Reliability improvements (#77)

* fixing identation for AgentTools
* updating gitignore to exclude quick test script
* startingprompt translation
* supporting individual task output
* adding agent to task output
* cutting new version
* Updating README example

.circleci/config.yml

@@ -0,0 +1,27 @@
+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

.gitignore

@@ -2,5 +2,7 @@
 .pytest_cache
 __pycache__
 dist/
-*/**/cassettes/*
-.env
+.env
+assets/*
+.idea
+test.py

.pre-commit-config.yaml

@@ -0,0 +1,21 @@
+repos:
+
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 23.12.1
+    hooks:
+      - id: black
+        language_version: python3.11
+        files: \.(py)$
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: isort (python)
+        args: ["--profile", "black", "--filter-files"]
+
+  - repo: https://github.com/PyCQA/autoflake
+    rev: v2.2.1
+    hooks:
+      - id: autoflake
+        args: ['--in-place', '--remove-all-unused-imports', '--remove-unused-variables', '--ignore-init-module-imports']

README.md

@@ -1,12 +1,18 @@
-# CrewAI
+# crewAI
+
+![Logo of crewAI, tow people rowing on a boat](./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)
+- [💬 CrewAI Discord Community](https://discord.gg/4ZqbAStv)
+- [Hire Consulting](#hire-consulting)
 - [License](#license)
 
 ## Why CrewAI?
@@ -15,7 +21,7 @@ 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)
+- 📄 [Documentation Wiki](https://github.com/joaomdmoura/CrewAI/wiki)
 
 ## Getting Started
 
@@ -27,40 +33,89 @@ To get started with CrewAI, follow these simple steps:
 pip install crewai
 ```
 
+The example bellow 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.
+#
+# 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",
-  verbose=True
-  # llm=OpenAI(temperature=0.7, model_name="gpt-4"). It uses langchain.chat_models, default is GPT4 
+  role='Senior Research Analyst',
+  goal='Uncover cutting-edge developments in AI and data science in',
+  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='Writer',
-  goal='Create engaging content',
-  backstory="You're a famous technical writer, specialized on writing data related content",
-  verbose=True 
+  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='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=True # Crew verbose more will let you know what tasks are being worked on
-  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.
@@ -74,6 +129,53 @@ Currently the only supported process is `Process.sequential`, where one task is
 
 ![CrewAI Mind Map](/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)
+
+### 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](https://github.com/joaomdmoura/crewAI/wiki/Human-Input-on-Execution)
+
+### Video
+#### Quick Tutorial
+[![CrewAI Tutorial](https://img.youtube.com/vi/tnejrr-0a94/0.jpg)](https://www.youtube.com/watch?v=tnejrr-0a94 "CrewAI Tutorial")
+
+#### Trip Planner
+[![Trip Planner](https://img.youtube.com/vi/xis7rWp-hjs/0.jpg)](https://www.youtube.com/watch?v=xis7rWp-hjs "Trip Planner")
+
+#### Stock Analysis
+[![Stock Analysis](https://img.youtube.com/vi/e0Uj4yWdaAg/0.jpg)](https://www.youtube.com/watch?v=e0Uj4yWdaAg "Stock Analysis")
+
+## 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.
+
+### 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
+)
+```
 
 ## How CrewAI Compares
 
@@ -104,6 +206,12 @@ poetry install
 poetry shell
 ```
 
+### Pre-commit hooks
+
+```bash
+pre-commit install
+```
+
 ### Running Tests
 ```bash
 poetry run pytest
@@ -119,6 +227,10 @@ poetry build
 pip install dist/*.tar.gz
 ```
 
+## Hire Consulting
+I, [@joaomdmoura](https://github.com/joaomdmoura) (creator or crewAI), offer consulting through my LLC ([AI Nest Labs](https://ainestlabs.com)).
+If you are interested on hiring weekly hours with me on a retainer, feel free to email me at [joao@ainestlabs.com](mailto:joao@ainestlabs.com)
+
 ## License
 CrewAI is released under the MIT License
 

crewai/__init__.py

@@ -1,4 +1,4 @@
-from .task import Task
-from .crew import Crew
-from .agent import Agent
-from .process import Process
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.process import Process
+from crewai.task import Task

crewai/agent.py

@@ -1,99 +1,181 @@
-"""Generic agent."""
+import uuid
+from typing import Any, List, Optional
 
