Update feature_request.md

Add both Bug and Feature templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,35 @@
+---
+name: Bug report
+about: Create a report to help us improve CrewAI
+title: "[BUG]"
+labels: bug
+assignees: ''
+
+---
+
+**Description**
+Provide a clear and concise description of what the bug is.
+
+**Steps to Reproduce**
+Provide a step-by-step process to reproduce the behavior:
+
+**Expected behavior**
+A clear and concise description of what you expected to happen.
+
+**Screenshots/Code snippets**
+If applicable, add screenshots or code snippets to help explain your problem.
+
+**Environment Details:**
+- **Operating System**: [e.g., Ubuntu 20.04, macOS Catalina, Windows 10]
+- **Python Version**: [e.g., 3.8, 3.9, 3.10]
+- **crewAI Version**: [e.g., 0.30.11]
+- **crewAI Tools Version**: [e.g., 0.2.6]
+
+**Logs**
+Include relevant logs or error messages if applicable.
+
+**Possible Solution**
+Have a solution in mind? Please suggest it here, or write "None".
+
+**Additional context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,21 @@
+---
+name: Feature request
+about: Suggest a Feature to improve CrewAI
+title: "[FEAT]"
+labels: feature-request, improvement
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+If possible attach the Issue related to it
+
+**Describe the solution you'd like / Use-case**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.gitignore

@@ -14,4 +14,5 @@ test.py
 rc-tests/*
 *.pkl
 temp/*
-.vscode/*
+.vscode/*
+crew_tasks_output.json

README.md

@@ -254,7 +254,7 @@ pip install dist/*.tar.gz
 
 CrewAI uses anonymous telemetry to collect usage data with the main purpose of helping us improve the library by focusing our efforts on the most used features, integrations and tools.
 
-There is NO data being collected on the prompts, tasks descriptions agents backstories or goals nor tools usage, no API calls, nor responses nor any data that is being processed by the agents, nor any secrets and env vars.
+It's pivotal to understand that **NO data is collected** concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy. We don't offer a way to disable it now, but we will in the future.
 
 Data collected includes:
 
@@ -279,7 +279,7 @@ Data collected includes:
 - Tools names available
   - Understand out of the publically available tools, which ones are being used the most so we can improve them
 
-Users can opt-in sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews.
+Users can opt-in to Further Telemetry, sharing the complete telemetry data by setting the `share_crew` attribute to `True` on their Crews. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
 
 ## License
 

docs/core-concepts/Agents.md

@@ -114,7 +114,7 @@ from langchain.agents import load_tools
 langchain_tools = load_tools(["google-serper"], llm=llm)
 
 agent1 = CustomAgent(
-    role="backstory agent",
+    role="agent role",
     goal="who is {input}?",
     backstory="agent backstory",
     verbose=True,
@@ -127,7 +127,7 @@ task1 = Task(
 )
 
 agent2 = Agent(
-    role="bio agent",
+    role="agent role",
     goal="summarize the short bio for {input} and if needed do more research",
     backstory="agent backstory",
     verbose=True,

docs/core-concepts/Crews.md

@@ -4,36 +4,39 @@ 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.                                                     |
+| 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.
+| **Planning LLM** *(optional)*         | `planning_llm`         | The language model used by the AgentPlanner in a planning process. |
 
 !!! 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
 
@@ -44,6 +47,12 @@ 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(
@@ -54,7 +63,7 @@ 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=[DuckDuckGoSearchRun()]
+    tools=[search]
 )
 
 writer = Agent(
@@ -89,6 +98,57 @@ 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
+)
+
+crew_output = 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.
@@ -156,3 +216,32 @@ for async_result in async_results:
 ```
 
 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.

docs/core-concepts/Memory.md

@@ -29,6 +29,11 @@ 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
@@ -161,10 +166,43 @@ 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

@@ -0,0 +1,138 @@
+---
+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.
+
+#### Planning LLM
+
+Now you can define the LLM that will be used to plan the tasks. You can use any ChatOpenAI LLM model available.
+
+```python
+from crewai import Crew, Agent, Task, Process
+from langchain_openai import ChatOpenAI
+
+# Assemble your crew with planning capabilities and custom LLM
+my_crew = Crew(
+    agents=self.agents,
+    tasks=self.tasks,
+    process=Process.sequential,
+    planning=True,
+    planning_llm=ChatOpenAI(model="gpt-4o")
+)
+```
+
+
+### 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

@@ -4,27 +4,29 @@ 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. |
-| **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                        | 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.                  |
 
 ## Creating a Task
 
@@ -35,12 +37,75 @@ from crewai import Task
 
 task = Task(
     description='Find and summarize the latest and most relevant news on AI',
-    agent=sales_agent
+    agent=sales_agent,
+    expected_output='A bullet list summary of the top 5 most important AI news',
 )
 ```
 
 !!! note "Task Assignment"
-    Directly specify an `agent` for assignment or let the `hierarchical` CrewAI's process decide based on roles, availability, etc.
+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}")
+```
 
 ## Integrating Tools with Tasks
 

docs/core-concepts/Testing.md

@@ -0,0 +1,41 @@
+---
+title: crewAI Testing
+description: Learn how to test your crewAI Crew and evaluate their performance.
+---
+
+## Introduction
+
+Testing is a crucial part of the development process, and it is essential to ensure that your crew is performing as expected. And with crewAI, you can easily test your crew and evaluate its performance using the built-in testing capabilities.
+
+### Using the Testing Feature
+
+We added the CLI command `crewai test` to make it easy to test your crew. This command will run your crew for a specified number of iterations and provide detailed performance metrics.
+The parameters are `n_iterations` and `model` which are optional and default to 2 and `gpt-4o-mini` respectively. For now the only provider available is OpenAI.
+
+```bash
+crewai test
+```
+
+If you want to run more iterations or use a different model, you can specify the parameters like this:
+
+```bash
+crewai test --n_iterations 5 --model gpt-4o
+```
+
+What happens when you run the `crewai test` command is that the crew will be executed for the specified number of iterations, and the performance metrics will be displayed at the end of the run.
+
+A table of scores at the end will show the performance of the crew in terms of the following metrics:
+```
+                Task Scores
+          (1-10 Higher is better)
+┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
+┃ Tasks/Crew ┃ Run 1 ┃ Run 2 ┃ Avg. Total ┃
+┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
+│ Task 1     │ 10.0  │ 9.0   │ 9.5        │
+│ Task 2     │ 9.0   │ 9.0   │ 9.0        │
+│ Crew       │ 9.5   │ 9.0   │ 9.2        │
+└────────────┴───────┴───────┴────────────┘
+```
+
+The example above shows the test results for two runs of the crew with two tasks, with the average total score for each task and the crew as a whole.
+

docs/core-concepts/Tools.md

@@ -100,16 +100,24 @@ 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. |
@@ -120,8 +128,6 @@ 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/getting-started/Installing-CrewAI.md

@@ -18,4 +18,7 @@ pip install crewai
 # Install the main crewAI package and the tools package
 # that includes a series of helpful tools for your agents
 pip install 'crewai[tools]'
+
+# Alternatively, you can also use:
+pip install crewai crewai-tools
 ```

docs/getting-started/Start-a-New-CrewAI-Project-Template-Method.md

@@ -0,0 +1,255 @@
+---
+title: Starting a New CrewAI Project - Using Template
+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.
+
+Beforre we start there are a couple of things to note:
+
+1. CrewAI is a Python package and requires Python >=3.10 and <=3.13 to run.
+2. The preferred way of setting up CrewAI is using the `crewai create` command.This will create a new project folder and install a skeleton template for you to work on.
+
+## Prerequisites
+
+Before getting started with CrewAI, make sure that you have installed it via pip:
+
+```shell
+$ pip install crewai crewai-tools
+```
+
+### Virtual Environments
+It is highly recommended that you use virtual environments to ensure that your CrewAI project is isolated from other projects and dependencies. Virtual environments provide a clean, separate workspace for each project, preventing conflicts between different versions of packages and libraries. This isolation is crucial for maintaining consistency and reproducibility in your development process. You have multiple options for setting up virtual environments depending on your operating system and Python version:
+
+1. Use venv (Python's built-in virtual environment tool):
+   venv is included with Python 3.3 and later, making it a convenient choice for many developers. It's lightweight and easy to use, perfect for simple project setups.
+
+   To set up virtual environments with venv, refer to the official [Python documentation](https://docs.python.org/3/tutorial/venv.html).
+
+2. Use Conda (A Python virtual environment manager):
+   Conda is an open-source package manager and environment management system for Python. It's widely used by data scientists, developers, and researchers to manage dependencies and environments in a reproducible way.
+
+   To set up virtual environments with Conda, refer to the official [Conda documentation](https://docs.conda.io/projects/conda/en/stable/user-guide/getting-started.html).
+
+3. Use Poetry (A Python package manager and dependency management tool):
+   Poetry is an open-source Python package manager that simplifies the installation of packages and their dependencies. Poetry offers a convenient way to manage virtual environments and dependencies.
+   Poetry is CrewAI's prefered tool for package / dependancy management in CrewAI.
+
+### Code IDEs
+
+Most users of CrewAI a Code Editor / Integrated Development Environment (IDE) for building there Crews. You can use any code IDE of your choice. Seee below for some popular options for Code Editors / Integrated Development Environments (IDE):
+
+- [Visual Studio Code](https://code.visualstudio.com/) - Most popular
+- [PyCharm](https://www.jetbrains.com/pycharm/)
+- [Cursor AI](https://cursor.com)
+
+Pick one that suits your style and needs.
+
+## Creating a New Project
+In this example we will be using Venv as our virtual environment manager.
+
+To setup a virtual environment, run the following CLI command:
+
+```shell
+$ python3 -m venv <venv-name>
+```
+
+Activate your virtual environment by running the following CLI command:
+
+```shell
+$ source <venv-name>/bin/activate
+```
+
+Now, to create a new CrewAI 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/Conditional-Tasks.md

@@ -0,0 +1,87 @@
+---
+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

@@ -7,6 +7,7 @@ description: Comprehensive guide on crafting, using, and managing custom tools w
 This guide provides detailed instructions on creating custom tools for the crewAI framework and how to efficiently manage and utilize these tools, incorporating the latest functionalities such as tool delegation, error handling, and dynamic tool calling. It also highlights the importance of collaboration tools, enabling agents to perform a wide range of actions.
 
 ### Prerequisites
+
 Before creating your own tools, ensure you have the crewAI extra tools package installed:
 
 ```bash
@@ -31,7 +32,7 @@ class MyCustomTool(BaseTool):
 
 ### Using the `tool` Decorator
 
-Alternatively, use the `tool` decorator for a direct approach to create tools. This requires specifying attributes and the tool's logic within a function.
+Alternatively, you can use the tool decorator `@tool`. This approach allows you to define the tool's attributes and functionality directly within a function, offering a concise and efficient way to create specialized tools tailored to your needs.
 
 ```python
 from crewai_tools import tool

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

@@ -1,82 +0,0 @@
----
-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.
----
-
-## 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.
-
-## Step 0: Installation
-Install CrewAI and any necessary packages for your project. CrewAI is compatible with Python >=3.10,<=3.13.
-
-```shell
-pip install crewai
-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.
-
-```python
-import os
-from langchain.llms import OpenAI
-from crewai import Agent
-from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
-
-os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
-os.environ["SERPER_API_KEY"] = "Your Serper Key"
-
-search_tool = SerperDevTool()
-browser_tool = BrowserbaseTool()
-exa_search_tool = ExaSearchTool()
-
-# Creating a senior researcher agent with advanced configurations
-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
-)
-
-# Creating a writer agent with custom tools and specific configurations
-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
-)
-
-# Setting a specific manager agent
-manager = Agent(
-  role='Manager',
-  goal='Ensure the smooth operation and coordination of the team',
-  verbose=True,
-  backstory=(
-    "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
-
-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.

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

@@ -7,7 +7,7 @@ description: Learn how to force tool output as the result in of an Agent's task
 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.
+To force the tool output as the result of an agent's task, you can set the `result_as_answer` parameter to `True` when creating the agent. 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:
 
@@ -16,7 +16,7 @@ Here's an example of how to force the tool output as the result of an agent's ta
 # Define a custom tool that returns the result as the answer
 coding_agent =Agent(
         role="Data Scientist",
-        goal="Product amazing resports on AI",
+        goal="Product amazing reports on AI",
         backstory="You work with data and AI",
         tools=[MyCustomTool(result_as_answer=True)],
     )

docs/how-to/LLM-Connections.md

@@ -6,33 +6,25 @@ description: Comprehensive guide on integrating CrewAI with various Large Langua
 ## 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-4o 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 (specifically, the model specified by the OPENAI_MODEL_NAME environment variable, defaulting to "gpt-4") for language processing. You can configure your agents to use a different model or API as described in this guide.
 
-CrewAI offers flexibility in connecting to various LLMs, including local models via [Ollama](https://ollama.ai) and different APIs like Azure. It's compatible with all [LangChain LLM](https://python.langchain.com/docs/integrations/llms/) components, enabling diverse integrations for tailored AI solutions.
+CrewAI provides extensive versatility in integrating with various Language Models (LLMs), including local options through Ollama such as  Llama and Mixtral to cloud-based solutions like Azure. Its compatibility extends to all [LangChain LLM components](https://python.langchain.com/v0.2/docs/integrations/llms/), offering a wide range of integration possibilities for customized AI applications.
 
-## CrewAI Agent Overview
+The platform supports connections to an array of Generative AI models, including:
 
-The `Agent` class is the cornerstone for implementing AI solutions in CrewAI. Here's a comprehensive overview of the Agent class attributes and methods:
+ - OpenAI's suite of advanced language models
+ - Anthropic's cutting-edge AI offerings
+ - Ollama's diverse range of locally-hosted generative model & embeddings
+ - LM Studio's diverse range of locally hosted generative models & embeddings
+ - Groq's Super Fast LLM offerings
+ - Azures' generative AI offerings
+ - HuggingFace's generative AI offerings
 
-- **Attributes**:
-    - `role`: Defines the agent's role within the solution.
-    - `goal`: Specifies the agent's objective.
-    - `backstory`: Provides a background story to the agent.
-    - `cache` *Optional*: Determines whether the agent should use a cache for tool usage. Default is `True`.
-    - `max_rpm` *Optional*: Maximum number of requests per minute the agent's execution should respect. Optional.
-    - `verbose` *Optional*: Enables detailed logging of the agent's execution. Default is `False`.
-    - `allow_delegation` *Optional*: Allows the agent to delegate tasks to other agents, default is `True`.
-    - `tools`: Specifies the tools available to the agent for task execution. Optional.
-    - `max_iter` *Optional*: Maximum number of iterations for an agent to execute a task, default is 25.
-    - `max_execution_time` *Optional*: Maximum execution time for an agent to execute a task. Optional.
-    - `step_callback` *Optional*: Provides a callback function to be executed after each step. Optional.
-    - `llm` *Optional*: Indicates the Large Language Model the agent uses. By default, it uses the GPT-4 model defined in the environment variable "OPENAI_MODEL_NAME".
-    - `function_calling_llm` *Optional* :  Will turn the ReAct CrewAI agent into a function-calling agent.
-    - `callbacks` *Optional*: A list of callback functions from the LangChain library that are triggered during the agent's execution process.
-    - `system_template` *Optional*: Optional string to define the system format for the agent.
-    - `prompt_template` *Optional*: Optional string to define the prompt format for the agent.
-    - `response_template` *Optional*: Optional string to define the response format for the agent.
+This broad spectrum of LLM options enables users to select the most suitable model for their specific needs, whether prioritizing local deployment, specialized capabilities, or cloud-based scalability.
 
+## Changing the default LLM
+The default LLM is provided through the `langchain openai` package, which is installed by default when you install CrewAI. You can change this default LLM to a different model or API by setting the `OPENAI_MODEL_NAME` environment variable. This straightforward process allows you to harness the power of different OpenAI models, enhancing the flexibility and capabilities of your CrewAI implementation.
 ```python
 # Required
 os.environ["OPENAI_MODEL_NAME"]="gpt-4-0125-preview"
@@ -45,30 +37,27 @@ example_agent = Agent(
   verbose=True
 )
 ```
+## Ollama Local Integration
+Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, you will need the `langchain-ollama` package. You can then set the following environment variables to connect to your Ollama instance running locally on port 11434.
 
-## Ollama Integration
-Ollama is preferred for local LLM integration, offering customization and privacy benefits. To integrate Ollama with CrewAI, set the appropriate environment variables as shown below.
-
-### 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_KEY=''
+os.environ[OPENAI_API_BASE]='http://localhost:11434'
+os.environ[OPENAI_MODEL_NAME]='llama2'  # Adjust based on available model
+os.environ[OPENAI_API_KEY]='' # No API Key required for Ollama
 ```
 
