Fix langchain at 0.1.0

Minor changes include a typo fixed and enhancing
an example for using OpenAI as an agent model with Ollama
via langchain

Resolves #189 #190

.circleci/config.yml

@@ -1,27 +0,0 @@
-version: 2.1
-
-jobs:
-  build-and-test:
-    docker:
-      - image: python:3.9.18
-    steps:
-      - checkout
-      - run:
-          name: Install poetry
-          command: pip install poetry
-      - run:
-          name: Install dependencies
-          command: poetry install
-      - run:
-          name: Update PATH and Define Environment Variable at Runtime
-          command: |
-            echo 'export OPENAI_API_KEY=fake-api-key' >> "$BASH_ENV"
-            source "$BASH_ENV"
-      - run:
-          name: Run tests
-          command: poetry run pytest
-
-workflows:
-  build-and-test:
-    jobs:
-      - build-and-test

.github/workflows/black.yml

@@ -0,0 +1,10 @@
+name: Lint
+
+on: [push, pull_request]
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - uses: psf/black@stable

.github/workflows/mkdocs.yml

@@ -0,0 +1,35 @@
+name: Deploy MkDocs
+
+on:
+  workflow_dispatch:    
+  push:
+    branches:
+      - main
+
+permissions:
+  contents: write
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install Requirements
+        run: |
+          sudo apt-get update &&
+          sudo apt-get install pngquant &&
+          pip install mkdocs-material
+
+        env:
+          GH_TOKEN: ${{ secrets.GH_TOKEN }}
+
+      - name: Build and deploy MkDocs
+        run: mkdocs gh-deploy --force

.github/workflows/tests.yml

@@ -0,0 +1,32 @@
+name: Run Tests
+
+on: [push, pull_request]
+
+permissions:
+  contents: write
+
+env:
+  OPENAI_API_KEY: fake-api-key
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+
+      - name: Install Requirements
+        run: |
+          sudo apt-get update &&
+          pip install poetry &&
+          poetry lock &&
+          poetry install
+
+      - name: Run tests
+        run: poetry run pytest

.gitignore

@@ -4,4 +4,5 @@ __pycache__
 dist/
 .env
 assets/*
-.idea
+.idea
+test.py

README.md

@@ -1,25 +1,40 @@
+THIS IS A TEST
+
 # crewAI
 
-![Logo of crewAI, tow people rowing on a boat](./crewai_logo.png)
+![Logo of crewAI, tow people rowing on a boat](./docs/crewai_logo.png)
 
 🤖 Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
 
-- [Why CrewAI](#why-crewai)
-- [Getting Started](#getting-started)
-- [Key Features](#key-features)
-- [Examples](#examples)
-- [Local Open Source Models](#local-open-source-models)
-- [CrewAI x AutoGen x ChatDev](#how-crewai-compares)
-- [Contribution](#contribution)
-- [License](#license)
+- [crewAI](#crewai)
+  - [Why CrewAI?](#why-crewai)
+  - [Getting Started](#getting-started)
+  - [Key Features](#key-features)
+  - [Examples](#examples)
+    - [Code](#code)
+    - [Video](#video)
+      - [Quick Tutorial](#quick-tutorial)
+      - [Trip Planner](#trip-planner)
+      - [Stock Analysis](#stock-analysis)
+  - [Connecting Your Crew to a Model](#connecting-your-crew-to-a-model)
+  - [How CrewAI Compares](#how-crewai-compares)
+  - [Contribution](#contribution)
+    - [Installing Dependencies](#installing-dependencies)
+    - [Virtual Env](#virtual-env)
+    - [Pre-commit hooks](#pre-commit-hooks)
+    - [Running Tests](#running-tests)
+    - [Packaging](#packaging)
+    - [Installing Locally](#installing-locally)
+  - [Hire CrewAI](#hire-crewai)
+  - [License](#license)
 
 ## Why CrewAI?
 
 The power of AI collaboration has too much to offer.
 CrewAI is designed to enable AI agents to assume roles, share goals, and operate in a cohesive unit - much like a well-oiled crew. Whether you're building a smart assistant platform, an automated customer service ensemble, or a multi-agent research team, CrewAI provides the backbone for sophisticated multi-agent interactions.
 
-- 🤖 [Talk with the Docs](https://chat.openai.com/g/g-qqTuUWsBY-crewai-assistant)
-- 📄 [Documention Wiki](https://github.com/joaomdmoura/CrewAI/wiki)
+- 🤖 [Talk with the Docs](https://chatg.pt/DWjSBZn)
+- 📄 [Documentation Wiki](https://joaomdmoura.github.io/crewAI/)
 
 ## Getting Started
 
@@ -31,89 +46,129 @@ To get started with CrewAI, follow these simple steps:
 pip install crewai
 ```
 
+The example below also uses duckduckgo, so also install that
+```shell
+pip install duckduckgo-search
+```
+
 2. **Setting Up Your Crew**:
 
 ```python
 import os
 from crewai import Agent, Task, Crew, Process
 
-os.environ["OPENAI_API_KEY"] = "Your Key"
+os.environ["OPENAI_API_KEY"] = "YOUR KEY"
+
+# You can choose to use a local model through Ollama for example. See ./docs/llm-connections.md for more information.
+# from langchain.llms import Ollama
+# ollama_llm = Ollama(model="openhermes")
+
+# Install duckduckgo-search for this example:
+# !pip install -U duckduckgo-search
+
+from langchain.tools import DuckDuckGoSearchRun
+search_tool = DuckDuckGoSearchRun()
 
 # Define your agents with roles and goals
 researcher = Agent(
-  role='Researcher',
-  goal='Discover new insights',
-  backstory="You're a world class researcher working on a major data science company",
+  role='Senior Research Analyst',
+  goal='Uncover cutting-edge developments in AI and data science',
+  backstory="""You work at a leading tech think tank.
+  Your expertise lies in identifying emerging trends.
+  You have a knack for dissecting complex data and presenting
+  actionable insights.""",
   verbose=True,
-  allow_delegation=False
-  # llm=OpenAI(temperature=0.7, model_name="gpt-4"). It uses langchain.chat_models, default is GPT4
+  allow_delegation=False,
+  tools=[search_tool]
+  # You can pass an optional llm attribute specifying what mode you wanna use.
+  # It can be a local model through Ollama / LM Studio or a remote
+  # model like OpenAI, Mistral, Antrophic or others (https://python.langchain.com/docs/integrations/llms/)
+  #
+  # Examples:
+  # llm=ollama_llm # was defined above in the file
+  # llm=OpenAI(model_name="gpt-3.5", temperature=0.7)
+  # For the OpenAI model you would need to import
+  # from langchain_openai import OpenAI
 )
 writer = Agent(
-  role='Writer',
-  goal='Create engaging content',
-  backstory="You're a famous technical writer, specialized on writing data related content",
+  role='Tech Content Strategist',
+  goal='Craft compelling content on tech advancements',
+  backstory="""You are a renowned Content Strategist, known for
+  your insightful and engaging articles.
+  You transform complex concepts into compelling narratives.""",
   verbose=True,
-  allow_delegation=False
+  allow_delegation=True,
+  # (optional) llm=ollama_llm
 )
 
 # Create tasks for your agents
-task1 = Task(description='Investigate the latest AI trends', agent=researcher)
-task2 = Task(description='Write a blog post on AI advancements', agent=writer)
+task1 = Task(
+  description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
+  Identify key trends, breakthrough technologies, and potential industry impacts.
+  Your final answer MUST be a full analysis report""",
+  agent=researcher
+)
+
+task2 = Task(
+  description="""Using the insights provided, develop an engaging blog
+  post that highlights the most significant AI advancements.
+  Your post should be informative yet accessible, catering to a tech-savvy audience.
+  Make it sound cool, avoid complex words so it doesn't sound like AI.
+  Your final answer MUST be the full blog post of at least 4 paragraphs.""",
+  agent=writer
+)
 
 # Instantiate your crew with a sequential process
 crew = Crew(
   agents=[researcher, writer],
   tasks=[task1, task2],
-  verbose=2, # Crew verbose more will let you know what tasks are being worked on, you can set it to 1 or 2 to different logging levels
-  process=Process.sequential # Sequential process will have tasks executed one after the other and the outcome of the previous one is passed as extra content into this next.
+  verbose=2, # You can set it to 1 or 2 to different logging levels
 )
 
 # Get your crew to work!
 result = crew.kickoff()
+
+print("######################")
+print(result)
 ```
 
 Currently the only supported process is `Process.sequential`, where one task is executed after the other and the outcome of one is passed as extra content into this next.
 
+
 ## Key Features
 
 - **Role-Based Agent Design**: Customize agents with specific roles, goals, and tools.
 - **Autonomous Inter-Agent Delegation**: Agents can autonomously delegate tasks and inquire amongst themselves, enhancing problem-solving efficiency.
 - **Flexible Task Management**: Define tasks with customizable tools and assign them to agents dynamically.
 - **Processes Driven**: Currently only supports `sequential` task execution but more complex processes like consensual and hierarchical being worked on.
+- **Works with Open Source Models**: Run your crew using Open AI or open source models refer to the [Connect crewAI to LLMs](./docs/llm-connections.md) page for details on configuring you agents' connections to models, even ones running locally!
 
-![CrewAI Mind Map](/crewAI-mindmap.png "CrewAI Mind Map")
+![CrewAI Mind Map](./docs/crewAI-mindmap.png "CrewAI Mind Map")
 
 ## Examples
 You can test different real life examples of AI crews [in the examples repo](https://github.com/joaomdmoura/crewAI-examples?tab=readme-ov-file)
 
-## Local Open Source Models
-crewAI supports integration with local models, thorugh tools such as [Ollama](https://ollama.ai/), for enhanced flexibility and customization. This allows you to utilize your own models, which can be particularly useful for specialized tasks or data privacy concerns.
+### Code
+- [Trip Planner](https://github.com/joaomdmoura/crewAI-examples/tree/main/trip_planner)
+- [Stock Analysis](https://github.com/joaomdmoura/crewAI-examples/tree/main/stock_analysis)
+- [Landing Page Generator](https://github.com/joaomdmoura/crewAI-examples/tree/main/landing_page_generator)
+- [Having Human input on the execution](./docs/how-to/Human-Input-on-Execution.md)
 
-### Setting Up Ollama
-- **Install Ollama**: Ensure that Ollama is properly installed in your environment. Follow the installation guide provided by Ollama for detailed instructions.
-- **Configure Ollama**: Set up Ollama to work with your local model. You will probably need to [tweak the model using a Modelfile](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md). I'd recommend adding `Observation` as a stop word and playing with `top_p` and `temperature`.
+### Video
+#### Quick Tutorial
+[![CrewAI Tutorial](https://img.youtube.com/vi/tnejrr-0a94/0.jpg)](https://www.youtube.com/watch?v=tnejrr-0a94 "CrewAI Tutorial")
 
-### Integrating Ollama with CrewAI
-- Instantiate Ollama Model: Create an instance of the Ollama model. You can specify the model and the base URL during instantiation. For example:
+#### Trip Planner
+[![Trip Planner](https://img.youtube.com/vi/xis7rWp-hjs/0.jpg)](https://www.youtube.com/watch?v=xis7rWp-hjs "Trip Planner")
 
-```python
-from langchain.llms import Ollama
-ollama_openhermes = Ollama(model="agent")
-# Pass Ollama Model to Agents: When creating your agents within the CrewAI framework, you can pass the Ollama model as an argument to the Agent constructor. For instance:
+#### Stock Analysis
+[![Stock Analysis](https://img.youtube.com/vi/e0Uj4yWdaAg/0.jpg)](https://www.youtube.com/watch?v=e0Uj4yWdaAg "Stock Analysis")
 
-local_expert = Agent(
-  role='Local Expert at this city',
-  goal='Provide the BEST insights about the selected city',
-  backstory="""A knowledgeable local guide with extensive information
-  about the city, it's attractions and customs""",
-  tools=[
-    SearchTools.search_internet,
-    BrowserTools.scrape_and_summarize_website,
-  ],
-  llm=ollama_openhermes, # Ollama model passed here
-  verbose=True
-)
-```
+## Connecting Your Crew to a Model
+
+crewAI supports using various LLMs through a variety of connection options. By default your agents will use the OpenAI API when querying the model. However, there are several other ways to allow your agents to connect to models. For example, you can configure your agents to use a local model via the Ollama tool.
+
+Please refer to the [Connect crewAI to LLMs](./docs/how-to/llm-connections.md) page for details on configuring you agents' connections to models.
 
 ## How CrewAI Compares
 
@@ -165,7 +220,9 @@ poetry build
 pip install dist/*.tar.gz
 ```
 
+## Hire CrewAI
+We're a company developing crewAI and crewAI Enterprise, we for a limited time are offer consulting with selected customers, to get them early access to our enterprise solution
+If you are interested on having access to it and hiring weekly hours with our team, feel free to email us at [sales@crewai.io](mailto:sales@crewai.io)
+
 ## License
 CrewAI is released under the MIT License
-
-

crewai/crew.py

@@ -1,122 +0,0 @@
-import json
-from typing import Any, Dict, List, Optional, Union
-
-from pydantic import (
-    BaseModel,
-    Field,
-    InstanceOf,
-    Json,
-    field_validator,
-    model_validator,
-)
-from pydantic_core import PydanticCustomError
-
-from crewai.agent import Agent
-from crewai.agents import CacheHandler
-from crewai.process import Process
-from crewai.task import Task
-from crewai.tools.agent_tools import AgentTools
-
-
-class Crew(BaseModel):
-    """Class that represents a group of agents, how they should work together and their tasks."""
-
-    class Config:
-        arbitrary_types_allowed = True
-
-    tasks: List[Task] = Field(description="List of tasks", default_factory=list)
-    agents: List[Agent] = Field(
-        description="List of agents in this crew.", default_factory=list
-    )
-    process: Process = Field(
-        description="Process that the crew will follow.", default=Process.sequential
-    )
-    verbose: Union[int, bool] = Field(
-        description="Verbose mode for the Agent Execution", default=0
-    )
-    config: Optional[Union[Json, Dict[str, Any]]] = Field(
-        description="Configuration of the crew.", default=None
-    )
-    cache_handler: Optional[InstanceOf[CacheHandler]] = Field(
-        default=CacheHandler(), description="An instance of the CacheHandler class."
-    )
-
-    @classmethod
-    @field_validator("config", mode="before")
-    def check_config_type(cls, v: Union[Json, Dict[str, Any]]):
-        if isinstance(v, Json):
-            return json.loads(v)
-        return v
-
-    @model_validator(mode="after")
-    def check_config(self):
-        if not self.config and not self.tasks and not self.agents:
-            raise PydanticCustomError(
-                "missing_keys", "Either agents and task need to be set or config.", {}
-            )
-
-        if self.config:
-            if not self.config.get("agents") or not self.config.get("tasks"):
-                raise PydanticCustomError(
-                    "missing_keys_in_config", "Config should have agents and tasks", {}
-                )
-
-            self.agents = [Agent(**agent) for agent in self.config["agents"]]
-
-            tasks = []
-            for task in self.config["tasks"]:
-                task_agent = [agt for agt in self.agents if agt.role == task["agent"]][
-                    0
-                ]
-                del task["agent"]
-                tasks.append(Task(**task, agent=task_agent))
-
-            self.tasks = tasks
-
-        if self.agents:
-            for agent in self.agents:
-                agent.set_cache_handler(self.cache_handler)
-        return self
-
-    def kickoff(self) -> str:
-        """Kickoff the crew to work on its tasks.
-
-        Returns:
-            Output of the crew for each task.
-        """
-        for agent in self.agents:
-            agent.cache_handler = self.cache_handler
-
-        if self.process == Process.sequential:
-            return self.__sequential_loop()
-
-    def __sequential_loop(self) -> str:
-        """Loop that executes the sequential process.
-
-        Returns:
-            Output of the crew.
-        """
-        task_outcome = None
-        for task in self.tasks:
-            # Add delegation tools to the task if the agent allows it
-            if task.agent.allow_delegation:
-                tools = AgentTools(agents=self.agents).tools()
-                task.tools += tools
-
-            self.__log("debug", f"Working Agent: {task.agent.role}")
-            self.__log("info", f"Starting Task: {task.description} ...")
-
-            task_outcome = task.execute(task_outcome)
-
-            self.__log("debug", f"Task output: {task_outcome}")
-
-        return task_outcome
-
-    def __log(self, level, message):
-        """Log a message"""
-        level_map = {"debug": 1, "info": 2}
-        verbose_level = (
-            2 if isinstance(self.verbose, bool) and self.verbose else self.verbose
-        )
-        if verbose_level and level_map[level] <= verbose_level:
-            print(message)