-from typing import List, Any, Optional
-from pydantic.v1 import BaseModel, Field, root_validator
-
-from langchain.agents import AgentExecutor
-from langchain.chat_models import ChatOpenAI as OpenAI
-from langchain.tools.render import render_text_description
 from langchain.agents.format_scratchpad import format_log_to_str
-from langchain.agents.output_parsers import ReActSingleInputOutputParser
+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 (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
+
+from crewai.agents import (
+    CacheHandler,
+    CrewAgentExecutor,
+    CrewAgentOutputParser,
+    ToolsHandler,
+)
+from crewai.prompts import Prompts
 
-from .prompts import Prompts
 
 class Agent(BaseModel):
-	"""Generic agent implementation."""
-	agent_executor: AgentExecutor = None
-	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(description="LLM that will run the agent")
-	verbose: bool = Field(
-		description="Verbose mode for the Agent Execution",
-		default=False
-	)
-	allow_delegation: bool = Field(
-		description="Allow delegation of tasks to agents",
-		default=True
-	)
-	tools: List[Any] = Field(
-		description="Tools at agents disposal",
-		default=[]
-	)
+    """Represents an agent in a system.
 
-	@root_validator(pre=True)
-	def check_llm(_cls, values):
-		if not values.get('llm'):
-			values['llm'] = OpenAI(
-				temperature=0.7,
-				model_name="gpt-4"
-			)
-		return values
+    Each agent has a role, a goal, a backstory, and an optional language model (llm).
+    The agent can also have memory, can operate in verbose mode, and can delegate tasks to other agents.
 
-	def __init__(self, **data):
-		super().__init__(**data)
-		execution_prompt = Prompts.TASK_EXECUTION_PROMPT.partial(
-			goal=self.goal,
-			role=self.role,
-			backstory=self.backstory,
-		)
+    Attributes:
+            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.
+            memory: Whether the agent should have memory or not.
+            verbose: Whether the agent execution should be in verbose mode.
+            allow_delegation: Whether the agent is allowed to delegate tasks to other agents.
+    """
 
-		llm_with_bind = self.llm.bind(stop=["\nObservation"])
-		inner_agent = {
-			"input": lambda x: x["input"],
-			"tools": lambda x: x["tools"],
-			"tool_names": lambda x: x["tool_names"],
-			"chat_history": lambda x: x["chat_history"],
-			"agent_scratchpad": lambda x: format_log_to_str(x['intermediate_steps']),
-		} | execution_prompt | llm_with_bind | ReActSingleInputOutputParser()
+    __hash__ = object.__hash__
+    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.",
+    )
+    memory: bool = Field(
+        default=True, description="Whether the agent should have memory or not"
+    )
+    verbose: bool = Field(
+        default=False, description="Verbose mode for the Agent Execution"
+    )
+    allow_delegation: bool = Field(
+        default=True, description="Allow delegation of tasks to agents"
+    )
+    tools: List[Any] = Field(
+        default_factory=list, description="Tools at agents disposal"
+    )
+    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."
+    )
+    cache_handler: Optional[InstanceOf[CacheHandler]] = Field(
+        default=CacheHandler(), description="An instance of the CacheHandler class."
+    )
 
-		summary_memory = ConversationSummaryMemory(
-			llm=self.llm,
-			memory_key='chat_history',
-			input_key="input"
-		)
+    @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.", {}
+            )
 
-		self.agent_executor = AgentExecutor(
-			agent=inner_agent,
-			tools=self.tools,
-			memory=summary_memory,
-			verbose=self.verbose,
-			handle_parsing_errors=True,
-		)
+    @model_validator(mode="after")
+    def check_agent_executor(self) -> "Agent":
+        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) -> str:
-		"""
-		Execute a task with the agent.
-			Parameters:
-				task (str): Task to execute
-			Returns:
-				output (str): Output of the agent
-		"""
-		if context:
-			task = "\n".join([
-				task,
-				"\nThis is the context you are working with:",
-				context
-			])
+    def execute_task(
+        self, task: str, context: str = None, tools: List[Any] = None
+    ) -> str:
+        """Execute a task with the agent.
 
