                 "id": str(task.id),
                                 "description": task.description,
-                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
-                                "human_input?": task.human_input,
+                                "output": task.expected_output,
                                 "agent_role": task.agent.role if task.agent else "None",
-                                "agent_key": task.agent.key if task.agent else None,
                                 "context": (
                                     [task.description for task in task.context]
                                     if task.context
-                                    else None
+                                    else "None"
                                 ),
                                 "tools_names": [
-                                    tool.name.casefold() for tool in task.tools or []
+                                    tool.name.casefold() for tool in task.tools
                                 ],
                             }
                             for task in crew.tasks
@@ -364,7 +273,7 @@ class Telemetry:
             except Exception:
                 pass
 
-    def end_crew(self, crew, final_string_output):
+    def end_crew(self, crew, output):
         if (self.ready) and (crew.share_crew):
             try:
                 self._add_attribute(
@@ -372,9 +281,7 @@ class Telemetry:
                     "crewai_version",
                     pkg_resources.get_distribution("crewai").version,
                 )
-                self._add_attribute(
-                    crew._execution_span, "crew_output", final_string_output
-                )
+                self._add_attribute(crew._execution_span, "crew_output", output)
                 self._add_attribute(
                     crew._execution_span,
                     "crew_tasks_output",

src/crewai/tools/agent_tools.py

@@ -1,25 +1,106 @@
+from typing import List, Union
+
 from langchain.tools import StructuredTool
+from pydantic import BaseModel, Field
 
-from crewai.agents.agent_builder.utilities.base_agent_tool import BaseAgentTools
+from crewai.agent import Agent
+from crewai.task import Task
+from crewai.utilities import I18N
 
 
-class AgentTools(BaseAgentTools):
+class AgentTools(BaseModel):
     """Default tools around agent delegation"""
 
+    agents: List[Agent] = Field(description="List of agents in this crew.")
+    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
+
     def tools(self):
-        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
         tools = [
             StructuredTool.from_function(
                 func=self.delegate_work,
                 name="Delegate work to coworker",
                 description=self.i18n.tools("delegate_work").format(
-                    coworkers=coworkers
+                    coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
                 ),
             ),
             StructuredTool.from_function(
                 func=self.ask_question,
                 name="Ask question to coworker",
-                description=self.i18n.tools("ask_question").format(coworkers=coworkers),
+                description=self.i18n.tools("ask_question").format(
+                    coworkers=f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
+                ),
             ),
         ]
         return tools
+
+    def delegate_work(
+        self,
+        task: str,
+        context: Union[str, None] = None,
+        coworker: Union[str, None] = None,
+        **kwargs,
+    ):
+        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
+        if coworker:
+            is_list = coworker.startswith("[") and coworker.endswith("]")
+            if is_list:
+                coworker = coworker[1:-1].split(",")[0]
+        return self._execute(coworker, task, context)
+
+    def ask_question(
+        self,
+        question: str,
+        context: Union[str, None] = None,
+        coworker: Union[str, None] = None,
+        **kwargs,
+    ):
+        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
+        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
+        if coworker:
+            is_list = coworker.startswith("[") and coworker.endswith("]")
+            if is_list:
+                coworker = coworker[1:-1].split(",")[0]
+        return self._execute(coworker, question, context)
+
+    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
+        """Execute the command."""
+        try:
+            if agent is None:
+                agent = ""
+
+            # It is important to remove the quotes from the agent name.
+            # The reason we have to do this is because less-powerful LLM's
+            # have difficulty producing valid JSON.
+            # As a result, we end up with invalid JSON that is truncated like this:
+            # {"task": "....", "coworker": "....
+            # when it should look like this:
+            # {"task": "....", "coworker": "...."}
+            agent_name = agent.casefold().replace('"', "").replace("\n", "")
+
+            agent = [  # type: ignore # Incompatible types in assignment (expression has type "list[Agent]", variable has type "str | None")
+                available_agent
+                for available_agent in self.agents
+                if available_agent.role.casefold().replace("\n", "") == agent_name
+            ]
+        except Exception as _:
+            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+                coworkers="\n".join(
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
+            )
+
+        if not agent:
+            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+                coworkers="\n".join(
+                    [f"- {agent.role.casefold()}" for agent in self.agents]
+                )
+            )
+
+        agent = agent[0]
+        task = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
+            description=task,
+            agent=agent,
+            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
+        )
+        return agent.execute_task(task, context)  # type: ignore # "str" has no attribute "execute_task"

src/crewai/tools/tool_calling.py

@@ -8,7 +8,7 @@ from pydantic.v1 import BaseModel, Field
 class ToolCalling(BaseModel):
     tool_name: str = Field(..., description="The name of the tool to be called.")
     arguments: Optional[Dict[str, Any]] = Field(
-        ..., description="A dictionary of arguments to be passed to the tool."
+        ..., description="A dictinary of arguments to be passed to the tool."
     )
 
 
@@ -17,5 +17,5 @@ class InstructorToolCalling(PydanticBaseModel):
         ..., description="The name of the tool to be called."
     )
     arguments: Optional[Dict[str, Any]] = PydanticField(
-        ..., description="A dictionary of arguments to be passed to the tool."
+        ..., description="A dictinary of arguments to be passed to the tool."
     )

src/crewai/tools/tool_usage.py

@@ -11,11 +11,6 @@ from crewai.telemetry import Telemetry
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
 from crewai.utilities import I18N, Converter, ConverterError, Printer
 