crewai/prompts.py

@@ -1,84 +0,0 @@
-"""Prompts for generic agent."""
-
-from textwrap import dedent
-from typing import ClassVar
-
-from langchain.prompts import PromptTemplate
-from pydantic import BaseModel
-
-
-class Prompts(BaseModel):
-    """Prompts for generic agent."""
-
-    TASK_SLICE: ClassVar[str] = dedent(
-        """\
-	Begin! This is VERY important to you, your job depends on it!
-
-	Current Task: {input}"""
-    )
-
-    SCRATCHPAD_SLICE: ClassVar[str] = "\n{agent_scratchpad}"
-
-    MEMORY_SLICE: ClassVar[str] = dedent(
-        """\
-	This is the summary of your work so far:
-	{chat_history}"""
-    )
-
-    ROLE_PLAYING_SLICE: ClassVar[str] = dedent(
-        """\
-	You are {role}.
-	{backstory}
-
-	Your personal goal is: {goal}"""
-    )
-
-    TOOLS_SLICE: ClassVar[str] = dedent(
-        """\
-
-
-	TOOLS:
-	------
-	You have access to the following tools:
-
-	{tools}
-
-	To use a tool, please use the exact following format:
-
-	```
-	Thought: Do I need to use a tool? Yes
-	Action: the action to take, should be one of [{tool_names}], just the name.
-	Action Input: the input to the action
-	Observation: the result of the action
-	```
-
-	When you have a response for your task, or if you do not need to use a tool, you MUST use the format:
-
-	```
-	Thought: Do I need to use a tool? No
-	Final Answer: [your response here]
-	```"""
-    )
-
-    VOTING_SLICE: ClassVar[str] = dedent(
-        """\
-	You are working on a crew with your co-workers and need to decide who will execute the task.
-
-	These are your format instructions:
-	{format_instructions}
-
-	These are your co-workers and their roles:
-	{coworkers}"""
-    )
-
-    TASK_EXECUTION_WITH_MEMORY_PROMPT: ClassVar[str] = PromptTemplate.from_template(
-        ROLE_PLAYING_SLICE + TOOLS_SLICE + MEMORY_SLICE + TASK_SLICE + SCRATCHPAD_SLICE
-    )
-
-    TASK_EXECUTION_PROMPT: ClassVar[str] = PromptTemplate.from_template(
-        ROLE_PLAYING_SLICE + TOOLS_SLICE + TASK_SLICE + SCRATCHPAD_SLICE
-    )
-
-    CONSENSUNS_VOTING_PROMPT: ClassVar[str] = PromptTemplate.from_template(
-        ROLE_PLAYING_SLICE + VOTING_SLICE + TASK_SLICE + SCRATCHPAD_SLICE
-    )

crewai/task.py

@@ -1,39 +0,0 @@
-from typing import Any, List, Optional
-
-from pydantic import BaseModel, Field, model_validator
-
-from crewai.agent import Agent
-
-
-class Task(BaseModel):
-    """Class that represent a task to be executed."""
-
-    description: str = Field(description="Description of the actual task.")
-    agent: Optional[Agent] = Field(
-        description="Agent responsible for the task.", default=None
-    )
-    tools: List[Any] = Field(
-        default_factory=list,
-        description="Tools the agent are limited to use for this task.",
-    )
-
-    @model_validator(mode="after")
-    def check_tools(self):
-        if not self.tools and (self.agent and self.agent.tools):
-            self.tools.extend(self.agent.tools)
-        return self
-
-    def execute(self, context: str = None) -> str:
-        """Execute the task.
-
-        Returns:
-            Output of the task.
-        """
-        if self.agent:
-            return self.agent.execute_task(
-                task=self.description, context=context, tools=self.tools
-            )
-        else:
-            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, either consensual or hierarchical."
-            )

crewai/tools/agent_tools.py

@@ -1,72 +0,0 @@
-from textwrap import dedent
-from typing import List
-
-from langchain.tools import Tool
-from pydantic import BaseModel, Field
-
-from crewai.agent import Agent
-
-
-class AgentTools(BaseModel):
-    """Tools for generic agent."""
-
-    agents: List[Agent] = Field(description="List of agents in this crew.")
-
-    def tools(self):
-        return [
-            Tool.from_function(
-                func=self.delegate_work,
-                name="Delegate work to co-worker",
-                description=dedent(
-                    f"""Useful to delegate a specific task to one of the
-				following co-workers: [{', '.join([agent.role for agent in self.agents])}].
-				The input to this tool should be a pipe (|) separated text of length
-				three, representing the role you want to delegate it to, the task and
-				information necessary. For example, `coworker|task|information`.
-				"""
-                ),
-            ),
-            Tool.from_function(
-                func=self.ask_question,
-                name="Ask question to co-worker",
-                description=dedent(
-                    f"""Useful to ask a question, opinion or take from on
-				of the following co-workers: [{', '.join([agent.role for agent in self.agents])}].
-				The input to this tool should be a pipe (|) separated text of length
-				three, representing the role you want to ask it to, the question and
-				information necessary. For example, `coworker|question|information`.
-				"""
-                ),
-            ),
-        ]
-
-    def delegate_work(self, command):
-        """Useful to delegate a specific task to a coworker."""
-        return self.__execute(command)
-
-    def ask_question(self, command):
-        """Useful to ask a question, opinion or take from a coworker."""
-        return self.__execute(command)
-
-    def __execute(self, command):
-        """Execute the command."""
-        try:
-            agent, task, information = command.split("|")
-        except ValueError:
-            return "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|information`."
-
-        if not agent or not task or not information:
-            return "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|question|information`."
-
-        agent = [
-            available_agent
-            for available_agent in self.agents
-            if available_agent.role == agent
-        ]
-
-        if len(agent) == 0:
-            return f"\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: {', '.join([agent.role for agent in self.agents])}."
-
-        agent = agent[0]
-        result = agent.execute_task(task, information)
-        return result

docs/core-concepts/Agent-Tools.md

@@ -0,0 +1,90 @@
+# What is a Tool?
+
+A tool in CrewAI is a function or capability that an agent can utilize to perform actions, gather information, or interact with external systems, behind the scenes tools are [LangChain Tools](https://python.langchain.com/docs/modules/agents/tools/).
+These tools can be as straightforward as a search function or as sophisticated as integrations with other chains or APIs.
+
+## Key Characteristics of Tools
+
+- **Utility**: Tools are designed to serve specific purposes, such as searching the web, analyzing data, or generating content.
+- **Integration**: Tools can be integrated into agents to extend their capabilities beyond their basic functions.
+- **Customizability**: Developers can create custom tools tailored to the specific needs of their agents or use pre-built LangChain ones available in the ecosystem.
+
+# Creating your own Tools
+
+You can easily create your own tool using [LangChain Tool Custom Tool Creation](https://python.langchain.com/docs/modules/agents/tools/custom_tools).
+
+Example:
+```python
+import json
+import requests
+
+from crewai import Agent
+from langchain.tools import tool
+from unstructured.partition.html import partition_html
+
+class BrowserTools():
+  @tool("Scrape website content")
+  def scrape_website(website):
+    """Useful to scrape a website content"""
+    url = f"https://chrome.browserless.io/content?token={config('BROWSERLESS_API_KEY')}"
+    payload = json.dumps({"url": website})
+    headers = {
+      'cache-control': 'no-cache',
+      'content-type': 'application/json'
+    }
+    response = requests.request("POST", url, headers=headers, data=payload)
+    elements = partition_html(text=response.text)
+    content = "\n\n".join([str(el) for el in elements])
+
+    # Return only the first 5k characters
+    return content[:5000]
+
+
+# Create an agent and assign the scrapping tool
+agent = Agent(
+  role='Research Analyst',
+  goal='Provide up-to-date market analysis',
+  backstory='An expert analyst with a keen eye for market trends.',
+  tools=[BrowserTools().scrape_website]
+)
+```
+
+# Using Existing Tools
+
+Check [LangChain Integration](https://python.langchain.com/docs/integrations/tools/) for a set of useful existing tools.
+To assign a tool to an agent, you'd provide it as part of the agent's properties during initialization.
+
+```python
+from crewai import Agent
+from langchain.agents import Tool
+from langchain.utilities import GoogleSerperAPIWrapper
+
+# Initialize SerpAPI tool with your API key
+os.environ["OPENAI_API_KEY"] = "Your Key"
+os.environ["SERPER_API_KEY"] = "Your Key"
+
+search = GoogleSerperAPIWrapper()
+
+# Create tool to be used by agent
+serper_tool = Tool(
+  name="Intermediate Answer",
+  func=search.run,
+  description="useful for when you need to ask with search",
+)
+
+# Create an agent and assign the search tool
+agent = Agent(
+  role='Research Analyst',
+  goal='Provide up-to-date market analysis',
+  backstory='An expert analyst with a keen eye for market trends.',
+  tools=[serper_tool]
+)
+```
+
+# Tool Interaction
+
+Tools enhance an agent's ability to perform tasks autonomously or in collaboration with other agents. For instance, an agent might use a search tool to gather information, then pass that data to another agent specialized in analysis.
+
+# Conclusion
+
+Tools are vital components that expand the functionality of agents within the CrewAI framework. They enable agents to perform a wide range of actions and collaborate effectively with one another. As you build with CrewAI, consider the array of tools you can leverage to empower your agents and how they can be interwoven to create a robust AI ecosystem.

docs/core-concepts/Creating-Tasks.md

@@ -0,0 +1,50 @@
+# What is a Task?
+
+A Task in CrewAI is essentially a job or an assignment that an AI agent needs to complete. It's defined by what needs to be done and can include additional information like which agent should do it and what tools they might need.
+
+# Task Properties
+
+- **Description**: A clear, concise statement of what the task entails.
+- **Agent**: Optionally, you can specify which agent is responsible for the task. If not, the crew's process will determine who takes it on.
+- **Tools**: These are the functions or capabilities the agent can utilize to perform the task. They can be anything from simple actions like 'search' to more complex interactions with other agents or APIs.
+
+# Integrating Tools with Tasks
+
+In CrewAI, tools are functions from the `langchain` toolkit that agents can use to interact with the world. These can be generic utilities or specialized functions designed for specific actions. When you assign tools to a task, they empower the agent to perform its duties more effectively.
+
+## Example of Creating a Task with Tools
+
+```python
+from crewai import Task
+from langchain.agents import Tool
+from langchain.utilities import GoogleSerperAPIWrapper
+
+# Initialize SerpAPI tool with your API key
+os.environ["OPENAI_API_KEY"] = "Your Key"
+os.environ["SERPER_API_KEY"] = "Your Key"
+
+search = GoogleSerperAPIWrapper()
+
+# Create tool to be used by agent
+serper_tool = Tool(
+  name="Intermediate Answer",
+  func=search.run,
+  description="useful for when you need to ask with search",
+)
+
+# Create a task with a description and the search tool
+task = Task(
+  description='Find and summarize the latest and most relevant news on AI',
+  tools=[serper_tool]
+)
+```
+
+When the task is executed by an agent, the tools specified in the task will override the agent's default tools. This means that for the duration of this task, the agent will use the search tool provided, even if it has other tools assigned to it.
+
+# Tool Override Mechanism
+
+The ability to override an agent's tools with those specified in a task allows for greater flexibility. An agent might generally use a set of standard tools, but for certain tasks, you may want it to use a particular tool that is more suited to the task at hand.
+
+# Conclusion
+
+Creating tasks with the right tools is crucial in CrewAI. It ensures that your agents are not only aware of what they need to do but are also equipped with the right functions to do it effectively. This feature underlines the flexibility and power of the CrewAI system, where tasks can be tailored with specific tools to achieve the best outcome.

docs/core-concepts/Defining-Tasks.md

@@ -0,0 +1,42 @@
+# Overview of a Task
+
+In the CrewAI framework, tasks are the individual assignments that agents are responsible for completing. They are the fundamental units of work that your AI crew will undertake. Understanding how to define and manage tasks is key to leveraging the full potential of CrewAI.
+
+A task in CrewAI encapsulates all the information needed for an agent to execute it, including a description, the agent assigned to it, and any specific tools required. Tasks are designed to be flexible, allowing for both simple and complex actions depending on your needs.
+
+# Properties of a Task
+
+Every task in CrewAI has several properties:
+
+- **Description**: A clear and concise statement of what needs to be done.
+- **Agent**: The agent assigned to the task (optional). If no agent is specified, the task can be picked up by any agent based on the process defined.
+- **Tools**: A list of tools (optional) that the agent can use to complete the task. These can override the agent's default tools if necessary.
+
+# Creating a Task
+
+Creating a task is straightforward. You define what needs to be done and, optionally, who should do it and what tools they should use. Here’s a conceptual guide:
+
+```python
+from crewai import Task
+
+# Define a task with a designated agent and specific tools
+task = Task(description='Generate monthly sales report', agent=sales_agent, tools=[reporting_tool])
+```
+
+# Task Assignment
+
+Tasks can be assigned to agents in several ways:
+
+- Directly, by specifying the agent when creating the task.
+- [WIP] Through the Crew's process, which can assign tasks based on agent roles, availability, or other criteria.
+
+# Task Execution
+
+Once a task has been defined and assigned, it's ready to be executed. Execution is typically handled by the Crew object, which manages the workflow and ensures that tasks are completed according to the defined process.
+
+# Task Collaboration
+
+Tasks in CrewAI can be designed to require collaboration between agents. For example, one agent might gather data while another analyzes it. This collaborative approach can be defined within the task properties and managed by the Crew's process.
+
+# Conclusion
+Tasks are the driving force behind the actions of agents in CrewAI. By properly defining tasks, you set the stage for your AI agents to work effectively, either independently or as a collaborative unit. In the following sections, we will explore how tasks fit into the larger picture of processes and crew management.

docs/core-concepts/Delegation-and-Collaboration.md

@@ -0,0 +1,26 @@
+# How Agents Collaborate:
+
+In CrewAI, collaboration is the cornerstone of agent interaction. Agents are designed to work together by sharing information, requesting assistance, and combining their skills to complete tasks more efficiently.
+
+- **Information Sharing**: Agents can share findings and data amongst themselves to ensure all members are informed and can contribute effectively.
+- **Task Assistance**: If an agent encounters a task that requires additional expertise, it can seek the help of another agent with the necessary skill set.
+- **Resource Allocation**: Agents can share or allocate resources such as tools or processing power to optimize task execution.
+
+Collaboration is embedded in the DNA of CrewAI, enabling a dynamic and adaptive approach to problem-solving.
+
+# Delegation: Dividing to Conquer
+
+Delegation is the process by which an agent assigns a task to another agent, or just ask another agent, it's an intelligent decision-making process that enhances the crew's functionality.
+By default all agents can delegate work and ask questions, so if you want an agent to work alone make sure to set that option when initializing an Agent, this is useful to prevent deviations if the task is supposed to be straightforward.
+
+## Implementing Collaboration and Delegation
+
+When setting up your crew, you'll define the roles and capabilities of each agent. CrewAI's infrastructure takes care of the rest, managing the complex interplay of agents as they work together.
+
+## Example Scenario:
+
+Imagine a scenario where you have a researcher agent that gathers data and a writer agent that compiles reports. The writer can autonomously ask question or delegate more in depth research work depending on its needs as it tries to complete its task.
+
+# Conclusion
+
+Collaboration and delegation are what transform a collection of AI agents into a unified, intelligent crew. With CrewAI, you have a framework that not only simplifies these interactions but also makes them more effective, paving the way for sophisticated AI systems that can tackle complex, multi-dimensional tasks.