-		tools = tools or self.tools
-		self.agent_executor.tools = tools
-		return self.agent_executor.invoke({
-			"input": task,
-			"tool_names": self.__tools_names(tools),
-			"tools": render_text_description(tools),
-		})['output']
+        Args:
+            task: Task to execute.
+            context: Context to execute the task in.
+            tools: Tools to use for the task.
 
-	def __tools_names(self, tools) -> str:
-		return ", ".join([t.name for t in tools])
+        Returns:
+            Output of the agent
+        """
+        if context:
+            task = "\n".join(
+                [task, "\nThis is the context you are working with:", context]
+            )
+
+        tools = tools or self.tools
+        self.agent_executor.tools = tools
+
+        return self.agent_executor.invoke(
+            {
+                "input": task,
+                "tool_names": self.__tools_names(tools),
+                "tools": render_text_description(tools),
+            },
+            RunnableConfig(callbacks=[self.tools_handler]),
+        )["output"]
+
+    def set_cache_handler(self, cache_handler) -> None:
+        self.cache_handler = cache_handler
+        self.tools_handler = ToolsHandler(cache=self.cache_handler)
+        self.__create_agent_executor()
+
+    def __create_agent_executor(self) -> CrewAgentExecutor:
+        """Create an agent executor for the agent.
+
+        Returns:
+            An instance of the CrewAgentExecutor class.
+        """
+        agent_args = {
+            "input": lambda x: x["input"],
+            "tools": lambda x: x["tools"],
+            "tool_names": lambda x: x["tool_names"],
+            "agent_scratchpad": lambda x: format_log_to_str(x["intermediate_steps"]),
+        }
+        executor_args = {
+            "tools": self.tools,
+            "verbose": self.verbose,
+            "handle_parsing_errors": True,
+        }
+
+        if self.memory:
+            summary_memory = ConversationSummaryMemory(
+                llm=self.llm, memory_key="chat_history", input_key="input"
+            )
+            executor_args["memory"] = summary_memory
+            agent_args["chat_history"] = lambda x: x["chat_history"]
+            prompt = Prompts().task_execution_with_memory()
+        else:
+            prompt = Prompts().task_execution()
+
+        execution_prompt = prompt.partial(
+            goal=self.goal,
+            role=self.role,
+            backstory=self.backstory,
+        )
+
+        bind = self.llm.bind(stop=["\nObservation"])
+        inner_agent = (
+            agent_args
+            | execution_prompt
+            | bind
+            | CrewAgentOutputParser(
+                tools_handler=self.tools_handler, cache=self.cache_handler
+            )
+        )
+        self.agent_executor = CrewAgentExecutor(agent=inner_agent, **executor_args)
+
+    @staticmethod
+    def __tools_names(tools) -> str:
+        return ", ".join([t.name for t in tools])

crewai/agents/__init__.py

@@ -0,0 +1,4 @@
+from .cache.cache_handler import CacheHandler
+from .executor import CrewAgentExecutor
+from .output_parser import CrewAgentOutputParser
+from .tools_handler import ToolsHandler

crewai/agents/agent_vote.py

@@ -1,5 +0,0 @@
-from pydantic.v1 import BaseModel, Field
-
-class AgentVote(BaseModel):
-    task: str = Field(description="Task to be executed by the agent")
-    agent_vote: str = Field(description="Agent that will execute the task")

crewai/agents/cache/__init__.py

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

crewai/agents/cache/cache_handler.py

@@ -0,0 +1,20 @@
+from typing import Optional
+
+from pydantic import PrivateAttr
+
+
+class CacheHandler:
+    """Callback handler for tool usage."""
+
+    _cache: PrivateAttr = {}
+
+    def __init__(self):
+        self._cache = {}
+
+    def add(self, tool, input, output):
+        input = input.strip()
+        self._cache[f"{tool}-{input}"] = output
+
+    def read(self, tool, input) -> Optional[str]:
+        input = input.strip()
+        return self._cache.get(f"{tool}-{input}")