-try:
-    import agentops
-except ImportError:
-    agentops = None
-
 OPENAI_BIGGER_MODELS = ["gpt-4"]
 
 
@@ -50,7 +45,6 @@ class ToolUsage:
         tools_names: str,
         task: Any,
         function_calling_llm: Any,
-        agent: Any,
         action: Any,
     ) -> None:
         self._i18n: I18N = I18N()
@@ -59,7 +53,6 @@ class ToolUsage:
         self._run_attempts: int = 1
         self._max_parsing_attempts: int = 3
         self._remember_format_after_usages: int = 3
-        self.agent = agent
         self.tools_description = tools_description
         self.tools_names = tools_names
         self.tools_handler = tools_handler
@@ -105,8 +98,7 @@ class ToolUsage:
         tool_string: str,
         tool: BaseTool,
         calling: Union[ToolCalling, InstructorToolCalling],
-    ) -> str:  # TODO: Fix this return type
-        tool_event = agentops.ToolEvent(name=calling.tool_name) if agentops else None
+    ) -> None:  # TODO: Fix this return type
         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(
@@ -119,7 +111,7 @@ class ToolUsage:
                     attempts=self._run_attempts,
                 )
                 result = self._format_result(result=result)  # type: ignore #  "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
-                return result  # type: ignore # Fix the return type of this function
+                return result  # type: ignore # Fix the reutrn type of this function
 
             except Exception:
                 self.task.increment_tools_errors()
@@ -131,11 +123,7 @@ class ToolUsage:
                 tool=calling.tool_name, input=calling.arguments
             )
 
-        original_tool = next(
-            (ot for ot in self.original_tools if ot.name == tool.name), None
-        )
-
-        if result is None:  #! finecwg: if not result --> if result is None
+        if not result:
             try:
                 if calling.tool_name in [
                     "Delegate work to coworker",
@@ -151,12 +139,16 @@ class ToolUsage:
                             for k, v in calling.arguments.items()
                             if k in acceptable_args
                         }
-                        result = tool.invoke(input=arguments)
+                        result = tool._run(**arguments)
                     except Exception:
-                        arguments = calling.arguments
-                        result = tool.invoke(input=arguments)
+                        if tool.args_schema:
+                            arguments = calling.arguments
+                            result = tool._run(**arguments)
+                        else:
+                            arguments = calling.arguments.values()  # type: ignore # Incompatible types in assignment (expression has type "dict_values[str, Any]", variable has type "dict[str, Any]")
+                            result = tool._run(*arguments)
                 else:
-                    result = tool.invoke(input={})
+                    result = tool._run()
             except Exception as e:
                 self._run_attempts += 1
                 if self._run_attempts > self._max_parsing_attempts:
@@ -172,14 +164,13 @@ 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:
                 should_cache = True
+                original_tool = next(
+                    (ot for ot in self.original_tools if ot.name == tool.name), None
+                )
                 if (
                     hasattr(original_tool, "cache_function")
                     and original_tool.cache_function  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
@@ -193,29 +184,12 @@ 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,
             attempts=self._run_attempts,
         )
         result = self._format_result(result=result)  # type: ignore # "_format_result" of "ToolUsage" does not return a value (it only ever returns None)
-        data = {
-            "result": result,
-            "tool_name": tool.name,
-            "tool_args": calling.arguments,
-        }
-
-        if (
-            hasattr(original_tool, "result_as_answer")
-            and original_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "cache_function"
-        ):
-            result_as_answer = original_tool.result_as_answer  # type: ignore # Item "None" of "Any | None" has no attribute "result_as_answer"
-            data["result_as_answer"] = result_as_answer
-
-        self.agent.tools_results.append(data)
-
         return result  # type: ignore # No return value expected
 
     def _format_result(self, result: Any) -> None:
@@ -316,7 +290,7 @@ class ToolUsage:
               Example:
               {"tool_name": "tool name", "arguments": {"arg_name1": "value", "arg_name2": 2}}""",
                     ),
-                    max_attempts=1,
+                    max_attemps=1,
                 )
                 calling = converter.to_pydantic()
 

src/crewai/translations/en.json

@@ -16,8 +16,8 @@
     "format_without_tools": "\nSorry, I didn't use the right format. I MUST either use a tool (among the available ones), OR give my best final answer.\nI just remembered the expected format I must follow:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\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\n",
     "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-evaluate it and give a new Final Answer when ready.\n {human_feedback}",
-    "getting_input": "This is the agent's final answer: {final_answer}\nPlease provide feedback: "
+    "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: "
   },
   "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

@@ -1,9 +1,9 @@
 import json
+from typing import Any, Optional
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
-
-from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
+from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
 
 class ConverterError(Exception):
@@ -14,18 +14,33 @@ class ConverterError(Exception):
         self.message = message
 
 
-class Converter(OutputConverter):
+class Converter(BaseModel):
     """Class that converts text into either pydantic or json."""
 