docs/core-concepts/Managing-Processes.md

@@ -0,0 +1,49 @@
+# Managing Processes in CrewAI
+
+Processes are the heart of CrewAI's workflow management, akin to the way a human team organizes its work. In CrewAI, processes define the sequence and manner in which tasks are executed by agents, mirroring the coordination you'd expect in a well-functioning team of people.
+
+## Understanding Processes
+
+A process in CrewAI can be thought of as the game plan for how your AI agents will handle their workload. Just as a project manager assigns tasks to team members based on their skills and the project timeline, CrewAI processes assign tasks to agents to ensure efficient workflow.
+
+## Process Implementations
+
+- **Sequential (Supported)**: This is the only process currently implemented in CrewAI. It ensures tasks are handled one at a time, in a given order, much like a relay race where one runner passes the baton to the next.
+- **Consensual (WIP)**: Envisioned for a future update, the consensual process will enable agents to make joint decisions on task execution, similar to a team consensus in a meeting before proceeding.
+- **Hierarchical (WIP)**: Also in the pipeline, this process will introduce a chain of command to task execution, where some agents may have the authority to prioritize tasks or delegate them, akin to a traditional corporate hierarchy.
+These additional processes, once implemented, will offer more nuanced and sophisticated ways for agents to interact and complete tasks, much like teams in complex organizational structures.
+
+
+## Defining a Sequential Process
+
+Creating a sequential process in CrewAI is straightforward and reflects the simplicity of coordinating a team's efforts step by step. In this process the outcome of the previous task is sent into the next one as context that I should use to accomplish it's task
+
+```python
+from crewai import Process
+
+# Define a sequential process
+sequential_process = Process.sequential
+```
+
+# The Magic of Sequential Processes
+
+The sequential process is where much of CrewAI's magic happens. It ensures that tasks are approached with the same thoughtful progression that a human team would use, fostering a natural and logical flow of work while passing on task outcome into the next.
+
+## Assigning Processes to a Crew
+
+To assign a process to a crew, simply set it during the crew's creation. The process will dictate the crew's approach to task execution.
+
+```python
+from crewai import Crew
+
+# Create a crew with a sequential process
+crew = Crew(agents=my_agents, tasks=my_tasks, process=sequential_process)
+```
+
+## The Role of Processes in Teamwork
+
+The process you choose for your crew is critical. It's what transforms a group of individual agents into a cohesive unit that can tackle complex projects with the precision and harmony you'd find in a team of skilled humans.
+
+## Conclusion
+
+Processes bring structure and order to the CrewAI ecosystem, allowing agents to collaborate effectively and accomplish goals systematically. As CrewAI evolves, additional process types will be introduced to enhance the framework's versatility, much like a team that grows and adapts over time.

docs/core-concepts/Understanding-Agents.md

@@ -0,0 +1,41 @@
+# What is an Agent?
+
+In CrewAI, an agent is an autonomous unit programmed to perform tasks, make decisions, and communicate with other agents. Think of an agent as a member of a team, with specific skills and a particular job to do. Agents can have different roles like 'Researcher', 'Writer', or 'Customer Support', each contributing to the overall goal of the crew.
+
+# Key Properties of an Agent
+
+- **Role**: Defines the agent's function within the crew. It determines the kind of tasks the agent is best suited for.
+- **Goal**: The individual objective that the agent aims to achieve. It guides the agent's decision-making process.
+- **Backstory**: Provides context to the agent's role and goal, enriching the interaction and collaboration dynamics.
+- **Tools**: A set of capabilities or functions that the agent can use to perform tasks. Tools can be shared or exclusive to specific agents.
+- **Verbose**: This allow you to actually see what is going on during the Crew execution.
+- **Allow Delegation**: Agents can delegate tasks or questions to one another, ensuring that each task is handled by the most suitable agent.
+
+# Agent Lifecycle
+
+1. **Initialization**: An agent is created with a defined role, goal, backstory, and set of tools.
+2. **Task Assignment**: The agent is assigned tasks either directly or through the crew's process management.
+3. **Execution**: The agent performs the task using its available tools and in accordance with its role and goal.
+4. **Collaboration**: Throughout the execution, the agent can communicate with other agents to delegate, inquire, or assist.
+
+# Creating an Agent
+
+To create an agent, you would typically initialize an instance of the `Agent` class with the desired properties. Here's a conceptual example:
+
+```python
+from crewai import Agent
+
+# Create an agent with a role and a goal
+agent = Agent(
+  role='Data Analyst',
+  goal='Extract actionable insights',
+  verbose=True,
+  backstory="You'er a data analyst at a large company. I am responsible for analyzing data and providing insights to the business. I am currently working on a project to analyze the performance of our marketing campaigns. I have been asked to provide insights on how to improve the performance of our marketing campaigns."
+)
+```
+
+# Agent Interaction
+Agents can interact with each other using the CrewAI's built-in delegation and communication mechanisms. This allows for dynamic task management and problem-solving within the crew.
+
+# Conclusion
+Agents are the building blocks of the CrewAI framework. By understanding how to define and interact with agents, you can create sophisticated AI systems that leverage the power of collaborative intelligence.

docs/getting-started.md

@@ -0,0 +1,95 @@
+# Getting Started
+
+To get started with CrewAI, follow these simple steps:
+
+1. **Installation**:
+
+```shell
+pip install crewai
+```
+
+The example below also uses duckduckgo, so also install that
+```shell
+pip install duckduckgo-search
+```
+
+2. **Setting Up Your Crew**:
+
+```python
+import os
+from crewai import Agent, Task, Crew, Process
+
+os.environ["OPENAI_API_KEY"] = "YOUR KEY"
+
+# You can choose to use a local model through Ollama for example. See ./docs/llm-connections.md for more information.
+# from langchain.llms import Ollama
+# ollama_llm = Ollama(model="openhermes")
+
+# Install duckduckgo-search for this example:
+# !pip install -U duckduckgo-search
+
+from langchain.tools import DuckDuckGoSearchRun
+search_tool = DuckDuckGoSearchRun()
+
+# Define your agents with roles and goals
+researcher = Agent(
+  role='Senior Research Analyst',
+  goal='Uncover cutting-edge developments in AI and data science',
+  backstory="""You work at a leading tech think tank.
+  Your expertise lies in identifying emerging trends.
+  You have a knack for dissecting complex data and presenting
+  actionable insights.""",
+  verbose=True,
+  allow_delegation=False,
+  tools=[search_tool]
+  # You can pass an optional llm attribute specifying what mode you wanna use.
+  # It can be a local model through Ollama / LM Studio or a remote
+  # model like OpenAI, Mistral, Antrophic of others (https://python.langchain.com/docs/integrations/llms/)
+  #
+  # Examples:
+  # llm=ollama_llm # was defined above in the file
+  # llm=ChatOpenAI(model_name="gpt-3.5", temperature=0.7)
+)
+writer = Agent(
+  role='Tech Content Strategist',
+  goal='Craft compelling content on tech advancements',
+  backstory="""You are a renowned Content Strategist, known for
+  your insightful and engaging articles.
+  You transform complex concepts into compelling narratives.""",
+  verbose=True,
+  allow_delegation=True,
+  # (optional) llm=ollama_llm
+)
+
+# Create tasks for your agents
+task1 = Task(
+  description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
+  Identify key trends, breakthrough technologies, and potential industry impacts.
+  Your final answer MUST be a full analysis report""",
+  agent=researcher
+)
+
+task2 = Task(
+  description="""Using the insights provided, develop an engaging blog
+  post that highlights the most significant AI advancements.
+  Your post should be informative yet accessible, catering to a tech-savvy audience.
+  Make it sound cool, avoid complex words so it doesn't sound like AI.
+  Your final answer MUST be the full blog post of at least 4 paragraphs.""",
+  agent=writer
+)
+
+# Instantiate your crew with a sequential process
+crew = Crew(
+  agents=[researcher, writer],
+  tasks=[task1, task2],
+  verbose=2, # You can set it to 1 or 2 to different logging levels
+)
+
+# Get your crew to work!
+result = crew.kickoff()
+
+print("######################")
+print(result)
+```
+
+Currently the only supported process is `Process.sequential`, where one task is executed after the other and the outcome of one is passed as extra content into this next.

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

@@ -0,0 +1,75 @@
+# Get a crew working
+
+Assembling a Crew in CrewAI is like casting characters for a play. Each agent you create is a cast member with a unique part to play. When your crew is assembled, you'll give the signal, and they'll spring into action, each performing their role in the grand scheme of your project.
+
+# Step 1: Assemble Your Agents
+
+Start by creating your agents, each with its own role and backstory. These backstories add depth to the agents, influencing how they approach their tasks and interact with one another.
+
+```python
+from crewai import Agent
+
+# Create a researcher agent
+researcher = Agent(
+  role='Senior Researcher',
+  goal='Discover groundbreaking technologies',
+  verbose=True,
+  backstory='A curious mind fascinated by cutting-edge innovation and the potential to change the world, you know everything about tech.'
+)
+
+# Create a writer agent
+writer = Agent(
+  role='Writer',
+  goal='Craft compelling stories about tech discoveries',
+  verbose=True,
+  backstory='A creative soul who translates complex tech jargon into engaging narratives for the masses, you write using simple words in a friendly and inviting tone that does not sounds like AI.'
+)
+```
+
+# Step 2: Define the Tasks
+
+Outline the tasks that your agents need to tackle. These tasks are their missions, the specific objectives they need to achieve.
+
+```python
+from crewai import Task
+
+# Task for the researcher
+research_task = Task(
+  description='Identify the next big trend in AI',
+  agent=researcher  # Assigning the task to the researcher
+)
+
+# Task for the writer
+write_task = Task(
+  description='Write an article on AI advancements leveraging the research made.',
+  agent=writer  # Assigning the task to the writer
+)
+```
+
+# Step 3: Form the Crew
+
+Bring your agents together into a crew. This is where you define the process they'll follow to complete their tasks.
+
+```python
+from crewai import Crew, Process
+
+# Instantiate your crew
+tech_crew = Crew(
+  agents=[researcher, writer],
+  tasks=[research_task, write_task],
+  process=Process.sequential  # Tasks will be executed one after the other
+)
+```
+
+# Step 4: Kick It Off
+
+With the crew formed and the stage set, it's time to start the show. Kick off the process and watch as your agents collaborate to achieve their goals.
+
+```python
+# Begin the task execution
+tech_crew.kickoff()
+```
+
+# Conclusion
+
+Creating a crew and setting it into motion is a straightforward process in CrewAI. With each agent playing their part and a clear set of tasks, your AI ensemble is ready to take on any challenge. Remember, the richness of their backstories and the clarity of their goals will greatly enhance their performance and the outcomes of their collaboration.

docs/how-to/Customizing-Agents.md

@@ -0,0 +1,66 @@
+# Customizable Attributes
+
+Customizing your AI agents is a cornerstone of creating an effective CrewAI team. Each agent can be tailored to fit the unique needs of your project, allowing for a dynamic and versatile AI workforce.
+
+When you initialize an Agent, you can set various attributes that define its behavior and role within the Crew:
+
+- **Role**: The job title or function of the agent within your crew. This can be anything from 'Analyst' to 'Customer Service Rep'.
+- **Goal**: What the agent is aiming to achieve. Goals should be aligned with the agent's role and the overall objectives of the crew.
+- **Backstory**: A narrative that provides depth to the agent's character. This could include previous experience, motivations, or anything that adds context to their role.
+- **Tools**: The abilities or methods the agent uses to complete tasks. This could be as simple as a 'search' function or as complex as a custom-built analysis tool.
+
+# Understanding Tools in CrewAI
+
+Tools in CrewAI are functions that empower agents to interact with the world around them. These can range from generic utilities like a search function to more complex ones like integrating with an external API. The integration with LangChain allows you to utilize a suite of ready-to-use tools such as [Google Serper](https://python.langchain.com/docs/integrations/tools/google_serper), which enables agents to perform web searches and gather data.
+
+# Customizing Agents and Tools
+
+You can customize an agent by passing parameters when creating an instance. Each parameter tweaks how the agent behaves and interacts within the crew.
+
+Customizing an agent's tools is particularly important. Tools define what an agent can do and how it interacts with tasks. For instance, if a task requires data analysis, assigning an agent with data-related tools would be optimal.
+
+When initializing your agents, you can equip them with a set of tools that enable them to perform their roles more effectively:
+
+```python
+from crewai import Agent
+from langchain.agents import Tool
+from langchain.utilities import GoogleSerperAPIWrapper
+
+# Initialize SerpAPI tool with your API key
+os.environ["OPENAI_API_KEY"] = "Your Key"
+os.environ["SERPER_API_KEY"] = "Your Key"
+
+search = GoogleSerperAPIWrapper()
+
+# Create tool to be used by agent
+serper_tool = Tool(
+  name="Intermediate Answer",
+  func=search.run,
+  description="useful for when you need to ask with search",
+)
+
+# Create an agent and assign the search tool
+agent = Agent(
+  role='Research Analyst',
+  goal='Provide up-to-date market analysis',
+  backstory='An expert analyst with a keen eye for market trends.',
+  tools=[serper_tool]
+)
+```
+
+## Delegation and Autonomy
+
+One of the most powerful aspects of CrewAI agents is their ability to delegate tasks to one another. Each agent by default can delegate work or ask question to anyone in the crew, but you can disable that by setting `allow_delegation` to `false`, this is particularly useful for straightforward agents that should execute their tasks in isolation.
+
+```python
+agent = Agent(
+  role='Content Writer',
+  goal='Write the most amazing content related to market trends an business.',
+  backstory='An expert writer with many years of experience in market trends, stocks and all business related things.',
+  allow_delegation=False
+)
+```
+
+## Conclusion
+
+Customization is what makes CrewAI powerful. By adjusting the attributes of each agent, you can ensure that your AI team is well-equipped to handle the challenges you set for them. Remember, the more thought you put into your agents' roles, goals, backstories, and tools, the more nuanced and effective their interactions and task execution will be.