crewai/agents/cache/cache_hit.py

@@ -0,0 +1,14 @@
+from langchain_core.agents import AgentAction
+from pydantic.v1 import BaseModel, Field
+
+from .cache_handler import CacheHandler
+
+
+class CacheHit(BaseModel):
+    """Cache Hit Object."""
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    action: AgentAction = Field(description="Action taken")
+    cache: CacheHandler = Field(description="Cache Handler for the tool")

crewai/agents/exceptions.py

@@ -0,0 +1,24 @@
+from langchain_core.exceptions import OutputParserException
+
+
+class TaskRepeatedUsageException(OutputParserException):
+    """Exception raised when a task is used twice in a roll."""
+
+    error: str = "TaskRepeatedUsageException"
+    message: str = "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"
+
+    def __init__(self, tool: str, tool_input: str, text: str):
+        self.text = text
+        self.tool = tool
+        self.tool_input = tool_input
+        self.message = self.message.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

crewai/agents/executor.py

@@ -0,0 +1,130 @@
+from typing import 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.tools import BaseTool
+
+from ..tools.cache_tools import CacheTools
+from .cache.cache_hit import CacheHit
+
+
+class CrewAgentExecutor(AgentExecutor):
+    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,
+            )
+        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,
+            )
+            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]
+        if isinstance(output, AgentAction):
+            actions = [output]
+        else:
+            actions = output
+        for agent_action in actions:
+            yield agent_action
+        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)

crewai/agents/output_parser.py

@@ -0,0 +1,78 @@
+import re
+from typing import Union
+
+from langchain.agents.output_parsers import ReActSingleInputOutputParser
+from langchain_core.agents import AgentAction, AgentFinish
+
+from .cache import CacheHandler, CacheHit
+from .exceptions import TaskRepeatedUsageException
+from .tools_handler import ToolsHandler
+
+FINAL_ANSWER_ACTION = "Final Answer:"
+FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (
+    "Parsing LLM output produced both a final answer and a parse-able action:"
+)
+
+
+class CrewAgentOutputParser(ReActSingleInputOutputParser):
+    """Parses ReAct-style LLM calls that have a single tool input.
+
+    Expects output to be in one of two formats.
+
+    If the output signals that an action should be taken,
+    should be in the below format. This will result in an AgentAction
+    being returned.
+
+    ```
+    Thought: agent thought here
+    Action: search
+    Action Input: what is the temperature in SF?
+    ```
+
+    If the output signals that a final answer should be given,
+    should be in the below format. This will result in an AgentFinish
+    being returned.
+
+    ```
+    Thought: agent thought here
+    Final Answer: The temperature is 100 degrees
+    ```
+
+    It also prevents tools from being reused in a roll.
+    """
+
+    class Config:
+        arbitrary_types_allowed = True
+
+    tools_handler: ToolsHandler
+    cache: CacheHandler
+
+    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:
+            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:
+                usage = {
+                    "tool": action,
+                    "input": tool_input,
+                }
+                if usage == last_tool_usage:
+                    raise TaskRepeatedUsageException(
+                        tool=action, tool_input=tool_input, text=text
+                    )
+
+            result = self.cache.read(action, tool_input)
+            if result:
+                action = AgentAction(action, tool_input, text)
+                return CacheHit(action=action, cache=self.cache)
+
+        return super().parse(text)

crewai/agents/tools_handler.py

@@ -0,0 +1,44 @@
+from typing import Any, Dict
+
+from langchain.callbacks.base import BaseCallbackHandler
+
+from ..tools.cache_tools import CacheTools
+from .cache.cache_handler import CacheHandler
+
+
+class ToolsHandler(BaseCallbackHandler):
+    """Callback handler for tool usage."""
+
+    last_used_tool: Dict[str, Any] = {}
+    cache: CacheHandler = None
+
+    def __init__(self, cache: CacheHandler = None, **kwargs: Any):
+        """Initialize the callback handler."""
+        self.cache = cache
+        super().__init__(**kwargs)
+
+    def on_tool_start(
+        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
+    ) -> Any:
+        """Run when tool starts running."""
+        name = serialized.get("name")
+        if name not in ["invalid_tool", "_Exception"]:
+            tools_usage = {
+                "tool": name,
+                "input": input_str,
+            }
+            self.last_used_tool = tools_usage
+
+    def on_tool_end(self, output: str, **kwargs: Any) -> Any:
+        """Run when tool ends running."""
+        if (
+            "is not a valid tool" not in output
+            and "Invalid or incomplete response" not in output
+            and "Invalid Format" not in 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,
+                )