-## 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.   
+## Ollama Integration Step by Step (ex. for using Llama 3.1 8B locally)
+1. [Download and install Ollama](https://ollama.com/download).   
+2. After setting up the Ollama, Pull the Llama3.1 8B model by typing following lines into your terminal ```ollama run llama3.1```.   
+3. Llama3.1 should now be served locally on `http://localhost:11434`
 ```
 from crewai import Agent, Task, Crew
-from langchain.llms import Ollama
+from langchain_ollama import ChatOllama
 import os
 os.environ["OPENAI_API_KEY"] = "NA"
 
 llm = Ollama(
-    model = "llama2",
+    model = "llama3.1",
     base_url = "http://localhost:11434")
 
 general_agent = Agent(role = "Math Professor",
@@ -98,13 +87,14 @@ There are a couple of different ways you can use HuggingFace to host your LLM.
 
 ### Your own HuggingFace endpoint
 ```python
-from langchain_community.llms import HuggingFaceEndpoint
+from langchain_huggingface import HuggingFaceEndpoint,
 
 llm = HuggingFaceEndpoint(
-    endpoint_url="<YOUR_ENDPOINT_URL_HERE>",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
+    repo_id="microsoft/Phi-3-mini-4k-instruct",
     task="text-generation",
-    max_new_tokens=512
+    max_new_tokens=512,
+    do_sample=False,
+    repetition_penalty=1.03,
 )
 
 agent = Agent(
@@ -115,59 +105,50 @@ agent = Agent(
 )
 ```
 
-### From HuggingFaceHub endpoint
-```python
-from langchain_community.llms import HuggingFaceHub
-
-llm = HuggingFaceHub(
-    repo_id="HuggingFaceH4/zephyr-7b-beta",
-    huggingfacehub_api_token="<HF_TOKEN_HERE>",
-    task="text-generation",
-)
-```
-
 ## OpenAI Compatible API Endpoints
-Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, and Mistral AI.
+Switch between APIs and models seamlessly using environment variables, supporting platforms like FastChat, LM Studio, Groq, and Mistral AI.
 
 ### Configuration Examples
 #### FastChat
 ```sh
-OPENAI_API_BASE="http://localhost:8001/v1"
-OPENAI_MODEL_NAME='oh-2.5m7b-q51'
-OPENAI_API_KEY=NA
+os.environ[OPENAI_API_BASE]="http://localhost:8001/v1"
+os.environ[OPENAI_MODEL_NAME]='oh-2.5m7b-q51'
+os.environ[OPENAI_API_KEY]=NA
 ```
 
 #### LM Studio
 Launch [LM Studio](https://lmstudio.ai) and go to the Server tab. Then select a model from the dropdown menu and wait for it to load. Once it's loaded, click the green Start Server button and use the URL, port, and API key that's shown (you can modify them). Below is an example of the default settings as of LM Studio 0.2.19:
 ```sh
-OPENAI_API_BASE="http://localhost:1234/v1"
-OPENAI_API_KEY="lm-studio"
+os.environ[OPENAI_API_BASE]="http://localhost:1234/v1"
+os.environ[OPENAI_API_KEY]="lm-studio"
+```
+
+#### Groq API
+```sh
+os.environ[OPENAI_API_KEY]=your-groq-api-key
+os.environ[OPENAI_MODEL_NAME]='llama3-8b-8192'
+os.environ[OPENAI_API_BASE]=https://api.groq.com/openai/v1
 ```
 
 #### Mistral API
 ```sh
-OPENAI_API_KEY=your-mistral-api-key
-OPENAI_API_BASE=https://api.mistral.ai/v1
-OPENAI_MODEL_NAME="mistral-small"
+os.environ[OPENAI_API_KEY]=your-mistral-api-key
+os.environ[OPENAI_API_BASE]=https://api.mistral.ai/v1
+os.environ[OPENAI_MODEL_NAME]="mistral-small"
 ```
 
 ### Solar
-```python
+```sh
 from langchain_community.chat_models.solar import SolarChat
-# Initialize language model
-os.environ["SOLAR_API_KEY"] = "your-solar-api-key"
-llm = SolarChat(max_tokens=1024)
+```
+```sh
+os.environ[SOLAR_API_BASE]="https://api.upstage.ai/v1/solar"
+os.environ[SOLAR_API_KEY]="your-solar-api-key"
+```
 
 # Free developer API key available here: https://console.upstage.ai/services/solar
 # Langchain Example: https://github.com/langchain-ai/langchain/pull/18556
-```
 
-### text-gen-web-ui
-```sh
-OPENAI_API_BASE=http://localhost:5000/v1
-OPENAI_MODEL_NAME=NA
-OPENAI_API_KEY=NA
-```
 
 ### Cohere
 ```python
@@ -183,10 +164,11 @@ llm = ChatCohere()
 ### Azure Open AI Configuration
 For Azure OpenAI API integration, set the following environment variables:
 ```sh
-AZURE_OPENAI_VERSION="2022-12-01"
-AZURE_OPENAI_DEPLOYMENT=""
-AZURE_OPENAI_ENDPOINT=""
-AZURE_OPENAI_KEY=""
+
+os.environ[AZURE_OPENAI_DEPLOYMENT] = "You deployment"
+os.environ["OPENAI_API_VERSION"] = "2023-12-01-preview"
+os.environ["AZURE_OPENAI_ENDPOINT"] = "Your Endpoint"
+os.environ["AZURE_OPENAI_API_KEY"] = "<Your API Key>"
 ```
 
 ### Example Agent with Azure LLM
@@ -209,6 +191,5 @@ azure_agent = Agent(
   llm=azure_llm
 )
 ```
-
 ## 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/Replay-tasks-from-latest-Crew-Kickoff.md

@@ -0,0 +1,49 @@
+---
+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/Start-a-New-CrewAI-Project.md

@@ -1,137 +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](how-to/Installing-CrewAI.md) to install CrewAI and its dependencies.
-
-## Creating a New Project
-
-To create a new project, run the following CLI command:
-
-```shell
-$ crewai create my_project
-```
-
-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.
-```
-
-## 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/index.md

@@ -5,6 +5,19 @@
 Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
 
 <div style="display:flex; margin:0 auto; justify-content: center;">
+    <div style="width:25%">
+        <h2>Getting Started</h2>
+        <ul>
+            <li><a href='./getting-started/Installing-CrewAI'>
+                   Installing CrewAI
+                 </a>
+            </li>
+            <li><a href='./getting-started/Start-a-New-CrewAI-Project-Template-Method'>
+                   Start a New CrewAI Project: Template Method
+                 </a>
+            </li>
+        </ul>
+    </div>
     <div style="width:25%">
         <h2>Core Concepts</h2>
         <ul>
@@ -43,26 +56,16 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     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
-                </a>
-            </li>
-            <li>
-                <a href="./how-to/Creating-a-Crew-and-kick-it-off">
-                    Getting Started
-                </a>
-            </li>
             <li>
                 <a href="./how-to/Create-Custom-Tools">
                     Create Custom Tools
@@ -113,6 +116,16 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     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

docs/telemetry/Telemetry.md

@@ -5,7 +5,7 @@ description: Understanding the telemetry data collected by CrewAI and how it con
 
 ## Telemetry
 
-CrewAI utilizes anonymous telemetry to gather usage statistics with the primary goal of enhancing the library. Our focus is on improving and developing the features, integrations, and tools most utilized by our users.
+CrewAI utilizes anonymous telemetry to gather usage statistics with the primary goal of enhancing the library. Our focus is on improving and developing the features, integrations, and tools most utilized by our users. We don't offer a way to disable it now, but we will in the future.
 
 It's pivotal to understand that **NO data is collected** concerning prompts, task descriptions, agents' backstories or goals, usage of tools, API calls, responses, any data processed by the agents, or secrets and environment variables, with the exception of the conditions mentioned. When the `share_crew` feature is enabled, detailed data including task descriptions, agents' backstories or goals, and other specific attributes are collected to provide deeper insights while respecting user privacy.
 
@@ -22,7 +22,7 @@ It's pivotal to understand that **NO data is collected** concerning prompts, tas
 - **Tool Usage**: Identifying which tools are most frequently used allows us to prioritize improvements in those areas.
 
 ### Opt-In Further Telemetry Sharing
-Users can choose to share their complete telemetry data by enabling the `share_crew` attribute to `True` in their crew configurations. This opt-in approach respects user privacy and aligns with data protection standards by ensuring users have control over their data sharing preferences. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
+Users can choose to share their complete telemetry data by enabling the `share_crew` attribute to `True` in their crew configurations. Enabling `share_crew` results in the collection of detailed crew and task execution data, including `goal`, `backstory`, `context`, and `output` of tasks. This enables a deeper insight into usage patterns while respecting the user's choice to share.
 
 ### Updates and Revisions
 We are committed to maintaining the accuracy and transparency of our documentation. Regular reviews and updates are performed to ensure our documentation accurately reflects the latest developments of our codebase and telemetry practices. Users are encouraged to review this section for the most current information on our data collection practices and how they contribute to the improvement of CrewAI.

docs/tools/CodeInterpreterTool.md

@@ -1,9 +1,9 @@
 # CodeInterpreterTool
 
 ## Description
-This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a sandboxed environment, so it is safe to run any code.
+This tool enables the Agent to execute Python 3 code that it has generated autonomously. The code is run in a secure, isolated environment, ensuring safety regardless of the content. 
 
-It is incredible useful since it allows the Agent to generate code, run it in the same environment, get the result and use it to make decisions.
+This functionality is particularly valuable as it allows the Agent to create code, execute it within the same ecosystem, obtain the results, and utilize that information to inform subsequent decisions and actions.
 
 ## Requirements
 

docs/tools/ComposioTool.md

@@ -2,7 +2,7 @@
 
 ## 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.
+This tools is a wrapper around the composio set of tools and gives your agent access to a wide variety of tools from the composio SDK.
 
 ## Installation
 
@@ -19,7 +19,7 @@ after the installation is complete, either run `composio login` or export your c
 
 The following example demonstrates how to initialize the tool and execute a github action:
 
-1. Initialize toolset
+1. Initialize Composio tools
 
 ```python
 from composio import App

docs/tools/SerperDevTool.md

@@ -29,5 +29,69 @@ To effectively use the `SerperDevTool`, follow these steps:
 2. **API Key Acquisition**: Acquire a `serper.dev` API key by registering for a free account at `serper.dev`.
 3. **Environment Configuration**: Store your obtained API key in an environment variable named `SERPER_API_KEY` to facilitate its use by the tool.
 