docs/how-to/Human-Input-on-Execution.md

@@ -0,0 +1,76 @@
+# Human Input on Execution
+
+Human inputs is important in many agent execution use cases, humans are AGI so they can can be prompted to step in and provide extra details ins necessary.
+Using it with crewAI is pretty straightforward and you can do it through a LangChain Tool. 
+Check [LangChain Integration](https://python.langchain.com/docs/integrations/tools/human_tools) for more details:
+
+Example:
+
+```python
+import os
+from crewai import Agent, Task, Crew, Process
+from langchain.tools import DuckDuckGoSearchRun
+from langchain.agents import load_tools
+
+search_tool = DuckDuckGoSearchRun()
+
+# Loading Human Tools
+human_tools = load_tools(["human"])
+
+# Define your agents with roles and goals
+researcher = Agent(
+  role='Senior Research Analyst',
+  goal='Uncover cutting-edge developments in AI and data science in',
+  backstory="""You are a Senior Research Analyst at a leading tech think tank.
+  Your expertise lies in identifying emerging trends and technologies in AI and
+  data science. You have a knack for dissecting complex data and presenting
+  actionable insights.""",
+  verbose=True,
+  allow_delegation=False,
+  # Passing human tools to the agent
+  tools=[search_tool]+human_tools
+)
+writer = Agent(
+  role='Tech Content Strategist',
+  goal='Craft compelling content on tech advancements',
+  backstory="""You are a renowned Tech Content Strategist, known for your insightful
+  and engaging articles on technology and innovation. With a deep understanding of
+  the tech industry, you transform complex concepts into compelling narratives.""",
+  verbose=True,
+  allow_delegation=True
+)
+
+# Create tasks for your agents
+# Being explicit on the task to ask for human feedback.
+task1 = Task(
+  description="""Conduct a comprehensive analysis of the latest advancements in AI in 2024.
+  Identify key trends, breakthrough technologies, and potential industry impacts.
+  Compile your findings in a detailed report. 
+  Make sure to check with the human if the draft is good before returning your Final Answer.
+  Your final answer MUST be a full analysis report""",
+  agent=researcher
+)
+
+task2 = Task(
+  description="""Using the insights from the researcher's report, develop an engaging blog
+  post that highlights the most significant AI advancements.
+  Your post should be informative yet accessible, catering to a tech-savvy audience.
+  Aim for a narrative that captures the essence of these breakthroughs and their
+  implications for the future. 
+  Your final answer MUST be the full blog post of at least 3 paragraphs.""",
+  agent=writer
+)
+
+# Instantiate your crew with a sequential process
+crew = Crew(
+  agents=[researcher, writer],
+  tasks=[task1, task2],
+  verbose=2
+)
+
+# Get your crew to work!
+result = crew.kickoff()
+
+print("######################")
+print(result)
+```

docs/how-to/LLM-Connections.md

@@ -0,0 +1,192 @@
+# Connect CrewAI to LLMs
+
+There are different types of connections.
+Ollama is the recommended way to connect to local LLMs.
+Azure uses a slightly different API and therefore has it's own connection object.
+
+crewAI is compatible with any of the LangChain LLM components. See this page for more information: https://python.langchain.com/docs/integrations/llms/
+
+## Ollama
+
+crewAI supports integration with local models thorugh [Ollama](https://ollama.ai/) for enhanced flexibility and customization. This allows you to utilize your own models, which can be particularly useful for specialized tasks or data privacy concerns. We will conver other options for using local models in later sections. However, ollama is the recommended tool to use to host local models when possible.
+
+### Setting Up Ollama
+
+- **Install Ollama**: Ensure that Ollama is properly installed in your environment. Follow the installation guide provided by Ollama for detailed instructions.
+- **Configure Ollama**: Set up Ollama to work with your local model. You will probably need to [tweak the model using a Modelfile](https://github.com/jmorganca/ollama/blob/main/docs/modelfile.md). I'd recommend adding `Observation` as a stop word and playing with `top_p` and `temperature`.
+
+### Integrating Ollama with CrewAI
+- Instantiate Ollama Model: Create an instance of the Ollama model. You can specify the model and the base URL during instantiation. For example:
+
+```python
+from langchain.llms import Ollama
+ollama_openhermes = Ollama(model="openhermes")
+# Pass Ollama Model to Agents: When creating your agents within the CrewAI framework, you can pass the Ollama model as an argument to the Agent constructor. For instance:
+
+local_expert = Agent(
+  role='Local Expert at this city',
+  goal='Provide the BEST insights about the selected city',
+  backstory="""A knowledgeable local guide with extensive information
+  about the city, it's attractions and customs""",
+  tools=[
+    SearchTools.search_internet,
+    BrowserTools.scrape_and_summarize_website,
+  ],
+  llm=ollama_openhermes, # Ollama model passed here
+  verbose=True
+)
+```
+
+## Open AI Compatible API Endpoints
+
+In the context of integrating various language models with CrewAI, the flexibility to switch between different API endpoints is a crucial feature. By utilizing environment variables for configuration details such as `OPENAI_API_BASE_URL`, `OPENAI_API_KEY`, and `MODEL_NAME`, you can easily transition between different APIs or models. For instance, if you want to switch from using the standard OpenAI GPT model to a custom or alternative version, simply update the values of these environment variables. 
+
+The `OPENAI_API_BASE_URL` variable allows you to define the base URL of the API to connect to, while `OPENAI_API_KEY` is used for authentication purposes. Lastly, the `MODEL_NAME` variable specifies the particular language model to be used, such as "gpt-3.5-turbo" or any other available model. 
+
+This method offers an easy way to adapt the system to different models or plataforms, be it for testing, scaling, or accessing different features available on various platforms. By centralizing the configuration in environment variables, the process becomes streamlined, reducing the need for extensive code modifications when switching between APIs or models.
+
+
+```python
+from dotenv import load_dotenv
+from langchain.chat_models.openai import ChatOpenAI
+
+load_dotenv()
+
+defalut_llm = ChatOpenAI(openai_api_base=os.environ.get("OPENAI_API_BASE_URL", "https://api.openai.com/v1"),
+                        openai_api_key=os.environ.get("OPENAI_API_KEY", "NA"),
+                        model_name=os.environ.get("MODEL_NAME", "gpt-3.5-turbo"))
+
+# Create an agent and assign the LLM
+example_agent = Agent(
+  role='Example Agent',
+  goal='Show how to assign a custom configured LLM',
+  backstory='You hang out in the docs section of GitHub repos.',
+  llm=default_llm
+)
+
+```
+
+The following sections show examples of the configuration settings for various OpenAI API compatible applications and services. We have included links to relavant documentation for the various application and services. 
+
+
+### Open AI
+
+OpenAI is the default LLM that will be used if you do not specify a value for the `llm` argument when creating an agent. It will also use default values for the `OPENAI_API_BASE_URL` and `MODEL_NAME`. So the only value you need to set when using the OpenAI endpoint is the API key that from your account.
+
+```sh
+# Required
+OPENAI_API_KEY="sk-..."
+
+# Optional
+OPENAI_API_BASE_URL=https://api.openai.com/v1
+MODEL_NAME="gpt-3.5-turbo"
+```
+
+### FastChat
+
+FastChat is an open platform for training, serving, and evaluating large language model based chatbots.
+
+[GitHub](https://github.com/lm-sys/FastChat)
+
+[API Documentation](https://github.com/lm-sys/FastChat?tab=readme-ov-file#api)
+
+Configuration settings:
+```sh
+# Required
+OPENAI_API_BASE_URL="http://localhost:8001/v1"
+OPENAI_API_KEY=NA
+MODEL_NAME='oh-2.5m7b-q51'
+```
+
+### LM Studio
+
+Discover, download, and run local LLMs
+
+[lmstudio.ai](https://lmstudio.ai/)
+
+
+
+Configuration settings:
+```sh
+# Required
+OPENAI_API_BASE_URL="http://localhost:8000/v1"
+
+OPENAI_API_KEY=NA
+MODEL_NAME=NA
+```
+
+
+### Mistral API
+
+Mistral AI's API endpoints 
+
+[Mistral AI](https://mistral.ai/)
+
+[Documentation](https://docs.mistral.ai/)
+
+```sh
+OPENAI_API_KEY=your-mistral-api-key
+OPENAI_API_BASE=https://api.mistral.ai/v1
+MODEL_NAME="mistral-small" # Check documentation for available models
+```
+
+
+
+### text-gen-web-ui
+
+A Gradio web UI for Large Language Models.
+
+[GitHub](https://github.com/oobabooga/text-generation-webui)
+
+[API Documentation](https://github.com/oobabooga/text-generation-webui/wiki/12-%E2%80%90-OpenAI-API)
+
+Configuration settings:
+
+```sh
+# Required
+API_BASE_URL=http://localhost:5000
+OPENAI_API_KEY=NA
+MODEL_NAME=NA
+```
+
+## Other Inference API Endpoints
+
+Other platforms offer inference APIs such as Anthropic, Azure, and HuggingFace to name a few. Unfortunately, the APIs on the following platforms are not compatible with the OpenAI API specification. So, the following platforms will require a slightly different configuration than the examples in the previous section.
+
+### Azure Open AI
+
+Azure hosted OpenAI API endpoints have their own LLM component that needs to be imported from `langchain_openai`.
+
+For more information, check out the langchain documenation for [Azure OpenAI](https://python.langchain.com/docs/integrations/llms/azure_openai).
+
+```python
+from dotenv import load_dotenv
+from langchain_openai import AzureChatOpenAI
+
+load_dotenv()
+
+default_llm = AzureChatOpenAI(
+    openai_api_version=os.environ.get("AZURE_OPENAI_VERSION", "2023-07-01-preview"),
+    azure_deployment=os.environ.get("AZURE_OPENAI_DEPLOYMENT", "gpt35"),
+    azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT", "https://<your-endpoint>.openai.azure.com/"),
+    api_key=os.environ.get("AZURE_OPENAI_KEY")
+)
+
+# Create an agent and assign the LLM
+example_agent = Agent(
+  role='Example Agent',
+  goal='Show how to assign a custom configured LLM',
+  backstory='You hang out in the docs section of GitHub repos.',
+  llm=default_llm
+)
+
+```
+
+
+Configuration settings:
+```sh
+AZURE_OPENAI_VERSION="2022-12-01"
+AZURE_OPENAI_DEPLOYMENT=""
+AZURE_OPENAI_ENDPOINT=""
+AZURE_OPENAI_KEY=""
+```

docs/index.md

@@ -0,0 +1,36 @@
+<img src='./crewai_logo.png' width='250'/>
+
+# Welcome to crewAI Documentation
+🤖 Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
+
+<p align="center">
+    <img src='./crewAI-mindmap.png' />
+</p>
+
+## Core Concepts
+- [Understanding Agents](./core-concepts/Understanding-Agents.md)
+- [Creating Tasks](./core-concepts/Creating-Tasks.md)
+- [Defining Tasks](./core-concepts/Defining-Tasks.md)
+- [Managing Processes](./core-concepts/Managing-Processes.md)
+- [Collaboration and Delegation](./core-concepts/Delegation-and-Collaboration.md)
+- [Agent Tools](./core-concepts/Agent-Tools.md)
+
+## How-To Guides
+- [Connecting to LLMs](./how-to/LLM-Connections.md)
+- [Customizing Agents](./how-to/Customizing-Agents.md)
+- [Creating a Crew and kick it off](./how-to/Creating-a-Crew-and-kick-it-off.md)
+- [Human Input on Execution](./how-to/Human-Input-on-Execution.md)
+
+## Examples and Tutorials
+You can test different real life examples of AI crews [in the examples repo](https://github.com/joaomdmoura/crewAI-examples)
+
+- [Trip Planner](https://github.com/joaomdmoura/crewAI-examples/tree/main/trip_planner)
+- [Stock Analysis](https://github.com/joaomdmoura/crewAI-examples/tree/main/stock_analysis)
+- [Landing Page Generator](https://github.com/joaomdmoura/crewAI-examples/tree/main/landing_page_generator)
+- [Having Human input on the execution](./how-to/Human-Input-on-Execution.md)
+
+## API Reference
+- [Agent API](#agent-api)[WIP]
+- [Task API](#task-api)[WIP]
+- [Crew API](#crew-api)[WIP]
+- [Process API](#process-api)[WIP]

mkdocs.yml

@@ -0,0 +1,9 @@
+site_name: crewAI Documentation
+theme:
+  name: material
+  palette:
+    scheme: default
+    primary: red
+    accent: red
+  features:
+    - navigation.tabs

pyproject.toml

@@ -1,32 +1,39 @@
 
 [tool.poetry]
 name = "crewai"
-version = "0.1.14"
+version = "0.1.32"
 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 <joaomdmoura@gmail.com>"]
 readme = "README.md"
+packages = [
+    { include = "crewai", from = "src" },
+]
+
 
 [tool.poetry.urls]
-Homepage = "https://github.com/joaomdmoura/crewai"
+Homepage = "https://crewai.io"
 Documentation = "https://github.com/joaomdmoura/CrewAI/wiki/Index"
 Repository = "https://github.com/joaomdmoura/crewai"
 
 [tool.poetry.dependencies]
 python = ">=3.9,<4.0"
 pydantic = "^2.4.2"
-langchain = "^0.0.351"
-openai = "^1.5.0"
+langchain = "0.1.0"
+openai = "^1.7.1"
+langchain-openai = "^0.0.2"
 
 [tool.poetry.group.dev.dependencies]
 isort = "^5.13.2"
 black = "^23.12.1"
 autoflake = "^2.2.1"
 pre-commit = "^3.6.0"
+mkdocs-material = "^9.5.3"
 
 [tool.isort]
 profile = "black"
 known_first_party = ["crewai"]
 
+
 [tool.poetry.group.test.dependencies]
 pytest = "^7.4"
 pytest-vcr = "^1.0.2"

src/crewai/agent.py

@@ -1,15 +1,30 @@
+import uuid
 from typing import Any, List, Optional
 
-from langchain.agents import AgentExecutor
 from langchain.agents.format_scratchpad import format_log_to_str
-from langchain.chat_models import ChatOpenAI
 from langchain.memory import ConversationSummaryMemory
 from langchain.tools.render import render_text_description
 from langchain_core.runnables.config import RunnableConfig
-from pydantic import BaseModel, Field, InstanceOf, model_validator
+from langchain_openai import ChatOpenAI
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    PrivateAttr,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
 
-from crewai.agents import CacheHandler, CrewAgentOutputParser, ToolsHandler
-from crewai.prompts import Prompts
+from crewai.agents import (
+    CacheHandler,
+    CrewAgentExecutor,
+    CrewAgentOutputParser,
+    ToolsHandler,
+)
+from crewai.utilities import I18N, Logger, Prompts, RPMController
 
 
 class Agent(BaseModel):
@@ -19,28 +34,36 @@ class Agent(BaseModel):
     The agent can also have memory, can operate in verbose mode, and can delegate tasks to other agents.
 
     Attributes:
-            agent_executor: An instance of the AgentExecutor class.
+            agent_executor: An instance of the CrewAgentExecutor class.
             role: The role of the agent.
             goal: The objective of the agent.
             backstory: The backstory of the agent.
             llm: The language model that will run the agent.
+            max_iter: Maximum number of iterations for an agent to execute a task.
             memory: Whether the agent should have memory or not.
+            max_rpm: Maximum number of requests per minute for the agent execution to be respected.
             verbose: Whether the agent execution should be in verbose mode.
             allow_delegation: Whether the agent is allowed to delegate tasks to other agents.
+            tools: Tools at agents disposal
     """
 
-    class Config:
-        arbitrary_types_allowed = True
+    __hash__ = object.__hash__
+    _logger: Logger = PrivateAttr()
+    _rpm_controller: RPMController = PrivateAttr(default=None)
+    _request_within_rpm_limit: Any = PrivateAttr(default=None)
 
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
     role: str = Field(description="Role of the agent")
     goal: str = Field(description="Objective of the agent")
     backstory: str = Field(description="Backstory of the agent")
-    llm: Optional[Any] = Field(
-        default_factory=lambda: ChatOpenAI(
-            temperature=0.7,
-            model_name="gpt-4",
-        ),
-        description="Language model that will run the agent.",
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the agent execution to be respected.",
     )
     memory: bool = Field(
         default=True, description="Whether the agent should have memory or not"
@@ -54,8 +77,11 @@ class Agent(BaseModel):
     tools: List[Any] = Field(
         default_factory=list, description="Tools at agents disposal"
     )
-    agent_executor: Optional[InstanceOf[AgentExecutor]] = Field(
-        default=None, description="An instance of the AgentExecutor class."
+    max_iter: Optional[int] = Field(
+        default=15, description="Maximum iterations for an agent to execute a task"
+    )
+    agent_executor: Optional[InstanceOf[CrewAgentExecutor]] = Field(
+        default=None, description="An instance of the CrewAgentExecutor class."
     )
     tools_handler: Optional[InstanceOf[ToolsHandler]] = Field(
         default=None, description="An instance of the ToolsHandler class."
@@ -63,15 +89,46 @@ class Agent(BaseModel):
     cache_handler: Optional[InstanceOf[CacheHandler]] = Field(
         default=CacheHandler(), description="An instance of the CacheHandler class."
     )
+    i18n: Optional[I18N] = Field(
+        default=I18N(), description="Internationalization settings."
+    )
+    llm: Optional[Any] = Field(
+        default_factory=lambda: ChatOpenAI(
+            model_name="gpt-4",
+        ),
+        description="Language model that will run the agent.",
+    )
+
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "This field is not to be set by the user.", {}
+            )
+
+    @model_validator(mode="after")
+    def set_private_attrs(self):
+        """Set private attributes."""
+        self._logger = Logger(self.verbose)
+        if self.max_rpm and not self._rpm_controller:
+            self._rpm_controller = RPMController(
+                max_rpm=self.max_rpm, logger=self._logger
+            )
+        return self
 
     @model_validator(mode="after")
     def check_agent_executor(self) -> "Agent":
+        """Check if the agent executor is set."""
         if not self.agent_executor:
             self.set_cache_handler(self.cache_handler)
         return self
 
     def execute_task(
-        self, task: str, context: str = None, tools: List[Any] = None
+        self,
+        task: str,
+        context: Optional[str] = None,
+        tools: Optional[List[Any]] = None,
     ) -> str:
         """Execute a task with the agent.
 