crewai/crew.py

@@ -1,86 +1,137 @@
 import json
-from typing import List, Optional
-from pydantic.v1 import BaseModel, Field, Json, root_validator
+import uuid
+from typing import Any, Dict, List, Optional, Union
+
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    Json,
+    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 .process import Process
-from .agent import Agent
-from .task import Task
-from .tools.agent_tools import AgentTools
 
 class Crew(BaseModel):
-	"""
-	Class that represents a group of agents, how they should work together and
-	their tasks.
-	"""
-	config: Optional[Json] = Field(description="Configuration of the crew.")
-	tasks: Optional[List[Task]] = Field(description="List of tasks")
-	agents: Optional[List[Agent]] = Field(description="List of agents in this crew.")
-	process: Process = Field(
-		description="Process that the crew will follow.",
-		default=Process.sequential
-	)
-	verbose: bool = Field(
-		description="Verbose mode for the Agent Execution",
-		default=False
-	)
+    """Class that represents a group of agents, how they should work together and their tasks."""
 
-	@root_validator(pre=True)
-	def check_config(_cls, values):
-		if (
-			not values.get('config') 
-			and (
-				not values.get('agents') and not values.get('tasks')
-			)
-		):
-			raise ValueError('Either agents and task need to be set or config.')
-		
-		if values.get('config'):
-			config = json.loads(values.get('config'))
-			if not config.get('agents') or not config.get('tasks'):
-				raise ValueError('Config should have agents and tasks.')
-			
-			values['agents'] = [Agent(**agent) for agent in config['agents']]
-			
-			tasks = []
-			for task in config['tasks']:
-				task_agent = [agt for agt in values['agents'] if agt.role == task['agent']][0]
-				del task['agent']
-				tasks.append(Task(**task, agent=task_agent))
-			
-			values['tasks'] = tasks
-		return values
+    __hash__ = object.__hash__
+    model_config = ConfigDict(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."
+    )
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
 
-	def kickoff(self) -> str:
-		"""
-		Kickoff the crew to work on it's tasks.
-			Returns:
-				output (List[str]): Output of the crew for each task.
-		"""
-		if self.process == Process.sequential:
-			return self.__sequential_loop()
+    @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.", {}
+            )
 
-	def __sequential_loop(self) -> str:
-		"""
-		Loop that executes the sequential process.
-			Returns:
-				output (str): 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
+    @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
 
-			self.__log(f"\nWorking Agent: {task.agent.role}")
-			self.__log(f"Starting Task: {task.description} ...")
+    @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.", {}
+            )
 
-			task_outcome = task.execute(task_outcome)
+        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.__log(f"Task output: {task_outcome}")
-		
-		return task_outcome
-	
-	def __log(self, message):
-		if self.verbose:
-			print(message)
+            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_output = None
+        for task in self.tasks:
+            # Add delegation tools to the task if the agent allows it
+            if task.agent.allow_delegation:
+                agent_tools = AgentTools(agents=self.agents).tools()
+                task.tools += agent_tools
+
+            self.__log("debug", f"Working Agent: {task.agent.role}")
+            self.__log("info", f"Starting Task: {task.description}")
+
+            task_output = task.execute(task_output)
+            self.__log(
+                "debug", f"\n\n[{task.agent.role}] Task output: {task_output}\n\n"
+            )
+        return task_output
+
+    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/process.py