+## Parameters
+
+The `SerperDevTool` comes with several parameters that will be passed to the API :
+
+- **search_url**: The URL endpoint for the search API. (Default is `https://google.serper.dev/search`)
+
+- **country**: Optional. Specify the country for the search results.
+- **location**: Optional. Specify the location for the search results.
+- **locale**: Optional. Specify the locale for the search results.
+- **n_results**: Number of search results to return. Default is `10`.
+
+The values for `country`, `location`, `locale` and `search_url` can be found on the [Serper Playground](https://serper.dev/playground).
+
+## Example with Parameters
+Here is an example demonstrating how to use the tool with additional parameters:
+
+```python
+from crewai_tools import SerperDevTool
+
+tool = SerperDevTool(
+    search_url="https://google.serper.dev/scholar",
+    n_results=2,
+)
+
+print(tool.run(search_query="ChatGPT"))
+
+# Using Tool: Search the internet
+
+# Search results: Title: Role of chat gpt in public health
+# Link: https://link.springer.com/article/10.1007/s10439-023-03172-7
+# Snippet: … ChatGPT in public health. In this overview, we will examine the potential uses of ChatGPT in
+# ---
+# Title: Potential use of chat gpt in global warming
+# Link: https://link.springer.com/article/10.1007/s10439-023-03171-8
+# Snippet: … as ChatGPT, have the potential to play a critical role in advancing our understanding of climate
+# ---
+
+```
+
+```python
+from crewai_tools import SerperDevTool
+
+tool = SerperDevTool(
+    country="fr",
+    locale="fr",
+    location="Paris, Paris, Ile-de-France, France",
+    n_results=2,
+)
+
+print(tool.run(search_query="Jeux Olympiques"))
+
+# Using Tool: Search the internet
+
+# Search results: Title: Jeux Olympiques de Paris 2024 - Actualités, calendriers, résultats
+# Link: https://olympics.com/fr/paris-2024
+# Snippet: Quels sont les sports présents aux Jeux Olympiques de Paris 2024 ? · Athlétisme · Aviron · Badminton · Basketball · Basketball 3x3 · Boxe · Breaking · Canoë ...
+# ---
+# Title: Billetterie Officielle de Paris 2024 - Jeux Olympiques et Paralympiques
+# Link: https://tickets.paris2024.org/
+# Snippet: Achetez vos billets exclusivement sur le site officiel de la billetterie de Paris 2024 pour participer au plus grand événement sportif au monde.
+# ---
+
+```
+
 ## Conclusion
-By integrating the `SerperDevTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.
+By integrating the `SerperDevTool` into Python projects, users gain the ability to conduct real-time, relevant searches across the internet directly from their applications. The updated parameters allow for more customized and localized search results. By adhering to the setup and usage guidelines provided, incorporating this tool into projects is streamlined and straightforward.

mkdocs.yml

@@ -119,6 +119,9 @@ theme:
 
 nav:
   - Home: '/'
+  - Getting Started:
+    - Installing CrewAI: 'getting-started/Installing-CrewAI.md'
+    - Starting a new CrewAI project: 'getting-started/Start-a-New-CrewAI-Project-Template-Method.md'
   - Core Concepts:
     - Agents: 'core-concepts/Agents.md'
     - Tasks: 'core-concepts/Tasks.md'
@@ -128,6 +131,8 @@ nav:
     - Collaboration: 'core-concepts/Collaboration.md'
     - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
+    - Planning: 'core-concepts/Planning.md'
+    - Testing: 'core-concepts/Testing.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
   - How to Guides:
@@ -145,6 +150,8 @@ nav:
     - 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:
@@ -180,6 +187,7 @@ 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 = "0.36.0"
+version = "0.46.0"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -21,13 +21,14 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.4.8", optional = true }
+crewai-tools = { version = "^0.4.26", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
 appdirs = "^1.4.4"
 jsonref = "^1.1.0"
-agentops = { version = "^0.1.9", optional = true }
+agentops = { version = "^0.3.0", optional = true }
 embedchain = "^0.1.114"
+json-repair = "^0.25.2"
 
 [tool.poetry.extras]
 tools = ["crewai-tools"]
@@ -45,7 +46,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.4.8"
+crewai-tools = "^0.4.26"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"

src/crewai/agent.py

@@ -1,13 +1,14 @@
 import os
+from inspect import signature
 from typing import Any, 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, model_validator
+from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 
 from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
 from crewai.agents.agent_builder.base_agent import BaseAgent
@@ -56,6 +57,7 @@ class Agent(BaseAgent):
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
     """
 
+    _times_executed: int = PrivateAttr(default=0)
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
@@ -96,6 +98,10 @@ class Agent(BaseAgent):
     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.",
+    )
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -167,14 +173,15 @@ class Agent(BaseAgent):
             if memory.strip() != "":
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
-        tools = tools or self.tools
-
-        parsed_tools = self._parse_tools(tools or [])  # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
+        tools = tools or self.tools or []
+        parsed_tools = self._parse_tools(tools)
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
         self.agent_executor.task = task
 
-        self.agent_executor.tools_description = render_text_description(parsed_tools)
+        self.agent_executor.tools_description = self._render_text_description_and_args(
+            parsed_tools
+        )
         self.agent_executor.tools_names = self.__tools_names(parsed_tools)
 
         if self.crew and self.crew._train:
@@ -182,13 +189,20 @@ class Agent(BaseAgent):
         else:
             task_prompt = self._use_trained_data(task_prompt=task_prompt)
 
-        result = self.agent_executor.invoke(
-            {
-                "input": task_prompt,
-                "tool_names": self.agent_executor.tools_names,
-                "tools": self.agent_executor.tools_description,
-            }
-        )["output"]
+        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)
+
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
 
@@ -220,7 +234,7 @@ class Agent(BaseAgent):
         Returns:
             An instance of the CrewAgentExecutor class.
         """
-        tools = tools or self.tools
+        tools = tools or self.tools or []
 
         agent_args = {
             "input": lambda x: x["input"],
@@ -246,6 +260,7 @@ class Agent(BaseAgent):
             "tools_handler": self.tools_handler,
             "function_calling_llm": self.function_calling_llm,
             "callbacks": self.callbacks,
+            "max_tokens": self.max_tokens,
         }
 
         if self._rpm_controller:
@@ -315,6 +330,7 @@ class Agent(BaseAgent):
             tools_list = []
             for tool in tools:
                 tools_list.append(tool)
+
         return tools_list
 
     def _training_handler(self, task_prompt: str) -> str:
@@ -341,6 +357,52 @@ 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

@@ -1,6 +1,7 @@
 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 (
@@ -44,6 +45,7 @@ class BaseAgent(ABC, BaseModel):
         i18n (I18N): Internationalization settings.
         cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
         tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
+        max_tokens: Maximum number of tokens for the agent to generate in a response.
 
 
     Methods:
@@ -117,6 +119,9 @@ class BaseAgent(ABC, BaseModel):
     tools_handler: InstanceOf[ToolsHandler] = Field(
         default=None, description="An instance of the ToolsHandler class."
     )
+    max_tokens: Optional[int] = Field(
+        default=None, description="Maximum number of tokens for the agent's execution."
+    )
 
     _original_role: str | None = None
     _original_goal: str | None = None
@@ -162,6 +167,11 @@ class BaseAgent(ABC, BaseModel):
             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,
@@ -180,7 +190,7 @@ class BaseAgent(ABC, BaseModel):
         pass
 
     @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]):
+    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[Any]:
         """Set the task tools that init BaseAgenTools class."""
         pass
 

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -3,7 +3,6 @@ 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
@@ -39,18 +38,17 @@ class CrewAgentExecutorMixin:
             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)
+                    self.crew._short_term_memory.save(
+                        value=output.log,
+                        metadata={
+                            "observation": self.task.description,
+                        },
+                        agent=self.crew_agent.role,
+                    )
             except Exception as e:
                 print(f"Failed to add to short term memory: {e}")
                 pass

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

@@ -24,6 +24,7 @@ class BaseAgentTools(BaseModel, ABC):
             is_list = coworker.startswith("[") and coworker.endswith("]")
             if is_list:
                 coworker = coworker[1:-1].split(",")[0]
+
         return coworker
 
     def delegate_work(
@@ -40,11 +41,13 @@ class BaseAgentTools(BaseModel, ABC):
         coworker = self._get_coworker(coworker, **kwargs)
         return self._execute(coworker, question, context)
 
-    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
+    def _execute(
+        self, agent_name: Union[str, None], task: str, context: Union[str, None]
+    ):
         """Execute the command."""
         try:
-            if agent is None:
-                agent = ""
+            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
@@ -53,7 +56,7 @@ class BaseAgentTools(BaseModel, ABC):
             # {"task": "....", "coworker": "....
             # when it should look like this:
             # {"task": "....", "coworker": "...."}
-            agent_name = agent.casefold().replace('"', "").replace("\n", "")
+            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
@@ -75,9 +78,9 @@ class BaseAgentTools(BaseModel, ABC):
             )
 
         agent = agent[0]
-        task = Task(  # type: ignore # Incompatible types in assignment (expression has type "Task", variable has type "str")
+        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, context)  # type: ignore # "str" has no attribute "execute_task"
+        return agent.execute_task(task_with_assigned_agent, context)

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

@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
 from typing import Any, Optional
 
-from pydantic import BaseModel, Field, PrivateAttr
+from pydantic import BaseModel, Field
 
 
 class OutputConverter(BaseModel, ABC):
@@ -21,7 +21,6 @@ class OutputConverter(BaseModel, ABC):
         max_attempts (int): Maximum number of conversion attempts (default: 3).
     """
 
-    _is_gpt: bool = PrivateAttr(default=True)
     text: str = Field(description="Text to be converted.")
     llm: Any = Field(description="The language model to be used to convert the text.")
     model: Any = Field(description="The model to be used to convert the text.")
@@ -41,7 +40,8 @@ class OutputConverter(BaseModel, ABC):
         """Convert text to json."""
         pass
 
-    @abstractmethod  # type: ignore #  Name "_is_gpt" already defined on line 25
-    def _is_gpt(self, llm):  # type: ignore #  Name "_is_gpt" already defined on line 25
+    @property
+    @abstractmethod
+    def is_gpt(self) -> bool:
         """Return if llm provided is of gpt from openai."""
         pass

src/crewai/agents/executor.py

@@ -1,14 +1,8 @@
 import threading
 import time
-from typing import (
-    Any,
-    Dict,
-    Iterator,
-    List,
-    Optional,
-    Tuple,
-    Union,
-)
+from typing import Any, Dict, Iterator, List, Literal, Optional, Tuple, Union
+import click
+
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
@@ -19,14 +13,21 @@ 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 langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.chains.summarize import load_summarize_chain
+
+from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.tools_handler import ToolsHandler
+
+
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 from crewai.utilities.training_handler import CrewTrainingHandler
+from crewai.utilities.logger import Logger
 
 
 class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
@@ -50,6 +51,8 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     system_template: Optional[str] = None
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
+    _logger: Logger = Logger(verbose_level=2)
+    _fit_context_window_strategy: Optional[Literal["summarize"]] = "summarize"
 
     def _call(
         self,
@@ -141,7 +144,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
 
             # Call the LLM to see what to do.
-            output = self.agent.plan(  # type: ignore #  Incompatible types in assignment (expression has type "AgentAction | AgentFinish | list[AgentAction]", variable has type "AgentAction")
+            output = self.agent.plan(
                 intermediate_steps,
                 callbacks=run_manager.get_child() if run_manager else None,
                 **inputs,
@@ -195,6 +198,27 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             yield AgentStep(action=output, observation=observation)
             return
 
+        except Exception as e:
+            if LLMContextLengthExceededException(str(e))._is_context_limit_error(
+                str(e)
+            ):
+                output = self._handle_context_length_error(
+                    intermediate_steps, run_manager, inputs
+                )
+
+                if isinstance(output, AgentFinish):
+                    yield output
+                elif isinstance(output, list):
+                    for step in output:
+                        yield step
+                return
+
+            yield AgentStep(
+                action=AgentAction("_Exception", str(e), str(e)),
+                observation=str(e),
+            )
+            return
+
         # If the tool chosen is the finishing tool, then we end and return.
         if isinstance(output, AgentFinish):
             if self.should_ask_for_human_input:
@@ -245,6 +269,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                 agent=self.crew_agent,
                 action=agent_action,
             )
+
             tool_calling = tool_usage.parse(agent_action.log)
 
             if isinstance(tool_calling, ToolUsageErrorException):
@@ -252,6 +277,8 @@ 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:
@@ -288,3 +315,91 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
             CrewTrainingHandler(TRAINING_DATA_FILE).append(
                 self.crew._train_iteration, agent_id, training_data
             )
+
+    def _handle_context_length(
+        self, intermediate_steps: List[Tuple[AgentAction, str]]
+    ) -> List[Tuple[AgentAction, str]]:
+        text = intermediate_steps[0][1]
+        original_action = intermediate_steps[0][0]
+
+        text_splitter = RecursiveCharacterTextSplitter(
+            separators=["\n\n", "\n"],
+            chunk_size=8000,
+            chunk_overlap=500,
+        )
+
+        if self._fit_context_window_strategy == "summarize":
+            docs = text_splitter.create_documents([text])
+            self._logger.log(
+                "debug",
+                "Summarizing Content, it is recommended to use a RAG tool",
+                color="bold_blue",
+            )
+            summarize_chain = load_summarize_chain(
+                self.llm, chain_type="map_reduce", verbose=True
+            )
+            summarized_docs = []
+            for doc in docs:
+                summary = summarize_chain.invoke(
+                    {"input_documents": [doc]}, return_only_outputs=True
+                )
+
+                summarized_docs.append(summary["output_text"])
+
+            formatted_results = "\n\n".join(summarized_docs)
+            summary_step = AgentStep(
+                action=AgentAction(
+                    tool=original_action.tool,
+                    tool_input=original_action.tool_input,
+                    log=original_action.log,
+                ),
+                observation=formatted_results,
+            )
+            summary_tuple = (summary_step.action, summary_step.observation)
+            return [summary_tuple]
+
+        return intermediate_steps
+
+    def _handle_context_length_error(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        run_manager: Optional[CallbackManagerForChainRun],
+        inputs: Dict[str, str],
+    ) -> Union[AgentFinish, List[AgentStep]]:
+        self._logger.log(
+            "debug",
+            "Context length exceeded. Asking user if they want to use summarize prompt to fit, this will reduce context length.",
+            color="yellow",
+        )
+        user_choice = click.confirm(
+            "Context length exceeded. Do you want to summarize the text to fit models context window?"
+        )
+        if user_choice:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Using summarize prompt to fit, this will reduce context length.",
+                color="bold_blue",
+            )
+            intermediate_steps = self._handle_context_length(intermediate_steps)
+
+            output = self.agent.plan(
+                intermediate_steps,
+                callbacks=run_manager.get_child() if run_manager else None,
+                **inputs,
+            )
+
+            if isinstance(output, AgentFinish):
+                return output
+            elif isinstance(output, AgentAction):
+                return [AgentStep(action=output, observation=None)]
+            else:
+                return [AgentStep(action=action, observation=None) for action in output]
+        else:
+            self._logger.log(
+                "debug",
+                "Context length exceeded. Consider using smaller text or RAG tools from crewai_tools.",
+                color="red",
+            )
+            raise SystemExit(
+                "Context length exceeded and user opted not to summarize. Consider using smaller text or RAG tools from crewai_tools."
+            )

src/crewai/agents/parser.py

@@ -1,6 +1,7 @@
 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
@@ -48,11 +49,15 @@ class CrewAgentParser(ReActSingleInputOutputParser):
                 raise OutputParserException(
                     f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {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)
+            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)
 
         elif includes_answer:
             return AgentFinish(
@@ -87,3 +92,30 @@ 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