+    _is_gpt: bool = PrivateAttr(default=True)
+    text: str = Field(description="Text to be converted.")
+    llm: Any = Field(description="The language model to be used to convert the text.")
+    model: Any = Field(description="The model to be used to convert the text.")
+    instructions: str = Field(description="Conversion instructions to the LLM.")
+    max_attemps: Optional[int] = Field(
+        description="Max number of attemps to try to get the output formated.",
+        default=3,
+    )
+
+    @model_validator(mode="after")
+    def check_llm_provider(self):
+        if not self._is_gpt(self.llm):
+            self._is_gpt = False
+
     def to_pydantic(self, current_attempt=1):
         """Convert text to pydantic."""
         try:
-            if self.is_gpt:
+            if self._is_gpt:
                 return self._create_instructor().to_pydantic()
             else:
                 return self._create_chain().invoke({})
         except Exception as e:
-            if current_attempt < self.max_attempts:
+            if current_attempt < self.max_attemps:
                 return self.to_pydantic(current_attempt + 1)
             return ConverterError(
                 f"Failed to convert text into a pydantic model due to the following error: {e}"
@@ -34,14 +49,14 @@ class Converter(OutputConverter):
     def to_json(self, current_attempt=1):
         """Convert text to json."""
         try:
-            if self.is_gpt:
+            if self._is_gpt:
                 return self._create_instructor().to_json()
             else:
                 return json.dumps(self._create_chain().invoke({}).model_dump())
-        except Exception as e:
-            if current_attempt < self.max_attempts:
+        except Exception:
+            if current_attempt < self.max_attemps:
                 return self.to_json(current_attempt + 1)
-            return ConverterError(f"Failed to convert text into JSON, error: {e}.")
+            return ConverterError("Failed to convert text into JSON.")
 
     def _create_instructor(self):
         """Create an instructor."""
@@ -49,7 +64,7 @@ class Converter(OutputConverter):
 
         inst = Instructor(
             llm=self.llm,
-            max_attempts=self.max_attempts,
+            max_attemps=self.max_attemps,
             model=self.model,
             content=self.text,
             instructions=self.instructions,
@@ -68,7 +83,5 @@ class Converter(OutputConverter):
         )
         return new_prompt | self.llm | parser
 
-    @property
-    def is_gpt(self) -> bool:
-        """Return if llm provided is of gpt from openai."""
-        return isinstance(self.llm, ChatOpenAI) and self.llm.openai_api_base is None
+    def _is_gpt(self, llm) -> bool:  # type: ignore # BUG? Name "_is_gpt" defined on line 20 hides name from outer scope
+        return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None

src/crewai/utilities/crew_json_encoder.py

@@ -1,31 +0,0 @@
-from datetime import datetime
-import json
-from uuid import UUID
-from pydantic import BaseModel
-
-
-class CrewJSONEncoder(json.JSONEncoder):
-    def default(self, obj):
-        if isinstance(obj, BaseModel):
-            return self._handle_pydantic_model(obj)
-        elif isinstance(obj, UUID):
-            return str(obj)
-
-        elif isinstance(obj, datetime):
-            return obj.isoformat()
-        return super().default(obj)
-
-    def _handle_pydantic_model(self, obj):
-        try:
-            data = obj.model_dump()
-            # Remove circular references
-            for key, value in data.items():
-                if isinstance(value, BaseModel):
-                    data[key] = str(
-                        value
-                    )  # Convert nested models to string representation
-            return data
-        except RecursionError:
-            return str(
-                obj
-            )  # Fall back to string representation if circular reference is detected

src/crewai/utilities/crew_pydantic_output_parser.py

@@ -17,16 +17,6 @@ class CrewPydanticOutputParser(PydanticOutputParser):
 
     def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
         result[0].text = self._transform_in_valid_json(result[0].text)
-
-        # Treating edge case of function calling llm returning the name instead of tool_name
-        json_object = json.loads(result[0].text)
-        json_object["tool_name"] = (
-            json_object["name"]
-            if "tool_name" not in json_object
-            else json_object["tool_name"]
-        )
-        result[0].text = json.dumps(json_object)
-
         json_object = super().parse_result(result)
         try:
             return self.pydantic_object.parse_obj(json_object)

src/crewai/utilities/evaluators/task_evaluator.py

@@ -6,17 +6,6 @@ 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.")
@@ -49,7 +38,6 @@ class TrainingTaskEvaluation(BaseModel):
     )
 
 
-@track_agent(name="Task Evaluator")
 class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm

src/crewai/utilities/file_handler.py

@@ -1,7 +1,5 @@
 import os
 import pickle
-
-
 from datetime import datetime
 
 
@@ -33,8 +31,9 @@ class PickleHandler:
         - file_name (str): The name of the file for saving and loading data.
         """
         self.file_path = os.path.join(os.getcwd(), file_name)
+        self._initialize_file()
 
-    def initialize_file(self) -> None:
+    def _initialize_file(self) -> None:
         """
         Initialize the file with an empty dictionary if it does not exist or is empty.
         """

src/crewai/utilities/formatter.py

@@ -1,20 +0,0 @@
-from typing import List
-
-from crewai.task import Task
-from crewai.tasks.task_output import TaskOutput
-
-
-def aggregate_raw_outputs_from_task_outputs(task_outputs: List[TaskOutput]) -> str:
-    """Generate string context from the task outputs."""
-    dividers = "\n\n----------\n\n"
-
-    # Join task outputs with dividers
-    context = dividers.join(output.raw for output in task_outputs)
-    return context
-
-
-def aggregate_raw_outputs_from_tasks(tasks: List[Task]) -> str:
-    """Generate string context from the tasks."""
-    task_outputs = [task.output for task in tasks if task.output is not None]
-
-    return aggregate_raw_outputs_from_task_outputs(task_outputs)

