Updated docs and telemetry to use raw instead of raw_output

* fix: planning feature output

* fix: add validation for planning result

docs/core-concepts/Crews.md

@@ -4,36 +4,38 @@ 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.
 
 !!! 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 +46,12 @@ 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 +62,7 @@ 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 +97,57 @@ 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
+)
+
+result = crew.kickoff()
+
+# Accessing the crew output
+print(f"Raw Output: {crew_output.raw}")
+if crew_output.json_dict:
+    print(f"JSON Output: {json.dumps(crew_output.json_dict, indent=2)}")
+if crew_output.pydantic:
+    print(f"Pydantic Output: {crew_output.pydantic}")
+print(f"Tasks Output: {crew_output.tasks_output}")
+print(f"Token Usage: {crew_output.token_usage}")
+```
+
 ## Memory Utilization
 
 Crews can utilize memory (short-term, long-term, and entity memory) to enhance their execution and learning over time. This feature allows crews to store and recall execution memories, aiding in decision-making and task execution strategies.
@@ -155,12 +214,15 @@ for async_result in async_results:
     print(async_result)
 ```
 
+These methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs
+
+
 ### Replaying from specific task:
 You can now replay from a specific task using our cli command replay.
 
-The replay_from_tasks 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 name for the replay process.
+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 create a `crew_tasks_ouput.json` file with the output of the tasks which you use to retrieve the task id to replay.
+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
@@ -170,8 +232,15 @@ To use the replay feature, follow these steps:
 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 methods provide flexibility in how you manage and execute tasks within your crew, allowing for both synchronous and asynchronous workflows tailored to your needs
+These 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/Pipeline.md

@@ -0,0 +1,202 @@
+---
+title: crewAI Pipelines
+description: Understanding and utilizing pipelines in the crewAI framework for efficient multi-stage task processing.
+---
+
+## What is a Pipeline?
+
+A pipeline in crewAI represents a structured workflow that allows for the sequential or parallel execution of multiple crews. It provides a way to organize complex processes involving multiple stages, where the output of one stage can serve as input for subsequent stages.
+
+## Key Terminology
+
+Understanding the following terms is crucial for working effectively with pipelines:
+
+- **Stage**: A distinct part of the pipeline, which can be either sequential (a single crew) or parallel (multiple crews executing concurrently).
+- **Run**: A specific execution of the pipeline for a given set of inputs, representing a single instance of processing through the pipeline.
+- **Branch**: Parallel executions within a stage (e.g., concurrent crew operations).
+- **Trace**: The journey of an individual input through the entire pipeline, capturing the path and transformations it undergoes.
+
+Example pipeline structure:
+
+```
+crew1 >> [crew2, crew3] >> crew4
+```
+
+This represents a pipeline with three stages:
+
+1. A sequential stage (crew1)
+2. A parallel stage with two branches (crew2 and crew3 executing concurrently)
+3. Another sequential stage (crew4)
+
+Each input creates its own run, flowing through all stages of the pipeline. Multiple runs can be processed concurrently, each following the defined pipeline structure.
+
+## Pipeline Attributes
+
+| Attribute  | Parameters | Description                                                                           |
+| :--------- | :--------- | :------------------------------------------------------------------------------------ |
+| **Stages** | `stages`   | A list of crews or lists of crews representing the stages to be executed in sequence. |
+
+## Creating a Pipeline
+
+When creating a pipeline, you define a series of stages, each consisting of either a single crew or a list of crews for parallel execution. The pipeline ensures that each stage is executed in order, with the output of one stage feeding into the next.
+
+### Example: Assembling a Pipeline
+
+```python
+from crewai import Crew, Agent, Task, Pipeline
+
+# Define your crews
+research_crew = Crew(
+    agents=[researcher],
+    tasks=[research_task],
+    process=Process.sequential
+)
+
+analysis_crew = Crew(
+    agents=[analyst],
+    tasks=[analysis_task],
+    process=Process.sequential
+)
+
+writing_crew = Crew(
+    agents=[writer],
+    tasks=[writing_task],
+    process=Process.sequential
+)
+
+# Assemble the pipeline
+my_pipeline = Pipeline(
+    stages=[research_crew, analysis_crew, writing_crew]
+)
+```
+
+## Pipeline Methods
+
+| Method           | Description                                                                                                                                                                    |
+| :--------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **process_runs** | Executes the pipeline, processing all stages and returning the results. This method initiates one or more runs through the pipeline, handling the flow of data between stages. |
+
+## Pipeline Output
+
+!!! note "Understanding Pipeline Outputs"
+The output of a pipeline in the crewAI framework is encapsulated within two main classes: `PipelineOutput` and `PipelineRunResult`. These classes provide a structured way to access the results of the pipeline's execution, including various formats such as raw strings, JSON, and Pydantic models.
+
+### Pipeline Output Attributes
+
+| Attribute       | Parameters    | Type                      | Description                                                                                               |
+| :-------------- | :------------ | :------------------------ | :-------------------------------------------------------------------------------------------------------- |
+| **ID**          | `id`          | `UUID4`                   | A unique identifier for the pipeline output.                                                              |
+| **Run Results** | `run_results` | `List[PipelineRunResult]` | A list of `PipelineRunResult` objects, each representing the output of a single run through the pipeline. |
+
+### Pipeline Output Methods
+
+| Method/Property    | Description                                            |
+| :----------------- | :----------------------------------------------------- |
+| **add_run_result** | Adds a `PipelineRunResult` to the list of run results. |
+
+### Pipeline Run Result Attributes
+
+| Attribute         | Parameters      | Type                       | Description                                                                                   |
+| :---------------- | :-------------- | :------------------------- | :-------------------------------------------------------------------------------------------- |
+| **ID**            | `id`            | `UUID4`                    | A unique identifier for the run result.                                                       |
+| **Raw**           | `raw`           | `str`                      | The raw output of the final stage in the pipeline run.                                        |
+| **Pydantic**      | `pydantic`      | `Optional[BaseModel]`      | A Pydantic model object representing the structured output of the final stage, if applicable. |
+| **JSON Dict**     | `json_dict`     | `Optional[Dict[str, Any]]` | A dictionary representing the JSON output of the final stage, if applicable.                  |
+| **Token Usage**   | `token_usage`   | `Dict[str, Any]`           | A summary of token usage across all stages of the pipeline run.                               |
+| **Trace**         | `trace`         | `List[Any]`                | A trace of the journey of inputs through the pipeline run.                                    |
+| **Crews Outputs** | `crews_outputs` | `List[CrewOutput]`         | A list of `CrewOutput` objects, representing the outputs from each crew in the pipeline run.  |
+
+### Pipeline Run Result Methods and Properties
+
+| Method/Property | Description                                                                                              |
+| :-------------- | :------------------------------------------------------------------------------------------------------- |
+| **json**        | Returns the JSON string representation of the run result if the output format of the final task is JSON. |
+| **to_dict**     | Converts the JSON and Pydantic outputs to a dictionary.                                                  |
+| \***\*str\*\*** | Returns the string representation of the run result, prioritizing Pydantic, then JSON, then raw.         |
+
+### Accessing Pipeline Outputs
+
+Once a pipeline has been executed, its output can be accessed through the `PipelineOutput` object returned by the `process_runs` method. The `PipelineOutput` class provides access to individual `PipelineRunResult` objects, each representing a single run through the pipeline.
+
+#### Example
+
+```python
+# Define input data for the pipeline
+input_data = [{"initial_query": "Latest advancements in AI"}, {"initial_query": "Future of robotics"}]
+
+# Execute the pipeline
+pipeline_output = await my_pipeline.process_runs(input_data)
+
+# Access the results
+for run_result in pipeline_output.run_results:
+    print(f"Run ID: {run_result.id}")
+    print(f"Final Raw Output: {run_result.raw}")
+    if run_result.json_dict:
+        print(f"JSON Output: {json.dumps(run_result.json_dict, indent=2)}")
+    if run_result.pydantic:
+        print(f"Pydantic Output: {run_result.pydantic}")
+    print(f"Token Usage: {run_result.token_usage}")
+    print(f"Trace: {run_result.trace}")
+    print("Crew Outputs:")
+    for crew_output in run_result.crews_outputs:
+        print(f"  Crew: {crew_output.raw}")
+    print("\n")
+```
+
+This example demonstrates how to access and work with the pipeline output, including individual run results and their associated data.
+
+## Using Pipelines
+
+Pipelines are particularly useful for complex workflows that involve multiple stages of processing, analysis, or content generation. They allow you to:
+
+1. **Sequence Operations**: Execute crews in a specific order, ensuring that the output of one crew is available as input to the next.
+2. **Parallel Processing**: Run multiple crews concurrently within a stage for increased efficiency.
+3. **Manage Complex Workflows**: Break down large tasks into smaller, manageable steps executed by specialized crews.
+
+### Example: Running a Pipeline
+
+```python
+# Define input data for the pipeline
+input_data = [{"initial_query": "Latest advancements in AI"}]
+
+# Execute the pipeline, initiating a run for each input
+results = await my_pipeline.process_runs(input_data)
+
+# Access the results
+for result in results:
+    print(f"Final Output: {result.raw}")
+    print(f"Token Usage: {result.token_usage}")
+    print(f"Trace: {result.trace}")  # Shows the path of the input through all stages
+```
+
+## Advanced Features
+
+### Parallel Execution within Stages
+
+You can define parallel execution within a stage by providing a list of crews, creating multiple branches:
+
+```python
+parallel_analysis_crew = Crew(agents=[financial_analyst], tasks=[financial_analysis_task])
+market_analysis_crew = Crew(agents=[market_analyst], tasks=[market_analysis_task])
+
+my_pipeline = Pipeline(
+    stages=[
+        research_crew,
+        [parallel_analysis_crew, market_analysis_crew],  # Parallel execution (branching)
+        writing_crew
+    ]
+)
+```
+
+### Error Handling and Validation
+
+The Pipeline class includes validation mechanisms to ensure the robustness of the pipeline structure:
+
+- Validates that stages contain only Crew instances or lists of Crew instances.
+- Prevents double nesting of stages to maintain a clear structure.
+
+## Best Practices for Pipelines
+
+1. **Clear Stage Definition**: Define each stage with a clear purpose and expected output.
+2. **Effective Data Flow**: Ensure that the output of each stage is in a format suitable for the input of the next stage.
+3. \*\*Parallel Proce

docs/core-concepts/Planning.md

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

docs/core-concepts/Tasks.md

@@ -4,27 +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
 
@@ -167,7 +232,7 @@ def callback_function(output: TaskOutput):
     print(f"""
         Task completed!
         Task: {output.description}
-        Output: {output.raw_output}
+        Output: {output.raw}
     """)
 
 research_task = Task(

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/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/Creating-a-Crew-and-kick-it-off.md

@@ -21,14 +21,16 @@ Define your agents with distinct roles, backstories, and enhanced capabilities.
 import os
 from langchain.llms import OpenAI
 from crewai import Agent
-from crewai_tools import SerperDevTool, BrowserbaseTool, ExaSearchTool
+from crewai_tools import SerperDevTool, BrowserbaseLoadTool, EXASearchTool
 
 os.environ["OPENAI_API_KEY"] = "Your OpenAI Key"
 os.environ["SERPER_API_KEY"] = "Your Serper Key"
+os.environ["BROWSERBASE_API_KEY"] = "Your BrowserBase Key"
+os.environ["BROWSERBASE_PROJECT_ID"] = "Your BrowserBase Project Id"
 
 search_tool = SerperDevTool()
-browser_tool = BrowserbaseTool()
-exa_search_tool = ExaSearchTool()
+browser_tool = BrowserbaseLoadTool()
+exa_search_tool = EXASearchTool()
 
 # Creating a senior researcher agent with advanced configurations
 researcher = Agent(

docs/how-to/LLM-Connections.md

@@ -127,7 +127,7 @@ llm = HuggingFaceHub(
 ```
 
 ## 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
@@ -144,6 +144,13 @@ OPENAI_API_BASE="http://localhost:1234/v1"
 OPENAI_API_KEY="lm-studio"
 ```
 
+#### Groq API
+```sh
+OPENAI_API_KEY=your-groq-api-key
+OPENAI_MODEL_NAME='llama3-8b-8192'
+OPENAI_API_BASE=https://api.groq.com/openai/v1
+```
+
 #### Mistral API
 ```sh
 OPENAI_API_KEY=your-mistral-api-key
@@ -211,4 +218,4 @@ azure_agent = Agent(
 ```
 
 ## Conclusion
-Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.
+Integrating CrewAI with different LLMs expands the framework's versatility, allowing for customized, efficient AI solutions across various domains and platforms.

docs/how-to/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

@@ -9,7 +9,7 @@ Welcome to the ultimate guide for starting a new CrewAI project. This document w
 
 ## 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.
+We assume you have already installed CrewAI. If not, please refer to the [installation guide](https://docs.crewai.com/how-to/Installing-CrewAI/) to install CrewAI and its dependencies.
 
 ## Creating a New Project
 
@@ -134,4 +134,4 @@ This will initialize your crew of AI agents and begin task execution as defined
 
 ## 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.
+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

@@ -33,6 +33,11 @@ Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By
                     Crews
                 </a>
             </li>
+            <li>
+                <a href="./core-concepts/Pipeline">
+                    Pipeline
+                </a>
+            </li>
             <li>
                 <a href="./core-concepts/Training-Crew">
                     Training
@@ -43,6 +48,11 @@ 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%">
@@ -113,6 +123,16 @@ 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

mkdocs.yml

@@ -128,6 +128,7 @@ nav:
     - Collaboration: 'core-concepts/Collaboration.md'
     - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
+    - Planning: 'core-concepts/Planning.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
   - How to Guides:
@@ -145,6 +146,8 @@ 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 +183,7 @@ 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 = "0.41.1"
 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"]
@@ -45,12 +46,13 @@ 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"
 pytest-vcr = "^1.0.2"
 python-dotenv = "1.0.0"
+pytest-asyncio = "^0.23.7"
 
 [tool.poetry.scripts]
 crewai = "crewai.cli.cli:crewai"

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
@@ -54,8 +55,11 @@ class Agent(BaseAgent):
             tools: Tools at agents disposal
             step_callback: Callback to be executed after each step of the agent execution.
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
+            allow_code_execution: Enable code execution for the agent.
+            max_retry_limit: Maximum number of retries for an agent to execute a task when an error occurs.
     """
 
+    _times_executed: int = PrivateAttr(default=0)
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
@@ -96,6 +100,10 @@ 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 +175,15 @@ 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 +191,22 @@ 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"]
+            print("Result when things went well:", result)
+        except Exception as e:
+            print("FAILED TO EXECUTE TASK", 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()
 
@@ -199,6 +217,7 @@ class Agent(BaseAgent):
             if tool_result.get("result_as_answer", False):
                 result = tool_result["result"]
 
+        print("RESULT TO RETURN", result)
         return result
 
     def format_log_to_str(
@@ -220,7 +239,7 @@ 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"],
@@ -315,6 +334,7 @@ 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 +361,52 @@ 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 (
@@ -162,6 +163,11 @@ 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 +186,7 @@ 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/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 +1,6 @@
 import threading
 import time
-from typing import (
-    Any,
-    Dict,
-    Iterator,
-    List,
-    Optional,
-    Tuple,
-    Union,
-)
+from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
 
 from langchain.agents import AgentExecutor
 from langchain.agents.agent import ExceptionTool
@@ -19,9 +11,7 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
 
-from crewai.agents.agent_builder.base_agent_executor_mixin import (
-    CrewAgentExecutorMixin,
-)
+from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
@@ -66,7 +56,7 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
         )
         intermediate_steps: List[Tuple[AgentAction, str]] = []
         # Allowing human input given task setting
-        if self.task.human_input:
+        if self.task and self.task.human_input:
             self.should_ask_for_human_input = True
 
         # Let's start tracking the number of iterations and time elapsed
@@ -252,6 +242,8 @@ 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:

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

@@ -1,11 +1,15 @@
 import click
 import pkg_resources
 
+from crewai.memory.storage.kickoff_task_outputs_storage import (
+    KickoffTaskOutputsSQLiteStorage,
+)
+
 
 from .create_crew import create_crew
 from .train_crew import train_crew
 from .replay_from_task import replay_task_command
-from .list_task_outputs import show_task_outputs
+from .reset_memories_command import reset_memories_command
 
 
 @click.group()
@@ -73,9 +77,53 @@ def replay(task_id: str) -> None:
 
 
 @crewai.command()
-def list_completed_tasks_ids():
-    """List all task outputs saved from crew_tasks_output.json."""
-    show_task_outputs()
+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)
 
 
 if __name__ == "__main__":

src/crewai/cli/list_task_outputs.py

@@ -1,34 +0,0 @@
-import subprocess
-import click
-from pathlib import Path
-import json
-
-
-def show_task_outputs() -> None:
-    """
-    Replay the crew execution from a specific task.
-
-    Args:
-      task_id (str): The ID of the task to replay from.
-    """
-
-    try:
-        file_path = Path("crew_tasks_output.json")
-        if not file_path.exists():
-            click.echo("crew_tasks_output.json not found.")
-            return
-
-        with open(file_path, "r") as f:
-            tasks = json.load(f)
-
-        for index, task in enumerate(tasks):
-            click.echo(f"Task {index + 1}: {task['task_id']}")
-            click.echo(f"Description: {task['output']['description']}")
-            click.echo("---")
-
-    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/replay_from_task.py

@@ -9,7 +9,7 @@ def replay_task_command(task_id: str) -> None:
     Args:
       task_id (str): The ID of the task to replay from.
     """
-    command = ["poetry", "run", "replay_from_task", task_id]
+    command = ["poetry", "run", "replay", task_id]
 
     try:
         result = subprocess.run(command, capture_output=False, text=True, check=True)

src/crewai/cli/reset_memories_command.py

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

src/crewai/cli/templates/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'
     }
@@ -15,19 +21,21 @@ 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_from_task():
+def replay():
     """
     Replay the crew execution from a specific task.
     """
     try:
-        {{crew_name}}Crew().crew().replay_from_task(task_id=sys.argv[1])
+        {{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}")

src/crewai/cli/templates/pyproject.toml

@@ -6,12 +6,12 @@ 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 = "^0.41.1" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"
 train = "{{folder_name}}.main:train"
-replay = "{{folder_name}}.main:replay_from_task"
+replay = "{{folder_name}}.main:replay"
 
 [build-system]
 requires = ["poetry-core"]

src/crewai/crew.py

@@ -2,7 +2,8 @@ import asyncio
 import json
 import uuid
 from concurrent.futures import Future
-from typing import Any, Dict, List, Optional, Tuple, Union
+from hashlib import md5
+from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple, Union
 
 from langchain_core.callbacks import BaseCallbackHandler
 from pydantic import (
@@ -27,24 +28,19 @@ 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 (
-    CREW_TASKS_OUTPUT_FILE,
-    TRAINED_AGENTS_DATA_FILE,
-    TRAINING_DATA_FILE,
-)
+from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
-from crewai.utilities.task_output_handler import (
-    ExecutionLog,
-    TaskOutputJsonHandler,
-)
 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:
@@ -52,6 +48,9 @@ try:
 except ImportError:
     agentops = None
 
+if TYPE_CHECKING:
+    from crewai.pipeline.pipeline import Pipeline
+
 
 class Crew(BaseModel):
     """
@@ -75,6 +74,7 @@ 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
@@ -92,13 +92,17 @@ class Crew(BaseModel):
     _logging_color: str = PrivateAttr(
         default="bold_purple",
     )
+    _task_output_handler: TaskOutputStorageHandler = PrivateAttr(
+        default_factory=TaskOutputStorageHandler
+    )
 
+    name: Optional[str] = Field(default="")
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
     agents: List[BaseAgent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
-    verbose: Union[int, bool] = Field(default=0)
+    verbose: int = Field(default=0)
     memory: bool = Field(
         default=False,
         description="Whether the crew should use memory to store memories of it's execution",
@@ -143,15 +147,19 @@ class Crew(BaseModel):
         default=None,
         description="Path to the prompt json file to be used for the crew.",
     )
-    output_log_file: Optional[Union[bool, str]] = Field(
-        default=False,
+    output_log_file: Optional[str] = Field(
+        default="",
         description="output_log_file",
     )
+    planning: Optional[bool] = Field(
+        default=False,
+        description="Plan the crew execution and add the plan to the crew.",
+    )
     task_execution_output_json_files: Optional[List[str]] = Field(
         default=None,
         description="List of file paths for task execution JSON files.",
     )
-    execution_logs: List[ExecutionLog] = Field(
+    execution_logs: List[Dict[str, Any]] = Field(
         default=[],
         description="List of execution logs for tasks",
     )
@@ -190,7 +198,6 @@ 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")
@@ -295,6 +302,29 @@ 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):
         """
@@ -331,6 +361,13 @@ 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."