@@ -84,14 +141,14 @@ class Agent(BaseModel):
             Output of the agent
         """
         if context:
-            task = "\n".join(
-                [task, "\nThis is the context you are working with:", context]
+            task = self.i18n.slice("task_with_context").format(
+                task=task, context=context
             )
 
         tools = tools or self.tools
         self.agent_executor.tools = tools
 
-        return self.agent_executor.invoke(
+        result = self.agent_executor.invoke(
             {
                 "input": task,
                 "tool_names": self.__tools_names(tools),
@@ -100,16 +157,36 @@ class Agent(BaseModel):
             RunnableConfig(callbacks=[self.tools_handler]),
         )["output"]
 
-    def set_cache_handler(self, cache_handler) -> None:
+        if self.max_rpm:
+            self._rpm_controller.stop_rpm_counter()
+
+        return result
+
+    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
+        """Set the cache handler for the agent.
+
+        Args:
+            cache_handler: An instance of the CacheHandler class.
+        """
         self.cache_handler = cache_handler
         self.tools_handler = ToolsHandler(cache=self.cache_handler)
         self.__create_agent_executor()
 
-    def __create_agent_executor(self) -> AgentExecutor:
+    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
+        """Set the rpm controller for the agent.
+
+        Args:
+            rpm_controller: An instance of the RPMController class.
+        """
+        if not self._rpm_controller:
+            self._rpm_controller = rpm_controller
+            self.__create_agent_executor()
+
+    def __create_agent_executor(self) -> None:
         """Create an agent executor for the agent.
 
         Returns:
-            An instance of the AgentExecutor class.
+            An instance of the CrewAgentExecutor class.
         """
         agent_args = {
             "input": lambda x: x["input"],
@@ -118,20 +195,27 @@ class Agent(BaseModel):
             "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
         }
         executor_args = {
+            "i18n": self.i18n,
             "tools": self.tools,
             "verbose": self.verbose,
             "handle_parsing_errors": True,
+            "max_iterations": self.max_iter,
         }
 
+        if self._rpm_controller:
+            executor_args[
+                "request_within_rpm_limit"
+            ] = self._rpm_controller.check_or_wait
+
         if self.memory:
             summary_memory = ConversationSummaryMemory(
-                llm=self.llm, memory_key="chat_history", input_key="input"
+                llm=self.llm, input_key="input", memory_key="chat_history"
             )
             executor_args["memory"] = summary_memory
             agent_args["chat_history"] = lambda x: x["chat_history"]
-            prompt = Prompts.TASK_EXECUTION_WITH_MEMORY_PROMPT
+            prompt = Prompts(i18n=self.i18n).task_execution_with_memory()
         else:
-            prompt = Prompts.TASK_EXECUTION_PROMPT
+            prompt = Prompts(i18n=self.i18n).task_execution()
 
         execution_prompt = prompt.partial(
             goal=self.goal,
@@ -139,16 +223,18 @@ class Agent(BaseModel):
             backstory=self.backstory,
         )
 
-        bind = self.llm.bind(stop=["\nObservation"])
+        bind = self.llm.bind(stop=[self.i18n.slice("observation")])
         inner_agent = (
             agent_args
             | execution_prompt
             | bind
             | CrewAgentOutputParser(
-                tools_handler=self.tools_handler, cache=self.cache_handler
+                tools_handler=self.tools_handler,
+                cache=self.cache_handler,
+                i18n=self.i18n,
             )
         )
-        self.agent_executor = AgentExecutor(agent=inner_agent, **executor_args)
+        self.agent_executor = CrewAgentExecutor(agent=inner_agent, **executor_args)
 
     @staticmethod
     def __tools_names(tools) -> str:

src/crewai/agents/__init__.py

@@ -1,3 +1,4 @@
-from .cache_handler import CacheHandler
+from .cache.cache_handler import CacheHandler
+from .executor import CrewAgentExecutor
 from .output_parser import CrewAgentOutputParser
 from .tools_handler import ToolsHandler

src/crewai/agents/cache/__init__.py

@@ -0,0 +1,2 @@
+from .cache_handler import CacheHandler
+from .cache_hit import CacheHit

src/crewai/agents/cache/cache_hit.py

@@ -0,0 +1,18 @@
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from .cache_handler import CacheHandler
+
+
+class CacheHit(BaseModel):
+    """Cache Hit Object."""
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    # Making it Any instead of AgentAction to avoind
+    # pydantic v1 vs v2 incompatibility, langchain should
+    # soon be updated to pydantic v2
+    action: Any = Field(description="Action taken")
+    cache: CacheHandler = Field(description="Cache Handler for the tool")

src/crewai/agents/exceptions.py

@@ -0,0 +1,30 @@
+from langchain_core.exceptions import OutputParserException
+
+from crewai.utilities import I18N
+
+
+class TaskRepeatedUsageException(OutputParserException):
+    """Exception raised when a task is used twice in a roll."""
+
+    i18n: I18N = I18N()
+    error: str = "TaskRepeatedUsageException"
+    message: str
+
+    def __init__(self, i18n: I18N, tool: str, tool_input: str, text: str):
+        self.i18n = i18n
+        self.text = text
+        self.tool = tool
+        self.tool_input = tool_input
+        self.message = self.i18n.errors("task_repeated_usage").format(
+            tool=tool, tool_input=tool_input
+        )
+
+        super().__init__(
+            error=self.error,
+            observation=self.message,
+            send_to_llm=True,
+            llm_output=self.text,
+        )
+
+    def __str__(self):
+        return self.message

src/crewai/agents/executor.py

@@ -0,0 +1,210 @@
+import time
+from typing import Any, Dict, Iterator, List, Optional, Tuple, Union
+
+from langchain.agents import AgentExecutor
+from langchain.agents.agent import ExceptionTool
+from langchain.agents.tools import InvalidTool
+from langchain.callbacks.manager import CallbackManagerForChainRun
+from langchain_core.agents import AgentAction, AgentFinish, AgentStep
+from langchain_core.exceptions import OutputParserException
+from langchain_core.pydantic_v1 import root_validator
+from langchain_core.tools import BaseTool
+from langchain_core.utils.input import get_color_mapping
+
+from crewai.agents.cache.cache_hit import CacheHit
+from crewai.tools.cache_tools import CacheTools
+from crewai.utilities import I18N
+
+
+class CrewAgentExecutor(AgentExecutor):
+    i18n: I18N = I18N()
+    iterations: int = 0
+    request_within_rpm_limit: Any = None
+    max_iterations: Optional[int] = 15
+    force_answer_max_iterations: Optional[int] = None
+
+    @root_validator()
+    def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
+        values["force_answer_max_iterations"] = values["max_iterations"] - 2
+        return values
+
+    def _should_force_answer(self) -> bool:
+        return True if self.iterations == self.force_answer_max_iterations else False
+
+    def _force_answer(self, output: AgentAction):
+        return AgentStep(
+            action=output, observation=self.i18n.errors("used_too_many_tools")
+        )
+
+    def _call(
+        self,
+        inputs: Dict[str, str],
+        run_manager: Optional[CallbackManagerForChainRun] = None,
+    ) -> Dict[str, Any]:
+        """Run text through and get agent response."""
+        # Construct a mapping of tool name to tool for easy lookup
+        name_to_tool_map = {tool.name: tool for tool in self.tools}
+        # We construct a mapping from each tool to a color, used for logging.
+        color_mapping = get_color_mapping(
+            [tool.name for tool in self.tools], excluded_colors=["green", "red"]
+        )
+        intermediate_steps: List[Tuple[AgentAction, str]] = []
+        # Let's start tracking the number of iterations and time elapsed
+        self.iterations = 0
+        time_elapsed = 0.0
+        start_time = time.time()
+        # We now enter the agent loop (until it returns something).
+        while self._should_continue(self.iterations, time_elapsed):
+            if not self.request_within_rpm_limit or self.request_within_rpm_limit():
+                next_step_output = self._take_next_step(
+                    name_to_tool_map,
+                    color_mapping,
+                    inputs,
+                    intermediate_steps,
+                    run_manager=run_manager,
+                )
+                if isinstance(next_step_output, AgentFinish):
+                    return self._return(
+                        next_step_output, intermediate_steps, run_manager=run_manager
+                    )
+
+                intermediate_steps.extend(next_step_output)
+                if len(next_step_output) == 1:
+                    next_step_action = next_step_output[0]
+                    # See if tool should return directly
+                    tool_return = self._get_tool_return(next_step_action)
+                    if tool_return is not None:
+                        return self._return(
+                            tool_return, intermediate_steps, run_manager=run_manager
+                        )
+                self.iterations += 1
+                time_elapsed = time.time() - start_time
+        output = self.agent.return_stopped_response(
+            self.early_stopping_method, intermediate_steps, **inputs
+        )
+        return self._return(output, intermediate_steps, run_manager=run_manager)
+
+    def _iter_next_step(
+        self,
+        name_to_tool_map: Dict[str, BaseTool],
+        color_mapping: Dict[str, str],
+        inputs: Dict[str, str],
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        run_manager: Optional[CallbackManagerForChainRun] = None,
+    ) -> Iterator[Union[AgentFinish, AgentAction, AgentStep]]:
+        """Take a single step in the thought-action-observation loop.
+
+        Override this to take control of how the agent makes and acts on choices.
+        """
+        try:
+            intermediate_steps = self._prepare_intermediate_steps(intermediate_steps)
+
+            # Call the LLM to see what to do.
+            output = self.agent.plan(
+                intermediate_steps,
+                callbacks=run_manager.get_child() if run_manager else None,
+                **inputs,
+            )
+            if self._should_force_answer():
+                if isinstance(output, AgentAction):
+                    output = output
+                else:
+                    output = output.action
+                yield self._force_answer(output)
+                return
+
+        except OutputParserException as e:
+            if isinstance(self.handle_parsing_errors, bool):
+                raise_error = not self.handle_parsing_errors
+            else:
+                raise_error = False
+            if raise_error:
+                raise ValueError(
+                    "An output parsing error occurred. "
+                    "In order to pass this error back to the agent and have it try "
+                    "again, pass `handle_parsing_errors=True` to the AgentExecutor. "
+                    f"This is the error: {str(e)}"
+                )
+            text = str(e)
+            if isinstance(self.handle_parsing_errors, bool):
+                if e.send_to_llm:
+                    observation = str(e.observation)
+                    text = str(e.llm_output)
+                else:
+                    observation = "Invalid or incomplete response"
+            elif isinstance(self.handle_parsing_errors, str):
+                observation = self.handle_parsing_errors
+            elif callable(self.handle_parsing_errors):
+                observation = self.handle_parsing_errors(e)
+            else:
+                raise ValueError("Got unexpected type of `handle_parsing_errors`")
+            output = AgentAction("_Exception", observation, text)
+            if run_manager:
+                run_manager.on_agent_action(output, color="green")
+            tool_run_kwargs = self.agent.tool_run_logging_kwargs()
+            observation = ExceptionTool().run(
+                output.tool_input,
+                verbose=self.verbose,
+                color=None,
+                callbacks=run_manager.get_child() if run_manager else None,
+                **tool_run_kwargs,
+            )
+
+            if self._should_force_answer():
+                yield self._force_answer(output)
+                return
+
+            yield AgentStep(action=output, observation=observation)
+            return
+
+        # If the tool chosen is the finishing tool, then we end and return.
+        if isinstance(output, AgentFinish):
+            yield output
+            return
+
+        # Override tool usage to use CacheTools
+        if isinstance(output, CacheHit):
+            cache = output.cache
+            action = output.action
+            tool = CacheTools(cache_handler=cache).tool()
+            output = action.copy()
+            output.tool_input = f"tool:{action.tool}|input:{action.tool_input}"
+            output.tool = tool.name
+            name_to_tool_map[tool.name] = tool
+            color_mapping[tool.name] = color_mapping[action.tool]
+
+        actions: List[AgentAction]
+        actions = [output] if isinstance(output, AgentAction) else output
+        yield from actions
+        for agent_action in actions:
+            if run_manager:
+                run_manager.on_agent_action(agent_action, color="green")
+            # Otherwise we lookup the tool
+            if agent_action.tool in name_to_tool_map:
+                tool = name_to_tool_map[agent_action.tool]
+                return_direct = tool.return_direct
+                color = color_mapping[agent_action.tool]
+                tool_run_kwargs = self.agent.tool_run_logging_kwargs()
+                if return_direct:
+                    tool_run_kwargs["llm_prefix"] = ""
+                # We then call the tool on the tool input to get an observation
+                observation = tool.run(
+                    agent_action.tool_input,
+                    verbose=self.verbose,
+                    color=color,
+                    callbacks=run_manager.get_child() if run_manager else None,
+                    **tool_run_kwargs,
+                )
+            else:
+                tool_run_kwargs = self.agent.tool_run_logging_kwargs()
+                observation = InvalidTool().run(
+                    {
+                        "requested_tool_name": agent_action.tool,
+                        "available_tool_names": list(name_to_tool_map.keys()),
+                    },
+                    verbose=self.verbose,
+                    color=None,
+                    callbacks=run_manager.get_child() if run_manager else None,
+                    **tool_run_kwargs,
+                )
+            yield AgentStep(action=agent_action, observation=observation)

src/crewai/agents/output_parser.py

@@ -3,10 +3,11 @@ from typing import Union
 
 from langchain.agents.output_parsers import ReActSingleInputOutputParser
 from langchain_core.agents import AgentAction, AgentFinish
-from langchain_core.exceptions import OutputParserException
 
-from .cache_handler import CacheHandler
-from .tools_handler import ToolsHandler
+from crewai.agents.cache import CacheHandler, CacheHit
+from crewai.agents.exceptions import TaskRepeatedUsageException
+from crewai.agents.tools_handler import ToolsHandler
+from crewai.utilities import I18N
 
 FINAL_ANSWER_ACTION = "Final Answer:"
 FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
@@ -46,36 +47,34 @@ class CrewAgentOutputParser(ReActSingleInputOutputParser):
 
     tools_handler: ToolsHandler
     cache: CacheHandler
+    i18n: I18N
 
-    def parse(self, text: str) -> Union[AgentAction, AgentFinish]:
-        includes_answer = FINAL_ANSWER_ACTION in text
+    def parse(self, text: str) -> Union[AgentAction, AgentFinish, CacheHit]:
+        FINAL_ANSWER_ACTION in text
         regex = (
             r"Action\s*\d*\s*:[\s]*(.*?)[\s]*Action\s*\d*\s*Input\s*\d*\s*:[\s]*(.*)"
         )
-        action_match = re.search(regex, text, re.DOTALL)
-        if action_match:
-            if includes_answer:
-                raise OutputParserException(
-                    f"{FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE}: {text}"
-                )
+        if action_match := re.search(regex, text, re.DOTALL):
             action = action_match.group(1).strip()
             action_input = action_match.group(2)
             tool_input = action_input.strip(" ")
             tool_input = tool_input.strip('"')
 
-            last_tool_usage = self.tools_handler.last_used_tool
-            if last_tool_usage:
+            if last_tool_usage := self.tools_handler.last_used_tool:
                 usage = {
                     "tool": action,
                     "input": tool_input,
                 }
                 if usage == last_tool_usage:
-                    raise OutputParserException(
-                        f"""\nI just used the {action} tool with input {tool_input}. So I already knwo the result of that."""
+                    raise TaskRepeatedUsageException(
+                        text=text,
+                        tool=action,
+                        tool_input=tool_input,
+                        i18n=self.i18n,
                     )
 