src/crewai/utilities/planning_handler.py

@@ -1,64 +0,0 @@
-from typing import List, Optional
-
-from pydantic import BaseModel
-
-from crewai.agent import Agent
-from crewai.task import Task
-
-
-class PlannerTaskPydanticOutput(BaseModel):
-    list_of_plans_per_task: List[str]
-
-
-class CrewPlanner:
-    def __init__(self, tasks: List[Task]):
-        self.tasks = tasks
-
-    def _handle_crew_planning(self) -> Optional[BaseModel]:
-        """Handles the Crew planning by creating detailed step-by-step plans for each task."""
-        planning_agent = self._create_planning_agent()
-        tasks_summary = self._create_tasks_summary()
-
-        planner_task = self._create_planner_task(planning_agent, tasks_summary)
-
-        return planner_task.execute_sync().pydantic
-
-    def _create_planning_agent(self) -> Agent:
-        """Creates the planning agent for the crew planning."""
-        return Agent(
-            role="Task Execution Planner",
-            goal=(
-                "Your goal is to create an extremely detailed, step-by-step plan based on the tasks and tools "
-                "available to each agent so that they can perform the tasks in an exemplary manner"
-            ),
-            backstory="Planner agent for crew planning",
-        )
-
-    def _create_planner_task(self, planning_agent: Agent, tasks_summary: str) -> Task:
-        """Creates the planner task using the given agent and tasks summary."""
-        return Task(
-            description=(
-                f"Based on these tasks summary: {tasks_summary} \n Create the most descriptive plan based on the tasks "
-                "descriptions, tools available, and agents' goals for them to execute their goals with perfection."
-            ),
-            expected_output="Step by step plan on how the agents can execute their tasks using the available tools with mastery",
-            agent=planning_agent,
-            output_pydantic=PlannerTaskPydanticOutput,
-        )
-
-    def _create_tasks_summary(self) -> str:
-        """Creates a summary of all tasks."""
-        tasks_summary = []
-        for idx, task in enumerate(self.tasks):
-            tasks_summary.append(
-                f"""
-                Task Number {idx + 1} - {task.description}
-                "task_description": {task.description}
-                "task_expected_output": {task.expected_output}
-                "agent": {task.agent.role if task.agent else "None"}
-                "agent_goal": {task.agent.goal if task.agent else "None"}
-                "task_tools": {task.tools}
-                "agent_tools": {task.agent.tools if task.agent else "None"}
-                """
-            )
-        return " ".join(tasks_summary)

src/crewai/utilities/printer.py

@@ -8,10 +8,6 @@ class Printer:
             self._print_bold_green(content)
         elif color == "bold_purple":
             self._print_bold_purple(content)
-        elif color == "bold_blue":
-            self._print_bold_blue(content)
-        elif color == "yellow":
-            self._print_yellow(content)
         else:
             print(content)
 
@@ -26,9 +22,3 @@ class Printer:
 
     def _print_red(self, content):
         print("\033[91m {}\033[00m".format(content))
-
-    def _print_bold_blue(self, content):
-        print("\033[1m\033[94m {}\033[00m".format(content))
-
-    def _print_yellow(self, content):
-        print("\033[93m {}\033[00m".format(content))

src/crewai/utilities/task_output_storage_handler.py

@@ -1,61 +0,0 @@
-from pydantic import BaseModel, Field
-from datetime import datetime
-from typing import Dict, Any, Optional, List
-from crewai.memory.storage.kickoff_task_outputs_storage import (
-    KickoffTaskOutputsSQLiteStorage,
-)
-from crewai.task import Task
-
-
-class ExecutionLog(BaseModel):
-    task_id: str
-    expected_output: Optional[str] = None
-    output: Dict[str, Any]
-    timestamp: datetime = Field(default_factory=datetime.now)
-    task_index: int
-    inputs: Dict[str, Any] = Field(default_factory=dict)
-    was_replayed: bool = False
-
-    def __getitem__(self, key: str) -> Any:
-        return getattr(self, key)
-
-
-class TaskOutputStorageHandler:
-    def __init__(self) -> None:
-        self.storage = KickoffTaskOutputsSQLiteStorage()
-
-    def update(self, task_index: int, log: Dict[str, Any]):
-        saved_outputs = self.load()
-        if saved_outputs is None:
-            raise ValueError("Logs cannot be None")
-
-        if log.get("was_replayed", False):
-            replayed = {
-                "task_id": str(log["task"].id),
-                "expected_output": log["task"].expected_output,
-                "output": log["output"],
-                "was_replayed": log["was_replayed"],
-                "inputs": log["inputs"],
-            }
-            self.storage.update(
-                task_index,
-                **replayed,
-            )
-        else:
-            self.storage.add(**log)
-
-    def add(
-        self,
-        task: Task,
-        output: Dict[str, Any],
-        task_index: int,
-        inputs: Dict[str, Any] = {},
-        was_replayed: bool = False,
-    ):
-        self.storage.add(task, output, task_index, was_replayed, inputs)
-
-    def reset(self):
-        self.storage.delete_all()
-
-    def load(self) -> Optional[List[Dict[str, Any]]]:
-        return self.storage.load()

src/crewai/utilities/token_counter_callback.py

@@ -4,22 +4,46 @@ import tiktoken
 from langchain.callbacks.base import BaseCallbackHandler
 from langchain.schema import LLMResult
 