@@ -1,7 +1,14 @@
 import click
 import pkg_resources
 
+from crewai.memory.storage.kickoff_task_outputs_storage import (
+    KickoffTaskOutputsSQLiteStorage,
+)
+
 from .create_crew import create_crew
+from .evaluate_crew import evaluate_crew
+from .replay_from_task import replay_task_command
+from .reset_memories_command import reset_memories_command
 from .train_crew import train_crew
 
 
@@ -48,5 +55,97 @@ 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}")
+    evaluate_crew(n_iterations, model)
+
+
 if __name__ == "__main__":
     crewai()

src/crewai/cli/evaluate_crew.py

@@ -0,0 +1,30 @@
+import subprocess
+
+import click
+
+
+def evaluate_crew(n_iterations: int, model: str) -> None:
+    """
+    Test and Evaluate 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/cli/replay_from_task.py

@@ -0,0 +1,24 @@
+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

@@ -0,0 +1,49 @@
+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:
+    """
+    Reset the crew memories.
+
+    Args:
+      long (bool): Whether to reset the long-term memory.
+      short (bool): Whether to reset the short-term memory.
+      entity (bool): Whether to reset the entity memory.
+      kickoff_outputs (bool): Whether to reset the latest kickoff task outputs.
+      all (bool): Whether to reset all memories.
+    """
+
+    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

@@ -5,6 +5,7 @@ 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: >
@@ -13,3 +14,4 @@ reporting_task:
   expected_output: >
     A fully fledge reports with the mains topics, each with a full section of information.
     Formatted as markdown without '```'
+  agent: reporting_analyst

src/crewai/cli/templates/crew.py

@@ -32,14 +32,12 @@ 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

@@ -2,9 +2,15 @@
 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():
-    # Replace with your inputs, it will automatically interpolate any tasks and agents information
+    """
+    Run the crew.
+    """
     inputs = {
         'topic': 'AI LLMs'
     }
@@ -15,9 +21,34 @@ 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]), openai_model_name=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

@@ -6,11 +6,13 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.35.8" }
+crewai = { extras = ["tools"], version = "^0.46.0" }
 
 [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/crew.py

@@ -2,6 +2,7 @@ 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 langchain_core.callbacks import BaseCallbackHandler
@@ -27,16 +28,23 @@ 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.constants import (
+    TRAINED_AGENTS_DATA_FILE,
+    TRAINING_DATA_FILE,
+)
+from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 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:
@@ -67,6 +75,7 @@ class Crew(BaseModel):
         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
@@ -80,6 +89,13 @@ 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)
@@ -135,6 +151,22 @@ 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.",
+    )
+    planning_llm: Optional[Any] = Field(
+        default=None,
+        description="Language model that will run the AgentPlanner if planning is True.",
+    )
+    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
@@ -170,7 +202,6 @@ 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")
@@ -240,20 +271,6 @@ class Crew(BaseModel):
 
         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."""
@@ -275,6 +292,29 @@ class Crew(BaseModel):
 
         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):
         """
@@ -311,6 +351,13 @@ class Crew(BaseModel):
                         )
         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."
 
@@ -377,7 +424,11 @@ class Crew(BaseModel):
     ) -> CrewOutput:
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self, inputs)
+        self._task_output_handler.reset()
+        self._logging_color = "bold_purple"
+
         if inputs is not None:
+            self._inputs = inputs
             self._interpolate_inputs(inputs)
         self._set_tasks_callbacks()
 
@@ -399,12 +450,15 @@ class Crew(BaseModel):
 
             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()  # type: ignore # Incompatible types in assignment (expression has type "str | dict[str, Any]", variable has type "str")
+            result = self._run_hierarchical_process()
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
@@ -441,6 +495,7 @@ class Crew(BaseModel):
             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:
@@ -489,106 +544,58 @@ class Crew(BaseModel):
                     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(
+            tasks=self.tasks, planning_agent_llm=self.planning_llm
+        )._handle_crew_planning()
+
+        for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
+            task.description += step_plan
+
+    def _store_execution_log(
+        self,
+        task: Task,
+        output: TaskOutput,
+        task_index: int,
+        was_replayed: bool = False,
+    ):
+        if self._inputs:
+            inputs = self._inputs
+        else:
+            inputs = {}
+
+        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)
+
     def _run_sequential_process(self) -> CrewOutput:
         """Executes tasks sequentially and returns the final output."""
-        task_outputs: List[TaskOutput] = []
-        futures: List[Tuple[Task, Future[TaskOutput]]] = []
+        return self._execute_tasks(self.tasks)
 
-        for task in self.tasks:
-            if task.agent and task.agent.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 += task.agent.get_delegation_tools(agents_for_delegation)
-
-            role = task.agent.role if task.agent is not None else "None"
-            self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
-            self._logger.log(
-                "info", f"== Starting Task: {task.description}", color="bold_purple"
-            )
-
-            if self.output_log_file:
-                self._file_handler.log(
-                    agent=role, task=task.description, status="started"
-                )
-
-            if task.async_execution:
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
-                future = task.execute_async(
-                    agent=task.agent, context=context, tools=task.tools
-                )
-                futures.append((task, future))
-            else:
-                # Before executing a synchronous task, wait for all async tasks to complete
-                if futures:
-                    # Clear task_outputs before processing async tasks
-                    task_outputs = []
-                    for future_task, future in futures:
-                        task_output = future.result()
-                        task_outputs.append(task_output)
-                        self._process_task_result(future_task, task_output)
-
-                    # Clear the futures list after processing all async results
-                    futures.clear()
-
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
-                task_output = task.execute_sync(
-                    agent=task.agent, context=context, tools=task.tools
-                )
-                task_outputs = [task_output]
-                self._process_task_result(task, task_output)
-
-        if futures:
-            # Clear task_outputs before processing async tasks
-            task_outputs = []
-            for future_task, future in futures:
-                task_output = future.result()
-                task_outputs.append(task_output)
-                self._process_task_result(future_task, task_output)
-
-        # Important: There should only be one task output in the list
-        #            If there are more or 0, something went wrong.
-        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_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")
-
-    # TODO: @joao, Breaking change. Changed return type. Usage metrics is included in crewoutput
     def _run_hierarchical_process(self) -> CrewOutput:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
+        self._create_manager_agent()
+        return self._execute_tasks(self.tasks)
+
+    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
@@ -607,74 +614,186 @@ class Crew(BaseModel):
             )
             self.manager_agent = manager
 
+    def _execute_tasks(
+        self,
+        tasks: List[Task],
+        start_index: Optional[int] = 0,
+        was_replayed: bool = False,
+    ) -> CrewOutput:
+        """Executes tasks sequentially and returns the final output.
+
+        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]]] = []
+        futures: List[Tuple[Task, Future[TaskOutput], int]] = []
+        last_sync_output: Optional[TaskOutput] = None
 
-        # TODO: IF USER OVERRIDE THE CONTEXT, PASS THAT
-        for task in self.tasks:
-            self._logger.log("debug", f"Working Agent: {manager.role}")
-            self._logger.log("info", f"Starting Task: {task.description}")
+        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
 
-            if self.output_log_file:
-                self._file_handler.log(
-                    agent=manager.role, task=task.description, status="started"
+            agent_to_use = self._get_agent_to_use(task)
+            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."
                 )
 
+            self._prepare_agent_tools(task)
+            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 = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
+                context = self._get_context(
+                    task, [last_sync_output] if last_sync_output else []
                 )
                 future = task.execute_async(
-                    agent=manager, context=context, tools=manager.tools
+                    agent=agent_to_use,
+                    context=context,
+                    tools=agent_to_use.tools,
                 )
-                futures.append((task, future))
+                futures.append((task, future, task_index))
             else:
-                # Before executing a synchronous task, wait for all async tasks to complete
                 if futures:
-                    # Clear task_outputs before processing async tasks
-                    task_outputs = []
-                    for future_task, future in futures:
-                        task_output = future.result()
-                        task_outputs.append(task_output)
-                        self._process_task_result(future_task, task_output)
-
-                    # Clear the futures list after processing all async results
+                    task_outputs = self._process_async_tasks(futures, was_replayed)
                     futures.clear()
 
-                context = (
-                    aggregate_raw_outputs_from_tasks(task.context)
-                    if task.context
-                    else aggregate_raw_outputs_from_task_outputs(task_outputs)
-                )
+                context = self._get_context(task, task_outputs)
                 task_output = task.execute_sync(
-                    agent=manager, context=context, tools=manager.tools
+                    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)
 
-        # Process any remaining async results
         if futures:
-            # Clear task_outputs before processing async tasks
-            task_outputs = []
-            for future_task, future in futures:
-                task_output = future.result()
-                task_outputs.append(task_output)
-                self._process_task_result(future_task, task_output)
+            task_outputs = self._process_async_tasks(futures, was_replayed)
 
-        # Important: There should only be one task output in the list
-        #            If there are more or 0, something went wrong.
+        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",
+            )
+            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
+
+    def _prepare_agent_tools(self, task: Task):
+        if self.process == Process.hierarchical:
+            if self.manager_agent:
+                self._update_manager_tools(task)
+            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) -> Optional[BaseAgent]:
+        if self.process == Process.hierarchical:
+            return self.manager_agent
+        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 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)
+
+    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):
+        if self.manager_agent:
+            if task.agent:
+                self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
+            else:
+                self.manager_agent.tools = self.manager_agent.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(
@@ -685,6 +804,74 @@ class Crew(BaseModel):
             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, start_index, True)
+        return result
+
     def copy(self):
         """Create a deep copy of the Crew."""
 
@@ -767,5 +954,20 @@ class Crew(BaseModel):
 
         return total_usage_metrics
 
+    def test(
+        self,
+        n_iterations: int,
+        openai_model_name: str,
+        inputs: Optional[Dict[str, Any]] = None,
+    ) -> None:
+        """Test and evaluate the Crew with the given inputs for n iterations."""
+        evaluator = CrewEvaluator(self, openai_model_name)
+
+        for i in range(1, n_iterations + 1):
+            evaluator.set_iteration(i)
+            self.kickoff(inputs=inputs)
+
+        evaluator.print_crew_evaluation_result()
+
     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/crew_output.py

@@ -24,18 +24,6 @@ class CrewOutput(BaseModel):
         description="Processed token summary", default={}
     )
 
-    # TODO: Joao - Adding this safety check breakes when people want to see
-    #                   The full output of a CrewOutput.
-    # @property
-    # def pydantic(self) -> Optional[BaseModel]:
-    #     # Check if the final task output included a pydantic model
-    #     if self.tasks_output[-1].output_format != OutputFormat.PYDANTIC:
-    #         raise ValueError(
-    #             "No pydantic model found in the final task. Please make sure to set the output_pydantic property in the final task in your crew."
-    #         )
-
-    #     return self._pydantic
-
     @property
     def json(self) -> Optional[str]:
         if self.tasks_output[-1].output_format != OutputFormat.JSON:
@@ -46,11 +34,13 @@ class CrewOutput(BaseModel):
         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:
-            return self.json_dict
-        if self.pydantic:
-            return self.pydantic.model_dump()
-        raise ValueError("No output to convert to dictionary")
+            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:

src/crewai/memory/entity/entity_memory.py

@@ -23,3 +23,9 @@ 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

@@ -30,3 +30,6 @@ 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

@@ -1,3 +1,4 @@
+from typing import Any, Dict, Optional
 from crewai.memory.memory import Memory
 from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.memory.storage.rag_storage import RAGStorage
@@ -18,8 +19,23 @@ class ShortTermMemory(Memory):
         )
         super().__init__(storage)
 
-    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 save(
+        self,
+        value: Any,
+        metadata: Optional[Dict[str, Any]] = None,
+        agent: Optional[str] = None,
+    ) -> None:
+        item = ShortTermMemoryItem(data=value, metadata=metadata, agent=agent)
+
+        super().save(value=item.data, metadata=item.metadata, agent=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/short_term/short_term_memory_item.py

@@ -3,7 +3,10 @@ from typing import Any, Dict, Optional
 
 class ShortTermMemoryItem:
     def __init__(
-        self, data: Any, agent: str, metadata: Optional[Dict[str, Any]] = None
+        self,
+        data: Any,
+        agent: Optional[str] = None,
+        metadata: Optional[Dict[str, Any]] = None,
     ):
         self.data = data
         self.agent = agent

src/crewai/memory/storage/interface.py

@@ -4,8 +4,11 @@ from typing import Any, Dict
 class Storage:
     """Abstract base class defining the storage interface"""
 
-    def save(self, key: str, value: Any, metadata: Dict[str, Any]) -> None:
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         pass
 