 
@@ -397,8 +434,7 @@ class Crew(BaseModel):
     ) -> CrewOutput:
         """Starts the crew to work on its assigned tasks."""
         self._execution_span = self._telemetry.crew_execution_span(self, inputs)
-        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).initialize_file()
-        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).reset()
+        self._task_output_handler.reset()
         self._logging_color = "bold_purple"
 
         if inputs is not None:
@@ -424,6 +460,9 @@ class Crew(BaseModel):
 
             agent.create_agent_executor()
 
+        if self.planning:
+            self._handle_crew_planning()
+
         metrics = []
 
         if self.process == Process.sequential:
@@ -466,6 +505,7 @@ 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:
@@ -514,9 +554,22 @@ 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(self.tasks)._handle_crew_planning()
+
+        if result is not None and hasattr(result, "list_of_plans_per_task"):
+            for task, step_plan in zip(self.tasks, result.list_of_plans_per_task):
+                task.description += step_plan
+        else:
+            self._logger.log(
+                "info", "Something went wrong with the planning process of the Crew"
+            )
+
     def _store_execution_log(
         self,
         task: Task,
@@ -529,10 +582,9 @@ class Crew(BaseModel):
         else:
             inputs = {}
 
-        log = ExecutionLog(
-            task_id=str(task.id),
-            expected_output=task.expected_output,
-            output={
+        log = {
+            "task": task,
+            "output": {
                 "description": output.description,
                 "summary": output.summary,
                 "raw": output.raw,
@@ -541,16 +593,11 @@ class Crew(BaseModel):
                 "output_format": output.output_format,
                 "agent": output.agent,
             },
-            task_index=task_index,
-            inputs=inputs,
-            was_replayed=was_replayed,
-        )
-        if task_index < len(self.execution_logs):
-            self.execution_logs[task_index] = log
-        else:
-            self.execution_logs.append(log)
-
-        TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).update(task_index, log)
+            "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."""
@@ -611,16 +658,21 @@ class Crew(BaseModel):
                         last_sync_output = task.output
                 continue
 
-            self._prepare_task(task, manager)
-            if self.process == Process.hierarchical:
-                agent_to_use = manager
-            else:
-                agent_to_use = task.agent
+            agent_to_use = self._get_agent_to_use(task, manager)
             if agent_to_use is None:
                 raise ValueError(
                     f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
-            self._log_task_start(task, agent_to_use)
+
+            self._prepare_agent_tools(task, manager)
+            self._log_task_start(task, agent_to_use.role)
+
+            if isinstance(task, ConditionalTask):
+                skipped_task_output = self._handle_conditional_task(
+                    task, task_outputs, futures, task_index, was_replayed
+                )
+                if skipped_task_output:
+                    continue
 
             if task.async_execution:
                 context = self._get_context(
@@ -634,9 +686,7 @@ class Crew(BaseModel):
                 futures.append((task, future, task_index))
             else:
                 if futures:
-                    task_outputs.extend(
-                        self._process_async_tasks(futures, was_replayed)
-                    )
+                    task_outputs = self._process_async_tasks(futures, was_replayed)
                     futures.clear()
 
                 context = self._get_context(task, task_outputs)
@@ -654,29 +704,85 @@ class Crew(BaseModel):
 
         return self._create_crew_output(task_outputs)
 
-    def _prepare_task(self, task: Task, manager: Optional[BaseAgent]):
+    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, manager: Optional[BaseAgent]):
         if self.process == Process.hierarchical:
-            self._update_manager_tools(task, manager)
+            if manager:
+                self._update_manager_tools(task, manager)
+            else:
+                raise ValueError("Manager agent is required for hierarchical process.")
         elif task.agent and task.agent.allow_delegation:
             self._add_delegation_tools(task)
 
+    def _get_agent_to_use(
+        self, task: Task, manager: Optional[BaseAgent]
+    ) -> Optional[BaseAgent]:
+        if self.process == Process.hierarchical:
+            return manager
+        return task.agent
+
     def _add_delegation_tools(self, task: Task):
         agents_for_delegation = [agent for agent in self.agents if agent != task.agent]
-        if len(self.agents) > 1 and agents_for_delegation:
-            task.tools += task.agent.get_delegation_tools(agents_for_delegation)  # type: ignore
+        if len(self.agents) > 1 and len(agents_for_delegation) > 0 and task.agent:
+            delegation_tools = task.agent.get_delegation_tools(agents_for_delegation)
 
-    def _log_task_start(self, task: Task, agent: Optional[BaseAgent]):
+            # 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
-        role = agent.role if agent else "None"
         self._logger.log("debug", f"== Working Agent: {role}", color=color)
         self._logger.log("info", f"== Starting Task: {task.description}", color=color)
         if self.output_log_file:
             self._file_handler.log(agent=role, task=task.description, status="started")
 
-    def _update_manager_tools(self, task: Task, manager: Optional[BaseAgent]):
-        if task.agent and manager:
+    def _update_manager_tools(self, task: Task, manager: BaseAgent):
+        if task.agent:
             manager.tools = task.agent.get_delegation_tools([task.agent])
-        if manager:
+        else:
             manager.tools = manager.get_delegation_tools(self.agents)
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
@@ -716,7 +822,7 @@ class Crew(BaseModel):
         futures: List[Tuple[Task, Future[TaskOutput], int]],
         was_replayed: bool = False,
     ) -> List[TaskOutput]:
-        task_outputs = []
+        task_outputs: List[TaskOutput] = []
         for future_task, future, task_index in futures:
             task_output = future.result()
             task_outputs.append(task_output)
@@ -738,10 +844,13 @@ class Crew(BaseModel):
             None,
         )
 
-    def replay_from_task(
+    def replay(
         self, task_id: str, inputs: Optional[Dict[str, Any]] = None
     ) -> CrewOutput:
-        stored_outputs = TaskOutputJsonHandler(CREW_TASKS_OUTPUT_FILE).load()
+        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:
@@ -759,7 +868,9 @@ class Crew(BaseModel):
             self._create_manager_agent()
 
         for i in range(start_index):
-            stored_output = stored_outputs[i]["output"]
+            stored_output = stored_outputs[i][
+                "output"
+            ]  # for adding context to the task
             task_output = TaskOutput(
                 description=stored_output["description"],
                 agent=stored_output["agent"],
@@ -856,5 +967,17 @@ class Crew(BaseModel):
 
         return total_usage_metrics
 
+    def __rshift__(self, other: "Crew") -> "Pipeline":
+        """
+        Implements the >> operator to add another Crew to an existing Pipeline.
+        """
+        from crewai.pipeline.pipeline import Pipeline
+
+        if not isinstance(other, Crew):
+            raise TypeError(
+                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
+            )
+        return Pipeline(stages=[self, other])
+
     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

@@ -24,16 +24,6 @@ class CrewOutput(BaseModel):
         description="Processed token summary", default={}
     )
 
-    # @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:
@@ -44,11 +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

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

src/crewai/memory/storage/interface.py

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

src/crewai/memory/storage/kickoff_task_outputs_storage.py

@@ -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/pipeline/__init__.py

@@ -0,0 +1,3 @@
+from crewai.pipeline.pipeline import Pipeline
+
+__all__ = ["Pipeline"]

src/crewai/pipeline/pipeline.py

@@ -0,0 +1,218 @@
+import asyncio
+import copy
+from typing import Any, Dict, List, Tuple, Union
+
+from pydantic import BaseModel, Field, model_validator
+
+from crewai.crew import Crew
+from crewai.crews.crew_output import CrewOutput
+from crewai.pipeline.pipeline_run_result import PipelineRunResult
+
+Trace = Union[Union[str, Dict[str, Any]], List[Union[str, Dict[str, Any]]]]
+
+
+"""
+Pipeline Terminology:
+Pipeline: The overall structure that defines a sequence of operations.
+Stage: A distinct part of the pipeline, which can be either sequential or parallel.
+Run: A specific execution of the pipeline for a given set of inputs, representing a single instance of processing through the pipeline.
+Branch: Parallel executions within a stage (e.g., concurrent crew operations).
+Trace: The journey of an individual input through the entire pipeline.
+
+Example pipeline structure:
+crew1 >> crew2 >> crew3
+
+This represents a pipeline with three sequential stages:
+1. crew1 is the first stage, which processes the input and passes its output to crew2.
+2. crew2 is the second stage, which takes the output from crew1 as its input, processes it, and passes its output to crew3.
+3. crew3 is the final stage, which takes the output from crew2 as its input and produces the final output of the pipeline.
+
+Each input creates its own run, flowing through all stages of the pipeline.
+Multiple runs can be processed concurrently, each following the defined pipeline structure.
+
+Another example pipeline structure:
+crew1 >> [crew2, crew3] >> crew4
+
+This represents a pipeline with three stages:
+1. A sequential stage (crew1)
+2. A parallel stage with two branches (crew2 and crew3 executing concurrently)
+3. Another sequential stage (crew4)
+
+Each input creates its own run, flowing through all stages of the pipeline.
+Multiple runs can be processed concurrently, each following the defined pipeline structure.
+"""
+
+
+class Pipeline(BaseModel):
+    stages: List[Union[Crew, List[Crew]]] = Field(
+        ..., description="List of crews representing stages to be executed in sequence"
+    )
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_stages(cls, values):
+        stages = values.get("stages", [])
+
+        def check_nesting_and_type(item, depth=0):
+            if depth > 1:
+                raise ValueError("Double nesting is not allowed in pipeline stages")
+            if isinstance(item, list):
+                for sub_item in item:
+                    check_nesting_and_type(sub_item, depth + 1)
+            elif not isinstance(item, Crew):
+                raise ValueError(
+                    f"Expected Crew instance or list of Crews, got {type(item)}"
+                )
+
+        for stage in stages:
+            check_nesting_and_type(stage)
+        return values
+
+    async def process_runs(
+        self, run_inputs: List[Dict[str, Any]]
+    ) -> List[PipelineRunResult]:
+        """
+        Process multiple runs in parallel, with each run going through all stages.
+        """
+        pipeline_results = []
+
+        # Process all runs in parallel
+        all_run_results = await asyncio.gather(
+            *(self.process_single_run(input_data) for input_data in run_inputs)
+        )
+
+        # Flatten the list of lists into a single list of results
+        pipeline_results.extend(
+            result for run_result in all_run_results for result in run_result
+        )
+
+        return pipeline_results
+
+    async def process_single_run(
+        self, run_input: Dict[str, Any]
+    ) -> List[PipelineRunResult]:
+        initial_input = copy.deepcopy(run_input)
+        current_input = copy.deepcopy(run_input)
+        usage_metrics = {}
+        all_stage_outputs: List[List[CrewOutput]] = []
+        traces: List[List[Union[str, Dict[str, Any]]]] = [[initial_input]]
+
+        for stage in self.stages:
+            stage_input = copy.deepcopy(current_input)
+            stage_outputs, stage_trace = await self._process_stage(stage, stage_input)
+
+            self._update_metrics_and_input(
+                usage_metrics, current_input, stage, stage_outputs
+            )
+            traces.append(stage_trace)
+            all_stage_outputs.append(stage_outputs)
+
+        return self._build_pipeline_run_results(
+            all_stage_outputs, traces, usage_metrics
+        )
+
+    async def _process_stage(
+        self, stage: Union[Crew, List[Crew]], current_input: Dict[str, Any]
+    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
+        if isinstance(stage, Crew):
+            return await self._process_single_crew(stage, current_input)
+        else:
+            return await self._process_parallel_crews(stage, current_input)
+
+    async def _process_single_crew(
+        self, crew: Crew, current_input: Dict[str, Any]
+    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
+        output = await crew.kickoff_async(inputs=current_input)
+        return [output], [crew.name or str(crew.id)]
+
+    async def _process_parallel_crews(
+        self, crews: List[Crew], current_input: Dict[str, Any]
+    ) -> Tuple[List[CrewOutput], List[Union[str, Dict[str, Any]]]]:
+        parallel_outputs = await asyncio.gather(
+            *[crew.kickoff_async(inputs=current_input) for crew in crews]
+        )
+        return parallel_outputs, [crew.name or str(crew.id) for crew in crews]
+
+    def _update_metrics_and_input(
+        self,
+        usage_metrics: Dict[str, Any],
+        current_input: Dict[str, Any],
+        stage: Union[Crew, List[Crew]],
+        outputs: List[CrewOutput],
+    ) -> None:
+        for crew, output in zip([stage] if isinstance(stage, Crew) else stage, outputs):
+            usage_metrics[crew.name or str(crew.id)] = output.token_usage
+            current_input.update(output.to_dict())
+
+    def _build_pipeline_run_results(
+        self,
+        all_stage_outputs: List[List[CrewOutput]],
+        traces: List[List[Union[str, Dict[str, Any]]]],
+        token_usage: Dict[str, Any],
+    ) -> List[PipelineRunResult]:
+        formatted_traces = self._format_traces(traces)
+        formatted_crew_outputs = self._format_crew_outputs(all_stage_outputs)
+
+        return [
+            PipelineRunResult(
+                token_usage=token_usage,
+                trace=formatted_trace,
+                raw=crews_outputs[-1].raw,
+                pydantic=crews_outputs[-1].pydantic,
+                json_dict=crews_outputs[-1].json_dict,
+                crews_outputs=crews_outputs,
+            )
+            for crews_outputs, formatted_trace in zip(
+                formatted_crew_outputs, formatted_traces
+            )
+        ]
+
+    def _format_traces(
+        self, traces: List[List[Union[str, Dict[str, Any]]]]
+    ) -> List[List[Trace]]:
+        formatted_traces: List[Trace] = []
+        for trace in traces[:-1]:
+            formatted_traces.append(trace[0] if len(trace) == 1 else trace)
+
+        traces_to_return: List[List[Trace]] = []
+        final_trace = traces[-1]
+        if len(final_trace) == 1:
+            formatted_traces.append(final_trace[0])
+            traces_to_return.append(formatted_traces)
+        else:
+            for trace in final_trace:
+                copied_traces = formatted_traces.copy()
+                copied_traces.append(trace)
+                traces_to_return.append(copied_traces)
+
+        return traces_to_return
+
+    def _format_crew_outputs(
+        self, all_stage_outputs: List[List[CrewOutput]]
+    ) -> List[List[CrewOutput]]:
+        crew_outputs: List[CrewOutput] = [
+            output
+            for stage_outputs in all_stage_outputs[:-1]
+            for output in stage_outputs
+        ]
+        return [crew_outputs + [output] for output in all_stage_outputs[-1]]
+
+    def __rshift__(self, other: Any) -> "Pipeline":
+        """
+        Implements the >> operator to add another Stage (Crew or List[Crew]) to an existing Pipeline.
+        """
+        if isinstance(other, Crew):
+            return type(self)(stages=self.stages + [other])
+        elif isinstance(other, list) and all(isinstance(crew, Crew) for crew in other):
+            return type(self)(stages=self.stages + [other])
+        else:
+            raise TypeError(
+                f"Unsupported operand type for >>: '{type(self).__name__}' and '{type(other).__name__}'"
+            )
+
+
+# Helper function to run the pipeline
+async def run_pipeline(
+    pipeline: Pipeline, inputs: List[Dict[str, Any]]
+) -> List[PipelineRunResult]:
+    return await pipeline.process_runs(inputs)

src/crewai/pipeline/pipeline_output.py

@@ -0,0 +1,20 @@
+import uuid
+from typing import List
+
+from pydantic import UUID4, BaseModel, Field
+
+from crewai.pipeline.pipeline_run_result import PipelineRunResult
+
+
+class PipelineOutput(BaseModel):
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
+    run_results: List[PipelineRunResult] = Field(
+        description="List of results for each run through the pipeline", default=[]
+    )
+
+    def add_run_result(self, result: PipelineRunResult):
+        self.run_results.append(result)

src/crewai/pipeline/pipeline_run_result.py

@@ -0,0 +1,60 @@
+import json
+import uuid
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import UUID4, BaseModel, Field
+
+from crewai.crews.crew_output import CrewOutput
+
+
+class PipelineRunResult(BaseModel):
+    """Class that represents the result of a pipeline run."""
+
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
+    raw: str = Field(description="Raw output of the pipeline run", default="")
+    pydantic: Any = Field(
+        description="Pydantic output of the pipeline run", default=None
+    )
+    json_dict: Union[Dict[str, Any], None] = Field(
+        description="JSON dict output of the pipeline run", default={}
+    )
+
+    token_usage: Dict[str, Any] = Field(
+        description="Token usage for each crew in the run"
+    )
+    trace: List[Any] = Field(
+        description="Trace of the journey of inputs through the run"
+    )
+    crews_outputs: List[CrewOutput] = Field(
+        description="Output from each crew in the run",
+        default=[],
+    )
+
+    @property
+    def json(self) -> Optional[str]:
+        if self.crews_outputs[-1].tasks_output[-1].output_format != "json":
+            raise ValueError(
+                "No JSON output found in the final task of the final crew. Please make sure to set the output_json property in the final task in your crew."
+            )
+
+        return json.dumps(self.json_dict)
+
+    def to_dict(self) -> Dict[str, Any]:
+        """Convert json_output and pydantic_output to a dictionary."""
+        output_dict = {}
+        if self.json_dict:
+            output_dict.update(self.json_dict)
+        elif self.pydantic:
+            output_dict.update(self.pydantic.model_dump())
+        return output_dict
+
+    def __str__(self):
+        if self.pydantic:
+            return str(self.pydantic)
+        if self.json_dict:
+            return str(self.json_dict)
+        return self.raw

src/crewai/router/router.py

@@ -0,0 +1,67 @@
+from typing import Any, Callable, Dict, List, Tuple, Union
+
+from crewai.crew import Crew
+from crewai.pipeline.pipeline import Pipeline
+
+
+class Router:
+    def __init__(self):
+        self.conditions: List[
+            Tuple[Callable[[Dict[str, Any]], bool], Union[Crew, Pipeline]]
+        ] = []
+        self.default: Union[Crew, Pipeline, None] = None
+
+    def add_condition(
+        self,
+        condition: Callable[[Dict[str, Any]], bool],
+        next_stage: Union[Crew, Pipeline],
+    ):
+        """
+        Add a condition and its corresponding next stage to the router.
+
+        Args:
+            condition: A function that takes the input dictionary and returns a boolean.
+            next_stage: The Crew or Pipeline to execute if the condition is met.
+        """
+        self.conditions.append((condition, next_stage))
+
+    def set_default(self, default_stage: Union[Crew, Pipeline]):
+        """Set the default stage to be executed if no conditions are met."""
+        self.default = default_stage
+
+    def route(self, input_dict: Dict[str, Any]) -> Union[Crew, Pipeline]:
+        """
+        Evaluate the input against the conditions and return the appropriate next stage.
+
+        Args:
+            input_dict: The input dictionary to be evaluated.
+
+        Returns:
+            The next Crew or Pipeline to be executed.
+
+        Raises:
+            ValueError: If no conditions are met and no default is set.
+        """
+        for condition, next_stage in self.conditions:
+            if condition(input_dict):
+                self._update_trace(input_dict, next_stage)
+                return next_stage
+
+        if self.default is not None:
+            self._update_trace(input_dict, self.default)
+            return self.default
+
+        raise ValueError("No conditions were met and no default stage was set.")