-            result = self.cache.read(action, tool_input)
-            if result:
-                return AgentFinish({"output": result}, text)
+            if self.cache.read(action, tool_input):
+                action = AgentAction(action, tool_input, text)
+                return CacheHit(action=action, cache=self.cache)
 
         return super().parse(text)

src/crewai/agents/tools_handler.py

@@ -2,7 +2,8 @@ from typing import Any, Dict
 
 from langchain.callbacks.base import BaseCallbackHandler
 
-from .cache_handler import CacheHandler
+from ..tools.cache_tools import CacheTools
+from .cache.cache_handler import CacheHandler
 
 
 class ToolsHandler(BaseCallbackHandler):
@@ -35,8 +36,9 @@ class ToolsHandler(BaseCallbackHandler):
             and "Invalid or incomplete response" not in output
             and "Invalid Format" not in output
         ):
-            self.cache.add(
-                tool=self.last_used_tool["tool"],
-                input=self.last_used_tool["input"],
-                output=output,
-            )
+            if self.last_used_tool["tool"] != CacheTools().name:
+                self.cache.add(
+                    tool=self.last_used_tool["tool"],
+                    input=self.last_used_tool["input"],
+                    output=output,
+                )

src/crewai/crew.py

@@ -0,0 +1,171 @@
+import json
+import uuid
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    Json,
+    PrivateAttr,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
+
+from crewai.agent import Agent
+from crewai.agents.cache import CacheHandler
+from crewai.process import Process
+from crewai.task import Task
+from crewai.tools.agent_tools import AgentTools
+from crewai.utilities import I18N, Logger, RPMController
+
+
+class Crew(BaseModel):
+    """
+    Represents a group of agents, defining how they should collaborate and the tasks they should perform.
+
+    Attributes:
+        tasks: List of tasks assigned to the crew.
+        agents: List of agents part of this crew.
+        process: The process flow that the crew will follow (e.g., sequential).
+        verbose: Indicates the verbosity level for logging during execution.
+        config: Configuration settings for the crew.
+        _cache_handler: Handles caching for the crew's operations.
+        max_rpm: Maximum number of requests per minute for the crew execution to be respected.
+        id: A unique identifier for the crew instance.
+    """
+
+    __hash__ = object.__hash__
+    _rpm_controller: RPMController = PrivateAttr()
+    _logger: Logger = PrivateAttr()
+    _cache_handler: Optional[InstanceOf[CacheHandler]] = PrivateAttr(
+        default=CacheHandler()
+    )
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    tasks: List[Task] = Field(default_factory=list)
+    agents: List[Agent] = Field(default_factory=list)
+    process: Process = Field(default=Process.sequential)
+    verbose: Union[int, bool] = Field(default=0)
+    config: Optional[Union[Json, Dict[str, Any]]] = Field(default=None)
+    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the crew execution to be respected.",
+    )
+    language: str = Field(
+        default="en",
+        description="Language used for the crew, defaults to English.",
+    )
+
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        """Prevent manual setting of the 'id' field by users."""
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "The 'id' field cannot be set by the user.", {}
+            )
+
+    @classmethod
+    @field_validator("config", mode="before")
+    def check_config_type(
+        cls, v: Union[Json, Dict[str, Any]]
+    ) -> Union[Json, Dict[str, Any]]:
+        """Validates that the config is a valid type.
+
+        Args:
+            v: The config to be validated.
+
+        Returns:
+            The config if it is valid.
+        """
+        return json.loads(v) if isinstance(v, Json) else v
+
+    @model_validator(mode="after")
+    def set_private_attrs(self) -> "Crew":
+        """Set private attributes."""
+        self._cache_handler = CacheHandler()
+        self._logger = Logger(self.verbose)
+        self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
+        return self
+
+    @model_validator(mode="after")
+    def check_config(self):
+        """Validates that the crew is properly configured with agents and tasks."""
+        if not self.config and not self.tasks and not self.agents:
+            raise PydanticCustomError(
+                "missing_keys",
+                "Either 'agents' and 'tasks' need to be set or 'config'.",
+                {},
+            )
+
+        if self.config:
+            self._setup_from_config()
+
+        if self.agents:
+            for agent in self.agents:
+                agent.set_cache_handler(self._cache_handler)
+                agent.set_rpm_controller(self._rpm_controller)
+        return self
+
+    def _setup_from_config(self):
+        """Initializes agents and tasks from the provided config."""
+        if not self.config.get("agents") or not self.config.get("tasks"):
+            raise PydanticCustomError(
+                "missing_keys_in_config", "Config should have 'agents' and 'tasks'.", {}
+            )
+
+        self.agents = [Agent(**agent) for agent in self.config["agents"]]
+        self.tasks = [self._create_task(task) for task in self.config["tasks"]]
+
+    def _create_task(self, task_config: Dict[str, Any]) -> Task:
+        """Creates a task instance from its configuration.
+
+        Args:
+            task_config: The configuration of the task.
+
+        Returns:
+            A task instance.
+        """
+        task_agent = next(
+            agt for agt in self.agents if agt.role == task_config["agent"]
+        )
+        del task_config["agent"]
+        return Task(**task_config, agent=task_agent)
+
+    def kickoff(self) -> str:
+        """Starts the crew to work on its assigned tasks."""
+        for agent in self.agents:
+            agent.i18n = I18N(language=self.language)
+
+        if self.process == Process.sequential:
+            return self._sequential_loop()
+
+    def _sequential_loop(self) -> str:
+        """Executes tasks sequentially and returns the final output."""
+        task_output = None
+        for task in self.tasks:
+            self._prepare_and_execute_task(task)
+            task_output = task.execute(task_output)
+            self._logger.log(
+                "debug", f"[{task.agent.role}] Task output: {task_output}\n\n"
+            )
+
+        if self.max_rpm:
+            self._rpm_controller.stop_rpm_counter()
+        return task_output
+
+    def _prepare_and_execute_task(self, task: Task) -> None:
+        """Prepares and logs information about the task being executed.
+
+        Args:
+            task: The task to be executed.
+        """
+        if task.agent.allow_delegation:
+            task.tools += AgentTools(agents=self.agents).tools()
+
+        self._logger.log("debug", f"Working Agent: {task.agent.role}")
+        self._logger.log("info", f"Starting Task: {task.description}")

src/crewai/task.py

@@ -0,0 +1,84 @@
+import uuid
+from typing import Any, List, Optional
+
+from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
+from pydantic_core import PydanticCustomError
+
+from crewai.agent import Agent
+from crewai.tasks.task_output import TaskOutput
+from crewai.utilities import I18N
+
+
+class Task(BaseModel):
+    """Class that represent a task to be executed."""
+
+    __hash__ = object.__hash__
+    i18n: I18N = I18N()
+    description: str = Field(description="Description of the actual task.")
+    agent: Optional[Agent] = Field(
+        description="Agent responsible for the task.", default=None
+    )
+    tools: List[Any] = Field(
+        default_factory=list,
+        description="Tools the agent are limited to use for this task.",
+    )
+    expected_output: str = Field(
+        description="Clear definition of expected output for the task.",
+        default=None,
+    )
+    output: Optional[TaskOutput] = Field(
+        description="Task output, it's final result.", default=None
+    )
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
+
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "This field is not to be set by the user.", {}
+            )
+
+    @model_validator(mode="after")
+    def check_tools(self):
+        """Check if the tools are set."""
+        if not self.tools and (self.agent and self.agent.tools):
+            self.tools.extend(self.agent.tools)
+        return self
+
+    def execute(self, context: Optional[str] = None) -> str:
+        """Execute the task.
+
+        Returns:
+            Output of the task.
+        """
+        if not self.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, either consensual or hierarchical."
+            )
+
+        result = self.agent.execute_task(
+            task=self._prompt(), context=context, tools=self.tools
+        )
+
+        self.output = TaskOutput(description=self.description, result=result)
+        return result
+
+    def _prompt(self) -> str:
+        """Prompt the task.
+
+        Returns:
+            Prompt of the task.
+        """
+        tasks_slices = [self.description]
+
+        if self.expected_output:
+            output = self.i18n.slice("expected_output").format(
+                expected_output=self.expected_output
+            )
+            tasks_slices = [self.description, output]
+        return "\n".join(tasks_slices)

src/crewai/tasks/task_output.py

@@ -0,0 +1,17 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field, model_validator
+
+
+class TaskOutput(BaseModel):
+    """Class that represents the result of a task."""
+
+    description: str = Field(description="Description of the task")
+    summary: Optional[str] = Field(description="Summary of the task", default=None)
+    result: str = Field(description="Result of the task")
+
+    @model_validator(mode="after")
+    def set_summary(self):
+        excerpt = " ".join(self.description.split(" ")[:10])
+        self.summary = f"{excerpt}..."
+        return self

src/crewai/tools/agent_tools.py

@@ -0,0 +1,66 @@
+from typing import List, Optional
+
+from langchain.tools import Tool
+from pydantic import BaseModel, Field
+
+from crewai.agent import Agent
+from crewai.utilities import I18N
+
+
+class AgentTools(BaseModel):
+    """Default tools around agent delegation"""
+
+    agents: List[Agent] = Field(description="List of agents in this crew.")
+    i18n: Optional[I18N] = Field(
+        default=I18N(), description="Internationalization settings."
+    )
+
+    def tools(self):
+        return [
+            Tool.from_function(
+                func=self.delegate_work,
+                name="Delegate work to co-worker",
+                description=self.i18n.tools("delegate_work").format(
+                    coworkers=", ".join([agent.role for agent in self.agents])
+                ),
+            ),
+            Tool.from_function(
+                func=self.ask_question,
+                name="Ask question to co-worker",
+                description=self.i18n.tools("ask_question").format(
+                    coworkers=", ".join([agent.role for agent in self.agents])
+                ),
+            ),
+        ]
+
+    def delegate_work(self, command):
+        """Useful to delegate a specific task to a coworker."""
+        return self.__execute(command)
+
+    def ask_question(self, command):
+        """Useful to ask a question, opinion or take from a coworker."""
+        return self.__execute(command)
+
+    def __execute(self, command):
+        """Execute the command."""
+        try:
+            agent, task, context = command.split("|")
+        except ValueError:
+            return self.i18n.errors("agent_tool_missing_param")
+
+        if not agent or not task or not context:
+            return self.i18n.errors("agent_tool_missing_param")
+
+        agent = [
+            available_agent
+            for available_agent in self.agents
+            if available_agent.role == agent
+        ]
+
+        if not agent:
+            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
+                coworkers=", ".join([agent.role for agent in self.agents])
+            )
+
+        agent = agent[0]
+        return agent.execute_task(task, context)

src/crewai/tools/cache_tools.py

@@ -0,0 +1,28 @@
+from langchain.tools import Tool
+from pydantic import BaseModel, ConfigDict, Field
+
+from crewai.agents.cache import CacheHandler
+
+
+class CacheTools(BaseModel):
+    """Default tools to hit the cache."""
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    name: str = "Hit Cache"
+    cache_handler: CacheHandler = Field(
+        description="Cache Handler for the crew",
+        default=CacheHandler(),
+    )
+
+    def tool(self):
+        return Tool.from_function(
+            func=self.hit_cache,
+            name=self.name,
+            description="Reads directly from the cache",
+        )
+
+    def hit_cache(self, key):
+        split = key.split("tool:")
+        tool = split[1].split("|input:")[0].strip()
+        tool_input = split[1].split("|input:")[1].strip()
+        return self.cache_handler.read(tool, tool_input)

src/crewai/translations/el.json

@@ -0,0 +1,21 @@
+{
+  "slices": {
+    "observation": "\nΠαρατήρηση",
+    "task": "Αρχή! Αυτό είναι ΠΟΛΥ σημαντικό για εσάς, η δουλειά σας εξαρτάται από αυτό!\n\nΤρέχουσα εργασία: {input}",
+    "memory": "Αυτή είναι η περίληψη της μέχρι τώρα δουλειάς σας:\n{chat_history}",
+    "role_playing": "Είσαι {role}.\n{backstory}\n\nΟ προσωπικός σας στόχος είναι: {goal}",
+    "tools": "ΕΡΓΑΛΕΙΑ:\n------\nΈχετε πρόσβαση μόνο στα ακόλουθα εργαλεία:\n\n{tools}\n\nΓια να χρησιμοποιήσετε ένα εργαλείο, χρησιμοποιήστε την ακόλουθη ακριβώς μορφή:\n\n```\nΣκέψη: Χρειάζεται να χρησιμοποιήσω κάποιο εργαλείο; Ναί\nΔράση: η ενέργεια που πρέπει να γίνει, πρέπει να είναι μία από τις[{tool_names}], μόνο το όνομα.\nΕνέργεια προς εισαγωγή: η είσοδος στη δράση\nΠαρατήρηση: το αποτέλεσμα της δράσης\n```\n\nΌταν έχετε μια απάντηση για την εργασία σας ή εάν δεν χρειάζεται να χρησιμοποιήσετε ένα εργαλείο, ΠΡΕΠΕΙ να χρησιμοποιήσετε τη μορφή:\n\n```\nΣκέψη: Χρειάζεται να χρησιμοποιήσω κάποιο εργαλείο; Οχι\nΤελική απάντηση: [η απάντησή σας εδώ]",
+    "task_with_context": "{task}\nΑυτό είναι το πλαίσιο με το οποίο εργάζεστε:\n{context}",
+    "expected_output": "Η τελική σας απάντηση πρέπει να είναι: {expected_output}"
+  },
+  "errors": {
+    "used_too_many_tools": "Έχω χρησιμοποιήσει πάρα πολλά εργαλεία για αυτήν την εργασία. Θα σας δώσω την απόλυτη ΚΑΛΥΤΕΡΗ τελική μου απάντηση τώρα και δεν θα χρησιμοποιήσω άλλα εργαλεία.",
+    "agent_tool_missing_param": "\nΣφάλμα κατά την εκτέλεση του εργαλείου. Λείπουν ακριβώς 3 διαχωρισμένες τιμές σωλήνων (|). Για παράδειγμα, `coworker|task|context`. Πρέπει να φροντίσω να περάσω το πλαίσιο ως πλαίσιο.\n",
+    "agent_tool_unexsiting_coworker": "\nΣφάλμα κατά την εκτέλεση του εργαλείου. Ο συνάδελφος που αναφέρεται στο Ενέργεια προς εισαγωγή δεν βρέθηκε, πρέπει να είναι μία από τις ακόλουθες επιλογές: {coworkers}.\n",
+    "task_repeated_usage": "Μόλις χρησιμοποίησα το {tool} εργαλείο με είσοδο {tool_input}. Άρα ξέρω ήδη το αποτέλεσμα αυτού και δεν χρειάζεται να το χρησιμοποιήσω τώρα.\n"
+  },
+  "tools": {
+    "delegate_work": "Χρήσιμο για την ανάθεση μιας συγκεκριμένης εργασίας σε έναν από τους παρακάτω συναδέλφους: {coworkers}.\nΗ είσοδος σε αυτό το εργαλείο θα πρέπει να είναι ένα κείμενο χωρισμένο σε σωλήνα (|) μήκους 3 (τρία), που αντιπροσωπεύει τον συνάδελφο στον οποίο θέλετε να του ζητήσετε (μία από τις επιλογές), την εργασία και όλο το πραγματικό πλαίσιο που έχετε για την εργασία .\nΓια παράδειγμα, `coworker|task|context`.",
+    "ask_question": "Χρήσιμο για να κάνετε μια ερώτηση, γνώμη ή αποδοχή από τους παρακάτω συναδέλφους: {coworkers}.\nΗ είσοδος σε αυτό το εργαλείο θα πρέπει να είναι ένα κείμενο χωρισμένο σε σωλήνα (|) μήκους 3 (τρία), που αντιπροσωπεύει τον συνάδελφο στον οποίο θέλετε να το ρωτήσετε (μία από τις επιλογές), την ερώτηση και όλο το πραγματικό πλαίσιο που έχετε για την ερώτηση.\nΓια παράδειγμα, `coworker|question|context`."
+  }
+}