     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

@@ -0,0 +1,166 @@
+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

@@ -103,3 +103,20 @@ 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

@@ -2,6 +2,7 @@ import contextlib
 import io
 import logging
 import os
+import shutil
 from typing import Any, Dict, List, Optional
 
 from embedchain import App
@@ -71,13 +72,13 @@ 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:  # type: ignore # BUG?: Should be save(key, value, metadata)  Signature of "save" incompatible with supertype "Storage"
+    def save(self, value: Any, metadata: Dict[str, Any]) -> None:
         self._generate_embedding(value, metadata)
 
     def search(  # type: ignore # BUG?: Signature of "search" incompatible with supertype "Storage"
@@ -102,3 +103,11 @@ 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

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

src/crewai/project/annotations.py

@@ -30,6 +30,37 @@ 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

@@ -1,6 +1,7 @@
 import inspect
 import os
 from pathlib import Path
+from typing import Any, Callable, Dict
 
 import yaml
 from dotenv import load_dotenv
@@ -20,11 +21,6 @@ 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"
         )
@@ -32,12 +28,20 @@ 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):
@@ -45,4 +49,138 @@ 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

@@ -1,13 +1,13 @@
+import datetime
 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 langchain_openai import ChatOpenAI
 from opentelemetry.trace import Span
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
@@ -16,10 +16,8 @@ from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities.converter import Converter, ConverterError
+from crewai.utilities.converter import Converter, convert_to_model
 from crewai.utilities.i18n import I18N
-from crewai.utilities.printer import Printer
-from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
 class Task(BaseModel):
@@ -110,6 +108,7 @@ class Task(BaseModel):
     _original_description: str | None = None
     _original_expected_output: str | None = None
     _thread: threading.Thread | None = None
+    _execution_time: float | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -123,9 +122,15 @@ class Task(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
+    def _set_start_execution_time(self) -> float:
+        return datetime.datetime.now().timestamp()
+
+    def _set_end_execution_time(self, start_time: float) -> None:
+        self._execution_time = datetime.datetime.now().timestamp() - start_time
+
     @field_validator("output_file")
     @classmethod
-    def output_file_validattion(cls, value: str) -> str:
+    def output_file_validation(cls, value: str) -> str:
         """Validate the output file path by removing the / from the beginning of the path."""
         if value.startswith("/"):
             return value[1:]
@@ -173,6 +178,14 @@ class Task(BaseModel):
         """Execute the task synchronously."""
         return self._execute_core(agent, context, tools)
 
+    @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]
+
+        return md5("|".join(source).encode()).hexdigest()
+
     def execute_async(
         self,
         agent: BaseAgent | None = None,
@@ -205,11 +218,13 @@ class Task(BaseModel):
     ) -> 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."
             )
 
+        start_time = self._set_start_execution_time()
         self._execution_span = self._telemetry.task_started(crew=agent.crew, task=self)
 
         self.prompt_context = context
@@ -233,18 +248,21 @@ class Task(BaseModel):
         )
         self.output = task_output
 
+        self._set_end_execution_time(start_time)
         if self.callback:
             self.callback(self.output)
 
         if self._execution_span:
-            self._telemetry.task_ended(self._execution_span, self)
+            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
+                else pydantic_output.model_dump_json()
+                if pydantic_output
+                else result
             )
             self._save_file(content)
 
@@ -314,13 +332,6 @@ class Task(BaseModel):
 
         return copied_task
 
-    def _create_converter(self, *args, **kwargs) -> Converter:
-        """Create a converter instance."""
-        converter = self.agent.get_output_converter(*args, **kwargs)
-        if self.converter_cls:
-            converter = self.converter_cls(*args, **kwargs)
-        return converter
-
     def _export_output(
         self, result: str
     ) -> Tuple[Optional[BaseModel], Optional[Dict[str, Any]]]:
@@ -328,75 +339,26 @@ class Task(BaseModel):
         json_output: Optional[Dict[str, Any]] = None
 
         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
+            model_output = convert_to_model(
+                result,
+                self.output_pydantic,
+                self.output_json,
+                self.agent,
+                self.converter_cls,
             )
-            if isinstance(model_output, str):
+
+            if isinstance(model_output, BaseModel):
+                pydantic_output = model_output
+            elif isinstance(model_output, dict):
+                json_output = model_output
+            elif 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
 
         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:
-                exported_result = model.model_validate_json(match.group(0))
-                if self.output_json:
-                    return exported_result.model_dump()
-                return exported_result
-            except Exception:
-                pass
-
-        return self._convert_with_instructions(result, model)
-
-    def _convert_with_instructions(
-        self, result: str, model: Type[BaseModel]
-    ) -> Union[dict, BaseModel, str]:
-        llm = self.agent.function_calling_llm or self.agent.llm
-        instructions = self._get_conversion_instructions(model, llm)
-
-        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",
-            )
-            return result
-
-        return exported_result
-
     def _get_output_format(self) -> OutputFormat:
         if self.output_json:
             return OutputFormat.JSON
@@ -404,34 +366,22 @@ class Task(BaseModel):
             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
-
     def _save_file(self, result: Any) -> None:
+        if self.output_file is None:
+            raise ValueError("output_file is not set.")
+
         directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
 
         if directory and not os.path.exists(directory):
             os.makedirs(directory)
 
-        with open(self.output_file, "w", encoding="utf-8") as file:  # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
-            file.write(result)
+        with open(self.output_file, "w", encoding="utf-8") as file:
+            if isinstance(result, dict):
+                import json
+
+                json.dump(result, file, ensure_ascii=False, indent=2)
+            else:
+                file.write(str(result))
         return None
 
     def __repr__(self):

src/crewai/tasks/conditional_task.py

@@ -0,0 +1,47 @@
+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/task_output.py

@@ -11,9 +11,7 @@ class TaskOutput(BaseModel):
 
     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=""
-    )  # TODO: @joao: breaking change, by renaming raw_output to raw, but now consistent with CrewOutput
+    raw: str = Field(description="Raw output of the task", default="")
     pydantic: Optional[BaseModel] = Field(
         description="Pydantic output of task", default=None
     )
@@ -32,22 +30,6 @@ class TaskOutput(BaseModel):
         self.summary = f"{excerpt}..."
         return self
 
-    # TODO: Joao - Adding this safety check breakes when people want to see
-    #                   The full output of a TaskOutput or CrewOutput.
-    # @property
-    # def pydantic(self) -> Optional[BaseModel]:
-    #     # Check if the final task output included a pydantic model
-    #     if self.output_format != OutputFormat.PYDANTIC:
-    #         raise ValueError(
-    #             """
-    #             Invalid output format requested.
-    #             If you would like to access the pydantic model,
-    #             please make sure to set the output_pydantic property for the task.
-    #             """
-    #         )
-
-    #     return self._pydantic
-
     @property
     def json(self) -> Optional[str]:
         if self.output_format != OutputFormat.JSON:
@@ -66,7 +48,7 @@ class TaskOutput(BaseModel):
         output_dict = {}
         if self.json_dict:
             output_dict.update(self.json_dict)
-        if self.pydantic:
+        elif self.pydantic:
             output_dict.update(self.pydantic.model_dump())
         return output_dict
 

src/crewai/telemetry/telemetry.py

@@ -40,7 +40,7 @@ class Telemetry:
     - Roles of agents in a crew
     - Tools names available
 
-    Users can opt-in to sharing more complete data suing the `share_crew`
+    Users can opt-in to sharing more complete data using the `share_crew`
     attribute in the Crew class.
     """
 
@@ -80,7 +80,7 @@ class Telemetry:
                 self.ready = False
                 self.trace_set = False
 
-    def crew_creation(self, crew):
+    def crew_creation(self, crew: Crew, inputs: dict[str, Any] | None):
         """Records the creation of a crew."""
         if self.ready:
             try:
@@ -92,6 +92,7 @@ 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_memory", crew.memory)
@@ -103,6 +104,7 @@ class Telemetry:
                     json.dumps(
                         [
                             {
+                                "key": agent.key,
                                 "id": str(agent.id),
                                 "role": agent.role,
                                 "goal": agent.goal,
@@ -114,7 +116,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools
+                                    tool.name.casefold() for tool in agent.tools or []
                                 ],
                             }
                             for agent in crew.agents
@@ -127,19 +129,21 @@ 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
+                                    tool.name.casefold() for tool in task.tools or []
                                 ],
                             }
                             for task in crew.tasks
@@ -151,6 +155,12 @@ 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:
@@ -161,10 +171,12 @@ class Telemetry:
         if self.ready:
             try:
                 tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Task Execution")
 
                 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:
@@ -178,6 +190,11 @@ class Telemetry:
                 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:
@@ -192,13 +209,16 @@ class Telemetry:
 
         return None
 
-    def task_ended(self, span: Span, task: Task):
+    def task_ended(self, span: Span, task: Task, crew: Crew):
         """Records task execution in a crew."""
         if self.ready:
             try:
-                self._add_attribute(
-                    span, "output", task.output.raw_output if task.output else ""
-                )
+                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()
@@ -273,6 +293,8 @@ class Telemetry:
         """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")
@@ -282,14 +304,18 @@ 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, "inputs", json.dumps(inputs))
+                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,
@@ -320,6 +346,7 @@ class Telemetry:
                                 "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

src/crewai/tools/agent_tools.py

@@ -7,7 +7,7 @@ class AgentTools(BaseAgentTools):
     """Default tools around agent delegation"""
 
     def tools(self):
-        coworkers = f"[{', '.join([f'{agent.role}' for agent in self.agents])}]"
+        coworkers = ", ".join([f"{agent.role}" for agent in self.agents])
         tools = [
             StructuredTool.from_function(
                 func=self.delegate_work,

src/crewai/tools/tool_usage.py

@@ -16,7 +16,7 @@ try:
 except ImportError:
     agentops = None
 
-OPENAI_BIGGER_MODELS = ["gpt-4"]
+OPENAI_BIGGER_MODELS = ["gpt-4o"]
 
 
 class ToolUsageErrorException(Exception):
@@ -86,7 +86,8 @@ class ToolUsage:
     ) -> str:
         if isinstance(calling, ToolUsageErrorException):
             error = calling.message
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             self.task.increment_tools_errors()
             return error
 
@@ -96,7 +97,8 @@ class ToolUsage:
         except Exception as e:
             error = getattr(e, "message", str(e))
             self.task.increment_tools_errors()
-            self._printer.print(content=f"\n\n{error}\n", color="red")
+            if self.agent.verbose:
+                self._printer.print(content=f"\n\n{error}\n", color="red")
             return error
         return f"{self._use(tool_string=tool_string, tool=tool, calling=calling)}"  # type: ignore # BUG?: "_use" of "ToolUsage" does not return a value (it only ever returns None)
 
@@ -112,7 +114,8 @@ class ToolUsage:
                 result = self._i18n.errors("task_repeated_usage").format(
                     tool_names=self.tools_names
                 )
-                self._printer.print(content=f"\n\n{result}\n", color="purple")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{result}\n", color="purple")
                 self._telemetry.tool_repeated_usage(
                     llm=self.function_calling_llm,
                     tool_name=tool.name,
@@ -151,16 +154,12 @@ class ToolUsage:
                             for k, v in calling.arguments.items()
                             if k in acceptable_args
                         }
-                        result = tool._run(**arguments)
+                        result = tool.invoke(input=arguments)
                     except Exception:
-                        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)
+                        arguments = calling.arguments
+                        result = tool.invoke(input=arguments)
                 else:
-                    result = tool._run()
+                    result = tool.invoke(input={})
             except Exception as e:
                 self._run_attempts += 1
                 if self._run_attempts > self._max_parsing_attempts:
@@ -172,7 +171,10 @@ class ToolUsage:
                         f'\n{error_message}.\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                     ).message
                     self.task.increment_tools_errors()
-                    self._printer.print(content=f"\n\n{error_message}\n", color="red")
+                    if self.agent.verbose:
+                        self._printer.print(
+                            content=f"\n\n{error_message}\n", color="red"
+                        )
                     return error  # type: ignore # No return value expected
 
                 self.task.increment_tools_errors()
@@ -196,7 +198,8 @@ class ToolUsage:
                     calling=calling, output=result, should_cache=should_cache
                 )
 
-        self._printer.print(content=f"\n\n{result}\n", color="purple")
+        if self.agent.verbose:
+            self._printer.print(content=f"\n\n{result}\n", color="purple")
         if agentops:
             agentops.record(tool_event)
         self._telemetry.tool_usage(
@@ -350,7 +353,8 @@ class ToolUsage:
             if self._run_attempts > self._max_parsing_attempts:
                 self._telemetry.tool_usage_error(llm=self.function_calling_llm)
                 self.task.increment_tools_errors()
-                self._printer.print(content=f"\n\n{e}\n", color="red")
+                if self.agent.verbose:
+                    self._printer.print(content=f"\n\n{e}\n", color="red")
                 return ToolUsageErrorException(  # type: ignore # Incompatible return value type (got "ToolUsageErrorException", expected "ToolCalling | InstructorToolCalling")
                     f'{self._i18n.errors("tool_usage_error").format(error=e)}\nMoving on then. {self._i18n.slice("format").format(tool_names=self.tools_names)}'
                 )

src/crewai/utilities/__init__.py

@@ -7,6 +7,9 @@ from .parser import YamlParser
 from .printer import Printer
 from .prompts import Prompts
 from .rpm_controller import RPMController
+from .exceptions.context_window_exceeding_exception import (
+    LLMContextLengthExceededException,
+)
 
 __all__ = [
     "Converter",
@@ -19,4 +22,5 @@ __all__ = [
     "Prompts",
     "RPMController",
     "YamlParser",
+    "LLMContextLengthExceededException",
 ]

src/crewai/utilities/converter.py

@@ -1,11 +1,14 @@
 import json
+import re
+from typing import Any, Optional, Type, Union
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
-from pydantic import model_validator
-from crewai.agents.agent_builder.utilities.base_output_converter_base import (
-    OutputConverter,
-)
+from pydantic import BaseModel, ValidationError
+
+from crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
+from crewai.utilities.printer import Printer
+from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
 class ConverterError(Exception):
@@ -19,15 +22,10 @@ class ConverterError(Exception):
 class Converter(OutputConverter):
     """Class that converts text into either pydantic or json."""
 