-from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
+
+class TokenProcess:
+    total_tokens: int = 0
+    prompt_tokens: int = 0
+    completion_tokens: int = 0
+    successful_requests: int = 0
+
+    def sum_prompt_tokens(self, tokens: int):
+        self.prompt_tokens = self.prompt_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_completion_tokens(self, tokens: int):
+        self.completion_tokens = self.completion_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_successful_requests(self, requests: int):
+        self.successful_requests = self.successful_requests + requests
+
+    def get_summary(self) -> Dict[str, Any]:
+        return {
+            "total_tokens": self.total_tokens,
+            "prompt_tokens": self.prompt_tokens,
+            "completion_tokens": self.completion_tokens,
+            "successful_requests": self.successful_requests,
+        }
 
 
 class TokenCalcHandler(BaseCallbackHandler):
-    model_name: str = ""
+    model: str = ""
     token_cost_process: TokenProcess
 
-    def __init__(self, model_name, token_cost_process):
-        self.model_name = model_name
+    def __init__(self, model, token_cost_process):
+        self.model = model
         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_name)
+            encoding = tiktoken.encoding_for_model(self.model)
         except KeyError:
             encoding = tiktoken.get_encoding("cl100k_base")
 

tests/agent_test.py

@@ -631,9 +631,8 @@ def test_agent_use_specific_tasks_output_as_context(capsys):
 
     crew = Crew(agents=[agent1, agent2], tasks=tasks)
     result = crew.kickoff()
-    print("LOWER RESULT", result.raw)
-    assert "bye" not in result.raw.lower()
-    assert "hi" in result.raw.lower() or "hello" in result.raw.lower()
+    assert "bye" not in result.lower()
+    assert "hi" in result.lower() or "hello" in result.lower()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -645,7 +644,7 @@ def test_agent_step_callback():
     with patch.object(StepCallback, "callback") as callback:
 
         @tool
-        def learn_about_AI(topic) -> str:
+        def learn_about_AI(topic) -> float:
             """Useful for when you need to learn about AI to write an paragraph about it."""
             return "AI is a very broad field."
 
@@ -679,7 +678,7 @@ def test_agent_function_calling_llm():
     with patch.object(llm.client, "create", wraps=llm.client.create) as private_mock:
 
         @tool
-        def learn_about_AI(topic) -> str:
+        def learn_about_AI(topic) -> float:
             """Useful for when you need to learn about AI to write an paragraph about it."""
             return "AI is a very broad field."
 
@@ -724,74 +723,6 @@ def test_agent_count_formatting_error():
         mock_count_errors.assert_called_once()
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_tool_result_as_answer_is_the_final_answer_for_the_agent():
-    from crewai_tools import BaseTool
-
-    class MyCustomTool(BaseTool):
-        name: str = "Get Greetings"
-        description: str = "Get a random greeting back"
-
-        def _run(self) -> str:
-            return "Howdy!"
-
-    agent1 = Agent(
-        role="Data Scientist",
-        goal="Product amazing resports on AI",
-        backstory="You work with data and AI",
-        tools=[MyCustomTool(result_as_answer=True)],
-    )
-
-    essay = Task(
-        description="Write and then review an small paragraph on AI until it's AMAZING. But first use the `Get Greetings` tool to get a greeting.",
-        expected_output="The final paragraph with the full review on AI and no greeting.",
-        agent=agent1,
-    )
-    tasks = [essay]
-    crew = Crew(agents=[agent1], tasks=tasks)
-
-    result = crew.kickoff()
-    print("RESULT: ", result.raw)
-    assert result.raw == "Howdy!"
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_tool_usage_information_is_appended_to_agent():
-    from crewai_tools import BaseTool
-
-    class MyCustomTool(BaseTool):
-        name: str = "Decide Greetings"
-        description: str = "Decide what is the appropriate greeting to use"
-
-        def _run(self) -> str:
-            return "Howdy!"
-
-    agent1 = Agent(
-        role="Friendly Neighbor",
-        goal="Make everyone feel welcome",
-        backstory="You are the friendly neighbor",
-        tools=[MyCustomTool(result_as_answer=True)],
-    )
-
-    greeting = Task(
-        description="Say an appropriate greeting.",
-        expected_output="The greeting.",
-        agent=agent1,
-    )
-    tasks = [greeting]
-    crew = Crew(agents=[agent1], tasks=tasks)
-
-    crew.kickoff()
-    assert agent1.tools_results == [
-        {
-            "result": "Howdy!",
-            "tool_name": "Decide Greetings",
-            "tool_args": {},
-            "result_as_answer": True,
-        }
-    ]
-
-
 def test_agent_llm_uses_token_calc_handler_with_llm_has_model_name():
     agent1 = Agent(
         role="test role",
@@ -802,7 +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_name == "gpt-4o"
+    assert agent1.llm.callbacks[0].model == "gpt-4o"
     assert (
         agent1.llm.callbacks[0].token_cost_process.__class__.__name__ == "TokenProcess"
     )
@@ -963,54 +894,3 @@ def test_agent_use_trained_data(crew_training_handler):
     crew_training_handler.assert_has_calls(
         [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
     )
-
-
-def test_agent_max_retry_limit():
-    agent = Agent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-        max_retry_limit=1,
-    )
-
-    task = Task(
-        agent=agent,
-        description="Say the word: Hi",
-        expected_output="The word: Hi",
-        human_input=True,
-    )
-
-    error_message = "Error happening while sending prompt to model."
-    with patch.object(
-        CrewAgentExecutor, "invoke", wraps=agent.agent_executor.invoke
-    ) as invoke_mock:
-        invoke_mock.side_effect = Exception(error_message)
-
-        assert agent._times_executed == 0
-        assert agent.max_retry_limit == 1
-
-        with pytest.raises(Exception) as e:
-            agent.execute_task(
-                task=task,
-            )
-        assert e.value.args[0] == error_message
-        assert agent._times_executed == 2
-
-        invoke_mock.assert_has_calls(
-            [
-                mock.call(
-                    {
-                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
-                        "tool_names": "",
-                        "tools": "",
-                    }
-                ),
-                mock.call(
-                    {
-                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
-                        "tool_names": "",
-                        "tools": "",
-                    }
-                ),
-            ]
-        )