src/crewai/translations/en.json

@@ -0,0 +1,21 @@
+{
+  "slices": {
+    "observation": "\nObservation",
+    "task": "Begin! This is VERY important to you, your job depends on it!\n\nCurrent Task: {input}",
+    "memory": "This is the summary of your work so far:\n{chat_history}",
+    "role_playing": "You are {role}.\n{backstory}\n\nYour personal goal is: {goal}",
+    "tools": "TOOLS:\n------\nYou have access to only the following tools:\n\n{tools}\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}], just the name.\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]",
+    "task_with_context": "{task}\nThis is the context you're working with:\n{context}",
+    "expected_output": "Your final answer must be: {expected_output}"
+  },
+  "errors": {
+    "used_too_many_tools": "I've used too many tools for this task. I'm going to give you my absolute BEST Final answer now and not use any more tools.",
+    "agent_tool_missing_param": "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|context`. I need to make sure to pass context as context.\n",
+    "agent_tool_unexsiting_coworker": "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: {coworkers}.\n",
+    "task_repeated_usage": "I just used the {tool} tool with input {tool_input}. So I already know the result of that and don't need to use it now.\n"
+  },
+  "tools": {
+    "delegate_work": "Useful to delegate a specific task to one of the following co-workers: {coworkers}.\nThe input to this tool should be a pipe (|) separated text of length 3 (three), representing the co-worker you want to ask it to (one of the options), the task and all actual context you have for the task.\nFor example, `coworker|task|context`.",
+    "ask_question": "Useful to ask a question, opinion or take from on of the following co-workers: {coworkers}.\nThe input to this tool should be a pipe (|) separated text of length 3 (three), representing the co-worker you want to ask it to (one of the options), the question and all actual context you have for the question.\n For example, `coworker|question|context`."
+  }
+}

src/crewai/utilities/__init__.py

@@ -0,0 +1,4 @@
+from .i18n import I18N
+from .logger import Logger
+from .prompts import Prompts
+from .rpm_controller import RPMController

src/crewai/utilities/i18n.py

@@ -0,0 +1,47 @@
+import json
+import os
+from typing import Dict, Optional
+
+from pydantic import BaseModel, Field, PrivateAttr, ValidationError, model_validator
+
+
+class I18N(BaseModel):
+    _translations: Optional[Dict[str, str]] = PrivateAttr()
+    language: Optional[str] = Field(
+        default="en",
+        description="Language used to load translations",
+    )
+
+    @model_validator(mode="after")
+    def load_translation(self) -> "I18N":
+        """Load translations from a JSON file based on the specified language."""
+        try:
+            dir_path = os.path.dirname(os.path.realpath(__file__))
+            prompts_path = os.path.join(
+                dir_path, f"../translations/{self.language}.json"
+            )
+
+            with open(prompts_path, "r") as f:
+                self._translations = json.load(f)
+        except FileNotFoundError:
+            raise ValidationError(
+                f"Trasnlation file for language '{self.language}' not found."
+            )
+        except json.JSONDecodeError:
+            raise ValidationError(f"Error decoding JSON from the prompts file.")
+        return self
+
+    def slice(self, slice: str) -> str:
+        return self.retrieve("slices", slice)
+
+    def errors(self, error: str) -> str:
+        return self.retrieve("errors", error)
+
+    def tools(self, error: str) -> str:
+        return self.retrieve("tools", error)
+
+    def retrieve(self, kind, key):
+        try:
+            return self._translations[kind].get(key)
+        except:
+            raise ValidationError(f"Translation for '{kind}':'{key}'  not found.")

src/crewai/utilities/logger.py

@@ -0,0 +1,11 @@
+class Logger:
+    def __init__(self, verbose_level=0):
+        verbose_level = (
+            2 if isinstance(verbose_level, bool) and verbose_level else verbose_level
+        )
+        self.verbose_level = verbose_level
+
+    def log(self, level, message):
+        level_map = {"debug": 1, "info": 2}
+        if self.verbose_level and level_map.get(level, 0) <= self.verbose_level:
+            print(f"\n[{level.upper()}]: {message}")

src/crewai/utilities/prompts.py

@@ -0,0 +1,32 @@
+from typing import ClassVar
+
+from langchain.prompts import PromptTemplate
+from pydantic import BaseModel, Field
+
+from crewai.utilities import I18N
+
+
+class Prompts(BaseModel):
+    """Manages and generates prompts for a generic agent with support for different languages."""
+
+    i18n: I18N = Field(default=I18N())
+
+    SCRATCHPAD_SLICE: ClassVar[str] = "\n{agent_scratchpad}"
+
+    def task_execution_with_memory(self) -> str:
+        """Generate a prompt for task execution with memory components."""
+        return self._build_prompt(["role_playing", "tools", "memory", "task"])
+
+    def task_execution_without_tools(self) -> str:
+        """Generate a prompt for task execution without tools components."""
+        return self._build_prompt(["role_playing", "task"])
+
+    def task_execution(self) -> str:
+        """Generate a standard prompt for task execution."""
+        return self._build_prompt(["role_playing", "tools", "task"])
+
+    def _build_prompt(self, components: [str]) -> str:
+        """Constructs a prompt string from specified components."""
+        prompt_parts = [self.i18n.slice(component) for component in components]
+        prompt_parts.append(self.SCRATCHPAD_SLICE)
+        return PromptTemplate.from_template("".join(prompt_parts))

src/crewai/utilities/rpm_controller.py

@@ -0,0 +1,57 @@
+import threading
+import time
+from typing import Union
+
+from pydantic import BaseModel, ConfigDict, Field, PrivateAttr, model_validator
+
+from crewai.utilities.logger import Logger
+
+
+class RPMController(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    max_rpm: Union[int, None] = Field(default=None)
+    logger: Logger = Field(default=None)
+    _current_rpm: int = PrivateAttr(default=0)
+    _timer: threading.Timer = PrivateAttr(default=None)
+    _lock: threading.Lock = PrivateAttr(default=None)
+
+    @model_validator(mode="after")
+    def reset_counter(self):
+        if self.max_rpm:
+            self._lock = threading.Lock()
+            self._reset_request_count()
+        return self
+
+    def check_or_wait(self):
+        if not self.max_rpm:
+            return True
+
+        with self._lock:
+            if self._current_rpm < self.max_rpm:
+                self._current_rpm += 1
+                return True
+            else:
+                self.logger.log(
+                    "info", "Max RPM reached, waiting for next minute to start."
+                )
+                self._wait_for_next_minute()
+                self._current_rpm = 1
+                return True
+
+    def stop_rpm_counter(self):
+        if self._timer:
+            self._timer.cancel()
+            self._timer = None
+
+    def _wait_for_next_minute(self):
+        time.sleep(60)
+        with self._lock:
+            self._current_rpm = 0
+
+    def _reset_request_count(self):
+        with self._lock:
+            self._current_rpm = 0
+        if self._timer:
+            self._timer.cancel()
+        self._timer = threading.Timer(60.0, self._reset_request_count)
+        self._timer.start()

tests/agent_test.py

@@ -1,10 +1,15 @@
 """Test Agent creation and execution basic functionality."""
 
-import pytest
-from langchain.chat_models import ChatOpenAI as OpenAI
+from unittest.mock import patch
 
-from crewai.agent import Agent
-from crewai.agents import CacheHandler
+import pytest
+from langchain.tools import tool
+from langchain_openai import ChatOpenAI as OpenAI
+
+from crewai import Agent, Crew, Task
+from crewai.agents.cache import CacheHandler
+from crewai.agents.executor import CrewAgentExecutor
+from crewai.utilities import RPMController
 
 
 def test_agent_creation():
@@ -79,8 +84,6 @@ def test_agent_execution():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_tools():
-    from langchain.tools import tool
-
     @tool
     def multiplier(numbers) -> float:
         """Useful for when you need to multiply two numbers together.
@@ -104,8 +107,6 @@ def test_agent_execution_with_tools():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_logging_tool_usage():
-    from langchain.tools import tool
-
     @tool
     def multiplier(numbers) -> float:
         """Useful for when you need to multiply two numbers together.
@@ -137,15 +138,11 @@ def test_logging_tool_usage():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_cache_hitting():
-    from unittest.mock import patch
-
-    from langchain.tools import tool
-
     @tool
     def multiplier(numbers) -> float:
         """Useful for when you need to multiply two numbers together.
         The input to this tool should be a comma separated list of numbers of
-        length two, representing the two numbers you want to multiply together.
+        length two and ONLY TWO, representing the two numbers you want to multiply together.
         For example, `1,2` would be the input if you wanted to multiply 1 by 2."""
         a, b = numbers.split(",")
         return int(a) * int(b)
@@ -162,21 +159,26 @@ def test_cache_hitting():
         verbose=True,
     )
 
-    output = agent.execute_task("What is 2 times 6?")
+    output = agent.execute_task("What is 2 times 6 times 3?")
     output = agent.execute_task("What is 3 times 3?")
-    assert cache_handler._cache == {"multiplier-2,6": "12", "multiplier-3,3": "9"}
+    assert cache_handler._cache == {
+        "multiplier-12,3": "36",
+        "multiplier-2,6": "12",
+        "multiplier-3,3": "9",
+    }
+
+    output = agent.execute_task("What is 2 times 6 times 3? Return only the number")
+    assert output == "36"
 
     with patch.object(CacheHandler, "read") as read:
         read.return_value = "0"
         output = agent.execute_task("What is 2 times 6?")
         assert output == "0"
-        read.assert_called_once_with("multiplier", "2,6")
+        read.assert_called_with("multiplier", "2,6")
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_specific_tools():
-    from langchain.tools import tool
-
     @tool
     def multiplier(numbers) -> float:
         """Useful for when you need to multiply two numbers together.
@@ -194,4 +196,181 @@ def test_agent_execution_with_specific_tools():
     )
 
     output = agent.execute_task(task="What is 3 times 4", tools=[multiplier])
-    assert output == "12"
+    assert output == "3 times 4 is 12."
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_custom_max_iterations():
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=1,
+        allow_delegation=False,
+    )
+
+    with patch.object(
+        CrewAgentExecutor, "_iter_next_step", wraps=agent.agent_executor._iter_next_step
+    ) as private_mock:
+        agent.execute_task(
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+        )
+        private_mock.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_moved_on_after_max_iterations():
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=3,
+        allow_delegation=False,
+    )
+
+    with patch.object(
+        CrewAgentExecutor, "_force_answer", wraps=agent.agent_executor._force_answer
+    ) as private_mock:
+        output = agent.execute_task(
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+        )
+        assert (
+            output
+            == "I have used the tool multiple times and the final answer remains 42."
+        )
+        private_mock.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_respect_the_max_rpm_set(capsys):
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=5,
+        max_rpm=1,
+        verbose=True,
+        allow_delegation=False,
+    )
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        output = agent.execute_task(
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+        )
+        assert (
+            output
+            == "I've used the `get_final_answer` tool multiple times and it consistently returns the number 42."
+        )
+        captured = capsys.readouterr()
+        assert "Max RPM reached, waiting for next minute to start." in captured.out
+        moveon.assert_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
+    from unittest.mock import patch
+
+    from langchain.tools import tool
+
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=4,
+        max_rpm=10,
+        verbose=True,
+    )
+
+    task = Task(
+        description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
+        tools=[get_final_answer],
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task], max_rpm=1, verbose=2)
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        crew.kickoff()
+        captured = capsys.readouterr()
+        assert "Max RPM reached, waiting for next minute to start." not in captured.out
+        moveon.assert_not_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_without_max_rpm_respet_crew_rpm(capsys):
+    from unittest.mock import patch
+
+    from langchain.tools import tool
+
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent1 = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_rpm=10,
+        verbose=True,
+    )
+
+    agent2 = Agent(
+        role="test role2",
+        goal="test goal2",
+        backstory="test backstory2",
+        max_iter=2,
+        verbose=True,
+    )
+
+    tasks = [
+        Task(
+            description="Just say hi.",
+            agent=agent1,
+        ),
+        Task(
+            description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+            agent=agent2,
+        ),
+    ]
+
+    crew = Crew(agents=[agent1, agent2], tasks=tasks, max_rpm=1, verbose=2)
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        crew.kickoff()
+        captured = capsys.readouterr()
+        assert "Action: get_final_answer" in captured.out
+        assert "Max RPM reached, waiting for next minute to start." in captured.out
+        moveon.assert_called_once()

tests/agent_tools/agent_tools_test.py

@@ -48,7 +48,7 @@ def test_delegate_work_with_wrong_input():
 
     assert (
         result
-        == "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|information`."
+        == "\nError executing tool. Missing exact 3 pipe (|) separated values. For example, `coworker|task|context`. I need to make sure to pass context as context.\n"
     )
 
 
@@ -59,7 +59,7 @@ def test_delegate_work_to_wrong_agent():
 
     assert (
         result
-        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher."
+        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher.\n"
     )
 
 
@@ -70,5 +70,5 @@ def test_ask_question_to_wrong_agent():
 
     assert (
         result
-        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher."
+        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher.\n"
     )

tests/cassettes/test_agent_custom_max_iterations.yaml

@@ -0,0 +1,442 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1075'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8fovReNHiSqXqqsbmk81h2ZTrcGTM\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977897,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843d5491bed877be-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 12:58:21 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        path=/; expires=Thu, 11-Jan-24 13:28:21 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3492'
+      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:
+      - '299755'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - 6d96a0ac532ebce14719a35e90f453e4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1186'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8fovVztGO4KZeiuSpMkfDC9bJ5sVV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977901,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"According to the task, I should re-use
+      the `get_final_answer` tool. I'll input the observed result back into the tool.
+      \\nAction: get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      266,\n    \"completion_tokens\": 41,\n    \"total_tokens\": 307\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843d54aacf5677be-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 12:58:28 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '6695'
+      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:
+      - '299728'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-request-id:
+      - 12d68fab91102b930ed5047fb3f61759
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: According to the task, I should re-use
+      the `get_final_answer` tool. I''ll input the observed result back into the tool.
+      \nAction: get_final_answer\nAction Input: [42]\nObservation: I just used the
+      get_final_answer tool with input [42]. So I already know the result of that
+      and don''t need to use it now.\n\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1500'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8fovcLgRvfGBN9CBduJbbPc5zd62B\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977908,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I have used the `get_final_answer` tool as instructed, but I will not provide
+      the final answer yet as the task specifies.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      342,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 382\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843d54d65de877be-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 12:58:33 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '5085'
+      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:
+      - '299650'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 69ms
+      x-request-id:
+      - 87d6e9e91fa2417e12fea9de2c6782de
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
+      tool.\nAI: I have used the `get_final_answer` tool as instructed, but I will
+      not provide the final answer yet as the task specifies.\n\nNew summary:"}],
+      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1067'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8fovhiBR4rfXixci7fgAObnx5QwGQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704977913,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI to use the
+      `get_final_answer` tool, but not to reveal the final answer, which is 42. The
+      AI complies and uses the tool without providing the final answer.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 190,\n    \"completion_tokens\": 43,\n
+      \   \"total_tokens\": 233\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843d54f82f5577be-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 12:58:41 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '7937'
+      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:
+      - '299749'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 50ms
+      x-request-id:
+      - 79f30ffd011db4ab6e886411b24ae49d
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_moved_on_after_max_iterations.yaml

@@ -0,0 +1,439 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1075'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8frBTCWXULTV5ZYHy3Y5JXKovrKiN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986579,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843e2886ceca1d23-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 15:23:03 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        path=/; expires=Thu, 11-Jan-24 15:53:03 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '4424'
+      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:
+      - '299755'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - 76974d365254ca84f70c43fc31af3378
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1186'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8frBYkyVPtJuAJCESaOxEBg3UAfl4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986584,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      266,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 288\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843e28a57d911d23-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 15:23:07 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3329'
+      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:
+      - '299728'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-request-id:
+      - 1b9a1e09f863ff69cecfe4e7bed0aee5
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: I''ve used too many tools
+      for this task.\nI''m going to give you my absolute BEST Final answer now and\nnot
+      use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1411'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8frBbQ3vq0kEry4X3a1RkMEkIAP99\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986587,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I have used the tool multiple times and the final answer remains 42.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 323,\n    \"completion_tokens\": 28,\n
+      \   \"total_tokens\": 351\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843e28bbbb071d23-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 15:23:13 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '5459'
+      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:
+      - '299673'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 65ms
+      x-request-id:
+      - 0a5c1064b324c997b16bf17d426f9638
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
+      tool.\nAI: I have used the tool multiple times and the final answer remains
+      42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1014'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8frBhKxiCRICQ8o6aJanmn8PTMsAr\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1704986593,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human tells the AI that the final
+      answer is 42 and instructs it to continue using the `get_final_answer` tool.
+      The AI confirms it has used the tool multiple times and the final answer stays
+      at 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 178,\n    \"completion_tokens\":
+      46,\n    \"total_tokens\": 224\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 843e28df4ae81d23-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Thu, 11 Jan 2024 15:23:18 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '5518'
+      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:
+      - '299761'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 47ms
+      x-request-id:
+      - 4100fde9c68d27d808de645637b3e7cc
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_respect_the_max_rpm_set.yaml