-    @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({})
@@ -41,14 +39,14 @@ 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:
+        except Exception as e:
             if current_attempt < self.max_attempts:
                 return self.to_json(current_attempt + 1)
-            return ConverterError("Failed to convert text into JSON.")
+            return ConverterError(f"Failed to convert text into JSON, error: {e}.")
 
     def _create_instructor(self):
         """Create an instructor."""
@@ -75,5 +73,157 @@ class Converter(OutputConverter):
         )
         return new_prompt | self.llm | parser
 
-    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
+    @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 convert_to_model(
+    result: str,
+    output_pydantic: Optional[Type[BaseModel]],
+    output_json: Optional[Type[BaseModel]],
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    model = output_pydantic or output_json
+    if model is None:
+        return result
+
+    try:
+        escaped_result = json.dumps(json.loads(result, strict=False))
+        return validate_model(escaped_result, model, bool(output_json))
+    except json.JSONDecodeError as e:
+        Printer().print(
+            content=f"Error parsing JSON: {e}. Attempting to handle partial JSON.",
+            color="yellow",
+        )
+        return handle_partial_json(
+            result, model, bool(output_json), agent, converter_cls
+        )
+    except ValidationError as e:
+        Printer().print(
+            content=f"Pydantic validation error: {e}. Attempting to handle partial JSON.",
+            color="yellow",
+        )
+        return handle_partial_json(
+            result, model, bool(output_json), agent, converter_cls
+        )
+    except Exception as e:
+        Printer().print(
+            content=f"Unexpected error during model conversion: {type(e).__name__}: {e}. Returning original result.",
+            color="red",
+        )
+        return result
+
+
+def validate_model(
+    result: str, model: Type[BaseModel], is_json_output: bool
+) -> Union[dict, BaseModel]:
+    exported_result = model.model_validate_json(result)
+    if is_json_output:
+        return exported_result.model_dump()
+    return exported_result
+
+
+def handle_partial_json(
+    result: str,
+    model: Type[BaseModel],
+    is_json_output: bool,
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    match = re.search(r"({.*})", result, re.DOTALL)
+    if match:
+        try:
+            exported_result = model.model_validate_json(match.group(0))
+            if is_json_output:
+                return exported_result.model_dump()
+            return exported_result
+        except json.JSONDecodeError as e:
+            Printer().print(
+                content=f"Error parsing JSON: {e}. The extracted JSON-like string is not valid JSON. Attempting alternative conversion method.",
+                color="yellow",
+            )
+        except ValidationError as e:
+            Printer().print(
+                content=f"Pydantic validation error: {e}. The JSON structure doesn't match the expected model. Attempting alternative conversion method.",
+                color="yellow",
+            )
+        except Exception as e:
+            Printer().print(
+                content=f"Unexpected error during partial JSON handling: {type(e).__name__}: {e}. Attempting alternative conversion method.",
+                color="red",
+            )
+
+    return convert_with_instructions(
+        result, model, is_json_output, agent, converter_cls
+    )
+
+
+def convert_with_instructions(
+    result: str,
+    model: Type[BaseModel],
+    is_json_output: bool,
+    agent: Any,
+    converter_cls: Optional[Type[Converter]] = None,
+) -> Union[dict, BaseModel, str]:
+    llm = agent.function_calling_llm or agent.llm
+    instructions = get_conversion_instructions(model, llm)
+
+    converter = create_converter(
+        agent=agent,
+        converter_cls=converter_cls,
+        llm=llm,
+        text=result,
+        model=model,
+        instructions=instructions,
+    )
+    exported_result = (
+        converter.to_pydantic() if not is_json_output else converter.to_json()
+    )
+
+    if isinstance(exported_result, ConverterError):
+        Printer().print(
+            content=f"{exported_result.message} Using raw output instead.",
+            color="red",
+        )
+        return result
+
+    return exported_result
+
+
+def get_conversion_instructions(model: Type[BaseModel], llm: Any) -> str:
+    instructions = "I'm gonna convert this raw text into valid JSON."
+    if not 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 is_gpt(llm: Any) -> bool:
+    from langchain_openai import ChatOpenAI
+
+    return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
+
+
+def create_converter(
+    agent: Optional[Any] = None,
+    converter_cls: Optional[Type[Converter]] = None,
+    *args,
+    **kwargs,
+) -> Converter:
+    if agent and not converter_cls:
+        if hasattr(agent, "get_output_converter"):
+            converter = agent.get_output_converter(*args, **kwargs)
+        else:
+            raise AttributeError("Agent does not have a 'get_output_converter' method")
+    elif converter_cls:
+        converter = converter_cls(*args, **kwargs)
+    else:
+        raise ValueError("Either agent or converter_cls must be provided")
+
+    if not converter:
+        raise Exception("No output converter found or set.")
+
+    return converter

src/crewai/utilities/crew_json_encoder.py

@@ -0,0 +1,31 @@
+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

@@ -1,5 +1,5 @@
 import json
-from typing import Any, List, Type, Union
+from typing import Any, List, Type
 
 import regex
 from langchain.output_parsers import PydanticOutputParser
@@ -7,19 +7,24 @@ from langchain_core.exceptions import OutputParserException
 from langchain_core.outputs import Generation
 from langchain_core.pydantic_v1 import ValidationError
 from pydantic import BaseModel
-from pydantic.v1 import BaseModel as V1BaseModel
 
 
 class CrewPydanticOutputParser(PydanticOutputParser):
     """Parses the text into pydantic models"""
 
-    pydantic_object: Union[Type[BaseModel], Type[V1BaseModel]]
+    pydantic_object: Type[BaseModel]
 
-    def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
+    def parse_result(self, result: List[Generation]) -> Any:
         result[0].text = self._transform_in_valid_json(result[0].text)
-        json_object = super().parse_result(result)
+
+        # Treating edge case of function calling llm returning the name instead of tool_name
+        json_object = json.loads(result[0].text)
+        if "tool_name" not in json_object:
+            json_object["tool_name"] = json_object.get("name", "")
+        result[0].text = json.dumps(json_object)
+
         try:
-            return self.pydantic_object.parse_obj(json_object)
+            return self.pydantic_object.model_validate(json_object)
         except ValidationError as e:
             name = self.pydantic_object.__name__
             msg = f"Failed to parse {name} from completion {json_object}. Got: {e}"

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -0,0 +1,163 @@
+from collections import defaultdict
+
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel, Field
+from rich.console import Console
+from rich.table import Table
+
+from crewai.agent import Agent
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+
+
+class TaskEvaluationPydanticOutput(BaseModel):
+    quality: float = Field(
+        description="A score from 1 to 10 evaluating on completion, quality, and overall performance from the task_description and task_expected_output to the actual Task Output."
+    )
+
+
+class CrewEvaluator:
+    """
+    A class to evaluate the performance of the agents in the crew based on the tasks they have performed.
+
+    Attributes:
+        crew (Crew): The crew of agents to evaluate.
+        openai_model_name (str): The model to use for evaluating the performance of the agents (for now ONLY OpenAI accepted).
+        tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
+        iteration (int): The current iteration of the evaluation.
+    """
+
+    tasks_scores: defaultdict = defaultdict(list)
+    run_execution_times: defaultdict = defaultdict(list)
+    iteration: int = 0
+
+    def __init__(self, crew, openai_model_name: str):
+        self.crew = crew
+        self.openai_model_name = openai_model_name
+        self._setup_for_evaluating()
+
+    def _setup_for_evaluating(self) -> None:
+        """Sets up the crew for evaluating."""
+        for task in self.crew.tasks:
+            task.callback = self.evaluate
+
+    def _evaluator_agent(self):
+        return Agent(
+            role="Task Execution Evaluator",
+            goal=(
+                "Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
+            ),
+            backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
+            verbose=False,
+            llm=ChatOpenAI(model=self.openai_model_name),
+        )
+
+    def _evaluation_task(
+        self, evaluator_agent: Agent, task_to_evaluate: Task, task_output: str
+    ) -> Task:
+        return Task(
+            description=(
+                "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
+                f"task_description: {task_to_evaluate.description} "
+                f"task_expected_output: {task_to_evaluate.expected_output} "
+                f"agent: {task_to_evaluate.agent.role if task_to_evaluate.agent else None} "
+                f"agent_goal: {task_to_evaluate.agent.goal if task_to_evaluate.agent else None} "
+                f"Task Output: {task_output}"
+            ),
+            expected_output="Evaluation Score from 1 to 10 based on the performance of the agents on the tasks",
+            agent=evaluator_agent,
+            output_pydantic=TaskEvaluationPydanticOutput,
+        )
+
+    def set_iteration(self, iteration: int) -> None:
+        self.iteration = iteration
+
+    def print_crew_evaluation_result(self) -> None:
+        """
+        Prints the evaluation result of the crew in a table.
+        A Crew with 2 tasks using the command crewai test -n 2
+        will output the following table:
+
+                        Task Scores
+                    (1-10 Higher is better)
+            ┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
+            ┃ Tasks/Crew ┃ Run 1 ┃ Run 2 ┃ Avg. Total ┃
+            ┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
+            │ Task 1     │ 10.0  │ 9.0   │ 9.5        │
+            │ Task 2     │ 9.0   │ 9.0   │ 9.0        │
+            │ Crew       │ 9.5   │ 9.0   │ 9.2        │
+            └────────────┴───────┴───────┴────────────┘
+        """
+        task_averages = [
+            sum(scores) / len(scores) for scores in zip(*self.tasks_scores.values())
+        ]
+        crew_average = sum(task_averages) / len(task_averages)
+
+        # Create a table
+        table = Table(title="Tasks Scores \n (1-10 Higher is better)")
+
+        # Add columns for the table
+        table.add_column("Tasks/Crew")
+        for run in range(1, len(self.tasks_scores) + 1):
+            table.add_column(f"Run {run}")
+        table.add_column("Avg. Total")
+
+        # Add rows for each task
+        for task_index in range(len(task_averages)):
+            task_scores = [
+                self.tasks_scores[run][task_index]
+                for run in range(1, len(self.tasks_scores) + 1)
+            ]
+            avg_score = task_averages[task_index]
+            table.add_row(
+                f"Task {task_index + 1}", *map(str, task_scores), f"{avg_score:.1f}"
+            )
+
+        # Add a row for the crew average
+        crew_scores = [
+            sum(self.tasks_scores[run]) / len(self.tasks_scores[run])
+            for run in range(1, len(self.tasks_scores) + 1)
+        ]
+        table.add_row("Crew", *map(str, crew_scores), f"{crew_average:.1f}")
+
+        run_exec_times = [
+            int(sum(tasks_exec_times))
+            for _, tasks_exec_times in self.run_execution_times.items()
+        ]
+        execution_time_avg = int(sum(run_exec_times) / len(run_exec_times))
+        table.add_row(
+            "Execution Time (s)",
+            *map(str, run_exec_times),
+            f"{execution_time_avg}",
+        )
+        # Display the table in the terminal
+        console = Console()
+        console.print(table)
+
+    def evaluate(self, task_output: TaskOutput):
+        """Evaluates the performance of the agents in the crew based on the tasks they have performed."""
+        current_task = None
+        for task in self.crew.tasks:
+            if task.description == task_output.description:
+                current_task = task
+                break
+
+        if not current_task or not task_output:
+            raise ValueError(
+                "Task to evaluate and task output are required for evaluation"
+            )
+
+        evaluator_agent = self._evaluator_agent()
+        evaluation_task = self._evaluation_task(
+            evaluator_agent, current_task, task_output.raw
+        )
+
+        evaluation_result = evaluation_task.execute_sync()
+
+        if isinstance(evaluation_result.pydantic, TaskEvaluationPydanticOutput):
+            self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
+            self.run_execution_times[self.iteration].append(
+                current_task._execution_time
+            )
+        else:
+            raise ValueError("Evaluation result is not in the expected format")

src/crewai/utilities/evaluators/task_evaluator.py

@@ -54,23 +54,23 @@ class TaskEvaluator:
     def __init__(self, original_agent):
         self.llm = original_agent.llm
 
-    def evaluate(self, task, ouput) -> TaskEvaluation:
+    def evaluate(self, task, output) -> TaskEvaluation:
         evaluation_query = (
             f"Assess the quality of the task completed based on the description, expected output, and actual results.\n\n"
             f"Task Description:\n{task.description}\n\n"
             f"Expected Output:\n{task.expected_output}\n\n"
-            f"Actual Output:\n{ouput}\n\n"
+            f"Actual Output:\n{output}\n\n"
             "Please provide:\n"
             "- Bullet points suggestions to improve future similar tasks\n"
             "- A score from 0 to 10 evaluating on completion, quality, and overall performance"
             "- Entities extracted from the task output, if any, their type, description, and relationships"
         )
 
-        instructions = "I'm gonna convert this raw text into valid JSON."
+        instructions = "Convert all responses into valid JSON output."
 