tests/agents/agent_builder/base_agent_test.py

@@ -1,36 +0,0 @@
-import hashlib
-from typing import Any, List, Optional
-
-from crewai.agents.agent_builder.base_agent import BaseAgent
-from pydantic import BaseModel
-
-
-class TestAgent(BaseAgent):
-    def execute_task(
-        self,
-        task: Any,
-        context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
-    ) -> str:
-        return ""
-
-    def create_agent_executor(self, tools=None) -> None: ...
-
-    def _parse_tools(self, tools: List[Any]) -> List[Any]:
-        return []
-
-    def get_delegation_tools(self, agents: List["BaseAgent"]): ...
-
-    def get_output_converter(
-        self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
-    ): ...
-
-
-def test_key():
-    agent = TestAgent(
-        role="test role",
-        goal="test goal",
-        backstory="test backstory",
-    )
-    hash = hashlib.md5("test role|test goal|test backstory".encode()).hexdigest()
-    assert agent.key == hash

tests/agents/test_crew_agent_parser.py

@@ -1,378 +0,0 @@
-import pytest
-from crewai.agents.parser import CrewAgentParser
-from langchain_core.agents import AgentAction, AgentFinish
-from langchain_core.exceptions import OutputParserException
-
-
-@pytest.fixture
-def parser():
-    p = CrewAgentParser()
-    p.agent = MockAgent()
-    return p
-
-
-def test_valid_action_parsing_special_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what's the temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in SF?"
-
-
-def test_valid_action_parsing_with_json_tool_input(parser):
-    text = """
-    Thought: Let's find the information
-    Action: query
-    Action Input: ** {"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we've discussed recent advancements in AI applications in healthcare, it's crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}
-    """
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    expected_tool_input = '{"task": "What are some common challenges or barriers that you have observed or experienced when implementing AI-powered solutions in healthcare settings?", "context": "As we\'ve discussed recent advancements in AI applications in healthcare, it\'s crucial to acknowledge the potential hurdles. Some possible obstacles include...", "coworker": "Senior Researcher"}'
-    assert result.tool == "query"
-    assert result.tool_input == expected_tool_input
-
-
-def test_valid_action_parsing_with_quotes(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "temperature in SF"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "temperature in SF"
-
-
-def test_valid_action_parsing_with_curly_braces(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: {temperature in SF}"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "{temperature in SF}"
-
-
-def test_valid_action_parsing_with_angle_brackets(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: <temperature in SF>"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "<temperature in SF>"
-
-
-def test_valid_action_parsing_with_parentheses(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: (temperature in SF)"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "(temperature in SF)"
-
-
-def test_valid_action_parsing_with_mixed_brackets(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: [temperature in {SF}]"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "[temperature in {SF}]"
-
-
-def test_valid_action_parsing_with_nested_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in 'SF'?\""
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in 'SF'?"
-
-
-def test_valid_action_parsing_with_incomplete_json(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == '{"query": "temperature in SF"}'
-
-
-def test_valid_action_parsing_with_special_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? @$%^&*"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF? @$%^&*"
-
-
-def test_valid_action_parsing_with_combination(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "[what is the temperature in SF?]"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "[what is the temperature in SF?]"
-
-
-def test_valid_action_parsing_with_mixed_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what's the temperature in SF?\""
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what's the temperature in SF?"
-
-
-def test_valid_action_parsing_with_newlines(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is\nthe temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is\nthe temperature in SF?"
-
-
-def test_valid_action_parsing_with_escaped_characters(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: what is the temperature in SF? \\n"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF? \\n"
-
-
-def test_valid_action_parsing_with_json_string(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: {"query": "temperature in SF"}'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == '{"query": "temperature in SF"}'
-
-
-def test_valid_action_parsing_with_unbalanced_quotes(parser):
-    text = "Thought: Let's find the temperature\nAction: search\nAction Input: \"what is the temperature in SF?"
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_clean_action_no_formatting(parser):
-    action = "Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_leading_asterisks(parser):
-    action = "** Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_trailing_asterisks(parser):
-    action = "Ask question to senior researcher **"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_leading_and_trailing_asterisks(parser):
-    action = "** Ask question to senior researcher **"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_multiple_leading_asterisks(parser):
-    action = "**** Ask question to senior researcher"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_multiple_trailing_asterisks(parser):