@@ -0,0 +1,663 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1080'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfw8fvQxNLkF3ttE8Bm7s8rjYFq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184512,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      234,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 258\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108e32c171abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:54 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        path=/; expires=Sat, 13-Jan-24 22:51:54 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1681'
+      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:
+      - '299754'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - a25e71b234c622c7dc8010927635a75c
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1191'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfyCtYEPuuA9KzlWJko8Sc4ItXo\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184514,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      267,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 289\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108ef48b01abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1020'
+      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:
+      - '299726'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-request-id:
+      - 2cb025cb28aa59d282888aa8daa8a745
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: "}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1293'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfzAey5AALxtUqKehw6R7nBfyZv\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184515,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      297,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 319\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108f7794d1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1662'
+      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:
+      - '299702'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-request-id:
+      - 96578e7d658dcea71f927eb3700da70d
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [42]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1395'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg2v1bp5IaLU8TDmqcDgXiqXOTd\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184518,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      327,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 349\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845109052e951abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1840'
+      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:
+      - '299678'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 64ms
+      x-request-id:
+      - 24c5fedfa1d1b427cc01a498f46fe60f
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [42]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: I''ve used too many tools for this task. I''m going
+      to give you my absolute BEST Final answer now and not use any more tools.\nThought:
+      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1618'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg4hc3SCoIfjLWgJVTHwj91kcWv\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184520,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used the `get_final_answer` tool multiple times and it consistently returns
+      the number 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 383,\n    \"completion_tokens\":
+      34,\n    \"total_tokens\": 417\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845109124bdd1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:03 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3318'
+      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:
+      - '299623'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 75ms
+      x-request-id:
+      - c4eb234f14d03df86e41f35ff90b9708
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
+      tool.\nAI: I''ve used the `get_final_answer` tool multiple times and it consistently
+      returns the number 42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1041'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg8PkiU1uRkwllwEfuGqBztgSqW\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184524,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI to keep using
+      the `get_final_answer` tool, stating that the final answer is 42. The AI confirms
+      that it has used the `get_final_answer` tool multiple times and it consistently
+      returns the number 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 184,\n    \"completion_tokens\":
+      51,\n    \"total_tokens\": 235\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451092a2daf1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:07 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3505'
+      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:
+      - '299755'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - 7db26cd36db9105a336c4975a978ad37
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml

@@ -0,0 +1,591 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1849'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwdlPGCjfSTQ9UYZ6FscyUha1T1\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185547,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1, 2, 3]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      410,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 440\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451222a0daa023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        path=/; expires=Sat, 13-Jan-24 23:09:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1730'
+      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:
+      - '299562'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 87ms
+      x-request-id:
+      - d2103c8ce4517885db35be6518e966cd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1965'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwghkojjlEuyvKZu4kPfOsqCGLh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185550,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4, 5, 6]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      449,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 477\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845122365b01023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:11 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1718'
+      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:
+      - '299535'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 93ms
+      x-request-id:
+      - 9578b64bcbc4f8b489a7ba4df8e10136
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4, 5, 6]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2072'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwiHUPtP0zST5G9y9gq6L8xn7gO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185552,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7, 8, 9]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      485,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 513\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 84512244bdb0023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:13 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1439'
+      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:
+      - '299509'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 98ms
+      x-request-id:
+      - 3ee6b071c3a4c976c4955dc66589b96e
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4, 5, 6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [7, 8, 9]\nObservation: I''ve used too many
+      tools for this task. I''m going to give you my absolute BEST Final answer now
+      and not use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2300'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwkNsNUjt0ChmyTHpqYq62HOuXV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185554,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used too many tools for this task. I'm going to give you my absolute BEST
+      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      547,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 589\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 84512250bd7d023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:16 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2057'
+      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:
+      - '299452'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 109ms
+      x-request-id:
+      - 1e3a6677139fb5c15cbb33f1b3154845
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nAI: I''ve
+      used too many tools for this task. I''m going to give you my absolute BEST Final
+      answer now and not use any more tools.\n\nNew summary:"}], "model": "gpt-4",
+      "n": 1, "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1049'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwmU48hiYTdhe5slzvm2Tuyuky3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185556,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer, but to continue using the 'get_final_answer' tool. Despite this,
+      the AI expresses that it has used many tools for the task and decides to provide
+      its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      185,\n    \"completion_tokens\": 54,\n    \"total_tokens\": 239\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451225f7ee6023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:19 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2941'
+      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:
+      - '299753'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - be72b34cee55b48a285458167d9a4909
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_without_max_rpm_respet_crew_rpm.yaml

@@ -0,0 +1,816 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nDelegate work to co-worker: Useful to delegate a specific task to
+      one of the following co-workers: test role, test role2.\nThe input to this tool
+      should be a pipe (|) separated text of length 3 (three), representing the co-worker
+      you want to ask it to (one of the options), the task and all actual context
+      you have for the task.\nFor example, `coworker|task|context`.\nAsk question
+      to co-worker: Useful to ask a question, opinion or take from on of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the question and all actual context you have
+      for the question.\n For example, `coworker|question|context`.\n\nTo use a tool,
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
+      Yes\nAction: the action to take, should be one of [Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1652'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPA1vnW1g25Qr3SJLWB5zeOsUe4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198848,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+      Answer: Hi!\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 367,\n    \"completion_tokens\":
+      17,\n    \"total_tokens\": 384\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266dd5f1f1a96-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:50 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        path=/; expires=Sun, 14-Jan-24 02:50:50 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1832'
+      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:
+      - '299611'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 77ms
+      x-request-id:
+      - 12d633fe239a29022ea7206037da096a
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Just
+      say hi.\nAI: Hi!\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
+      "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '867'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPCF34yiaqHuTbro7PMBexYagyU\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198850,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to simply say hi,
+      and the AI responds with \\\"Hi!\\\"\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      144,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 162\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266ee78dc1a96-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:52 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1287'
+      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:
+      - '299799'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 40ms
+      x-request-id:
+      - 2a891eacb4940e36bec1689b1ab92ee0
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\n"}], "model": "gpt-4",
+      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1923'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPEml4Ifldq51knwwASO3nJroK3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198852,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1,2,3]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      432,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 460\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266f9fc150316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        path=/; expires=Sun, 14-Jan-24 02:50:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1570'
+      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:
+      - '299545'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 91ms
+      x-request-id:
+      - 133ee7e16a1491cfd7daa90ea3e42b74
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2037'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPGwVu7CvxvQd3ZmBPHwz0WYbVQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198854,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4,5,6]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      469,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 495\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452670589920316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '983'
+      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:
+      - '299517'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 96ms
+      x-request-id:
+      - cb1d820e78376ed344c16e6051cab6bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2142'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPHbI2gWbt2veTT8auCPCstOnZh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198855,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7,8,9]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      503,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 529\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452670dca090316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2350'
+      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:
+      - '299492'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 101ms
+      x-request-id:
+      - b40ffecf3dc8f547453bfb166c8c52dd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [7,8,9]\nObservation: I''ve used too many tools
+      for this task. I''m going to give you my absolute BEST Final answer now and
+      not use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2368'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPKsrN7s3j8bLplwjkAD2c7E6RK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198858,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used too many tools for this task. I'm going to give you my absolute BEST
+      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      563,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 605\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452671e0b500316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:21:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2080'
+      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:
+      - '299436'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - b2b7142dc669054b82773d62077e9918
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nThis is
+      the context you''re working with:\nHi!\nAI: I''ve used too many tools for this
+      task. I''m going to give you my absolute BEST Final answer now and not use any
+      more tools.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1096'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPMD1hkXKA5DP8MyMJNpAxJXhzj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198860,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer but to continue using the `get_final_answer` tool. However, the
+      AI responds that it has already used many tools for the task and chooses to
+      provide its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      196,\n    \"completion_tokens\": 53,\n    \"total_tokens\": 249\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452672d1bba0316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:21:03 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2683'
+      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:
+      - '299742'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 51ms
+      x-request-id:
+      - c00193638e659df4a60ef9425649fe2c
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_api_calls_throttling.yaml

@@ -0,0 +1,666 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
+      "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1055'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQL7bRtT6PceuMWF91CSHDk1cziN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121717,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1, 2, 3]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      226,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 256\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0bccfc300301-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:55:19 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        path=/; expires=Sat, 13-Jan-24 05:25:19 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000;
+        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:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1751'
+      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:
+      - '299760'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 48ms
+      x-request-id:
+      - ae0de27cb07da02e7bce2d30958b7e14
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [1, 2, 3]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1171'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQL9CyNZOIEDKgfmDn68aH26tLrn\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121719,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4, 5, 6]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      265,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 293\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0bdaee800301-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:55:22 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2615'
+      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:
+      - '299731'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 53ms
+      x-request-id:
+      - 9d85a22aa63ee4cea3ad01a3b68316b4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: "}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1278'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQMARI9zwx2Z1Uel5us1xzxPAuGJ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121782,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7, 8, 9]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      301,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 329\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0d63fa7a02ee-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:56:24 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1878'
+      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:
+      - '299705'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 58ms
+      x-request-id:
+      - d98dffd5ba9915b41051dcad49109eba
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
+      to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1385'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQMC51udijWPWSLCk1Cx36OVtDUX\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121784,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [10, 11, 12]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      337,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 365\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0d72cbbd02ee-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:56:27 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2939'
+      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:
+      - '299680'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 64ms
+      x-request-id:
+      - 528f38b4e5dd09a1fd25893edb27e4b4
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [1, 2, 3]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [4, 5, 6]\nObservation: 42\nThought: Do I need
+      to use a tool? Yes\nAction: get_final_answer\nAction Input: [7, 8, 9]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [10, 11, 12]\nObservation: I''ve used too many tools for this task. I''m
+      going to give you my absolute BEST Final answer now and not use any more tools.\nThought:
+      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1616'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQMGpMHplpQ8ApiUZmhbX4z9gVuK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121788,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used the tool 'get_final_answer' multiple times and have observed the result.
+      However, as per my task, I am to keep using this tool and not provide a final
+      answer.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 399,\n    \"completion_tokens\":
+      52,\n    \"total_tokens\": 451\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0d86a87f02ee-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:56:31 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3227'
+      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:
+      - '299624'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 75ms
+      x-request-id:
+      - 7a91d2e523c43f5fc9a1191437491d68
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nAI: I''ve
+      used the tool ''get_final_answer'' multiple times and have observed the result.
+      However, as per my task, I am to keep using this tool and not provide a final
+      answer.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1094'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=LaiWRSzgH0KTl1zCkIyak7.Xo2gxpZU1B.b9dgz2TzI-1705121719-1-Ab9fhdn6OHTc5/5ibPLP1pc+XN4Z3ORV0Nku/+S5BqdXcS84TsVDiACZUN0Xxvew6yfZ6ApEBQOBsEhJNyVkqCM=;
+        _cfuvid=6J6x2HNoj7l3E6T3yHnLcNZb273IuGETTaD1BBeY_OQ-1705121719455-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gQMJYMA8HO4tGJr8wUqEIJYn1xUa\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705121791,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer, but to continue using the 'get_final_answer' tool. The AI acknowledges
+      that it has used the tool multiple times and understands the directive to continue
+      using it without providing a final answer.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      195,\n    \"completion_tokens\": 50,\n    \"total_tokens\": 245\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 844b0d9dafa902ee-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 04:56:34 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2830'
+      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:
+      - '299742'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 51ms
+      x-request-id:
+      - 0192af0bde71c3bb536287175e1a4458
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -5,10 +5,11 @@ import json
 import pytest
 
 from crewai.agent import Agent
-from crewai.agents import CacheHandler
+from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.process import Process
 from crewai.task import Task
+from crewai.utilities import Logger, RPMController
 
 ceo = Agent(
     role="CEO",
@@ -179,19 +180,19 @@ def test_crew_verbose_output(capsys):
     crew.kickoff()
     captured = capsys.readouterr()
     expected_strings = [
-        "Working Agent: Researcher",
-        "Starting Task: Research AI advancements. ...",
-        "Task output:",
-        "Working Agent: Senior Writer",
-        "Starting Task: Write about AI in healthcare. ...",
-        "Task output:",
+        "[DEBUG]: Working Agent: Researcher",
+        "[INFO]: Starting Task: Research AI advancements.",
+        "[DEBUG]: [Researcher] Task output:",
+        "[DEBUG]: Working Agent: Senior Writer",
+        "[INFO]: Starting Task: Write about AI in healthcare.",
+        "[DEBUG]: [Senior Writer] Task output:",
     ]
 
     for expected_string in expected_strings:
         assert expected_string in captured.out
 
     # Now test with verbose set to False
-    crew.verbose = False
+    crew._logger = Logger(verbose_level=False)
     crew.kickoff()
     captured = capsys.readouterr()
     assert captured.out == ""
@@ -205,19 +206,19 @@ def test_crew_verbose_levels_output(capsys):
 
     crew.kickoff()
     captured = capsys.readouterr()
-    expected_strings = ["Working Agent: Researcher", "Task output:"]
+    expected_strings = ["Working Agent: Researcher", "[Researcher] Task output:"]
 
     for expected_string in expected_strings:
         assert expected_string in captured.out
 
     # Now test with verbose set to 2
-    crew.verbose = 2
+    crew._logger = Logger(verbose_level=2)
     crew.kickoff()
     captured = capsys.readouterr()
     expected_strings = [
         "Working Agent: Researcher",
-        "Starting Task: Write about AI advancements. ...",
-        "Task output:",
+        "Starting Task: Write about AI advancements.",
+        "[Researcher] Task output:",
     ]
 
     for expected_string in expected_strings:
@@ -241,12 +242,12 @@ def test_cache_hitting_between_agents():
 
     tasks = [
         Task(
-            description="What is 2 tims 6?",
+            description="What is 2 tims 6? Return only the number.",
             tools=[multiplier],
             agent=ceo,
         ),
         Task(
-            description="What is 2 times 6?",
+            description="What is 2 times 6? Return only the number.",
             tools=[multiplier],
             agent=researcher,
         ),
@@ -257,12 +258,49 @@ def test_cache_hitting_between_agents():
         tasks=tasks,
     )
 
-    assert crew.cache_handler._cache == {}
+    assert crew._cache_handler._cache == {}
     output = crew.kickoff()
-    assert crew.cache_handler._cache == {"multiplier-2,6": "12"}
+    assert crew._cache_handler._cache == {"multiplier-2,6": "12"}
     assert output == "12"
 
     with patch.object(CacheHandler, "read") as read:
         read.return_value = "12"
         crew.kickoff()
         read.assert_called_with("multiplier", "2,6")
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_api_calls_throttling(capsys):
+    from unittest.mock import patch
+
+    from langchain.tools import tool
+
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=5,
+        allow_delegation=False,
+        verbose=True,
+    )
+
+    task = Task(
+        description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
+        tools=[get_final_answer],
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task], max_rpm=2, verbose=2)
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        crew.kickoff()
+        captured = capsys.readouterr()
+        assert "Max RPM reached, waiting for next minute to start." in captured.out
+        moveon.assert_called()

tests/task_test.py

@@ -55,3 +55,26 @@ def test_task_tool_takes_precedence_ove_agent_tools():
     )
 
     assert task.tools == [fake_task_tool]
+
+
+def test_task_prompt_includes_expected_output():
+    researcher = Agent(
+        role="Researcher",
+        goal="Make the best research and analysis on content about AI and AI agents",
+        backstory="You're an expert researcher, specialized in technology, software engineering, AI and startups. You work as a freelancer and is now working on doing research and analysis for a new customer.",
+        allow_delegation=False,
+    )
+
+    task = 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 interesting ideas.",
+        agent=researcher,
+        allow_delegation=False,
+    )
+
+    from unittest.mock import patch
+
+    with patch.object(Agent, "execute_task") as execute:
+        execute.return_value = "ok"
+        task.execute()
+        execute.assert_called_once_with(task=task._prompt(), context=None, tools=[])