+
+    def _update_trace(
+        self, input_dict: Dict[str, Any], next_stage: Union[Crew, Pipeline]
+    ):
+        """Update the trace to show that the input went through the router."""
+        if "trace" not in input_dict:
+            input_dict["trace"] = []
+        input_dict["trace"].append(
+            {
+                "router": self.__class__.__name__,
+                "next_stage": next_stage.__class__.__name__,
+            }
+        )

src/crewai/task.py

@@ -5,6 +5,7 @@ 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
@@ -173,6 +174,14 @@ 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,
@@ -204,8 +213,8 @@ class Task(BaseModel):
         tools: Optional[List[Any]],
     ) -> TaskOutput:
         """Run the core execution logic of the task."""
-        self.agent = agent
         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."
@@ -238,7 +247,7 @@ class Task(BaseModel):
             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:
@@ -319,9 +328,14 @@ class Task(BaseModel):
 
     def _create_converter(self, *args, **kwargs) -> Converter:
         """Create a converter instance."""
-        converter = self.agent.get_output_converter(*args, **kwargs)
-        if self.converter_cls:
+        if self.agent and not self.converter_cls:
+            converter = self.agent.get_output_converter(*args, **kwargs)
+        elif self.converter_cls:
             converter = self.converter_cls(*args, **kwargs)
+
+        if not converter:
+            raise Exception("No output converter found or set.")
+
         return converter
 
     def _export_output(

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

@@ -30,20 +30,6 @@ class TaskOutput(BaseModel):
         self.summary = f"{excerpt}..."
         return self
 
-    # @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:
@@ -62,7 +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

@@ -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
@@ -356,7 +383,7 @@ class Telemetry:
                             {
                                 "id": str(task.id),
                                 "description": task.description,
-                                "output": task.output.raw_output,
+                                "output": task.output.raw,
                             }
                             for task in crew.tasks
                         ]

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

@@ -151,16 +151,12 @@ 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:

src/crewai/utilities/constants.py

@@ -1,3 +1,2 @@
 TRAINING_DATA_FILE = "training_data.pkl"
 TRAINED_AGENTS_DATA_FILE = "trained_agents_data.pkl"
-CREW_TASKS_OUTPUT_FILE = "crew_tasks_output.json"

src/crewai/utilities/converter.py

@@ -2,10 +2,8 @@ import json
 
 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 crewai.agents.agent_builder.utilities.base_output_converter import OutputConverter
 
 
 class ConverterError(Exception):
@@ -19,15 +17,10 @@ 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 +34,14 @@ 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 +68,7 @@ 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

src/crewai/utilities/crew_pydantic_output_parser.py

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

src/crewai/utilities/planning_handler.py

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

src/crewai/utilities/printer.py

@@ -10,6 +10,8 @@ class Printer:
             self._print_bold_purple(content)
         elif color == "bold_blue":
             self._print_bold_blue(content)
+        elif color == "yellow":
+            self._print_yellow(content)
         else:
             print(content)
 
@@ -27,3 +29,6 @@ class Printer:
 
     def _print_bold_blue(self, content):
         print("\033[1m\033[94m {}\033[00m".format(content))
+
+    def _print_yellow(self, content):
+        print("\033[93m {}\033[00m".format(content))

src/crewai/utilities/task_output_handler.py

@@ -1,69 +0,0 @@
-import json
-import os
-
-from pydantic import BaseModel, Field
-from datetime import datetime
-from typing import Dict, Any, Optional, List
-from crewai.utilities.crew_json_encoder import CrewJSONEncoder
-
-
-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 TaskOutputJsonHandler:
-    def __init__(self, file_name: str) -> None:
-        self.file_path = os.path.join(os.getcwd(), file_name)
-
-    def initialize_file(self) -> None:
-        if not os.path.exists(self.file_path) or os.path.getsize(self.file_path) == 0:
-            with open(self.file_path, "w") as file:
-                json.dump([], file)
-
-    def update(self, task_index: int, log: ExecutionLog):
-        logs = self.load()
-        if task_index < len(logs):
-            logs[task_index] = log
-        else:
-            logs.append(log)
-        self.save(logs)
-
-    def save(self, logs: List[ExecutionLog]):
-        with open(self.file_path, "w") as file:
-            json.dump(logs, file, indent=2, cls=CrewJSONEncoder)
-
-    def reset(self):
-        """Reset the JSON file by creating an empty file."""
-        with open(self.file_path, "w") as f:
-            json.dump([], f)
-
-    def load(self) -> List[ExecutionLog]:
-        try:
-            if (
-                not os.path.exists(self.file_path)
-                or os.path.getsize(self.file_path) == 0
-            ):
-                return []
-
-            with open(self.file_path, "r") as file:
-                return json.load(file)
-        except FileNotFoundError:
-            print(f"File {self.file_path} not found. Returning empty list.")
-            return []
-        except json.JSONDecodeError:
-            print(
-                f"Error decoding JSON from file {self.file_path}. Returning empty list."
-            )
-            return []
-        except Exception as e:
-            print(f"An unexpected error occurred: {e}")
-            return []

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()

tests/agent_test.py

@@ -963,3 +963,54 @@ def test_agent_use_trained_data(crew_training_handler):
     crew_training_handler.assert_has_calls(
         [mock.call(), mock.call("trained_agents_data.pkl"), mock.call().load()]
     )
+
+
+def test_agent_max_retry_limit():
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_retry_limit=1,
+    )
+
+    task = Task(
+        agent=agent,
+        description="Say the word: Hi",
+        expected_output="The word: Hi",
+        human_input=True,
+    )
+
+    error_message = "Error happening while sending prompt to model."
+    with patch.object(
+        CrewAgentExecutor, "invoke", wraps=agent.agent_executor.invoke
+    ) as invoke_mock:
+        invoke_mock.side_effect = Exception(error_message)
+
+        assert agent._times_executed == 0
+        assert agent.max_retry_limit == 1
+
+        with pytest.raises(Exception) as e:
+            agent.execute_task(
+                task=task,
+            )
+        assert e.value.args[0] == error_message
+        assert agent._times_executed == 2
+
+        invoke_mock.assert_has_calls(
+            [
+                mock.call(
+                    {
+                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
+                        "tool_names": "",
+                        "tools": "",
+                    }
+                ),
+                mock.call(
+                    {
+                        "input": "Say the word: Hi\n\nThis is the expect criteria for your final answer: The word: Hi \n you MUST return the actual complete content as the final answer, not a summary.",
+                        "tool_names": "",
+                        "tools": "",
+                    }
+                ),
+            ]
+        )

tests/agents/agent_builder/base_agent_test.py

@@ -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_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_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

tests/cassettes/test_replay_setup_context.yaml

@@ -0,0 +1,163 @@
+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", "logprobs": false,
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '937'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.36.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.36.0
+      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-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"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-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_400f27fa1f","choices":[{"index":0,"delta":{"content":"
+        John"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wQ7bzZKcXAmiNgs4nn5Of0EFiM","object":"chat.completion.chunk","created":1721491782,"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:
+      - 8a643794fe0341e9-EWR
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Sat, 20 Jul 2024 16:09:42 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=7kfE3khl2E.6zM44yel5nToHzdtz0QeQ4wkLuGYyqSs-1721491782-1.0.1.1-XUb95eXTriHvSUSCH.TCyAmCGCbPK6L7p_tRTDBon8Fo6ns8TDbDoDGA.wVCFI4MTXSxkqrjD0GpYDj4GBTeSQ;
+        path=/; expires=Sat, 20-Jul-24 16:39:42 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=iN41lAEk.DjpRMAtG.K0NEvIN0xB9eS0CUCU2iWmjv4-1721491782137-0.0.1.1-604800000;
+        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:
+      - '104'
+      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:
+      - '29999791'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_4d90924dd28a0fb48c857f03515f0ca8
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_task_with_context.yaml

@@ -0,0 +1,449 @@
+interactions:
+- request:
+    body: !!binary |
+      CrG5AQokCiIKDHNlcnZpY2UubmFtZRISChBjcmV3QUktdGVsZW1ldHJ5Eoe5AQoSChBjcmV3YWku
+      dGVsZW1ldHJ5EpACChB1aPb7uNmPUxB3quhKypN4EgjnW4at80oLKCoOVGFzayBFeGVjdXRpb24w
+      ATnIwfLEssXiF0FI2USctcXiF0ouCghjcmV3X2tleRIiCiA5OGE3ZDIxNDI1MjEwNzY5MzhjYzg3
+      Yzc2OWRlZGNkM0oxCgdjcmV3X2lkEiYKJDQzOTNlYjRmLTRiMDMtNDgzOS1hMmMwLWViY2IwNTMy
+      NDJjNEouCgh0YXNrX2tleRIiCiBhZmE2OThiMjYyZDM1NDNmOWE2MTFlNGQ1MTQ1ZWQ2YUoxCgd0
+      YXNrX2lkEiYKJDM1ZTA0MTVkLTlhNzYtNDc5YS1hOGFkLTI2NjJiZDQ0NjRiMXoCGAGFAQABAAAS
+      ig0KEBXTWyRbS66PohO2H7pX1jQSCBQxHUkWdA7dKgxDcmV3IENyZWF0ZWQwATmAAQ+ftcXiF0E4
+      fhGftcXiF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjM2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoG
+      My4xMS41Si4KCGNyZXdfa2V5EiIKIGNhN2MwMTM2ZWM3YmY1ZGU3NWRlNWQyNjY5OWRhM2I0SjEK
+      B2NyZXdfaWQSJgokYzk5MzVhMDItOGJjYi00YTJlLThhZjktYTU5NWNmMTgyMzYzShwKDGNyZXdf
+      cHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9v
+      Zl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUr+BAoLY3Jld19hZ2VudHMS
+      7gQK6wRbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAi
+      Yjg4NzA5MjYtYzNiYi00MDUyLWIxYTctNDY3ZDdjNDJmMjVkIiwgInJvbGUiOiAiUmVzZWFyY2hl
+      ciIsICJnb2FsIjogIk1ha2UgdGhlIGJlc3QgcmVzZWFyY2ggYW5kIGFuYWx5c2lzIG9uIGNvbnRl
+      bnQgYWJvdXQgQUkgYW5kIEFJIGFnZW50cyIsICJiYWNrc3RvcnkiOiAiWW91J3JlIGFuIGV4cGVy
+      dCByZXNlYXJjaGVyLCBzcGVjaWFsaXplZCBpbiB0ZWNobm9sb2d5LCBzb2Z0d2FyZSBlbmdpbmVl
+      cmluZywgQUkgYW5kIHN0YXJ0dXBzLiBZb3Ugd29yayBhcyBhIGZyZWVsYW5jZXIgYW5kIGlzIG5v
+      dyB3b3JraW5nIG9uIGRvaW5nIHJlc2VhcmNoIGFuZCBhbmFseXNpcyBmb3IgYSBuZXcgY3VzdG9t
+      ZXIuIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGws
+      ICJpMThuIjogbnVsbCwgImxsbSI6ICJ7XCJuYW1lXCI6IG51bGwsIFwibW9kZWxfbmFtZVwiOiBc
+      ImdwdC00b1wiLCBcInRlbXBlcmF0dXJlXCI6IDAuNywgXCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlc
+      In0iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAidG9vbHNfbmFtZXMiOiBbXX1dSskD
+      CgpjcmV3X3Rhc2tzEroDCrcDW3sia2V5IjogIjk0NGFlZjBiYWM4NDBmMWMyN2JkODNhOTM3YmMz
+      NjFiIiwgImlkIjogIjVkZDRjMTJhLThmOWItNDRmNi1iYjRhLWVkODdiNTgzZGU1MCIsICJkZXNj
+      cmlwdGlvbiI6ICJHaXZlIG1lIGEgbGlzdCBvZiA1IGludGVyZXN0aW5nIGlkZWFzIHRvIGV4cGxv
+      cmUgZm9yIG5hIGFydGljbGUsIHdoYXQgbWFrZXMgdGhlbSB1bmlxdWUgYW5kIGludGVyZXN0aW5n
+      LiIsICJleHBlY3RlZF9vdXRwdXQiOiAiQnVsbGV0IHBvaW50IGxpc3Qgb2YgNSBpbXBvcnRhbnQg
+      ZXZlbnRzLiIsICJhc3luY19leGVjdXRpb24/IjogdHJ1ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
+      LCAiYWdlbnRfcm9sZSI6ICJSZXNlYXJjaGVyIiwgImFnZW50X2tleSI6ICI4YmQyMTM5YjU5NzUx
+      ODE1MDZlNDFmZDljNDU2M2Q3NSIsICJjb250ZXh0IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119
+      XUoqCghwbGF0Zm9ybRIeChxtYWNPUy0xNC4xLjEtYXJtNjQtYXJtLTY0Yml0ShwKEHBsYXRmb3Jt
+      X3JlbGVhc2USCAoGMjMuMS4wShsKD3BsYXRmb3JtX3N5c3RlbRIICgZEYXJ3aW5KewoQcGxhdGZv
+      cm1fdmVyc2lvbhJnCmVEYXJ3aW4gS2VybmVsIFZlcnNpb24gMjMuMS4wOiBNb24gT2N0ICA5IDIx
+      OjI3OjI0IFBEVCAyMDIzOyByb290OnhudS0xMDAwMi40MS45fjYvUkVMRUFTRV9BUk02NF9UNjAw
+      MEoKCgRjcHVzEgIYCnoCGAGFAQABAAASjgIKEIq7Mjq32M5Kt5dKJnjskZ0SCMx1TtvU1+T2KgxU
+      YXNrIENyZWF0ZWQwATkI9iiftcXiF0HAfimftcXiF0ouCghjcmV3X2tleRIiCiBjYTdjMDEzNmVj
+      N2JmNWRlNzVkZTVkMjY2OTlkYTNiNEoxCgdjcmV3X2lkEiYKJGM5OTM1YTAyLThiY2ItNGEyZS04
+      YWY5LWE1OTVjZjE4MjM2M0ouCgh0YXNrX2tleRIiCiA5NDRhZWYwYmFjODQwZjFjMjdiZDgzYTkz