-    action = "Ask question to senior researcher ****"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_spaces_and_asterisks(parser):
-    action = "  **  Ask question to senior researcher  **  "
-    cleaned_action = parser._clean_action(action)
-    print(f"Original action: '{action}'")
-    print(f"Cleaned action: '{cleaned_action}'")
-    assert cleaned_action == "Ask question to senior researcher"
-
-
-def test_clean_action_with_only_asterisks(parser):
-    action = "****"
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == ""
-
-
-def test_clean_action_with_empty_string(parser):
-    action = ""
-    cleaned_action = parser._clean_action(action)
-    assert cleaned_action == ""
-
-
-def test_valid_final_answer_parsing(parser):
-    text = (
-        "Thought: I found the information\nFinal Answer: The temperature is 100 degrees"
-    )
-    result = parser.parse(text)
-    assert isinstance(result, AgentFinish)
-    assert result.return_values["output"] == "The temperature is 100 degrees"
-
-
-def test_missing_action_error(parser):
-    text = "Thought: Let's find the temperature\nAction Input: what is the temperature in SF?"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "Could not parse LLM output" in str(exc_info.value)
-
-
-def test_missing_action_input_error(parser):
-    text = "Thought: Let's find the temperature\nAction: search"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "Could not parse LLM output" in str(exc_info.value)
-
-
-def test_action_and_final_answer_error(parser):
-    text = "Thought: I found the information\nAction: search\nAction Input: what is the temperature in SF?\nFinal Answer: The temperature is 100 degrees"
-    with pytest.raises(OutputParserException) as exc_info:
-        parser.parse(text)
-    assert "both perform Action and give a Final Answer" in str(exc_info.value)
-
-
-def test_safe_repair_json(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": Senior Researcher'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unrepairable(parser):
-    invalid_json = "{invalid_json"
-    result = parser._safe_repair_json(invalid_json)
-    print("result:", invalid_json)
-    assert result == invalid_json  # Should return the original if unrepairable
-
-
-def test_safe_repair_json_missing_quotes(parser):
-    invalid_json = (
-        '{task: "Research XAI", context: "Explainable AI", coworker: Senior Researcher}'
-    )
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unclosed_brackets(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_extra_commas(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_trailing_commas(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher",}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_single_quotes(parser):
-    invalid_json = "{'task': 'Research XAI', 'context': 'Explainable AI', 'coworker': 'Senior Researcher'}"
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_mixed_quotes(parser):
-    invalid_json = "{'task': \"Research XAI\", 'context': \"Explainable AI\", 'coworker': 'Senior Researcher'}"
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unescaped_characters(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher\n"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    print("result:", result)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_missing_colon(parser):
-    invalid_json = '{"task" "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_missing_comma(parser):
-    invalid_json = '{"task": "Research XAI" "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_unexpected_trailing_characters(parser):
-    invalid_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"} random text'
-    expected_repaired_json = '{"task": "Research XAI", "context": "Explainable AI", "coworker": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_safe_repair_json_special_characters_key(parser):
-    invalid_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
-    expected_repaired_json = '{"task!@#": "Research XAI", "context$%^": "Explainable AI", "coworker&*()": "Senior Researcher"}'
-    result = parser._safe_repair_json(invalid_json)
-    assert result == expected_repaired_json
-
-
-def test_parsing_with_whitespace(parser):
-    text = " Thought: Let's find the temperature \n Action: search \n Action Input: what is the temperature in SF? "
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_parsing_with_special_characters(parser):
-    text = 'Thought: Let\'s find the temperature\nAction: search\nAction Input: "what is the temperature in SF?"'
-    result = parser.parse(text)
-    assert isinstance(result, AgentAction)
-    assert result.tool == "search"
-    assert result.tool_input == "what is the temperature in SF?"
-
-
-def test_integration_valid_and_invalid(parser):
-    text = """
-    Thought: Let's find the temperature
-    Action: search
-    Action Input: what is the temperature in SF?
-
-    Thought: I found the information
-    Final Answer: The temperature is 100 degrees
-
-    Thought: Missing action
-    Action Input: invalid
-
-    Thought: Missing action input
-    Action: invalid
-    """
-    parts = text.strip().split("\n\n")
-    results = []
-    for part in parts:
-        try:
-            result = parser.parse(part.strip())
-            results.append(result)
-        except OutputParserException as e:
-            results.append(e)
-
-    assert isinstance(results[0], AgentAction)
-    assert isinstance(results[1], AgentFinish)
-    assert isinstance(results[2], OutputParserException)
-    assert isinstance(results[3], OutputParserException)
-
-
-class MockAgent:
-    def increment_formatting_errors(self):
-        pass
-
-
-# TODO: ADD TEST TO MAKE SURE ** REMOVAL DOESN'T MESS UP ANYTHING