         if not self._is_gpt(self.llm):
             model_schema = PydanticSchemaParser(model=TaskEvaluation).get_schema()
-            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
+            instructions = f"{instructions}\n\nReturn only valid JSON with the following schema:\n```json\n{model_schema}\n```"
 
         converter = Converter(
             llm=self.llm,

src/crewai/utilities/exceptions/context_window_exceeding_exception.py

@@ -0,0 +1,26 @@
+class LLMContextLengthExceededException(Exception):
+    CONTEXT_LIMIT_ERRORS = [
+        "maximum context length",
+        "context length exceeded",
+        "context_length_exceeded",
+        "context window full",
+        "too many tokens",
+        "input is too long",
+        "exceeds token limit",
+    ]
+
+    def __init__(self, error_message: str):
+        self.original_error_message = error_message
+        super().__init__(self._get_error_message(error_message))
+
+    def _is_context_limit_error(self, error_message: str) -> bool:
+        return any(
+            phrase.lower() in error_message.lower()
+            for phrase in self.CONTEXT_LIMIT_ERRORS
+        )
+
+    def _get_error_message(self, error_message: str):
+        return (
+            f"LLM context length exceeded. Original error: {error_message}\n"
+            "Consider using a smaller input or implementing a text splitting strategy."
+        )

src/crewai/utilities/file_handler.py

@@ -1,5 +1,7 @@
 import os
 import pickle
+
+
 from datetime import datetime
 
 

src/crewai/utilities/parser.py

@@ -1,17 +1,28 @@
 import re
 
-
 class YamlParser:
+    @staticmethod
     def parse(file):
+        """
+        Parses a YAML file, modifies specific patterns, and checks for unsupported 'context' usage.
+        Args:
+            file (file object): The YAML file to parse.
+        Returns:
+            str: The modified content of the YAML file.
+        Raises:
+            ValueError: If 'context:' is used incorrectly.
+        """
         content = file.read()
+
         # Replace single { and } with doubled ones, while leaving already doubled ones intact and the other special characters {# and {%
         modified_content = re.sub(r"(?<!\{){(?!\{)(?!\#)(?!\%)", "{{", content)
-        modified_content = re.sub(
-            r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content
-        )
+        modified_content = re.sub(r"(?<!\})(?<!\%)(?<!\#)\}(?!})", "}}", modified_content)
+
         # Check for 'context:' not followed by '[' and raise an error
         if re.search(r"context:(?!\s*\[)", modified_content):
             raise ValueError(
-                "Context is currently only supported in code when creating a task. Please use the 'context' key in the task configuration."
+                "Context is currently only supported in code when creating a task. "
+                "Please use the 'context' key in the task configuration."
             )
+
         return modified_content

src/crewai/utilities/planning_handler.py

@@ -0,0 +1,76 @@
+from typing import Any, List, Optional
+
+from langchain_openai import ChatOpenAI
+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], planning_agent_llm: Optional[Any] = None):
+        self.tasks = tasks
+
+        if planning_agent_llm is None:
+            self.planning_agent_llm = ChatOpenAI(model="gpt-4o-mini")
+        else:
+            self.planning_agent_llm = planning_agent_llm
+
+    def _handle_crew_planning(self) -> PlannerTaskPydanticOutput:
+        """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)
+
+        result = planner_task.execute_sync()
+
+        if isinstance(result.pydantic, PlannerTaskPydanticOutput):
+            return result.pydantic
+
+        raise ValueError("Failed to get the Planning output")
+
+    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",
+            llm=self.planning_agent_llm,
+        )
+
+    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

@@ -8,6 +8,10 @@ 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)
 
@@ -22,3 +26,9 @@ 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/pydantic_schema_parser.py

@@ -16,11 +16,13 @@ class PydanticSchemaParser(BaseModel):
         return self._get_model_schema(self.model)
 
     def _get_model_schema(self, model, depth=0) -> str:
-        lines = []
+        indent = "    " * depth
+        lines = [f"{indent}{{"]
         for field_name, field in model.model_fields.items():
             field_type_str = self._get_field_type(field, depth + 1)
-            lines.append(f"{' ' * 4 * depth}- {field_name}: {field_type_str}")
-
+            lines.append(f"{indent}    {field_name}: {field_type_str},")
+        lines[-1] = lines[-1].rstrip(",")  # Remove trailing comma from last item
+        lines.append(f"{indent}}}")
         return "\n".join(lines)
 
     def _get_field_type(self, field, depth) -> str:
@@ -35,6 +37,6 @@ class PydanticSchemaParser(BaseModel):
             else:
                 return f"List[{list_item_type.__name__}]"
         elif issubclass(field_type, BaseModel):
-            return f"\n{self._get_model_schema(field_type, depth)}"
+            return self._get_model_schema(field_type, depth)
         else:
             return field_type.__name__

src/crewai/utilities/task_output_storage_handler.py

@@ -0,0 +1,61 @@
+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

@@ -10,24 +10,24 @@ from crewai.agents.agent_builder.utilities.base_token_process import TokenProces
 class TokenCalcHandler(BaseCallbackHandler):
     model_name: str = ""
     token_cost_process: TokenProcess
+    encoding: tiktoken.Encoding
 
     def __init__(self, model_name, token_cost_process):
         self.model_name = model_name
         self.token_cost_process = token_cost_process
+        try:
+            self.encoding = tiktoken.encoding_for_model(self.model_name)
+        except KeyError:
+            self.encoding = tiktoken.get_encoding("cl100k_base")
 
     def on_llm_start(
         self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
     ) -> None:
-        try:
-            encoding = tiktoken.encoding_for_model(self.model_name)
-        except KeyError:
-            encoding = tiktoken.get_encoding("cl100k_base")
-
         if self.token_cost_process is None:
             return
 
         for prompt in prompts:
-            self.token_cost_process.sum_prompt_tokens(len(encoding.encode(prompt)))
+            self.token_cost_process.sum_prompt_tokens(len(self.encoding.encode(prompt)))
 
     async def on_llm_new_token(self, token: str, **kwargs) -> None:
         self.token_cost_process.sum_completion_tokens(1)

tests/agent_test.py

@@ -7,6 +7,7 @@ import pytest
 from langchain.tools import tool
 from langchain_core.exceptions import OutputParserException
 from langchain_openai import ChatOpenAI
+from langchain.schema import AgentAction
 
 from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
@@ -397,7 +398,7 @@ def test_agent_moved_on_after_max_iterations():
     )
 
     task = Task(
-        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool over and over until you're told you can give yout final answer.",
+        description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool over and over until you're told you can give your final answer.",
         expected_output="The final answer",
     )
     output = agent.execute_task(
@@ -948,7 +949,7 @@ def test_agent_use_trained_data(crew_training_handler):
     crew_training_handler().load.return_value = {
         agent.role: {
             "suggestions": [
-                "The result of the math operatio must be right.",
+                "The result of the math operation must be right.",
                 "Result must be better than 1.",
             ]
         }
@@ -958,8 +959,131 @@ def test_agent_use_trained_data(crew_training_handler):
 
     assert (
         result == "What is 1 + 1?You MUST follow these feedbacks: \n "
-        "The result of the math operatio must be right.\n - Result must be better than 1."
+        "The result of the math operation must be right.\n - Result must be better than 1."
     )
     crew_training_handler.assert_has_calls(
         [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
     )
+
+
+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": "",
+                    }
+                ),
+            ]
+        )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    original_action = AgentAction(
+        tool="test_tool", tool_input="test_input", log="test_log"
+    )
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "y"
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.side_effect = ValueError(
+                    "Context length limit exceeded"
+                )
+
+                long_input = "This is a very long input. " * 10000
+
+                # Attempt to handle context length, expecting the mocked error
+                with pytest.raises(ValueError) as excinfo:
+                    agent.agent_executor._handle_context_length(
+                        [(original_action, long_input)]
+                    )
+
+                assert "Context length limit exceeded" in str(excinfo.value)
+                mock_handle_context.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_handle_context_length_exceeds_limit_cli_no():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+    )
+    task = Task(description="test task", agent=agent, expected_output="test output")
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        task = Task(
+            description="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            expected_output="The final answer",
+        )
+        agent.execute_task(
+            task=task,
+        )
+        private_mock.assert_called_once()
+        with patch("crewai.agents.executor.click") as mock_prompt:
+            mock_prompt.return_value = "n"
+            pytest.raises(SystemExit)
+            with patch.object(
+                CrewAgentExecutor, "_handle_context_length"
+            ) as mock_handle_context:
+                mock_handle_context.assert_not_called()

tests/agents/agent_builder/base_agent_test.py

@@ -0,0 +1,36 @@
+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

@@ -0,0 +1,378 @@
+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

@@ -0,0 +1,151 @@
+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_handle_context_length_exceeds_limit.yaml

@@ -0,0 +1,181 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \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:
+      - '938'
+      content-type:
+      - application/json
+      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:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        The"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        is"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rDmhDy41qR9B2jdH1zkXoxv4LMn6","object":"chat.completion.chunk","created":1722471399,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac1a40879b87d1f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 00:16:40 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MHUl15YVi607cmuLtQ84ESiH30IyJiIW1a40fopQ81w-1722471400-1.0.1.1-OGpq5Ezj6iE0ToM1diQllGb70.J3O_K2De9NbwZPWmW2qN07U20adJ_0yd6PKUNqMdL.xEnLcNAOWVmsfrLUrQ;
+        path=/; expires=Thu, 01-Aug-24 00:46:40 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=G2ZVNvfNfFk4DeKyZ7jMYetG7wOasINAGHstrOnuAY8-1722471400129-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '131'
+      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:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_b68b417b3fe1c67244279551e411b37a
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_handle_context_length_exceeds_limit_cli_no.yaml

@@ -0,0 +1,162 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: The final answer is 42.
+      But don''t give it yet, instead keep using the `get_final_answer` tool.\n\nThis
+      is the expect criteria for your final answer: The final answer \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:
+      - '938'
+      content-type:
+      - application/json
+      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:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{"content":"42"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9rI1RAFocnugKoDvAxLndHW5uBeU9","object":"chat.completion.chunk","created":1722487689,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4e2b2da518","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8ac331b9eaee2b7f-LAX
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Thu, 01 Aug 2024 04:48:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OXht5zC71vWYFW_z_933m3sZfFS2xBez0DHv93FvT5s-1722487689-1.0.1.1-wE8JTR7MnwUgiiTDppYg8A7zLEiidth.MB0zrwONeAtNWRjKC1tuGf8LZYDlYIHUhqG73syYExpZ.5pZhzJkcg;
+        path=/; expires=Thu, 01-Aug-24 05:18:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=PAR7y4xRe4VzRT.7GK34Tq5r8vevY6xq0E.i.R40xnU-1722487689562-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '84'
+      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:
+      - '29999786'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_105dcfc53c9672dea0437249c12c3319
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_json_property_without_output_json.yaml

@@ -0,0 +1,262 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the titleTo 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 integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expect criteria for your final
+      answer: The score of the title. \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:
+      - '997'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.14
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.14
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltULlJQMDDjI2f7PpkjJ7DsxWjEQ","object":"chat.completion.chunk","created":1721201741,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a488e81aa7f0c7e-EWR
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Wed, 17 Jul 2024 07:35:41 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
+        path=/; expires=Wed, 17-Jul-24 08:05:41 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '106'
+      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:
+      - '29999771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_e52461a1ab2702e360f6303fbcb4cc3c
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
+      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
+      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
+      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
+      `ScoreOutput` with all the required parameters with correct types", "parameters":
+      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
+      ["score"], "type": "object"}}}]}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '519'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=Ypr9N3lq.OD8hpimnkpN61rAsWyk216I8Tq7RA8.uwQ-1721201741-1.0.1.1-6Cj4aX9I96QHMmPwJBpO1iCFOJsvzq_agUIrl3XS.YhlPuGyA4K9sDONExvLn.cDe3W_p_1ET7Pt_hxjtHPAXQ;
+        _cfuvid=NLa1BaUsRvD7shojIzUH9YSRXQIEzaoJVcq2_gNwqm0-1721201741646-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.14
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.14
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAA2xS22rjMBB991eIeY6LHTubrR9LKYUttKWUvbUYRRnb6sqSVhqTJiH/vshxYzes
+        H8QwZ86FGe8jxkCuoWAgGk6itSq+VPR8d8O/vXXZbiOzx13S5D9/PNwSv8nvYBYYZvWGgj5YF8K0
+        ViFJo4+wcMgJg2q6nKfzJF3maQ+0Zo0q0GpLcW7ieTLP42QRp9lAbIwU6KFgvyPGGNv3b4io1/gO
+        BUtmH50Wvec1QnEaYgycUaED3HvpiWuC2QgKowl1SK07pSYAGaNKwZUajY/fflKPe+JKlVe/nqvV
+        98vNtslul3/Xj7vrzaZ6StOJ31F6a/tAVafFaT8T/NQvzswYA83bnvskjMP7jmxHZ3TGgLu6a1FT
+        iA77F/Bh+AWK/ACfRg/R/+rXoTqc1qpMbZ1Z+bMtQSW19E3pkPs+LXgy9mgR5F7783WfLgLWmdZS
+        SeYP6iD4dbgejP/LCC4GjAxxNeEsoiEe+K0nbMtK6hqddbI/JVS2FDkuVl8qnqUQHaJ/AAAA//8D
+        ACb4o2zTAgAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a488e858ca50c7e-EWR
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 17 Jul 2024 07:35:42 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '241'
+      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:
+      - '29999968'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_01c2f40fe9c73f883b7ed5b60c8067e5
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_logging_tool_usage.yaml