+      N2JjMzYxYkoxCgd0YXNrX2lkEiYKJDVkZDRjMTJhLThmOWItNDRmNi1iYjRhLWVkODdiNTgzZGU1
+      MHoCGAGFAQABAAASkAIKEE4G7Oi0pafO3nARt5VKez4SCM6Ua5kmBYFDKg5UYXNrIEV4ZWN1dGlv
+      bjABOXC1KZ+1xeIXQWDhMJ+1xeIXSi4KCGNyZXdfa2V5EiIKIGNhN2MwMTM2ZWM3YmY1ZGU3NWRl
+      NWQyNjY5OWRhM2I0SjEKB2NyZXdfaWQSJgokYzk5MzVhMDItOGJjYi00YTJlLThhZjktYTU5NWNm
+      MTgyMzYzSi4KCHRhc2tfa2V5EiIKIDk0NGFlZjBiYWM4NDBmMWMyN2JkODNhOTM3YmMzNjFiSjEK
+      B3Rhc2tfaWQSJgokNWRkNGMxMmEtOGY5Yi00NGY2LWJiNGEtZWQ4N2I1ODNkZTUwegIYAYUBAAEA
+      ABLUGQoQX+5PRYVQ3O7KzTa1tWKiRxIIuu8x8CYW2KEqDENyZXcgQ3JlYXRlZDABOUjW1qO1xeIX
+      QUjE2aO1xeIXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzYuMEoaCg5weXRob25fdmVyc2lvbhII
+      CgYzLjExLjVKLgoIY3Jld19rZXkSIgogYTBhYzk1MzU0ZDMyOWJhN2Y2OTQ4M2FkZmUwYzdkMjhK
+      MQoHY3Jld19pZBImCiQ5MzgzYzU2Yy1lNzQ3LTQwYmItOTlhYi01NGE2NGRkY2Q3YTlKHAoMY3Jl
+      d19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVy
+      X29mX3Rhc2tzEgIYBEobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgCSvcHCgtjcmV3X2FnZW50
+      cxLnBwrkB1t7ImtleSI6ICJkYWI1MjFlYmQzMWFlMTJmZWUxODlhMzhkMzA5MGQ5MyIsICJpZCI6
+      ICJhMzAzNTliZi01Y2QwLTQ3MGYtOTk2NS0yYjZhZTU0YmVmY2MiLCAicm9sZSI6ICJXcml0ZXIi
+      LCAiZ29hbCI6ICJZb3Ugd3JpdGUgbGVzc3NvbnMgb2YgbWF0aCBmb3Iga2lkcy4iLCAiYmFja3N0
+      b3J5IjogIllvdSdyZSBhbiBleHBlcnQgaW4gd3JpdHRpbmcgYW5kIHlvdSBsb3ZlIHRvIHRlYWNo
+      IGtpZHMgYnV0IHlvdSBrbm93IG5vdGhpbmcgb2YgbWF0aC4iLCAidmVyYm9zZT8iOiBmYWxzZSwg
+      Im1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImkxOG4iOiBudWxsLCAibGxtIjogIntc
+      Im5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6IFwiZ3B0LTRvXCIsIFwidGVtcGVyYXR1cmVc
+      IjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5BSVwifSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/
+      IjogZmFsc2UsICJ0b29sc19uYW1lcyI6IFsibXVsdGlwbGNhdGlvbl90b29sIl19LCB7ImtleSI6
+      ICJkYWI1MjFlYmQzMWFlMTJmZWUxODlhMzhkMzA5MGQ5MyIsICJpZCI6ICJhN2JiNTI4ZS0yM2M4
+      LTQ1MzItYjNiYS0yOWU1NDNiMGFhN2YiLCAicm9sZSI6ICJXcml0ZXIiLCAiZ29hbCI6ICJZb3Ug
+      d3JpdGUgbGVzc3NvbnMgb2YgbWF0aCBmb3Iga2lkcy4iLCAiYmFja3N0b3J5IjogIllvdSdyZSBh
+      biBleHBlcnQgaW4gd3JpdHRpbmcgYW5kIHlvdSBsb3ZlIHRvIHRlYWNoIGtpZHMgYnV0IHlvdSBr
+      bm93IG5vdGhpbmcgb2YgbWF0aC4iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUs
+      ICJtYXhfcnBtIjogbnVsbCwgImkxOG4iOiBudWxsLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwg
+      XCJtb2RlbF9uYW1lXCI6IFwiZ3B0LTRvXCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNz
+      XCI6IFwiQ2hhdE9wZW5BSVwifSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJ0b29s
+      c19uYW1lcyI6IFsibXVsdGlwbGNhdGlvbl90b29sIl19XUqaDQoKY3Jld190YXNrcxKLDQqIDVt7
+      ImtleSI6ICIzMGYzMjg2M2EyZWI3OThkMTA5NmM5MDcwMjgwOTgzMCIsICJpZCI6ICIxNjhlOWNm
+      Ny1hYWJjLTRkMGUtYTg1OS01ODEyZGM4MDg4NTYiLCAiZGVzY3JpcHRpb24iOiAiV2hhdCBpcyAy
+      IHRpbWVzIDY/IFJldHVybiBvbmx5IHRoZSBudW1iZXIgYWZ0ZXIgdXNpbmcgdGhlIG11bHRpcGxp
+      Y2F0aW9uIHRvb2wuIiwgImV4cGVjdGVkX291dHB1dCI6ICJ0aGUgcmVzdWx0IG9mIG11bHRpcGxp
+      Y2F0aW9uIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
+      LCAiYWdlbnRfcm9sZSI6ICJXcml0ZXIiLCAiYWdlbnRfa2V5IjogImRhYjUyMWViZDMxYWUxMmZl
+      ZTE4OWEzOGQzMDkwZDkzIiwgImNvbnRleHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbIm11bHRp
+      cGxjYXRpb25fdG9vbCJdfSwgeyJrZXkiOiAiM2QwYmRlZTMxMjdhZjk5MGIzNjZjMTJkZGJkNGE4
+      YTYiLCAiaWQiOiAiMDdkYmU0MzAtZDMxNC00MjgwLWEwODUtOGQ0MTQyZjNjZTFlIiwgImRlc2Ny
+      aXB0aW9uIjogIldoYXQgaXMgMyB0aW1lcyAxPyBSZXR1cm4gb25seSB0aGUgbnVtYmVyIGFmdGVy
+      IHVzaW5nIHRoZSBtdWx0aXBsaWNhdGlvbiB0b29sLiIsICJleHBlY3RlZF9vdXRwdXQiOiAidGhl
+      IHJlc3VsdCBvZiBtdWx0aXBsaWNhdGlvbiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJo
+      dW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiV3JpdGVyIiwgImFnZW50X2tleSI6
+      ICJkYWI1MjFlYmQzMWFlMTJmZWUxODlhMzhkMzA5MGQ5MyIsICJjb250ZXh0IjogbnVsbCwgInRv
+      b2xzX25hbWVzIjogWyJtdWx0aXBsY2F0aW9uX3Rvb2wiXX0sIHsia2V5IjogIjMwZjMyODYzYTJl
+      Yjc5OGQxMDk2YzkwNzAyODA5ODMwIiwgImlkIjogImFlYjJmMjk1LTI3NDUtNGYwMi05MjQxLWU3
+      NTk2MjVjOWQyMCIsICJkZXNjcmlwdGlvbiI6ICJXaGF0IGlzIDIgdGltZXMgNj8gUmV0dXJuIG9u
+      bHkgdGhlIG51bWJlciBhZnRlciB1c2luZyB0aGUgbXVsdGlwbGljYXRpb24gdG9vbC4iLCAiZXhw
+      ZWN0ZWRfb3V0cHV0IjogInRoZSByZXN1bHQgb2YgbXVsdGlwbGljYXRpb24iLCAiYXN5bmNfZXhl
+      Y3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogIldy
+      aXRlciIsICJhZ2VudF9rZXkiOiAiZGFiNTIxZWJkMzFhZTEyZmVlMTg5YTM4ZDMwOTBkOTMiLCAi
+      Y29udGV4dCI6IG51bGwsICJ0b29sc19uYW1lcyI6IFsibXVsdGlwbGNhdGlvbl90b29sIl19LCB7
+      ImtleSI6ICIzZDBiZGVlMzEyN2FmOTkwYjM2NmMxMmRkYmQ0YThhNiIsICJpZCI6ICI5MGE0N2Fm
+      Ny1jZjc5LTQ3NjYtOWJjNS02Nzg3MWMwOTFiOTYiLCAiZGVzY3JpcHRpb24iOiAiV2hhdCBpcyAz
+      IHRpbWVzIDE/IFJldHVybiBvbmx5IHRoZSBudW1iZXIgYWZ0ZXIgdXNpbmcgdGhlIG11bHRpcGxp
+      Y2F0aW9uIHRvb2wuIiwgImV4cGVjdGVkX291dHB1dCI6ICJ0aGUgcmVzdWx0IG9mIG11bHRpcGxp
+      Y2F0aW9uIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNl
+      LCAiYWdlbnRfcm9sZSI6ICJXcml0ZXIiLCAiYWdlbnRfa2V5IjogImRhYjUyMWViZDMxYWUxMmZl
+      ZTE4OWEzOGQzMDkwZDkzIiwgImNvbnRleHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbIm11bHRp
+      cGxjYXRpb25fdG9vbCJdfV1KKgoIcGxhdGZvcm0SHgocbWFjT1MtMTQuMS4xLWFybTY0LWFybS02
+      NGJpdEocChBwbGF0Zm9ybV9yZWxlYXNlEggKBjIzLjEuMEobCg9wbGF0Zm9ybV9zeXN0ZW0SCAoG
+      RGFyd2luSnsKEHBsYXRmb3JtX3ZlcnNpb24SZwplRGFyd2luIEtlcm5lbCBWZXJzaW9uIDIzLjEu
+      MDogTW9uIE9jdCAgOSAyMToyNzoyNCBQRFQgMjAyMzsgcm9vdDp4bnUtMTAwMDIuNDEuOX42L1JF
+      TEVBU0VfQVJNNjRfVDYwMDBKCgoEY3B1cxICGAp6AhgBhQEAAQAAEo4CChDMsDVWCtNnTZd78P6M
+      F0qHEghu/cLCLfIljioMVGFzayBDcmVhdGVkMAE5ALHzo7XF4hdBMCb0o7XF4hdKLgoIY3Jld19r
+      ZXkSIgogYTBhYzk1MzU0ZDMyOWJhN2Y2OTQ4M2FkZmUwYzdkMjhKMQoHY3Jld19pZBImCiQ5Mzgz
+      YzU2Yy1lNzQ3LTQwYmItOTlhYi01NGE2NGRkY2Q3YTlKLgoIdGFza19rZXkSIgogMzBmMzI4NjNh
+      MmViNzk4ZDEwOTZjOTA3MDI4MDk4MzBKMQoHdGFza19pZBImCiQxNjhlOWNmNy1hYWJjLTRkMGUt
+      YTg1OS01ODEyZGM4MDg4NTZ6AhgBhQEAAQAAEpUBChB1ZPMBfoWizT2O65qegWcGEgjmR3EI+Dhz
+      KSoKVG9vbCBVc2FnZTABOUCLN6W1xeIXQWBWOKW1xeIXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAu
+      MzYuMEohCgl0b29sX25hbWUSFAoSbXVsdGlwbGNhdGlvbl90b29sSg4KCGF0dGVtcHRzEgIYAXoC
+      GAGFAQABAAASkAIKEEukGnCGulTfJ1/e50UIF5ASCBeMmMmX2ss5Kg5UYXNrIEV4ZWN1dGlvbjAB
+      OShR9KO1xeIXQQBL+KW1xeIXSi4KCGNyZXdfa2V5EiIKIGEwYWM5NTM1NGQzMjliYTdmNjk0ODNh
+      ZGZlMGM3ZDI4SjEKB2NyZXdfaWQSJgokOTM4M2M1NmMtZTc0Ny00MGJiLTk5YWItNTRhNjRkZGNk
+      N2E5Si4KCHRhc2tfa2V5EiIKIDMwZjMyODYzYTJlYjc5OGQxMDk2YzkwNzAyODA5ODMwSjEKB3Rh
+      c2tfaWQSJgokMTY4ZTljZjctYWFiYy00ZDBlLWE4NTktNTgxMmRjODA4ODU2egIYAYUBAAEAABKO
+      AgoQeq27u45vVnfO3QW8y5TkKhII8pwpZBclUSUqDFRhc2sgQ3JlYXRlZDABOXCRBaa1xeIXQeAl
+      Bqa1xeIXSi4KCGNyZXdfa2V5EiIKIGEwYWM5NTM1NGQzMjliYTdmNjk0ODNhZGZlMGM3ZDI4SjEK
+      B2NyZXdfaWQSJgokOTM4M2M1NmMtZTc0Ny00MGJiLTk5YWItNTRhNjRkZGNkN2E5Si4KCHRhc2tf
+      a2V5EiIKIDNkMGJkZWUzMTI3YWY5OTBiMzY2YzEyZGRiZDRhOGE2SjEKB3Rhc2tfaWQSJgokMDdk
+      YmU0MzAtZDMxNC00MjgwLWEwODUtOGQ0MTQyZjNjZTFlegIYAYUBAAEAABKVAQoQDpoau444Nc2P
+      TpqGSwuJUBII3odk2PVsECQqClRvb2wgVXNhZ2UwATlQXjmntcXiF0GwSDqntcXiF0oaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjM2LjBKIQoJdG9vbF9uYW1lEhQKEm11bHRpcGxjYXRpb25fdG9vbEoO
+      CghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpACChBW89qgKwxZoE48iGgYORjmEggn0gOg6T0j3SoO
+      VGFzayBFeGVjdXRpb24wATnYUAamtcXiF0GwUfSntcXiF0ouCghjcmV3X2tleRIiCiBhMGFjOTUz
+      NTRkMzI5YmE3ZjY5NDgzYWRmZTBjN2QyOEoxCgdjcmV3X2lkEiYKJDkzODNjNTZjLWU3NDctNDBi
+      Yi05OWFiLTU0YTY0ZGRjZDdhOUouCgh0YXNrX2tleRIiCiAzZDBiZGVlMzEyN2FmOTkwYjM2NmMx
+      MmRkYmQ0YThhNkoxCgd0YXNrX2lkEiYKJDA3ZGJlNDMwLWQzMTQtNDI4MC1hMDg1LThkNDE0MmYz
+      Y2UxZXoCGAGFAQABAAASjgIKECX4kiD6RrdHOsL/u1WPaKISCEn8hmiuaOxzKgxUYXNrIENyZWF0
+      ZWQwATngAQCotcXiF0GwhgCotcXiF0ouCghjcmV3X2tleRIiCiBhMGFjOTUzNTRkMzI5YmE3ZjY5
+      NDgzYWRmZTBjN2QyOEoxCgdjcmV3X2lkEiYKJDkzODNjNTZjLWU3NDctNDBiYi05OWFiLTU0YTY0
+      ZGRjZDdhOUouCgh0YXNrX2tleRIiCiAzMGYzMjg2M2EyZWI3OThkMTA5NmM5MDcwMjgwOTgzMEox
+      Cgd0YXNrX2lkEiYKJGFlYjJmMjk1LTI3NDUtNGYwMi05MjQxLWU3NTk2MjVjOWQyMHoCGAGFAQAB
+      AAASlQEKEA/spc2u3GsQSPtfjOb6NJISCG3tEmcOqAoDKgpUb29sIFVzYWdlMAE58GZDqbXF4hdB
+      IFlEqbXF4hdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zNi4wSiEKCXRvb2xfbmFtZRIUChJtdWx0
+      aXBsY2F0aW9uX3Rvb2xKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABKQAgoQsO+zsd47DClQTmS7
+      ZfZYLxII2UxCduX9osEqDlRhc2sgRXhlY3V0aW9uMAE5qLEAqLXF4hdByLEBqrXF4hdKLgoIY3Jl
+      d19rZXkSIgogYTBhYzk1MzU0ZDMyOWJhN2Y2OTQ4M2FkZmUwYzdkMjhKMQoHY3Jld19pZBImCiQ5
+      MzgzYzU2Yy1lNzQ3LTQwYmItOTlhYi01NGE2NGRkY2Q3YTlKLgoIdGFza19rZXkSIgogMzBmMzI4
+      NjNhMmViNzk4ZDEwOTZjOTA3MDI4MDk4MzBKMQoHdGFza19pZBImCiRhZWIyZjI5NS0yNzQ1LTRm
+      MDItOTI0MS1lNzU5NjI1YzlkMjB6AhgBhQEAAQAAEo4CChD55L/w1V+ezIjuajyG1hwUEggBdDur
+      +CTqUCoMVGFzayBDcmVhdGVkMAE52AcPqrXF4hdBSJwPqrXF4hdKLgoIY3Jld19rZXkSIgogYTBh
+      Yzk1MzU0ZDMyOWJhN2Y2OTQ4M2FkZmUwYzdkMjhKMQoHY3Jld19pZBImCiQ5MzgzYzU2Yy1lNzQ3
+      LTQwYmItOTlhYi01NGE2NGRkY2Q3YTlKLgoIdGFza19rZXkSIgogM2QwYmRlZTMxMjdhZjk5MGIz
+      NjZjMTJkZGJkNGE4YTZKMQoHdGFza19pZBImCiQ5MGE0N2FmNy1jZjc5LTQ3NjYtOWJjNS02Nzg3
+      MWMwOTFiOTZ6AhgBhQEAAQAAEpUBChA+cdY4kcsaUDolyJw3c952EggtUbX8zXBaySoKVG9vbCBV
+      c2FnZTABOaAHUKu1xeIXQcDSUKu1xeIXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzYuMEohCgl0
+      b29sX25hbWUSFAoSbXVsdGlwbGNhdGlvbl90b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS
+      kAIKEAvnVK0WhsX8u4xShcr/sooSCC+aS9IRpThCKg5UYXNrIEV4ZWN1dGlvbjABOUDHD6q1xeIX
+      QVC9IKy1xeIXSi4KCGNyZXdfa2V5EiIKIGEwYWM5NTM1NGQzMjliYTdmNjk0ODNhZGZlMGM3ZDI4
+      SjEKB2NyZXdfaWQSJgokOTM4M2M1NmMtZTc0Ny00MGJiLTk5YWItNTRhNjRkZGNkN2E5Si4KCHRh
+      c2tfa2V5EiIKIDNkMGJkZWUzMTI3YWY5OTBiMzY2YzEyZGRiZDRhOGE2SjEKB3Rhc2tfaWQSJgok
+      OTBhNDdhZjctY2Y3OS00NzY2LTliYzUtNjc4NzFjMDkxYjk2egIYAYUBAAEAABKrCwoQfae3w+r8
+      n0qGJnp7DP6RtxIILhPziA5VzRwqDENyZXcgQ3JlYXRlZDABOZipkrW1xeIXQZDIlLW1xeIXShoK
+      DmNyZXdhaV92ZXJzaW9uEggKBjAuMzYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjVKLgoI
+      Y3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZiYjU5MDA2YWFhMDFhMjljZDZKMQoHY3Jld19pZBIm
+      CiQ2M2Y2MGU1Yi1kMjZkLTQwZjMtYTQyMC0wNzQ3Y2MwOWM5YWRKHAoMY3Jld19wcm9jZXNzEgwK
+      CnNlcXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhABShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIY
+      AUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBStIDCgtjcmV3X2FnZW50cxLCAwq/A1t7Imtl
+      eSI6ICIwN2Q5OWI2MzA0MTFkMzVmZDkwNDdhNTMyZDUzZGRhNyIsICJpZCI6ICJhMGJlYjc4ZS04
+      ZGUzLTQ5YjEtYWRkZS1mODg3NWMzNjM3ZGYiLCAicm9sZSI6ICJSZXNlYXJjaGVyIiwgImdvYWwi
+      OiAiWW91IHJlc2VhcmNoIGFib3V0IG1hdGguIiwgImJhY2tzdG9yeSI6ICJZb3UncmUgYW4gZXhw
+      ZXJ0IGluIHJlc2VhcmNoIGFuZCB5b3UgbG92ZSB0byBsZWFybiBuZXcgdGhpbmdzLiIsICJ2ZXJi
+      b3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6IG51
+      bGwsICJsbG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNG9cIiwg
+      XCJ0ZW1wZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRlbGVn
+      YXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgInRvb2xzX25hbWVzIjogW119XUqWAwoKY3Jld190YXNr
+      cxKHAwqEA1t7ImtleSI6ICI2Mzk5NjUxN2YzZjNmMWM5NGQ2YmI2MTdhYTBiMWM0ZiIsICJpZCI6
+      ICIwMmNiOWIyYS0yODIyLTQwNTYtYjQ5MC04YjA0YzA2MTg2M2IiLCAiZGVzY3JpcHRpb24iOiAi
+      UmVzZWFyY2ggYSB0b3BpYyB0byB0ZWFjaCBhIGtpZCBhZ2VkIDYgYWJvdXQgbWF0aC4iLCAiZXhw
+      ZWN0ZWRfb3V0cHV0IjogIkEgdG9waWMsIGV4cGxhbmF0aW9uLCBhbmdsZSwgYW5kIGV4YW1wbGVz
+      LiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFn
+      ZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5
+      MDQ3YTUzMmQ1M2RkYTciLCAiY29udGV4dCI6IG51bGwsICJ0b29sc19uYW1lcyI6IFtdfV1KKgoI
+      cGxhdGZvcm0SHgocbWFjT1MtMTQuMS4xLWFybTY0LWFybS02NGJpdEocChBwbGF0Zm9ybV9yZWxl
+      YXNlEggKBjIzLjEuMEobCg9wbGF0Zm9ybV9zeXN0ZW0SCAoGRGFyd2luSnsKEHBsYXRmb3JtX3Zl
+      cnNpb24SZwplRGFyd2luIEtlcm5lbCBWZXJzaW9uIDIzLjEuMDogTW9uIE9jdCAgOSAyMToyNzoy
+      NCBQRFQgMjAyMzsgcm9vdDp4bnUtMTAwMDIuNDEuOX42L1JFTEVBU0VfQVJNNjRfVDYwMDBKCgoE
+      Y3B1cxICGAp6AhgBhQEAAQAAEo4CChDwvE8C6FMSvgaW9DsUngzEEgi69DWPEIv7/ioMVGFzayBD
+      cmVhdGVkMAE5QJOmtbXF4hdBSOWmtbXF4hdKLgoIY3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZi
+      YjU5MDA2YWFhMDFhMjljZDZKMQoHY3Jld19pZBImCiQ2M2Y2MGU1Yi1kMjZkLTQwZjMtYTQyMC0w
+      NzQ3Y2MwOWM5YWRKLgoIdGFza19rZXkSIgogNjM5OTY1MTdmM2YzZjFjOTRkNmJiNjE3YWEwYjFj
+      NGZKMQoHdGFza19pZBImCiQwMmNiOWIyYS0yODIyLTQwNTYtYjQ5MC04YjA0YzA2MTg2M2J6AhgB
+      hQEAAQAAEpACChA9ji0VC42jOLjDFsSGAZehEgi88WVi+J8WZyoOVGFzayBFeGVjdXRpb24wATlA
+      EKe1tcXiF0GwOXS9tcXiF0ouCghjcmV3X2tleRIiCiBjOTdiNWZlYjVkMWI2NmJiNTkwMDZhYWEw
+      MWEyOWNkNkoxCgdjcmV3X2lkEiYKJDYzZjYwZTViLWQyNmQtNDBmMy1hNDIwLTA3NDdjYzA5Yzlh
+      ZEouCgh0YXNrX2tleRIiCiA2Mzk5NjUxN2YzZjNmMWM5NGQ2YmI2MTdhYTBiMWM0ZkoxCgd0YXNr
+      X2lkEiYKJDAyY2I5YjJhLTI4MjItNDA1Ni1iNDkwLThiMDRjMDYxODYzYnoCGAGFAQABAAASqwsK
+      EOSKFi2MNd2ArhJhwSRFLU8SCLUBjfAc1xVOKgxDcmV3IENyZWF0ZWQwATlAcNi/tcXiF0G4zdq/
+      tcXiF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjM2LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4x