tests/cassettes/test_conditional_task_last_task_when_conditional_is_false.yaml

@@ -1,151 +0,0 @@
-interactions:
-- request:
-    body: '{"messages": [{"content": "You are Researcher. You''re an expert researcher,
-      specialized in technology, software engineering, AI and startups. You work as
-      a freelancer and is now working on doing research and analysis for a new customer.\nYour
-      personal goal is: Make the best research and analysis on content about AI and
-      AI agentsTo 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: Say Hi\n\nThis is the expect criteria for
-      your final answer: Hi \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
-      connection:
-      - keep-alive
-      content-length:
-      - '1072'
-      content-type:
-      - application/json
-      cookie:
-      - _cfuvid=Nxp5RE8CN2EyHxMIvB_SaTizIH5w0eWt9SPilMuIjMk-1721227661802-0.0.1.1-604800000;
-        __cf_bm=jadAYV2gh7qPDzgKO9A4JzJTaI9c2fnnjxloIQZeOIw-1721227661-1.0.1.1-apaA8kQyGiEV3kOuXHe8z1zeyvxd_jBHCQpdqWirUlylrUo.uRZjRDueI.sSXS4hXoWkyIW6kIMt7lamQM2mdw
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.35.10
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.35.10
-      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-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        now"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        can"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        give"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        great"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
-        Hi"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9m0FB4Oy6X0apYX2wcQ30rTBkmtxT","object":"chat.completion.chunk","created":1721227709,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
-
-
-        data: [DONE]
-
-
-        '
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8a4b087e7d024593-ATL
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream; charset=utf-8
-      Date:
-      - Wed, 17 Jul 2024 14:48:29 GMT
-      Server:
-      - cloudflare
-      Transfer-Encoding:
-      - chunked
-      X-Content-Type-Options:
-      - nosniff
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '142'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15552000; includeSubDomains; preload
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '30000000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '29999753'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_75100793afc289eaf8b56127e1cc0532
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_crew_async_kickoff.yaml

@@ -1,591 +0,0 @@
-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-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"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-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        now"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        can"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        give"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        great"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        Dogs"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        are"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        incredibly"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        loyal"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        provide"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        unmatched"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        companionship"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        humans"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXYXcf53VmxfiC6Q2NBDG2bPci","object":"chat.completion.chunk","created":1719947865,"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:
-      - 89d0fa4e7abf53db-ATL
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream; charset=utf-8
-      Date:
-      - Tue, 02 Jul 2024 19:17:45 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=6Xl2nvdsXT4uSfQ3C1ZK.LWKGYekVs5ErrLDZOdI.50-1719947865-1.0.1.1-6RQoTCznxe7H868MoxghRegIZaElbG_bN_jbs94hmnsnuR1P9bptoj8o2DbOSvj48ubewyvy8L16mOZHlMLw_A;
-        path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=kPTMOkGHQp0ytgVUrm3jFNiB9I.DDI2ONPRTr6IMTeo-1719947865623-0.0.1.1-604800000;
-        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:
-      - '102'
-      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:
-      - '9997'
-      x-ratelimit-remaining-tokens:
-      - '15999783'
-      x-ratelimit-reset-requests:
-      - 14ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_2c5219e228ce79f0131c497230904013
-    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-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"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-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        now"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        can"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        give"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        great"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        Apple"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        revolution"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"izes"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        technology"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        with"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        sleek"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        designs"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        seamless"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        integration"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        innovative"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        user"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"
-        experiences"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d576307f90","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXaXAntrwdA2E5Bhxgz9p7q5Nc","object":"chat.completion.chunk","created":1719947865,"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:
-      - 89d0fa4e7ca907e6-ATL
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream; charset=utf-8
-      Date:
-      - Tue, 02 Jul 2024 19:17:45 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=wf2ozMjr46sG0EhuZjpiDNagwTxC05ct3Hn7Y9Rs5AI-1719947865-1.0.1.1-uckxTTr7Yfe6sv4ZznqqrGTEz9E3_Cpp7OAWBIEeNz1Smdjwijw8YV5oYPe_6W4DrEtwVzRDxaqIHlWP55O0QA;
-        path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=F9pWw4TeoPa8puOm5RN9Gp2oY0lRoN53ChZ1qFYx1S8-1719947865726-0.0.1.1-604800000;
-        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:
-      - '168'
-      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:
-      - '15999780'
-      x-ratelimit-reset-requests:
-      - 10ms
-      x-ratelimit-reset-tokens:
-      - 0s
-      x-request-id:
-      - req_e6dfeda5935eae030bcc2da526234635
-    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-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"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-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        now"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        can"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        give"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        a"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        great"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        Cats"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        are"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        master"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ful"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        hunters"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        brilliant"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
-        problem"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-sol"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"vers"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9gdIXPfC85ZAgbI0KqvS9z396XBKw","object":"chat.completion.chunk","created":1719947865,"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:
-      - 89d0fa4e7ae912d7-ATL
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream; charset=utf-8
-      Date:
-      - Tue, 02 Jul 2024 19:17:45 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=y7JNZ8WEp.q5pMXLi79ajfcI.F6MfE0GeYLw34Apkf0-1719947865-1.0.1.1-QKklGeYuOnsQROgqMs42XwqKNvW.mPrmcbtaxMnUg3eSgI7TRnRq4qPuSan0ynDt4Hd9NMuls2FR.Caa1MVr9Q;
-        path=/; expires=Tue, 02-Jul-24 19:47:45 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=FVQoSgcvVyiB_o43X6y5MGYgzGojmsQqS.nPObW3JYU-1719947865679-0.0.1.1-604800000;
-        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:
-      - '132'
-      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_a06bde4044d3ee75edf08f333139679c
-    status:
-      code: 200
-      message: OK
-version: 1

tests/cassettes/test_crew_async_kickoff_for_each_full_ouput.yaml

@@ -1,585 +0,0 @@
-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