@@ -1,296 +1,266 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\n\nYou ONLY have access to the following tools,
-      and should NEVER make up tools that are not listed here:\n\nmultiplier: multiplier(first_number:
-      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers together.\n\nUse the following format:\n\nThought: you should always
-      think about what to do\nAction: the action to take, only one name of [multiplier],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple a python dictionary using \" to wrap keys and values.\nObservation:
-      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
-      I now know the final answer\nFinal Answer: the final answer to the original
-      input question\n\n\nCurrent Task: What is 3 times 4?\n\nThis is the expect criteria
-      for your final answer: The result of the multiplication. \n you MUST return
-      the actual complete content as the final answer, not a summary.\n\nBegin! This
-      is VERY important to you, use the tools available and give your best Final Answer,
-      your job depends on it!\n\nThought: \n"}], "model": "gpt-4", "n": 1, "stop":
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goal\nYou ONLY have access to the following tools, and should
+      NEVER make up tools that are not listed here:\n\nmultiplier(first_number: int,
+      second_number: int) -> float - Useful for when you need to multiply two numbers
+      together.\n\nUse the following format:\n\nThought: you should always think about
+      what to do\nAction: the action to take, only one name of [multiplier], just
+      the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question\n\nCurrent Task: What is 3 times
+      4?\n\nThis is the expect criteria for your final answer: The result of the multiplication.
+      \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:
+      - '1277'
+      content-type:
+      - application/json
+      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:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        need"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        to"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        determine"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        the"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        product"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        multiplier"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Input"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        {\""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"first"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        \""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"second"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        "},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"}"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFmdFjejvg8ErQVjcpCsY8q7QbBI","object":"chat.completion.chunk","created":1720810787,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a2345bd1ffd742e-MIA
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:59:47 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=EvHnbspWLzEWYmRV1sLsvFlp1S5ePQd_KIGldEvula4-1720810787-1.0.1.1-fcfgfphTZearpEpqAdn5vCov8FO3hERf4Zij0dZmjoTuHkfcpXthynLGlq2sBt7SpE72ogziXHDlNZsSvmBQzA;
+        path=/; expires=Fri, 12-Jul-24 19:29:47 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=QoRToNVlfxPsZucAm6jmW5xUqoEucDbQTYK4SkSwmUc-1720810787746-0.0.1.1-604800000;
+        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:
+      - '90'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999703'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_f9575c9cc6494a463ddd5681e599b56d
+    status:
+      code: 200
+      message: OK
+- request:
+    body: '{"messages": [{"content": "You are test role. test backstory\nYour personal
+      goal is: test goal\nYou ONLY have access to the following tools, and should
+      NEVER make up tools that are not listed here:\n\nmultiplier(first_number: int,
+      second_number: int) -> float - Useful for when you need to multiply two numbers
+      together.\n\nUse the following format:\n\nThought: you should always think about
+      what to do\nAction: the action to take, only one name of [multiplier], just
+      the name, exactly as it''s written.\nAction Input: the input to the action,
+      just a simple python dictionary, enclosed in curly braces, using \" to wrap
+      keys and values.\nObservation: the result of the action\n\nOnce all necessary
+      information is gathered:\n\nThought: I now know the final answer\nFinal Answer:
+      the final answer to the original input question\n\nCurrent Task: What is 3 times
+      4?\n\nThis is the expect criteria for your final answer: The result of the multiplication.
+      \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:\nI need to determine the product
+      of 3 and 4.\n\nAction: multiplier\nAction Input: {\"first_number\": 3, \"second_number\":
+      4}\nObservation: 12\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop":
       ["\nObservation"], "stream": true, "temperature": 0.7}'
     headers:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, br
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
-      - '1268'
-      content-type:
-      - application/json
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.12.0
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.12.0
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    body:
-      string: 'data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        need"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        to"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        calculate"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        product"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        \n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"multi"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"plier"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        Input"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        \n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"{\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        \""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"first"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"3"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":",\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        \""},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"second"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"_number"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"}\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-8yMQXsDdREkfWKHVzRsYPnQXOyQNX","object":"chat.completion.chunk","created":1709396581,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
-
-
-        data: [DONE]
-
-
-        '
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 85e2ba970e5851e6-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Type:
-      - text/event-stream
-      Date:
-      - Sat, 02 Mar 2024 16:23:01 GMT
-      Server:
-      - cloudflare
-      Set-Cookie:
-      - __cf_bm=C0VdYjpV_Hv7CqW8v18fK47fudXVna82_U1z_FcZ1Ng-1709396581-1.0.1.1-3mcMHbUjGImAUy9c5jtpPwFU1NQDoziKGjF8PNiFaGvST9S6PAOQVvyo4vHhKkznZM38Rs39YASCuQyyHRlkUg;
-        path=/; expires=Sat, 02-Mar-24 16:53:01 GMT; domain=.api.openai.com; HttpOnly;
-        Secure; SameSite=None
-      - _cfuvid=XwSpHIa8bLFKjduTc6qVKOscgm9TIoxw5Nm7uklFgXw-1709396581628-0.0.1.1-604800000;
-        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
-      Transfer-Encoding:
-      - chunked
-      access-control-allow-origin:
-      - '*'
-      alt-svc:
-      - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
-      openai-organization:
-      - crewai-iuxna1
-      openai-processing-ms:
-      - '360'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299706'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 58ms
-      x-request-id:
-      - req_e3515cf2ba7a535d68b03019b57dfbf1
-    status:
-      code: 200
-      message: OK
-- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role. test backstory\nYour
-      personal goal is: test goal\n\nYou ONLY have access to the following tools,
-      and should NEVER make up tools that are not listed here:\n\nmultiplier: multiplier(first_number:
-      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers together.\n\nUse the following format:\n\nThought: you should always
-      think about what to do\nAction: the action to take, only one name of [multiplier],
-      just the name, exactly as it''s written.\nAction Input: the input to the action,
-      just a simple a python dictionary using \" to wrap keys and values.\nObservation:
-      the result of the action\n\nOnce all necessary information is gathered:\n\nThought:
-      I now know the final answer\nFinal Answer: the final answer to the original
-      input question\n\n\nCurrent Task: What is 3 times 4?\n\nThis is the expect criteria
-      for your final answer: The result of the multiplication. \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: \nI need to calculate the product of 3 and
-      4.\n\nAction: \nmultiplier\n\nAction Input: \n{\n  \"first_number\": 3,\n  \"second_number\":
-      4\n}\n\nObservation: 12\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
-      "stream": true, "temperature": 0.7}'
-    headers:
-      accept:
-      - application/json
-      accept-encoding:
-      - gzip, deflate, br
-      connection:
-      - keep-alive
-      content-length:
-      - '1428'
+      - '1420'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=C0VdYjpV_Hv7CqW8v18fK47fudXVna82_U1z_FcZ1Ng-1709396581-1.0.1.1-3mcMHbUjGImAUy9c5jtpPwFU1NQDoziKGjF8PNiFaGvST9S6PAOQVvyo4vHhKkznZM38Rs39YASCuQyyHRlkUg;
-        _cfuvid=XwSpHIa8bLFKjduTc6qVKOscgm9TIoxw5Nm7uklFgXw-1709396581628-0.0.1.1-604800000
+      - __cf_bm=EvHnbspWLzEWYmRV1sLsvFlp1S5ePQd_KIGldEvula4-1720810787-1.0.1.1-fcfgfphTZearpEpqAdn5vCov8FO3hERf4Zij0dZmjoTuHkfcpXthynLGlq2sBt7SpE72ogziXHDlNZsSvmBQzA;
+        _cfuvid=QoRToNVlfxPsZucAm6jmW5xUqoEucDbQTYK4SkSwmUc-1720810787746-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.12.0
+      - OpenAI/Python 1.35.10
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -300,7 +270,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.12.0
+      - 1.35.10
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -309,60 +279,60 @@ interactions:
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         now"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         know"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         the"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         Answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         "},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"12"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"12"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-8yMQZOVWWNho7BfFEeCd0GJq4Qstq","object":"chat.completion.chunk","created":1709396583,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9kFme2PvSyqdXzFbvYY0WXafqzr5K","object":"chat.completion.chunk","created":1720810788,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -373,47 +343,41 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 85e2baa3593951e6-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
+      - 8a2345c21e0b742e-MIA
       Connection:
       - keep-alive
       Content-Type:
-      - text/event-stream
+      - text/event-stream; charset=utf-8
       Date:
-      - Sat, 02 Mar 2024 16:23:03 GMT
+      - Fri, 12 Jul 2024 18:59:48 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
       - chunked
-      access-control-allow-origin:
-      - '*'
       alt-svc:
       - h3=":443"; ma=86400
-      openai-model:
-      - gpt-4-0613
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '321'
+      - '133'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=15724800; includeSubDomains
+      - max-age=31536000; includeSubDomains
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '300000'
+      - '22000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299670'
+      - '21999671'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 65ms
+      - 0s
       x-request-id:
-      - req_5670da4792b11cfa6dd8ed3b6dd85cbc
+      - req_be7165ee4924469e40e6a6b89a758b39
     status:
       code: 200
       message: OK

tests/cassettes/test_replay_feature.yaml

@@ -0,0 +1,697 @@
+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: Generate a list of 5 interesting ideas
+      to explore for an article, where each bulletpoint is under 15 words.\n\nThis
+      is the expect criteria for your final answer: Bullet point list of 5 important
+      events. No additional commentary. \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:
+      - '1237'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"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-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        \n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Ethical"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        implications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        decision"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-making"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        healthcare"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        revolution"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"izing"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        customer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        service"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        e"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-commerce"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Advances"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-driven"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        predictive"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        maintenance"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        for"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        industries"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        The"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        role"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        autonomous"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        vehicle"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        safety"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        personalized"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        education"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Adaptive"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        learning"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        technologies"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7QxB9Y779gwWcC1EK2JtcMZ7vCS","object":"chat.completion.chunk","created":1720540363,"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:
+      - 8a097b99ad909e50-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 15:52:44 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
+        path=/; expires=Tue, 09-Jul-24 16:22:44 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-soijsnuwuk3xvbf91w0jc33c
+      openai-processing-ms:
+      - '114'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '5000'
+      x-ratelimit-limit-tokens:
+      - '450000'
+      x-ratelimit-remaining-requests:
+      - '4999'
+      x-ratelimit-remaining-tokens:
+      - '449712'
+      x-ratelimit-reset-requests:
+      - 12ms
+      x-ratelimit-reset-tokens:
+      - 38ms
+      x-request-id:
+      - req_94f0907cc8b2065f1e223070d2be2a85
+    status:
+      code: 200
+      message: OK
+- 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: Generate a list of 5 interesting ideas
+      to explore for an article, where each bulletpoint is under 15 words.\n\nThis
+      is the expect criteria for your final answer: Bullet point list of 5 important
+      events. No additional commentary. \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:
+      - '1237'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=3B5vxI0ieroGmK5h7cD7a8bCSrrPh4hLjrbw87J9XRE-1720540364-1.0.1.1-BXhaEwefXZ7Ez0Fg7.8O4AAnOoPc5b7O.4CdzhLnbo9WIF30RlsTzH58YBRxoQipeSCQMxhePm2HaNR6nNfWEQ;
+        _cfuvid=D7VkuRYil_ytD3F4vcJzvO0gmVHyb3ZlnhCIjCrlyWE-1720540364005-0.0.1.1-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"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-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        \n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Evolution"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Agents"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Customer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Service"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        in"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Healthcare"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Transform"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ing"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Diagnostics"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Treatment"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Ethical"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Imp"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"lications"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        of"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Autonomous"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Systems"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Driven"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Start"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ups"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Dis"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ruption"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Innovation"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"-"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        AI"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        and"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Cyber"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"security"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Def"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"ending"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Against"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Modern"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        Threat"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"s"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9j7Qz3vXpsGKDVKeZa6oBvQ1PkdmE","object":"chat.completion.chunk","created":1720540365,"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:
+      - 8a097ba2bc449e50-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Tue, 09 Jul 2024 15:52:45 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - user-soijsnuwuk3xvbf91w0jc33c
+      openai-processing-ms:
+      - '117'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '5000'
+      x-ratelimit-limit-tokens:
+      - '450000'
+      x-ratelimit-remaining-requests:
+      - '4999'
+      x-ratelimit-remaining-tokens:
+      - '449712'
+      x-ratelimit-reset-requests:
+      - 12ms
+      x-ratelimit-reset-tokens:
+      - 38ms
+      x-request-id:
+      - req_a28d912698f7b75be87900d3a64bc91f
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_from_task_setup_context.yaml

@@ -0,0 +1,161 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
+      expect criteria for your final answer: Say Hi to John \n you MUST return the
+      actual complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\ncontext raw output\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:
+      - '918'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.3
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.3
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.5
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFSxQSL63v0sL4iqWFRWkul8QbhP","object":"chat.completion.chunk","created":1720809567,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_d33f7b429e","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+
+
+        data: [DONE]
+
+
+        '
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8a2327f1190467c1-SJC
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Fri, 12 Jul 2024 18:39:27 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=df.hIcEr2QTS045wWa7HSF0ATx6AeLAoPPW0FoIx7W4-1720809567-1.0.1.1-1Y2nQ4DHdc5HUHFO08LdQOoWZykmQ0xe67vzmv2dS4OnnKEHYd9GMzcq.vWODTXoI.BoSxQiRrylKYuuO2t8Tw;
+        path=/; expires=Fri, 12-Jul-24 19:09:27 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Zmb0XRHa49q2R664FqlS3F.aojtATJKKGnkUiQoH92I-1720809567257-0.0.1.1-604800000;
+        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:
+      - '83'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '22000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '21999792'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4fd8c7c8d47e20be017fb8de1ccb07c9
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_from_task_with_context.yaml

@@ -0,0 +1,159 @@
+interactions:
+- request:
+    body: '{"messages": [{"content": "You are test_agent. Test Description\nYour personal
+      goal is: Test GoalTo give my best complete final answer to the task use the
+      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
+      my best complete final answer to the task.\nYour final answer must be the great
+      and the most complete as possible, it must be outcome described.\n\nI MUST use
+      these formats, my job depends on it!\nCurrent Task: Test Task\n\nThis is the
+      expect criteria for your final answer: Say Hi \n you MUST return the actual
+      complete content as the final answer, not a summary.\n\nThis is the context
+      you''re working with:\ncontext raw output\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:
+      - '910'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.35.14
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.35.14
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: 'data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"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-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9ltUKsvuhS55Ng70kOmxKNQcksxm4","object":"chat.completion.chunk","created":1721201740,"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:
+      - 8a488e7859304288-EWR
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Wed, 17 Jul 2024 07:35:40 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=tBullt04HIYduv1QEpAn86_ghx9PQ4DMe9LwLp7.bu4-1721201740-1.0.1.1-sGn3OYi9ntPGIzwuC4RH0UTUQFVy.BUFIvy9v9IrjorYeAsecsuuuREs7b19i4dXygWnZZEkH6cxvnQeJ62g7g;
+        path=/; expires=Wed, 17-Jul-24 08:05:40 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=uSSEccAecytxcWKGJoaQXLVBAwHLrZ.QckpcK..rN48-1721201740355-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - crewai-iuxna1
+      openai-processing-ms:
+      - '83'
+      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:
+      - '29999793'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_89b4947eaf51788bd7a69d6cc0da6c08
+    status:
+      code: 200
+      message: OK
+version: 1