+      MS41Si4KCGNyZXdfa2V5EiIKIGM5N2I1ZmViNWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2Ny
+      ZXdfaWQSJgokNmFlNzhhZjEtNDE5Ny00ODU2LWE1OTItYWEzZGNmMTI5OGJhShwKDGNyZXdfcHJv
+      Y2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUrSAwoLY3Jld19hZ2VudHMSwgMK
+      vwNbeyJrZXkiOiAiMDdkOTliNjMwNDExZDM1ZmQ5MDQ3YTUzMmQ1M2RkYTciLCAiaWQiOiAiYWUz
+      ZjEwYmYtNThlMy00NjNjLWI4YTUtMDZjNTAxYTVlNWY0IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJnb2FsIjogIllvdSByZXNlYXJjaCBhYm91dCBtYXRoLiIsICJiYWNrc3RvcnkiOiAiWW91J3Jl
+      IGFuIGV4cGVydCBpbiByZXNlYXJjaCBhbmQgeW91IGxvdmUgdG8gbGVhcm4gbmV3IHRoaW5ncy4i
+      LCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImkx
+      OG4iOiBudWxsLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6IFwiZ3B0
+      LTRvXCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5BSVwifSIs
+      ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJ0b29sc19uYW1lcyI6IFtdfV1KlgMKCmNy
+      ZXdfdGFza3MShwMKhANbeyJrZXkiOiAiNjM5OTY1MTdmM2YzZjFjOTRkNmJiNjE3YWEwYjFjNGYi
+      LCAiaWQiOiAiNTQ4NzY5YWUtMmFjZS00NzIwLTlhYWEtZWY3YmVjZGRmMjAyIiwgImRlc2NyaXB0
+      aW9uIjogIlJlc2VhcmNoIGEgdG9waWMgdG8gdGVhY2ggYSBraWQgYWdlZCA2IGFib3V0IG1hdGgu
+      IiwgImV4cGVjdGVkX291dHB1dCI6ICJBIHRvcGljLCBleHBsYW5hdGlvbiwgYW5nbGUsIGFuZCBl
+      eGFtcGxlcy4iLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFs
+      c2UsICJhZ2VudF9yb2xlIjogIlJlc2VhcmNoZXIiLCAiYWdlbnRfa2V5IjogIjA3ZDk5YjYzMDQx
+      MWQzNWZkOTA0N2E1MzJkNTNkZGE3IiwgImNvbnRleHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBb
+      XX1dSioKCHBsYXRmb3JtEh4KHG1hY09TLTE0LjEuMS1hcm02NC1hcm0tNjRiaXRKHAoQcGxhdGZv
+      cm1fcmVsZWFzZRIICgYyMy4xLjBKGwoPcGxhdGZvcm1fc3lzdGVtEggKBkRhcndpbkp7ChBwbGF0
+      Zm9ybV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAyMy4xLjA6IE1vbiBPY3QgIDkg
+      MjE6Mjc6MjQgUERUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjQxLjl+Ni9SRUxFQVNFX0FSTTY0X1Q2
+      MDAwSgoKBGNwdXMSAhgKegIYAYUBAAEAABKOAgoQJwZSCcuSu3diAuOYiVdE2BIIeF1BeIAKnP4q
+      DFRhc2sgQ3JlYXRlZDABOYhX77+1xeIXQcCh77+1xeIXSi4KCGNyZXdfa2V5EiIKIGM5N2I1ZmVi
+      NWQxYjY2YmI1OTAwNmFhYTAxYTI5Y2Q2SjEKB2NyZXdfaWQSJgokNmFlNzhhZjEtNDE5Ny00ODU2
+      LWE1OTItYWEzZGNmMTI5OGJhSi4KCHRhc2tfa2V5EiIKIDYzOTk2NTE3ZjNmM2YxYzk0ZDZiYjYx
+      N2FhMGIxYzRmSjEKB3Rhc2tfaWQSJgokNTQ4NzY5YWUtMmFjZS00NzIwLTlhYWEtZWY3YmVjZGRm
+      MjAyegIYAYUBAAEAABKQAgoQxBgL6L3Ce74Cu4q6j0ErDRIIEnXenwnk/A4qDlRhc2sgRXhlY3V0
+      aW9uMAE5uMzvv7XF4hdBAEPaxrXF4hdKLgoIY3Jld19rZXkSIgogYzk3YjVmZWI1ZDFiNjZiYjU5
+      MDA2YWFhMDFhMjljZDZKMQoHY3Jld19pZBImCiQ2YWU3OGFmMS00MTk3LTQ4NTYtYTU5Mi1hYTNk
+      Y2YxMjk4YmFKLgoIdGFza19rZXkSIgogNjM5OTY1MTdmM2YzZjFjOTRkNmJiNjE3YWEwYjFjNGZK
+      MQoHdGFza19pZBImCiQ1NDg3NjlhZS0yYWNlLTQ3MjAtOWFhYS1lZjdiZWNkZGYyMDJ6AhgBhQEA
+      AQAAEo0MChB2PHWFIMgXT4sbnL1Fk9tqEgj1iM6d8aLAFyoMQ3JldyBDcmVhdGVkMAE5SKovx7XF
+      4hdBwAcyx7XF4hdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zNi4wShoKDnB5dGhvbl92ZXJzaW9u
+      EggKBjMuMTEuNUouCghjcmV3X2tleRIiCiA4YzI3NTJmNDllNWI5ZDJiNjhjYjM1Y2FjOGZjYzg2
+      ZEoxCgdjcmV3X2lkEiYKJDA2MTdhZjU1LWEwNjQtNDEwMi05YjQ0LThhMThiZWU0NTg3OEocCgxj
+      cmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1i
+      ZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2FnZW50cxICGAFK/gQKC2NyZXdfYWdl
+      bnRzEu4ECusEW3sia2V5IjogIjhiZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1IiwgImlk
+      IjogIjc4YmM1N2I4LWIwZTgtNDZlNy04OTIzLTQ2ZDJlMWQ4MjQwNyIsICJyb2xlIjogIlJlc2Vh
+      cmNoZXIiLCAiZ29hbCI6ICJNYWtlIHRoZSBiZXN0IHJlc2VhcmNoIGFuZCBhbmFseXNpcyBvbiBj
+      b250ZW50IGFib3V0IEFJIGFuZCBBSSBhZ2VudHMiLCAiYmFja3N0b3J5IjogIllvdSdyZSBhbiBl
+      eHBlcnQgcmVzZWFyY2hlciwgc3BlY2lhbGl6ZWQgaW4gdGVjaG5vbG9neSwgc29mdHdhcmUgZW5n
+      aW5lZXJpbmcsIEFJIGFuZCBzdGFydHVwcy4gWW91IHdvcmsgYXMgYSBmcmVlbGFuY2VyIGFuZCBp
+      cyBub3cgd29ya2luZyBvbiBkb2luZyByZXNlYXJjaCBhbmQgYW5hbHlzaXMgZm9yIGEgbmV3IGN1
+      c3RvbWVyLiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBu
+      dWxsLCAiaTE4biI6IG51bGwsICJsbG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVc
+      IjogXCJncHQtNG9cIiwgXCJ0ZW1wZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3Bl
+      bkFJXCJ9IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgInRvb2xzX25hbWVzIjogW119
+      XUrMAgoKY3Jld190YXNrcxK9Agq6Alt7ImtleSI6ICIwZDY4NWEyMTk5NGQ5NDkwOTdiYzVhNTZk
+      NzM3ZTZkMSIsICJpZCI6ICI0M2JjZTUwNy0yZGJmLTRiMDMtYTIyMy0zYzMxMmU1MTI4YWQiLCAi
+      ZGVzY3JpcHRpb24iOiAiU2F5IEhpIiwgImV4cGVjdGVkX291dHB1dCI6ICJUaGUgd29yZDogSGki
+      LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
+      dF9yb2xlIjogIlJlc2VhcmNoZXIiLCAiYWdlbnRfa2V5IjogIjhiZDIxMzliNTk3NTE4MTUwNmU0
+      MWZkOWM0NTYzZDc1IiwgImNvbnRleHQiOiBudWxsLCAidG9vbHNfbmFtZXMiOiBbXX1dSioKCHBs
+      YXRmb3JtEh4KHG1hY09TLTE0LjEuMS1hcm02NC1hcm0tNjRiaXRKHAoQcGxhdGZvcm1fcmVsZWFz
+      ZRIICgYyMy4xLjBKGwoPcGxhdGZvcm1fc3lzdGVtEggKBkRhcndpbkp7ChBwbGF0Zm9ybV92ZXJz
+      aW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAyMy4xLjA6IE1vbiBPY3QgIDkgMjE6Mjc6MjQg
+      UERUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjQxLjl+Ni9SRUxFQVNFX0FSTTY0X1Q2MDAwSgoKBGNw
+      dXMSAhgKegIYAYUBAAEAABKOAgoQgFFdbbcq9b6XpdCgV4ygHxII5FvLDHBJWfYqDFRhc2sgQ3Jl
+      YXRlZDABOcB3Sce1xeIXQfDsSce1xeIXSi4KCGNyZXdfa2V5EiIKIDhjMjc1MmY0OWU1YjlkMmI2
+      OGNiMzVjYWM4ZmNjODZkSjEKB2NyZXdfaWQSJgokMDYxN2FmNTUtYTA2NC00MTAyLTliNDQtOGEx
+      OGJlZTQ1ODc4Si4KCHRhc2tfa2V5EiIKIDBkNjg1YTIxOTk0ZDk0OTA5N2JjNWE1NmQ3MzdlNmQx
+      SjEKB3Rhc2tfaWQSJgokNDNiY2U1MDctMmRiZi00YjAzLWEyMjMtM2MzMTJlNTEyOGFkegIYAYUB
+      AAEAABKQAgoQrD1woM4vvML78Ycv2kKJPBIIQiPC5tnfBsEqDlRhc2sgRXhlY3V0aW9uMAE5uB9K
+      x7XF4hdB0DoqyLXF4hdKLgoIY3Jld19rZXkSIgogOGMyNzUyZjQ5ZTViOWQyYjY4Y2IzNWNhYzhm
+      Y2M4NmRKMQoHY3Jld19pZBImCiQwNjE3YWY1NS1hMDY0LTQxMDItOWI0NC04YTE4YmVlNDU4NzhK
+      LgoIdGFza19rZXkSIgogMGQ2ODVhMjE5OTRkOTQ5MDk3YmM1YTU2ZDczN2U2ZDFKMQoHdGFza19p
+      ZBImCiQ0M2JjZTUwNy0yZGJmLTRiMDMtYTIyMy0zYzMxMmU1MTI4YWR6AhgBhQEAAQAAEskSChDy
+      v1twhKVTS2/hcmcIXG8LEginut5ahEsb9yoMQ3JldyBDcmVhdGVkMAE5eMNWyrXF4hdBUBFZyrXF
+      4hdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zNi4wShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEu
+      NUouCghjcmV3X2tleRIiCiBlM2ZkYTBmMzExMGZlODBiMTg5NDdjMDE0NzE0MzBhNEoxCgdjcmV3
+      X2lkEiYKJGJiZmUxOTdkLWFmM2QtNDUwYy04NzlhLWNkOWQyODQyYzk5NUoeCgxjcmV3X3Byb2Nl
+      c3MSDgoMaGllcmFyY2hpY2FsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90
+      YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAkrFCQoLY3Jld19hZ2VudHMStQkK
+      sglbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNzhi
+      YzU3YjgtYjBlOC00NmU3LTg5MjMtNDZkMmUxZDgyNDA3IiwgInJvbGUiOiAiUmVzZWFyY2hlciIs
+      ICJnb2FsIjogIk1ha2UgdGhlIGJlc3QgcmVzZWFyY2ggYW5kIGFuYWx5c2lzIG9uIGNvbnRlbnQg
+      YWJvdXQgQUkgYW5kIEFJIGFnZW50cyIsICJiYWNrc3RvcnkiOiAiWW91J3JlIGFuIGV4cGVydCBy
+      ZXNlYXJjaGVyLCBzcGVjaWFsaXplZCBpbiB0ZWNobm9sb2d5LCBzb2Z0d2FyZSBlbmdpbmVlcmlu
+      ZywgQUkgYW5kIHN0YXJ0dXBzLiBZb3Ugd29yayBhcyBhIGZyZWVsYW5jZXIgYW5kIGlzIG5vdyB3
+      b3JraW5nIG9uIGRvaW5nIHJlc2VhcmNoIGFuZCBhbmFseXNpcyBmb3IgYSBuZXcgY3VzdG9tZXIu
+      IiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRlciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJp
+      MThuIjogbnVsbCwgImxsbSI6ICJ7XCJuYW1lXCI6IG51bGwsIFwibW9kZWxfbmFtZVwiOiBcImdw
+      dC00b1wiLCBcInRlbXBlcmF0dXJlXCI6IDAuNywgXCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlcIn0i
+      LCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5
+      IjogIjlhNTAxNWVmNDg5NWRjNjI3OGQ1NDgxOGJhNDQ2YWY3IiwgImlkIjogIjk2YzIxOTk1LWFl
+      ZDItNGJjNC1iYjY4LTdiOTA3ZTYzYjQyNSIsICJyb2xlIjogIlNlbmlvciBXcml0ZXIiLCAiZ29h
+      bCI6ICJXcml0ZSB0aGUgYmVzdCBjb250ZW50IGFib3V0IEFJIGFuZCBBSSBhZ2VudHMuIiwgImJh
+      Y2tzdG9yeSI6ICJZb3UncmUgYSBzZW5pb3Igd3JpdGVyLCBzcGVjaWFsaXplZCBpbiB0ZWNobm9s
+      b2d5LCBzb2Z0d2FyZSBlbmdpbmVlcmluZywgQUkgYW5kIHN0YXJ0dXBzLiBZb3Ugd29yayBhcyBh
+      IGZyZWVsYW5jZXIgYW5kIGFyZSBub3cgd29ya2luZyBvbiB3cml0aW5nIGNvbnRlbnQgZm9yIGEg
+      bmV3IGN1c3RvbWVyLiIsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9y
+      cG0iOiBudWxsLCAiaTE4biI6IG51bGwsICJsbG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVs
+      X25hbWVcIjogXCJncHQtNG9cIiwgXCJ0ZW1wZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJD
+      aGF0T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiBmYWxzZSwgInRvb2xzX25hbWVz
+      IjogW119XUq/BAoKY3Jld190YXNrcxKwBAqtBFt7ImtleSI6ICI1ZmE2NWMwNmE5ZTMxZjJjNjk1
+      NDMyNjY4YWNkNjJkZCIsICJpZCI6ICJjNTFlMzZjZC1iMzc3LTRiMjMtOTY1ZC0xMjE4ZjAxN2Rl
+      NTkiLCAiZGVzY3JpcHRpb24iOiAiQ29tZSB1cCB3aXRoIGEgbGlzdCBvZiA1IGludGVyZXN0aW5n
+      IGlkZWFzIHRvIGV4cGxvcmUgZm9yIGFuIGFydGljbGUsIHRoZW4gd3JpdGUgb25lIGFtYXppbmcg
+      cGFyYWdyYXBoIGhpZ2hsaWdodCBmb3IgZWFjaCBpZGVhIHRoYXQgc2hvd2Nhc2VzIGhvdyBnb29k
+      IGFuIGFydGljbGUgYWJvdXQgdGhpcyB0b3BpYyBjb3VsZCBiZS4gUmV0dXJuIHRoZSBsaXN0IG9m
+      IGlkZWFzIHdpdGggdGhlaXIgcGFyYWdyYXBoIGFuZCB5b3VyIG5vdGVzLiIsICJleHBlY3RlZF9v
+      dXRwdXQiOiAiNSBidWxsZXQgcG9pbnRzIHdpdGggYSBwYXJhZ3JhcGggZm9yIGVhY2ggaWRlYS4i
+      LCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiaHVtYW5faW5wdXQ/IjogZmFsc2UsICJhZ2Vu
+      dF9yb2xlIjogIk5vbmUiLCAiYWdlbnRfa2V5IjogbnVsbCwgImNvbnRleHQiOiBudWxsLCAidG9v
+      bHNfbmFtZXMiOiBbXX1dSioKCHBsYXRmb3JtEh4KHG1hY09TLTE0LjEuMS1hcm02NC1hcm0tNjRi
+      aXRKHAoQcGxhdGZvcm1fcmVsZWFzZRIICgYyMy4xLjBKGwoPcGxhdGZvcm1fc3lzdGVtEggKBkRh
+      cndpbkp7ChBwbGF0Zm9ybV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAyMy4xLjA6
+      IE1vbiBPY3QgIDkgMjE6Mjc6MjQgUERUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjQxLjl+Ni9SRUxF
+      QVNFX0FSTTY0X1Q2MDAwSgoKBGNwdXMSAhgKegIYAYUBAAEAABLJEgoQC4ERVCPi0URQcsRKT+/y
+      GxIInSinsu8yhJsqDENyZXcgQ3JlYXRlZDABOcAcwM61xeIXQaiRws61xeIXShoKDmNyZXdhaV92
+      ZXJzaW9uEggKBjAuMzYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjVKLgoIY3Jld19rZXkS
+      IgogZTNmZGEwZjMxMTBmZTgwYjE4OTQ3YzAxNDcxNDMwYTRKMQoHY3Jld19pZBImCiQxMTUxYTA2
+      Zi02YjdhLTQzZGYtOWZjNi05MzJmYTYzY2RhZjRKHgoMY3Jld19wcm9jZXNzEg4KDGhpZXJhcmNo
+      aWNhbEoRCgtjcmV3X21lbW9yeRICEABKGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNy
+      ZXdfbnVtYmVyX29mX2FnZW50cxICGAJKxQkKC2NyZXdfYWdlbnRzErUJCrIJW3sia2V5IjogIjhi
+      ZDIxMzliNTk3NTE4MTUwNmU0MWZkOWM0NTYzZDc1IiwgImlkIjogIjc4YmM1N2I4LWIwZTgtNDZl
+      Ny04OTIzLTQ2ZDJlMWQ4MjQwNyIsICJyb2xlIjogIlJlc2VhcmNoZXIiLCAiZ29hbCI6ICJNYWtl
+      IHRoZSBiZXN0IHJlc2VhcmNoIGFuZCBhbmFseXNpcyBvbiBjb250ZW50IGFib3V0IEFJIGFuZCBB
+      SSBhZ2VudHMiLCAiYmFja3N0b3J5IjogIllvdSdyZSBhbiBleHBlcnQgcmVzZWFyY2hlciwgc3Bl
+      Y2lhbGl6ZWQgaW4gdGVjaG5vbG9neSwgc29mdHdhcmUgZW5naW5lZXJpbmcsIEFJIGFuZCBzdGFy
+      dHVwcy4gWW91IHdvcmsgYXMgYSBmcmVlbGFuY2VyIGFuZCBpcyBub3cgd29ya2luZyBvbiBkb2lu
+      ZyByZXNlYXJjaCBhbmQgYW5hbHlzaXMgZm9yIGEgbmV3IGN1c3RvbWVyLiIsICJ2ZXJib3NlPyI6
+      IGZhbHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6IG51bGwsICJs
+      bG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNG9cIiwgXCJ0ZW1w
+      ZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25f
+      ZW5hYmxlZD8iOiBmYWxzZSwgInRvb2xzX25hbWVzIjogW119LCB7ImtleSI6ICI5YTUwMTVlZjQ4
+      OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJpZCI6ICI5NmMyMTk5NS1hZWQyLTRiYzQtYmI2OC03
+      YjkwN2U2M2I0MjUiLCAicm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwgImdvYWwiOiAiV3JpdGUgdGhl
+      IGJlc3QgY29udGVudCBhYm91dCBBSSBhbmQgQUkgYWdlbnRzLiIsICJiYWNrc3RvcnkiOiAiWW91
+      J3JlIGEgc2VuaW9yIHdyaXRlciwgc3BlY2lhbGl6ZWQgaW4gdGVjaG5vbG9neSwgc29mdHdhcmUg
+      ZW5naW5lZXJpbmcsIEFJIGFuZCBzdGFydHVwcy4gWW91IHdvcmsgYXMgYSBmcmVlbGFuY2VyIGFu
+      ZCBhcmUgbm93IHdvcmtpbmcgb24gd3JpdGluZyBjb250ZW50IGZvciBhIG5ldyBjdXN0b21lci4i
+      LCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVsbCwgImkx
+      OG4iOiBudWxsLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6IFwiZ3B0
+      LTRvXCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5BSVwifSIs
+      ICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogZmFsc2UsICJ0b29sc19uYW1lcyI6IFtdfV1KvwQKCmNy
+      ZXdfdGFza3MSsAQKrQRbeyJrZXkiOiAiNWZhNjVjMDZhOWUzMWYyYzY5NTQzMjY2OGFjZDYyZGQi
+      LCAiaWQiOiAiMDIzOGY1NWUtZTMwYy00MDIwLWE0ZmQtNWY2ZmUzNjE1NjA4IiwgImRlc2NyaXB0
+      aW9uIjogIkNvbWUgdXAgd2l0aCBhIGxpc3Qgb2YgNSBpbnRlcmVzdGluZyBpZGVhcyB0byBleHBs
+      b3JlIGZvciBhbiBhcnRpY2xlLCB0aGVuIHdyaXRlIG9uZSBhbWF6aW5nIHBhcmFncmFwaCBoaWdo
+      bGlnaHQgZm9yIGVhY2ggaWRlYSB0aGF0IHNob3djYXNlcyBob3cgZ29vZCBhbiBhcnRpY2xlIGFi
+      b3V0IHRoaXMgdG9waWMgY291bGQgYmUuIFJldHVybiB0aGUgbGlzdCBvZiBpZGVhcyB3aXRoIHRo
+      ZWlyIHBhcmFncmFwaCBhbmQgeW91ciBub3Rlcy4iLCAiZXhwZWN0ZWRfb3V0cHV0IjogIjUgYnVs
+      bGV0IHBvaW50cyB3aXRoIGEgcGFyYWdyYXBoIGZvciBlYWNoIGlkZWEuIiwgImFzeW5jX2V4ZWN1
+      dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJOb25l
+      IiwgImFnZW50X2tleSI6IG51bGwsICJjb250ZXh0IjogbnVsbCwgInRvb2xzX25hbWVzIjogW119
+      XUoqCghwbGF0Zm9ybRIeChxtYWNPUy0xNC4xLjEtYXJtNjQtYXJtLTY0Yml0ShwKEHBsYXRmb3Jt
+      X3JlbGVhc2USCAoGMjMuMS4wShsKD3BsYXRmb3JtX3N5c3RlbRIICgZEYXJ3aW5KewoQcGxhdGZv
+      cm1fdmVyc2lvbhJnCmVEYXJ3aW4gS2VybmVsIFZlcnNpb24gMjMuMS4wOiBNb24gT2N0ICA5IDIx
+      OjI3OjI0IFBEVCAyMDIzOyByb290OnhudS0xMDAwMi40MS45fjYvUkVMRUFTRV9BUk02NF9UNjAw
+      MEoKCgRjcHVzEgIYCnoCGAGFAQABAAASwRUKEK+2FWN+LUsj3/10yDBx5MMSCPaor0csAVI6KgxD
+      cmV3IENyZWF0ZWQwATlwEcXPtcXiF0FQscfPtcXiF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjM2
+      LjBKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS41Si4KCGNyZXdfa2V5EiIKIGQzODQ2YzlkMjc2
+      ZThlNmU0M2UzMWY2MTc2MzU3YjRmSjEKB2NyZXdfaWQSJgokYzE0MGJlNTgtOTJjZS00YzQyLWJk
+      YjQtOThjNTlmMGUzYzAxShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVt
+      b3J5EgIQAEoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAJKGwoVY3Jld19udW1iZXJfb2ZfYWdl
+      bnRzEgIYAkrFCQoLY3Jld19hZ2VudHMStQkKsglbeyJrZXkiOiAiOGJkMjEzOWI1OTc1MTgxNTA2
+      ZTQxZmQ5YzQ1NjNkNzUiLCAiaWQiOiAiNzhiYzU3YjgtYjBlOC00NmU3LTg5MjMtNDZkMmUxZDgy
+      NDA3IiwgInJvbGUiOiAiUmVzZWFyY2hlciIsICJnb2FsIjogIk1ha2UgdGhlIGJlc3QgcmVzZWFy
+      Y2ggYW5kIGFuYWx5c2lzIG9uIGNvbnRlbnQgYWJvdXQgQUkgYW5kIEFJIGFnZW50cyIsICJiYWNr
+      c3RvcnkiOiAiWW91J3JlIGFuIGV4cGVydCByZXNlYXJjaGVyLCBzcGVjaWFsaXplZCBpbiB0ZWNo
+      bm9sb2d5LCBzb2Z0d2FyZSBlbmdpbmVlcmluZywgQUkgYW5kIHN0YXJ0dXBzLiBZb3Ugd29yayBh
+      cyBhIGZyZWVsYW5jZXIgYW5kIGlzIG5vdyB3b3JraW5nIG9uIGRvaW5nIHJlc2VhcmNoIGFuZCBh
+      bmFseXNpcyBmb3IgYSBuZXcgY3VzdG9tZXIuIiwgInZlcmJvc2U/IjogZmFsc2UsICJtYXhfaXRl
+      ciI6IDI1LCAibWF4X3JwbSI6IG51bGwsICJpMThuIjogbnVsbCwgImxsbSI6ICJ7XCJuYW1lXCI6
+      IG51bGwsIFwibW9kZWxfbmFtZVwiOiBcImdwdC00b1wiLCBcInRlbXBlcmF0dXJlXCI6IDAuNywg
+      XCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlcIn0iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNl
+      LCAidG9vbHNfbmFtZXMiOiBbXX0sIHsia2V5IjogIjlhNTAxNWVmNDg5NWRjNjI3OGQ1NDgxOGJh
+      NDQ2YWY3IiwgImlkIjogIjk2YzIxOTk1LWFlZDItNGJjNC1iYjY4LTdiOTA3ZTYzYjQyNSIsICJy
+      b2xlIjogIlNlbmlvciBXcml0ZXIiLCAiZ29hbCI6ICJXcml0ZSB0aGUgYmVzdCBjb250ZW50IGFi
+      b3V0IEFJIGFuZCBBSSBhZ2VudHMuIiwgImJhY2tzdG9yeSI6ICJZb3UncmUgYSBzZW5pb3Igd3Jp
+      dGVyLCBzcGVjaWFsaXplZCBpbiB0ZWNobm9sb2d5LCBzb2Z0d2FyZSBlbmdpbmVlcmluZywgQUkg
+      YW5kIHN0YXJ0dXBzLiBZb3Ugd29yayBhcyBhIGZyZWVsYW5jZXIgYW5kIGFyZSBub3cgd29ya2lu
+      ZyBvbiB3cml0aW5nIGNvbnRlbnQgZm9yIGEgbmV3IGN1c3RvbWVyLiIsICJ2ZXJib3NlPyI6IGZh
+      bHNlLCAibWF4X2l0ZXIiOiAyNSwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6IG51bGwsICJsbG0i
+      OiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNG9cIiwgXCJ0ZW1wZXJh
+      dHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25fZW5h
+      YmxlZD8iOiBmYWxzZSwgInRvb2xzX25hbWVzIjogW119XUq5BwoKY3Jld190YXNrcxKqBwqnB1t7
+      ImtleSI6ICJlOWU2YjcyYWFjMzI2NDU5ZGQ3MDY4ZjBiMTcxN2MxYyIsICJpZCI6ICI5NWE1NzQz
+      Yy1lMjRmLTQ4ODItYmQ3Mi02ZmZlZjViYTMzNTYiLCAiZGVzY3JpcHRpb24iOiAiR2VuZXJhdGUg
+      YSBsaXN0IG9mIDUgaW50ZXJlc3RpbmcgaWRlYXMgdG8gZXhwbG9yZSBmb3IgYW4gYXJ0aWNsZSwg
+      d2hlcmUgZWFjaCBidWxsZXRwb2ludCBpcyB1bmRlciAxNSB3b3Jkcy4iLCAiZXhwZWN0ZWRfb3V0
+      cHV0IjogIkJ1bGxldCBwb2ludCBsaXN0IG9mIDUgaW1wb3J0YW50IGV2ZW50cy4gTm8gYWRkaXRp
+      b25hbCBjb21tZW50YXJ5LiIsICJhc3luY19leGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1
+      dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAiUmVzZWFyY2hlciIsICJhZ2VudF9rZXkiOiAiOGJk
+      MjEzOWI1OTc1MTgxNTA2ZTQxZmQ5YzQ1NjNkNzUiLCAiY29udGV4dCI6IG51bGwsICJ0b29sc19u
+      YW1lcyI6IFtdfSwgeyJrZXkiOiAiZWVlZTdlNzNkNWRmNjZkNDhkMmQ4MDdiYWZmODc0ZjMiLCAi
+      aWQiOiAiNzA4MGY4M2YtNmQ1Zi00MzM0LTgwZTctODI3NzEzNmQ4ZDdkIiwgImRlc2NyaXB0aW9u
+      IjogIldyaXRlIGEgc2VudGVuY2UgYWJvdXQgdGhlIGV2ZW50cyIsICJleHBlY3RlZF9vdXRwdXQi
+      OiAiQSBzZW50ZW5jZSBhYm91dCB0aGUgZXZlbnRzIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxz
+      ZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJTZW5pb3IgV3JpdGVyIiwg
+      ImFnZW50X2tleSI6ICI5YTUwMTVlZjQ4OTVkYzYyNzhkNTQ4MThiYTQ0NmFmNyIsICJjb250ZXh0
+      IjogWyJHZW5lcmF0ZSBhIGxpc3Qgb2YgNSBpbnRlcmVzdGluZyBpZGVhcyB0byBleHBsb3JlIGZv
+      ciBhbiBhcnRpY2xlLCB3aGVyZSBlYWNoIGJ1bGxldHBvaW50IGlzIHVuZGVyIDE1IHdvcmRzLiJd
+      LCAidG9vbHNfbmFtZXMiOiBbXX1dSioKCHBsYXRmb3JtEh4KHG1hY09TLTE0LjEuMS1hcm02NC1h
+      cm0tNjRiaXRKHAoQcGxhdGZvcm1fcmVsZWFzZRIICgYyMy4xLjBKGwoPcGxhdGZvcm1fc3lzdGVt
+      EggKBkRhcndpbkp7ChBwbGF0Zm9ybV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAy
+      My4xLjA6IE1vbiBPY3QgIDkgMjE6Mjc6MjQgUERUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjQxLjl+
+      Ni9SRUxFQVNFX0FSTTY0X1Q2MDAwSgoKBGNwdXMSAhgKegIYAYUBAAEAABKxCwoQrufF6FYNBLX1
+      X9l1YHzEsBIIg+LU+V/XPr0qDENyZXcgQ3JlYXRlZDABOYhBV9K1xeIXQcB/WdK1xeIXShoKDmNy
+      ZXdhaV92ZXJzaW9uEggKBjAuMzYuMEoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjVKLgoIY3Jl
+      d19rZXkSIgogNjczOGFkNWI4Y2IzZTZmMWMxYzkzNTBiOTZjMmU2NzhKMQoHY3Jld19pZBImCiQw
+      ZDFjYjk0Yy1kMjgyLTQwYWUtYWVlYy0yN2JjNzc1NGZmOThKHAoMY3Jld19wcm9jZXNzEgwKCnNl
+      cXVlbnRpYWxKEQoLY3Jld19tZW1vcnkSAhAAShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYAUob
+      ChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSuEDCgtjcmV3X2FnZW50cxLRAwrOA1t7ImtleSI6
+      ICI1MTJhNmRjMzc5ZjY2YjIxZWVhYjI0ZTYzNDgzNmY3MiIsICJpZCI6ICJjOTMwNzU2OS05OTRl
+      LTRkMTItYWI5OS01NzlhYjZhNDMyMDkiLCAicm9sZSI6ICJDb250ZW50IFdyaXRlciIsICJnb2Fs
+      IjogIldyaXRlIGVuZ2FnaW5nIGNvbnRlbnQgb24gdmFyaW91cyB0b3BpY3MuIiwgImJhY2tzdG9y
+      eSI6ICJZb3UgaGF2ZSBhIGJhY2tncm91bmQgaW4gam91cm5hbGlzbSBhbmQgY3JlYXRpdmUgd3Jp
+      dGluZy4iLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMjUsICJtYXhfcnBtIjogbnVs
+      bCwgImkxOG4iOiBudWxsLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6
+      IFwiZ3B0LTRvXCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5B
+      SVwifSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogdHJ1ZSwgInRvb2xzX25hbWVzIjogW119XUqN
+      AwoKY3Jld190YXNrcxL+Agr7Alt7ImtleSI6ICIzNDc3MDc2YmUzYWY3MTMwNDYyZWRhYTJlYjhh
+      MDQ4ZSIsICJpZCI6ICI4NDMxNmNhOS05ZDNmLTRkZjctODQ4OC0zMDBmNDMxYWE1MDgiLCAiZGVz
+      Y3JpcHRpb24iOiAiV3JpdGUgYSBkZXRhaWxlZCBhcnRpY2xlIGFib3V0IEFJIGluIGhlYWx0aGNh
+      cmUuIiwgImV4cGVjdGVkX291dHB1dCI6ICJBIDEgcGFyYWdyYXBoIGFydGljbGUgYWJvdXQgQUku
+      IiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImh1bWFuX2lucHV0PyI6IGZhbHNlLCAiYWdl
+      bnRfcm9sZSI6ICJDb250ZW50IFdyaXRlciIsICJhZ2VudF9rZXkiOiAiNTEyYTZkYzM3OWY2NmIy
+      MWVlYWIyNGU2MzQ4MzZmNzIiLCAiY29udGV4dCI6IG51bGwsICJ0b29sc19uYW1lcyI6IFtdfV1K
+      KgoIcGxhdGZvcm0SHgocbWFjT1MtMTQuMS4xLWFybTY0LWFybS02NGJpdEocChBwbGF0Zm9ybV9y
+      ZWxlYXNlEggKBjIzLjEuMEobCg9wbGF0Zm9ybV9zeXN0ZW0SCAoGRGFyd2luSnsKEHBsYXRmb3Jt
+      X3ZlcnNpb24SZwplRGFyd2luIEtlcm5lbCBWZXJzaW9uIDIzLjEuMDogTW9uIE9jdCAgOSAyMToy
+      NzoyNCBQRFQgMjAyMzsgcm9vdDp4bnUtMTAwMDIuNDEuOX42L1JFTEVBU0VfQVJNNjRfVDYwMDBK
+      CgoEY3B1cxICGAp6AhgBhQEAAQAA
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, br
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '23733'
+      Content-Type:
+      - application/x-protobuf
+      User-Agent:
+      - OTel-OTLP-Exporter-Python/1.25.0
+    method: POST
+    uri: https://telemetry.crewai.com:4319/v1/traces
+  response:
+    body:
+      string: "\n\0"
+    headers:
+      Content-Length:
+      - '2'
+      Content-Type:
+      - application/x-protobuf
+      Date:
+      - Tue, 16 Jul 2024 18:43:12 GMT
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_replay_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", "logprobs": false,
+      "n": 1, "stop": ["\nObservation"], "stream": true, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '929'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.36.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.36.0
+      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-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"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-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        give"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        a"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_c4e5b6fa31","choices":[{"index":0,"delta":{"content":"
+        Hi"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9n6wPAClsh4tUGoLYKLh3VoX1vlAx","object":"chat.completion.chunk","created":1721491781,"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:
+      - 8a643791a80e8c96-EWR
+      Connection:
+      - keep-alive
+      Content-Type:
+      - text/event-stream; charset=utf-8
+      Date:
+      - Sat, 20 Jul 2024 16:09:41 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=cam5sECdaTzbttLIOaiuvh9flDIAXp_FLPODnDEOn6k-1721491781-1.0.1.1-hyFl43P7HIWZsGueyWuDeO579sZ41as2mvrM.cQS1E8KSLG2ZZ0DxDGbVvHYRO0eflTUJohgZu6CGltvjQfMtQ;
+        path=/; expires=Sat, 20-Jul-24 16:39:41 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=nmlgS.bqXAu0rZ.OlHPfXrIrdnVgrBSW3e0UuU3N5ng-1721491781661-0.0.1.1-604800000;
+        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:
+      - '126'
+      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:
+      - '29999794'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_31484eeb0af939af4e0d9c47441ba2db
+    status:
+      code: 200
+      message: OK
+version: 1

tests/cassettes/test_tool_usage_information_is_appended_to_agent.yaml

@@ -20,7 +20,7 @@ interactions:
       accept:
       - application/json
       accept-encoding:
-      - gzip, deflate, br
+      - gzip, deflate
       connection:
       - keep-alive
       content-length:
@@ -44,80 +44,103 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.11.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"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-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"I"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        I"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         need"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         to"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
-        decide"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        choose"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
-        on"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         an"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         appropriate"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         greeting"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        to"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        make"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        everyone"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        feel"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        welcome"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         Decide"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         Greetings"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"Action"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
         Input"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
-        {}\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{"content":"
+        {}"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWRAEA0akLHaVsdYQP1dYZ73QJC","object":"chat.completion.chunk","created":1720137083,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9kFn5wBmr3LxGG62NXc5GVlHvdhYu","object":"chat.completion.chunk","created":1720810815,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_298125635f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -128,20 +151,20 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 89e305e3c8e382f5-GIG
+      - 8a23466b68c6da17-MIA
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Thu, 04 Jul 2024 23:51:24 GMT
+      - Fri, 12 Jul 2024 19:00:15 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=y7BtDW9RWNaYoBExulKsMw50ppqr1itieWbcStDWqVc-1720137084-1.0.1.1-EYCEQ9jOimP45.FgXjdzWftUrV1HHm49W4wbcxFhbrj2DVC1LnMbz9.l.c._AqBRgFAE3xVolosvjmoFDAMPYQ;
-        path=/; expires=Fri, 05-Jul-24 00:21:24 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=5Q4fR7Axcb9pOI3.xD7MckzP6nvjl7aUGw1NJkxLXiY-1720810815-1.0.1.1-nBCqeg7gu9__SL5Jstz.kPKlKOisvW1iKhTWpyXfY.wyoYUCxPPcaOkFtXjn4wZuibClBrGVEsFDAAuB1Jwj1g;
+        path=/; expires=Fri, 12-Jul-24 19:30:15 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=pZBoWQ1_gTeUh2oe6ta.S2mxWtdaHvAtn6m2HszLdwk-1720137084219-0.0.1.1-604800000;
+      - _cfuvid=VtZy6_mT_xZheA53qWxlfPk4NhcrOjGYsGlKoh66LSw-1720810815947-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -150,7 +173,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '335'
+      - '537'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -158,17 +181,17 @@ interactions:
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '16000000'
+      - '22000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '15999700'
+      - '21999701'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 1ms
+      - 0s
       x-request-id:
-      - req_b3f7e3c47df2641d6bef704ef3ae8a0f
+      - req_1b582ffd4f0b3972542c2dff29ded287
     status:
       code: 200
       message: OK
@@ -187,24 +210,24 @@ interactions:
       greeting.\n\nThis is the expect criteria for your final answer: The greeting.
       \n you MUST return the actual complete content as the final answer, not a summary.\n\nBegin!
       This is VERY important to you, use the tools available and give your best Final
-      Answer, your job depends on it!\n\nThought:\nI need to decide on an appropriate
-      greeting.\n\nAction: Decide Greetings\nAction Input: {}\n\nObservation: Howdy!\n",
-      "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"], "stream":
-      true, "temperature": 0.7}'
+      Answer, your job depends on it!\n\nThought:\nThought: I need to choose an appropriate
+      greeting to make everyone feel welcome.\nAction: Decide Greetings\nAction Input:
+      {}\nObservation: Howdy!\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:
-      - '1404'
+      - '1436'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=y7BtDW9RWNaYoBExulKsMw50ppqr1itieWbcStDWqVc-1720137084-1.0.1.1-EYCEQ9jOimP45.FgXjdzWftUrV1HHm49W4wbcxFhbrj2DVC1LnMbz9.l.c._AqBRgFAE3xVolosvjmoFDAMPYQ;
-        _cfuvid=pZBoWQ1_gTeUh2oe6ta.S2mxWtdaHvAtn6m2HszLdwk-1720137084219-0.0.1.1-604800000
+      - __cf_bm=5Q4fR7Axcb9pOI3.xD7MckzP6nvjl7aUGw1NJkxLXiY-1720810815-1.0.1.1-nBCqeg7gu9__SL5Jstz.kPKlKOisvW1iKhTWpyXfY.wyoYUCxPPcaOkFtXjn4wZuibClBrGVEsFDAAuB1Jwj1g;
+        _cfuvid=VtZy6_mT_xZheA53qWxlfPk4NhcrOjGYsGlKoh66LSw-1720810815947-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
@@ -222,68 +245,68 @@ interactions:
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.9
+      - 3.11.7
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         now"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         know"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         the"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":".\n\n"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":".\n"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         Answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"
         How"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"dy"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"dy"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{"content":"!"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9hQWSD5B35ANI9JLmbxUdPECfNd43","object":"chat.completion.chunk","created":1720137084,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_ce0793330f","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9kFn6xVncEzHOGdnzGN9R8fMONMEi","object":"chat.completion.chunk","created":1720810816,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_dd932ca5d1","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -294,13 +317,13 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 89e305ea4abc82f5-GIG
+      - 8a234672c9fbda17-MIA
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Thu, 04 Jul 2024 23:51:24 GMT
+      - Fri, 12 Jul 2024 19:00:16 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -310,7 +333,7 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '91'
+      - '122'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -318,17 +341,17 @@ interactions:
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '16000000'
+      - '22000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '15999673'
+      - '21999666'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 1ms
+      - 0s
       x-request-id:
-      - req_10032db16fa190e8435947a6aaa700ff
+      - req_484dde23b57ef3f715ab183690fe73b9
     status:
       code: 200
       message: OK

tests/cli/cli_test.py

@@ -3,7 +3,7 @@ from unittest import mock
 import pytest
 from click.testing import CliRunner
 
-from crewai.cli.cli import train, version
+from crewai.cli.cli import train, version, reset_memories
 
 
 @pytest.fixture
@@ -41,6 +41,82 @@ def test_train_invalid_string_iterations(train_crew, runner):
     )
 
 
+@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
+@mock.patch("crewai.cli.reset_memories_command.EntityMemory")
+@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
+@mock.patch("crewai.cli.reset_memories_command.TaskOutputStorageHandler")
+def test_reset_all_memories(
+    MockTaskOutputStorageHandler,
+    MockLongTermMemory,
+    MockEntityMemory,
+    MockShortTermMemory,
+    runner,
+):
+    result = runner.invoke(reset_memories, ["--all"])
+    MockShortTermMemory().reset.assert_called_once()
+    MockEntityMemory().reset.assert_called_once()
+    MockLongTermMemory().reset.assert_called_once()
+    MockTaskOutputStorageHandler().reset.assert_called_once()
+
+    assert result.output == "All memories have been reset.\n"
+
+
+@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
+def test_reset_short_term_memories(MockShortTermMemory, runner):
+    result = runner.invoke(reset_memories, ["-s"])
+    MockShortTermMemory().reset.assert_called_once()
+    assert result.output == "Short term memory has been reset.\n"
+
+
+@mock.patch("crewai.cli.reset_memories_command.EntityMemory")
+def test_reset_entity_memories(MockEntityMemory, runner):
+    result = runner.invoke(reset_memories, ["-e"])
+    MockEntityMemory().reset.assert_called_once()
+    assert result.output == "Entity memory has been reset.\n"
+
+
+@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
+def test_reset_long_term_memories(MockLongTermMemory, runner):
+    result = runner.invoke(reset_memories, ["-l"])
+    MockLongTermMemory().reset.assert_called_once()
+    assert result.output == "Long term memory has been reset.\n"
+
+
+@mock.patch("crewai.cli.reset_memories_command.TaskOutputStorageHandler")
+def test_reset_kickoff_outputs(MockTaskOutputStorageHandler, runner):
+    result = runner.invoke(reset_memories, ["-k"])
+    MockTaskOutputStorageHandler().reset.assert_called_once()
+    assert result.output == "Latest Kickoff outputs stored has been reset.\n"
+
+
+@mock.patch("crewai.cli.reset_memories_command.ShortTermMemory")
+@mock.patch("crewai.cli.reset_memories_command.LongTermMemory")
+def test_reset_multiple_memory_flags(MockShortTermMemory, MockLongTermMemory, runner):
+    result = runner.invoke(
+        reset_memories,
+        [
+            "-s",
+            "-l",
+        ],
+    )
+    MockShortTermMemory().reset.assert_called_once()
+    MockLongTermMemory().reset.assert_called_once()
+    assert (
+        result.output
+        == "Long term memory has been reset.\nShort term memory has been reset.\n"
+    )
+
+
+def test_reset_no_memory_flags(runner):
+    result = runner.invoke(
+        reset_memories,
+    )
+    assert (
+        result.output
+        == "Please specify at least one memory type to reset using the appropriate flags.\n"
+    )
+
+
 def test_version_command(runner):
     result = runner.invoke(version)
 

tests/crew_test.py

@@ -1,14 +1,13 @@
 """Test Agent creation and execution basic functionality."""
 
-import os
+import hashlib
 import json
 from concurrent.futures import Future
 from unittest import mock
-from unittest.mock import patch
+from unittest.mock import MagicMock, patch
 
 import pydantic_core
 import pytest
-
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -16,10 +15,11 @@ from crewai.crews.crew_output import CrewOutput
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
 from crewai.task import Task
+from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.output_format import OutputFormat
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities import Logger, RPMController
-from crewai.utilities.constants import CREW_TASKS_OUTPUT_FILE
+from crewai.utilities.task_output_storage_handler import TaskOutputStorageHandler
 
 ceo = Agent(
     role="CEO",
@@ -286,7 +286,7 @@ def test_hierarchical_process():
     crew = Crew(
         agents=[researcher, writer],
         process=Process.hierarchical,
-        manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
+        manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
         tasks=[task],
     )
 
@@ -312,6 +312,82 @@ def test_manager_llm_requirement_for_hierarchical_process():
         )
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_manager_agent_delegating_to_assigned_task_agent():
+    """
+    Test that the manager agent delegates to the assigned task agent.
+    """
+    from langchain_openai import ChatOpenAI
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
+        tasks=[task],
+    )
+
+    crew.kickoff()
+
+    # Check if the manager agent has the correct tools
+    assert crew.manager_agent is not None
+    assert crew.manager_agent.tools is not None
+
+    assert len(crew.manager_agent.tools) == 2
+    assert (
+        "Delegate a specific task to one of the following coworkers: Researcher\n"
+        in crew.manager_agent.tools[0].description
+    )
+    assert (
+        "Ask a specific question to one of the following coworkers: Researcher\n"
+        in crew.manager_agent.tools[1].description
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_manager_agent_delegating_to_all_agents():
+    """
+    Test that the manager agent delegates to all agents when none are specified.
+    """
+    from langchain_openai import ChatOpenAI
+
+    task = Task(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.hierarchical,
+        manager_llm=ChatOpenAI(temperature=0, model="gpt-4o"),
+        tasks=[task],
+    )
+
+    crew.kickoff()
+
+    assert crew.manager_agent is not None
+    assert crew.manager_agent.tools is not None
+
+    assert len(crew.manager_agent.tools) == 2
+    print(
+        "crew.manager_agent.tools[0].description",
+        crew.manager_agent.tools[0].description,
+    )
+    assert (
+        "Delegate a specific task to one of the following coworkers: Researcher, Senior Writer\n"
+        in crew.manager_agent.tools[0].description
+    )
+    assert (
+        "Ask a specific question to one of the following coworkers: Researcher, Senior Writer\n"
+        in crew.manager_agent.tools[1].description
+    )
+
+
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents():
     tasks = [
@@ -917,9 +993,7 @@ async def test_kickoff_async_basic_functionality_and_output():
 @pytest.mark.vcr(filter_headers=["authorization"])
 @pytest.mark.asyncio
 async def test_async_kickoff_for_each_async_basic_functionality_and_output():
-    """Tests the basic functionality and output of akickoff_for_each_async."""
-    from unittest.mock import patch
-
+    """Tests the basic functionality and output of kickoff_for_each_async."""
     inputs = [
         {"topic": "dog"},
         {"topic": "cat"},
@@ -945,8 +1019,13 @@ async def test_async_kickoff_for_each_async_basic_functionality_and_output():
         agent=agent,
     )
 
+    async def mock_kickoff_async(**kwargs):
+        input_data = kwargs.get("inputs")
+        index = [input_["topic"] for input_ in inputs].index(input_data["topic"])
+        return expected_outputs[index]
+
     with patch.object(
-        Crew, "kickoff_async", side_effect=expected_outputs
+        Crew, "kickoff_async", side_effect=mock_kickoff_async
     ) as mock_kickoff_async:
         crew = Crew(agents=[agent], tasks=[task])
 
@@ -1270,7 +1349,7 @@ def test_hierarchical_crew_creation_tasks_with_agents():
     assert crew.manager_agent.tools is not None
     print("TOOL DESCRIPTION", crew.manager_agent.tools[0].description)
     assert crew.manager_agent.tools[0].description.startswith(
-        "Delegate a specific task to one of the following coworkers: [Senior Writer, Researcher]"
+        "Delegate a specific task to one of the following coworkers: Senior Writer"
     )
 
 
@@ -1355,6 +1434,7 @@ def test_crew_inputs_interpolate_both_agents_and_tasks_diff():
                 interpolate_task_inputs.assert_called()
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_does_not_interpolate_without_inputs():
     from unittest.mock import patch
 
@@ -1837,13 +1917,13 @@ def test_replay_feature():
         )
 
         crew.kickoff()
-        crew.replay_from_task(str(write.id))
+        crew.replay(str(write.id))
         # Ensure context was passed correctly
         assert mock_execute_task.call_count == 3
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_replay_from_task_error():
+def test_crew_replay_error():
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article",
         expected_output="5 bullet points with a paragraph for each idea.",
@@ -1856,12 +1936,12 @@ def test_crew_replay_from_task_error():
     )
 
     with pytest.raises(TypeError) as e:
-        crew.replay_from_task()  # type: ignore purposefully throwing err
+        crew.replay()  # type: ignore purposefully throwing err
         assert "task_id is required" in str(e)
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_crew_task_output_file_creation():
+def test_crew_task_db_init():
     agent = Agent(
         role="Content Writer",
         goal="Write engaging content on various topics.",
@@ -1889,46 +1969,13 @@ def test_crew_task_output_file_creation():
 
         crew.kickoff()
 
-        # Check if the crew_tasks_output.json file is created
-        assert os.path.exists(CREW_TASKS_OUTPUT_FILE)
-
-        # Clean up the file after test
-        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
-            os.remove(CREW_TASKS_OUTPUT_FILE)
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_replay_without_output_tasks_json():
-    agent = Agent(
-        role="Technical Writer",
-        goal="Write detailed technical documentation.",
-        backstory="You have a background in software engineering and technical writing.",
-    )
-
-    task = Task(
-        description="Document the process of setting up a Python project.",
-        expected_output="A step-by-step guide on setting up a Python project.",
-        agent=agent,
-    )
-
-    crew = Crew(agents=[agent], tasks=[task])
-
-    with patch.object(Task, "execute_sync") as mock_execute_task:
-        mock_execute_task.return_value = TaskOutput(
-            description="Document the process of setting up a Python project.",
-            raw="To set up a Python project, first create a virtual environment...",
-            agent="Technical Writer",
-            json_dict=None,
-            output_format=OutputFormat.RAW,
-            pydantic=None,
-            summary="Document the process of setting up a Python project...",
-        )
-
-        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
-            os.remove(CREW_TASKS_OUTPUT_FILE)
-
-        with pytest.raises(ValueError):
-            crew.replay_from_task(str(task.id))
+        # Check if this runs without raising an exception
+        try:
+            db_handler = TaskOutputStorageHandler()
+            db_handler.load()
+            assert True  # If we reach this point, no exception was raised
+        except Exception as e:
+            pytest.fail(f"An exception was raised: {str(e)}")
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -2018,23 +2065,20 @@ def test_replay_task_with_context():
         ]
 
         crew.kickoff()
+        db_handler = TaskOutputStorageHandler()
+        assert db_handler.load() != []
 
-        # Check if the crew_tasks_output.json file is created
-        assert os.path.exists(CREW_TASKS_OUTPUT_FILE)
-
-        # Replay task4 and ensure it uses task1's context properly
         with patch.object(Task, "execute_sync") as mock_replay_task:
             mock_replay_task.return_value = mock_task_output4
 
-            replayed_output = crew.replay_from_task(str(task4.id))
+            replayed_output = crew.replay(str(task4.id))
             assert replayed_output.raw == "Presentation on AI advancements..."
 
-        # Clean up the file after test
-        if os.path.exists(CREW_TASKS_OUTPUT_FILE):
-            os.remove(CREW_TASKS_OUTPUT_FILE)
+        db_handler.reset()
 
 
-def test_replay_from_task_with_context():
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_replay_with_context():
     agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
     task1 = Task(
         description="Context Task", expected_output="Say Task Output", agent=agent
@@ -2056,7 +2100,7 @@ def test_replay_from_task_with_context():
     crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
 
     with patch(
-        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        "crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
         return_value=[
             {
                 "task_id": str(task1.id),
@@ -2086,7 +2130,7 @@ def test_replay_from_task_with_context():
             },
         ],
     ):
-        crew.replay_from_task(str(task2.id))
+        crew.replay(str(task2.id))
 
         assert crew.tasks[1].context[0].output.raw == "context raw output"
 
@@ -2114,7 +2158,7 @@ def test_replay_with_invalid_task_id():
     crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
 
     with patch(
-        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        "crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
         return_value=[
             {
                 "task_id": str(task1.id),
@@ -2148,9 +2192,10 @@ def test_replay_with_invalid_task_id():
             ValueError,
             match="Task with id bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d not found in the crew's tasks.",
         ):
-            crew.replay_from_task("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
+            crew.replay("bf5b09c9-69bd-4eb8-be12-f9e5bae31c2d")
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 @patch.object(Crew, "_interpolate_inputs")
 def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
     agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
@@ -2176,7 +2221,7 @@ def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
     crew.kickoff(inputs={"name": "John"})
 
     with patch(
-        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        "crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
         return_value=[
             {
                 "task_id": str(task1.id),
@@ -2206,13 +2251,13 @@ def test_replay_interpolates_inputs_properly(mock_interpolate_inputs):
             },
         ],
     ):
-        crew.replay_from_task(str(task2.id))
+        crew.replay(str(task2.id))
         assert crew._inputs == {"name": "John"}
         assert mock_interpolate_inputs.call_count == 2
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
-def test_replay_from_task_setup_context():
+def test_replay_setup_context():
     agent = Agent(role="test_agent", backstory="Test Description", goal="Test Goal")
     task1 = Task(description="Context Task", expected_output="Say {name}", agent=agent)
     task2 = Task(
@@ -2231,7 +2276,7 @@ def test_replay_from_task_setup_context():
     task1.output = context_output
     crew = Crew(agents=[agent], tasks=[task1, task2], process=Process.sequential)
     with patch(
-        "crewai.utilities.task_output_handler.TaskOutputJsonHandler.load",
+        "crewai.utilities.task_output_storage_handler.TaskOutputStorageHandler.load",
         return_value=[
             {
                 "task_id": str(task1.id),
@@ -2261,7 +2306,7 @@ def test_replay_from_task_setup_context():
             },
         ],
     ):
-        crew.replay_from_task(str(task2.id))
+        crew.replay(str(task2.id))
 
         # Check if the first task's output was set correctly
         assert crew.tasks[0].output is not None
@@ -2272,3 +2317,185 @@ def test_replay_from_task_setup_context():
         assert crew.tasks[0].output.output_format == OutputFormat.RAW
 
         assert crew.tasks[1].prompt_context == "context raw output"
+
+
+def test_key():
+    tasks = [
+        Task(
+            description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+            expected_output="Bullet point list of 5 important events.",
+            agent=researcher,
+        ),
+        Task(
+            description="Write a 1 amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+            expected_output="A 4 paragraph article about AI.",
+            agent=writer,
+        ),
+    ]
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
+    hash = hashlib.md5(
+        f"{researcher.key}|{writer.key}|{tasks[0].key}|{tasks[1].key}".encode()
+    ).hexdigest()
+
+    assert crew.key == hash
+
+
+def test_conditional_task_requirement_breaks_when_singular_conditional_task():
+    def condition_fn(output) -> bool:
+        return output.raw.startswith("Andrew Ng has!!")
+
+    task = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        condition=condition_fn,
+    )
+
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError):
+        Crew(
+            agents=[researcher, writer],
+            tasks=[task],
+        )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_task_last_task_when_conditional_is_true():
+    def condition_fn(output) -> bool:
+        return True
+
+    task1 = Task(
+        description="Say Hi",
+        expected_output="Hi",
+        agent=researcher,
+    )
+    task2 = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        condition=condition_fn,
+        agent=writer,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2],
+    )
+    result = crew.kickoff()
+    assert result.raw.startswith(
+        "1. **The Rise of AI Agents in Customer Service: Revolutionizing Customer Interactions**"
+    )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_task_last_task_when_conditional_is_false():
+    def condition_fn(output) -> bool:
+        return False
+
+    task1 = Task(
+        description="Say Hi",
+        expected_output="Hi",
+        agent=researcher,
+    )
+    task2 = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        condition=condition_fn,
+        agent=writer,
+    )
+
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2],
+    )
+    result = crew.kickoff()
+    print(result.raw)
+    assert result.raw == "Hi"
+
+
+def test_conditional_task_requirement_breaks_when_task_async():
+    def my_condition(context):
+        return context.get("some_value") > 10
+
+    task = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        execute_async=True,
+        condition=my_condition,
+        agent=researcher,
+    )
+    task2 = Task(
+        description="Say Hi",
+        expected_output="Hi",
+        agent=writer,
+    )
+
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError):
+        Crew(
+            agents=[researcher, writer],
+            tasks=[task, task2],
+        )
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_should_skip():
+    task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
+
+    condition_mock = MagicMock(return_value=False)
+    task2 = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        condition=condition_mock,
+        agent=writer,
+    )
+    crew_met = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2],
+    )
+    with patch.object(Task, "execute_sync") as mock_execute_sync:
+        mock_execute_sync.return_value = TaskOutput(
+            description="Task 1 description",
+            raw="Task 1 output",
+            agent="Researcher",
+        )
+
+        result = crew_met.kickoff()
+        assert mock_execute_sync.call_count == 1
+
+        assert condition_mock.call_count == 1
+        assert condition_mock() is False
+
+        assert task2.output is None
+        assert result.raw.startswith("Task 1 output")
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_conditional_should_execute():
+    task1 = Task(description="Return hello", expected_output="say hi", agent=researcher)
+
+    condition_mock = MagicMock(
+        return_value=True
+    )  # should execute this conditional task
+    task2 = ConditionalTask(
+        description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        condition=condition_mock,
+        agent=writer,
+    )
+    crew_met = Crew(
+        agents=[researcher, writer],
+        tasks=[task1, task2],
+    )
+    with patch.object(Task, "execute_sync") as mock_execute_sync:
+        mock_execute_sync.return_value = TaskOutput(
+            description="Task 1 description",
+            raw="Task 1 output",
+            agent="Researcher",
+        )
+
+        crew_met.kickoff()
+
+        assert condition_mock.call_count == 1
+        assert condition_mock() is True
+        assert mock_execute_sync.call_count == 2

tests/pipeline/test_pipeline.py

@@ -0,0 +1,474 @@
+import json
+from unittest.mock import MagicMock
+
+import pytest
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.crews.crew_output import CrewOutput
+from crewai.pipeline.pipeline import Pipeline
+from crewai.pipeline.pipeline_run_result import PipelineRunResult
+from crewai.process import Process
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+from pydantic import BaseModel, ValidationError
+
+DEFAULT_TOKEN_USAGE = {
+    "total_tokens": 100,
+    "prompt_tokens": 50,
+    "completion_tokens": 50,
+}
+
+
+@pytest.fixture
+def mock_crew_factory():
+    def _create_mock_crew(name: str, output_json_dict=None, pydantic_output=None):
+        crew = MagicMock(spec=Crew)
+        task_output = TaskOutput(
+            description="Test task", raw="Task output", agent="Test Agent"
+        )
+        crew_output = CrewOutput(
+            raw="Test output",
+            tasks_output=[task_output],
+            token_usage=DEFAULT_TOKEN_USAGE,
+            json_dict=output_json_dict if output_json_dict else None,
+            pydantic=pydantic_output,
+        )
+
+        async def async_kickoff(inputs=None):
+            print("inputs in async_kickoff", inputs)
+            return crew_output
+
+        crew.kickoff_async.side_effect = async_kickoff
+
+        # Add more attributes that Procedure might be expecting
+        crew.verbose = False
+        crew.output_log_file = None
+        crew.max_rpm = None
+        crew.memory = False
+        crew.process = Process.sequential
+        crew.config = None
+        crew.cache = True
+        crew.name = name
+
+        # Add non-empty agents and tasks
+        mock_agent = MagicMock(spec=Agent)
+        mock_task = MagicMock(spec=Task)
+        mock_task.agent = mock_agent
+        mock_task.async_execution = False
+        mock_task.context = None
+
+        crew.agents = [mock_agent]
+        crew.tasks = [mock_task]
+
+        return crew
+
+    return _create_mock_crew
+
+
+def test_pipeline_initialization(mock_crew_factory):
+    """
+    Test that a Pipeline is correctly initialized with the given stages.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    crew2 = mock_crew_factory(name="Crew 2")
+
+    pipeline = Pipeline(stages=[crew1, crew2])
+    assert len(pipeline.stages) == 2
+    assert pipeline.stages[0] == crew1
+    assert pipeline.stages[1] == crew2
+
+
+@pytest.mark.asyncio
+async def test_pipeline_with_empty_input(mock_crew_factory):
+    """
+    Ensure the pipeline handles an empty input list correctly.
+    """
+    crew = mock_crew_factory(name="Test Crew")
+    pipeline = Pipeline(stages=[crew])
+
+    input_data = []
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    assert (
+        len(pipeline_results) == 0
+    ), "Pipeline should return empty results for empty input"
+
+
+@pytest.mark.asyncio
+async def test_pipeline_process_streams_single_input(mock_crew_factory):
+    """
+    Test that Pipeline.process_streams() correctly processes a single input
+    and returns the expected CrewOutput.
+    """
+    crew_name = "Test Crew"
+    mock_crew = mock_crew_factory(name="Test Crew")
+    pipeline = Pipeline(stages=[mock_crew])
+    input_data = [{"key": "value"}]
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    mock_crew.kickoff_async.assert_called_once_with(inputs={"key": "value"})
+
+    for pipeline_result in pipeline_results:
+        assert isinstance(pipeline_result, PipelineRunResult)
+        assert pipeline_result.raw == "Test output"
+        assert len(pipeline_result.crews_outputs) == 1
+        print("pipeline_result.token_usage", pipeline_result.token_usage)
+        assert pipeline_result.token_usage == {crew_name: DEFAULT_TOKEN_USAGE}
+        assert pipeline_result.trace == [input_data[0], "Test Crew"]
+
+
+@pytest.mark.asyncio
+async def test_pipeline_result_ordering(mock_crew_factory):
+    """
+    Ensure that results are returned in the same order as the inputs, especially with parallel processing.
+    """
+    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"output": "crew1"})
+    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"output": "crew2"})
+    crew3 = mock_crew_factory(name="Crew 3", output_json_dict={"output": "crew3"})
+
+    pipeline = Pipeline(
+        stages=[crew1, [crew2, crew3]]
+    )  # Parallel stage to test ordering
+
+    input_data = [{"id": 1}, {"id": 2}, {"id": 3}]
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    assert (
+        len(pipeline_results) == 6
+    ), "Should have 2 results for each input due to the parallel final stage"
+
+    # Group results by their original input id
+    grouped_results = {}
+    for result in pipeline_results:
+        input_id = result.trace[0]["id"]
+        if input_id not in grouped_results:
+            grouped_results[input_id] = []
+        grouped_results[input_id].append(result)
+
+    # Check that we have the correct number of groups and results per group
+    assert len(grouped_results) == 3, "Should have results for each of the 3 inputs"
+    for input_id, results in grouped_results.items():
+        assert (
+            len(results) == 2
+        ), f"Each input should have 2 results, but input {input_id} has {len(results)}"
+
+    # Check the ordering and content of the results
+    for input_id in range(1, 4):
+        group = grouped_results[input_id]
+        assert group[0].trace == [
+            {"id": input_id},
+            "Crew 1",
+            "Crew 2",
+        ], f"Unexpected trace for first result of input {input_id}"
+        assert group[1].trace == [
+            {"id": input_id},
+            "Crew 1",
+            "Crew 3",
+        ], f"Unexpected trace for second result of input {input_id}"
+        assert (
+            group[0].json_dict["output"] == "crew2"
+        ), f"Unexpected output for first result of input {input_id}"
+        assert (
+            group[1].json_dict["output"] == "crew3"
+        ), f"Unexpected output for second result of input {input_id}"
+
+
+class TestPydanticOutput(BaseModel):
+    key: str
+    value: int
+
+
+@pytest.mark.asyncio
+async def test_pipeline_process_streams_single_input_pydantic_output(mock_crew_factory):
+    crew_name = "Test Crew"
+    mock_crew = mock_crew_factory(
+        name=crew_name,
+        output_json_dict=None,
+        pydantic_output=TestPydanticOutput(key="test", value=42),
+    )
+    pipeline = Pipeline(stages=[mock_crew])
+    input_data = [{"key": "value"}]
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    assert len(pipeline_results) == 1
+    pipeline_result = pipeline_results[0]
+
+    print("pipeline_result.trace", pipeline_result.trace)
+
+    assert isinstance(pipeline_result, PipelineRunResult)
+    assert pipeline_result.raw == "Test output"
+    assert len(pipeline_result.crews_outputs) == 1
+    assert pipeline_result.token_usage == {crew_name: DEFAULT_TOKEN_USAGE}
+    print("INPUT DATA POST PROCESS", input_data)
+    assert pipeline_result.trace == [input_data[0], "Test Crew"]
+
+    assert isinstance(pipeline_result.pydantic, TestPydanticOutput)
+    assert pipeline_result.pydantic.key == "test"
+    assert pipeline_result.pydantic.value == 42
+    assert pipeline_result.json_dict is None
+
+
+@pytest.mark.asyncio
+async def test_pipeline_preserves_original_input(mock_crew_factory):
+    crew_name = "Test Crew"
+    mock_crew = mock_crew_factory(
+        name=crew_name,
+        output_json_dict={"new_key": "new_value"},
+    )
+    pipeline = Pipeline(stages=[mock_crew])
+
+    # Create a deep copy of the input data to ensure we're not comparing references
+    original_input_data = [{"key": "value", "nested": {"a": 1}}]
+    input_data = json.loads(json.dumps(original_input_data))
+
+    await pipeline.process_runs(input_data)
+
+    # Assert that the original input hasn't been modified
+    assert (
+        input_data == original_input_data
+    ), "The original input data should not be modified"
+
+    # Ensure that even nested structures haven't been modified
+    assert (
+        input_data[0]["nested"] == original_input_data[0]["nested"]
+    ), "Nested structures should not be modified"
+
+    # Verify that adding new keys to the crew output doesn't affect the original input
+    assert (
+        "new_key" not in input_data[0]
+    ), "New keys from crew output should not be added to the original input"
+
+
+@pytest.mark.asyncio
+async def test_pipeline_process_streams_multiple_inputs(mock_crew_factory):
+    """
+    Test that Pipeline.process_streams() correctly processes multiple inputs
+    and returns the expected CrewOutputs.
+    """
+    mock_crew = mock_crew_factory(name="Test Crew")
+    pipeline = Pipeline(stages=[mock_crew])
+    input_data = [{"key1": "value1"}, {"key2": "value2"}]
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    assert mock_crew.kickoff_async.call_count == 2
+    assert len(pipeline_results) == 2
+    for pipeline_result in pipeline_results:
+        print("pipeline_result,", pipeline_result)
+        assert all(
+            isinstance(crew_output, CrewOutput)
+            for crew_output in pipeline_result.crews_outputs
+        )
+
+
+@pytest.mark.asyncio
+async def test_pipeline_with_parallel_stages(mock_crew_factory):
+    """
+    Test that Pipeline correctly handles parallel stages.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    crew2 = mock_crew_factory(name="Crew 2")
+    crew3 = mock_crew_factory(name="Crew 3")
+
+    pipeline = Pipeline(stages=[crew1, [crew2, crew3]])
+    input_data = [{"initial": "data"}]
+
+    pipeline_result = await pipeline.process_runs(input_data)
+
+    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
+
+    assert len(pipeline_result) == 2
+    pipeline_result_1, pipeline_result_2 = pipeline_result
+
+    pipeline_result_1.trace = [
+        "Crew 1",
+        "Crew 2",
+    ]
+    pipeline_result_2.trace = [
+        "Crew 1",
+        "Crew 3",
+    ]
+
+    expected_token_usage = {
+        "Crew 1": DEFAULT_TOKEN_USAGE,
+        "Crew 2": DEFAULT_TOKEN_USAGE,
+        "Crew 3": DEFAULT_TOKEN_USAGE,
+    }
+
+    assert pipeline_result_1.token_usage == expected_token_usage
+    assert pipeline_result_2.token_usage == expected_token_usage
+
+
+@pytest.mark.asyncio
+async def test_pipeline_with_parallel_stages_end_in_single_stage(mock_crew_factory):
+    """
+    Test that Pipeline correctly handles parallel stages.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    crew2 = mock_crew_factory(name="Crew 2")
+    crew3 = mock_crew_factory(name="Crew 3")
+    crew4 = mock_crew_factory(name="Crew 4")
+
+    pipeline = Pipeline(stages=[crew1, [crew2, crew3], crew4])
+    input_data = [{"initial": "data"}]
+
+    pipeline_result = await pipeline.process_runs(input_data)
+
+    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
+
+    assert len(pipeline_result) == 1
+    pipeline_result_1 = pipeline_result[0]
+
+    pipeline_result_1.trace = [
+        input_data[0],
+        "Crew 1",
+        ["Crew 2", "Crew 3"],
+        "Crew 4",
+    ]
+
+    expected_token_usage = {
+        "Crew 1": DEFAULT_TOKEN_USAGE,
+        "Crew 2": DEFAULT_TOKEN_USAGE,
+        "Crew 3": DEFAULT_TOKEN_USAGE,
+        "Crew 4": DEFAULT_TOKEN_USAGE,
+    }
+
+    assert pipeline_result_1.token_usage == expected_token_usage
+
+
+@pytest.mark.asyncio
+async def test_pipeline_with_parallel_stages_multiple_inputs(mock_crew_factory):
+    # TODO: implement
+    pass
+
+
+def test_pipeline_rshift_operator(mock_crew_factory):
+    """
+    Test that the >> operator correctly creates a Pipeline from Crews and lists of Crews.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    crew2 = mock_crew_factory(name="Crew 2")
+    crew3 = mock_crew_factory(name="Crew 3")
+
+    # Test single crew addition
+    pipeline = Pipeline(stages=[]) >> crew1
+    assert len(pipeline.stages) == 1
+    assert pipeline.stages[0] == crew1
+
+    # Test adding a list of crews
+    pipeline = Pipeline(stages=[crew1])
+    pipeline = pipeline >> [crew2, crew3]
+    print("pipeline.stages:", pipeline.stages)
+    assert len(pipeline.stages) == 2
+    assert pipeline.stages[1] == [crew2, crew3]
+
+    # Test error case: trying to shift with non-Crew object
+    with pytest.raises(TypeError):
+        pipeline >> "not a crew"
+
+
+@pytest.mark.asyncio
+async def test_pipeline_parallel_crews_to_parallel_crews(mock_crew_factory):
+    """
+    Test that feeding parallel crews to parallel crews works correctly.
+    """
+    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"output1": "crew1"})
+    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"output2": "crew2"})
+    crew3 = mock_crew_factory(name="Crew 3", output_json_dict={"output3": "crew3"})
+    crew4 = mock_crew_factory(name="Crew 4", output_json_dict={"output4": "crew4"})
+
+    pipeline = Pipeline(stages=[[crew1, crew2], [crew3, crew4]])
+
+    input_data = [{"input": "test"}]
+    pipeline_results = await pipeline.process_runs(input_data)
+
+    assert len(pipeline_results) == 2, "Should have 2 results for final parallel stage"
+
+    pipeline_result_1, pipeline_result_2 = pipeline_results
+
+    # Check the outputs
+    assert pipeline_result_1.json_dict == {"output3": "crew3"}
+    assert pipeline_result_2.json_dict == {"output4": "crew4"}
+
+    # Check the traces
+    expected_traces = [
+        [{"input": "test"}, ["Crew 1", "Crew 2"], "Crew 3"],
+        [{"input": "test"}, ["Crew 1", "Crew 2"], "Crew 4"],
+    ]
+
+    for result, expected_trace in zip(pipeline_results, expected_traces):
+        assert result.trace == expected_trace, f"Unexpected trace: {result.trace}"
+
+
+def test_pipeline_double_nesting_not_allowed(mock_crew_factory):
+    """
+    Test that double nesting in pipeline stages is not allowed.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    crew2 = mock_crew_factory(name="Crew 2")
+    crew3 = mock_crew_factory(name="Crew 3")
+    crew4 = mock_crew_factory(name="Crew 4")
+
+    with pytest.raises(ValidationError) as exc_info:
+        Pipeline(stages=[crew1, [[crew2, crew3], crew4]])
+
+    error_msg = str(exc_info.value)
+    print(f"Full error message: {error_msg}")  # For debugging
+    assert (
+        "Double nesting is not allowed in pipeline stages" in error_msg
+    ), f"Unexpected error message: {error_msg}"
+
+
+def test_pipeline_invalid_crew(mock_crew_factory):
+    """
+    Test that non-Crew objects are not allowed in pipeline stages.
+    """
+    crew1 = mock_crew_factory(name="Crew 1")
+    not_a_crew = "This is not a crew"
+
+    with pytest.raises(ValidationError) as exc_info:
+        Pipeline(stages=[crew1, not_a_crew])
+
+    error_msg = str(exc_info.value)
+    print(f"Full error message: {error_msg}")  # For debugging
+    assert (
+        "Expected Crew instance or list of Crews, got <class 'str'>" in error_msg
+    ), f"Unexpected error message: {error_msg}"
+
+
+"""
+TODO: Figure out what is the proper output for a pipeline with multiple stages
+
+Options:
+- Should the final output only include the last stage's output?
+- Should the final output include the accumulation of previous stages' outputs?
+"""
+
+@pytest.mark.asyncio
+async def test_pipeline_data_accumulation(mock_crew_factory):
+    crew1 = mock_crew_factory(name="Crew 1", output_json_dict={"key1": "value1"})
+    crew2 = mock_crew_factory(name="Crew 2", output_json_dict={"key2": "value2"})
+
+    pipeline = Pipeline(stages=[crew1, crew2])
+    input_data = [{"initial": "data"}]
+    results = await pipeline.process_runs(input_data)
+
+    # Check that crew1 was called with only the initial input
+    crew1.kickoff_async.assert_called_once_with(inputs={"initial": "data"})
+
+    # Check that crew2 was called with the combined input from the initial data and crew1's output
+    crew2.kickoff_async.assert_called_once_with(
+        inputs={"initial": "data", "key1": "value1"}
+    )
+
+    # Check the final output
+    assert len(results) == 1
+    final_result = results[0]
+    assert final_result.json_dict == {"key2": "value2"}
+
+    # Check that the trace includes all stages
+    assert final_result.trace == [{"initial": "data"}, "Crew 1", "Crew 2"]
+
+    # Check that crews_outputs contain the correct information
+    assert len(final_result.crews_outputs) == 2
+    assert final_result.crews_outputs[0].json_dict == {"key1": "value1"}
+    assert final_result.crews_outputs[1].json_dict == {"key2": "value2"}

tests/task_test.py

@@ -1,5 +1,6 @@
 """Test Agent creation and execution basic functionality."""
 
+import hashlib
 import json
 from unittest.mock import MagicMock, patch
 
@@ -8,6 +9,7 @@ from pydantic import BaseModel
 from pydantic_core import ValidationError
 
 from crewai import Agent, Crew, Process, Task
+from crewai.tasks.conditional_task import ConditionalTask
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.converter import Converter
 
@@ -317,6 +319,7 @@ def test_output_json_hierarchical():
     assert result.to_dict() == {"score": 4}
 
 
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_json_property_without_output_json():
     class ScoreOutput(BaseModel):
         score: int
@@ -397,8 +400,8 @@ def test_output_json_dict_hierarchical():
         manager_llm=ChatOpenAI(model="gpt-4o"),
     )
     result = crew.kickoff()
-    assert {"score": 4} == result.json_dict
-    assert result.to_dict() == {"score": 4}
+    assert {"score": 5} == result.json_dict
+    assert result.to_dict() == {"score": 5}
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
@@ -695,6 +698,19 @@ def test_task_definition_based_on_dict():
     assert task.agent is None
 
 
+def test_conditional_task_definition_based_on_dict():
+    config = {
+        "description": "Give me an integer score between 1-5 for the following title: 'The impact of AI in the future of work', check examples to based your evaluation.",
+        "expected_output": "The score of the title.",
+    }
+
+    task = ConditionalTask(config=config, condition=lambda x: True)
+
+    assert task.description == config["description"]
+    assert task.expected_output == config["expected_output"]
+    assert task.agent is None
+
+
 def test_interpolate_inputs():
     task = Task(
         description="Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting.",
@@ -791,3 +807,22 @@ def test_task_output_str_with_none():
     )
 
     assert str(task_output) == ""
+
+
+def test_key():
+    original_description = "Give me a list of 5 interesting ideas about {topic} to explore for an article, what makes them unique and interesting."
+    original_expected_output = "Bullet point list of 5 interesting ideas about {topic}."
+    task = Task(
+        description=original_description,
+        expected_output=original_expected_output,
+    )
+    hash = hashlib.md5(
+        f"{original_description}|{original_expected_output}".encode()
+    ).hexdigest()
+
+    assert task.key == hash, "The key should be the hash of the description."
+
+    task.interpolate_inputs(inputs={"topic": "AI"})
+    assert (
+        task.key == hash
+    ), "The key should be the hash of the non-interpolated description."

tests/utilities/test_planning_handler.py

@@ -0,0 +1,74 @@
+from unittest.mock import patch
+from crewai.tasks.task_output import TaskOutput
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.task import Task
+from crewai.utilities.planning_handler import CrewPlanner, PlannerTaskPydanticOutput
+
+
+class TestCrewPlanner:
+    @pytest.fixture
+    def crew_planner(self):
+        tasks = [
+            Task(
+                description="Task 1",
+                expected_output="Output 1",
+                agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
+            ),
+            Task(
+                description="Task 2",
+                expected_output="Output 2",
+                agent=Agent(role="Agent 2", goal="Goal 2", backstory="Backstory 2"),
+            ),
+            Task(
+                description="Task 3",
+                expected_output="Output 3",
+                agent=Agent(role="Agent 3", goal="Goal 3", backstory="Backstory 3"),
+            ),
+        ]
+        return CrewPlanner(tasks)
+
+    def test_handle_crew_planning(self, crew_planner):
+        with patch.object(Task, "execute_sync") as execute:
+            execute.return_value = TaskOutput(
+                description="Description",
+                agent="agent",
+                pydantic=PlannerTaskPydanticOutput(
+                    list_of_plans_per_task=["Plan 1", "Plan 2", "Plan 3"]
+                ),
+            )
+            result = crew_planner._handle_crew_planning()
+
+            assert isinstance(result, PlannerTaskPydanticOutput)
+            assert len(result.list_of_plans_per_task) == len(crew_planner.tasks)
+            execute.assert_called_once()
+
+    def test_create_planning_agent(self, crew_planner):
+        agent = crew_planner._create_planning_agent()
+        assert isinstance(agent, Agent)
+        assert agent.role == "Task Execution Planner"
+
+    def test_create_planner_task(self, crew_planner):
+        planning_agent = Agent(
+            role="Planning Agent",
+            goal="Plan Step by Step Plan",
+            backstory="Master in Planning",
+        )
+        tasks_summary = "Summary of tasks"
+        task = crew_planner._create_planner_task(planning_agent, tasks_summary)
+
+        assert isinstance(task, Task)
+        assert task.description.startswith("Based on these tasks summary")
+        assert task.agent == planning_agent
+        assert (
+            task.expected_output
+            == "Step by step plan on how the agents can execute their tasks using the available tools with mastery"
+        )
+
+    def test_create_tasks_summary(self, crew_planner):
+        tasks_summary = crew_planner._create_tasks_summary()
+        assert isinstance(tasks_summary, str)
+        assert tasks_summary.startswith("\n                Task Number 1 - Task 1")
+        assert tasks_summary.endswith('"agent_tools": []\n                ')