@@ -1,9 +1,11 @@
 from enum import Enum
 
+
 class Process(str, Enum):
-	"""
-	Class representing the different processes that can be used to tackle tasks
-	"""
-	sequential = 'sequential'
-	# TODO: consensual = 'consensual'
-	# TODO: hierarchical = 'hierarchical'
+    """
+    Class representing the different processes that can be used to tackle tasks
+    """
+
+    sequential = "sequential"
+    # TODO: consensual = 'consensual'
+    # TODO: hierarchical = 'hierarchical'

crewai/prompts.py

@@ -1,71 +1,53 @@
 """Prompts for generic agent."""
+import json
+import os
+from typing import ClassVar, Dict, Optional
 
-from textwrap import dedent
-from typing import ClassVar
-from pydantic.v1 import BaseModel
 from langchain.prompts import PromptTemplate
+from pydantic import BaseModel, Field, PrivateAttr, model_validator
+
 
 class Prompts(BaseModel):
-	"""Prompts for generic agent."""
+    """Prompts for generic agent."""
 
-	TASK_SLICE: ClassVar[str] = dedent("""\
-		Begin! This is VERY important to you, your job depends on it!
+    _prompts: Optional[Dict[str, str]] = PrivateAttr()
+    language: Optional[str] = Field(
+        default="en",
+        description="Language of crewai prompts.",
+    )
 
-		Current Task: {input}
-		{agent_scratchpad}
-	""")
+    @model_validator(mode="after")
+    def load_prompts(self) -> "Prompts":
+        """Load prompts from file."""
+        dir_path = os.path.dirname(os.path.realpath(__file__))
+        prompts_path = os.path.join(dir_path, f"prompts/{self.language}.json")
 
-	MEMORY_SLICE: ClassVar[str] = dedent("""\
-		This is the summary of your work so far:
-        {chat_history}
-	""")
+        with open(prompts_path, "r") as f:
+            self._prompts = json.load(f)["slices"]
+        return self
 
-	ROLE_PLAYING_SLICE: ClassVar[str] = dedent("""\
-		You are {role}.
-		{backstory}
+    SCRATCHPAD_SLICE: ClassVar[str] = "\n{agent_scratchpad}"
 
-		Your personal goal is: {goal}
-	""")
+    def task_execution_with_memory(self) -> str:
+        return PromptTemplate.from_template(
+            self._prompts["role_playing"]
+            + self._prompts["tools"]
+            + self._prompts["memory"]
+            + self._prompts["task"]
+            + self.SCRATCHPAD_SLICE
+        )
 
-	TOOLS_SLICE: ClassVar[str] = dedent("""\
-		TOOLS:
-		------
+    def task_execution_without_tools(self) -> str:
+        return PromptTemplate.from_template(
+            self._prompts["role_playing"]
+            + self._prompts["task"]
+            + self.SCRATCHPAD_SLICE
+        )
 
-		You have access to the following tools:
-
-		{tools}
-
-		To use a tool, please use the following format:
-
-		```
-		Thought: Do I need to use a tool? Yes
-		Action: the action to take, should be one of [{tool_names}]
-		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 tyour format instructions:
-		{format_instructions}
-
-		These are your co-workers and their roles:
-		{coworkers}
-	""")
-
-	TASK_EXECUTION_PROMPT: ClassVar[str] = PromptTemplate.from_template(
-		ROLE_PLAYING_SLICE + TOOLS_SLICE + MEMORY_SLICE + TASK_SLICE
-	)
-	
-	CONSENSUNS_VOTING_PROMPT: ClassVar[str] = PromptTemplate.from_template(
-		ROLE_PLAYING_SLICE + VOTING_SLICE + TASK_SLICE
-	)
+    def task_execution(self) -> str:
+        return PromptTemplate.from_template(
+            self._prompts["role_playing"]
+            + self._prompts["tools"]
+            + self._prompts["task"]
+            + self.SCRATCHPAD_SLICE
+        )

crewai/prompts/en.json

@@ -0,0 +1,8 @@
+{
+  "slices": {
+    "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 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]"
+  }
+}

crewai/task.py

@@ -1,42 +1,62 @@
-from typing import List, Optional
-from pydantic.v1 import BaseModel, Field, root_validator
+import uuid
+from typing import Any, List, Optional
 
-from langchain.tools import Tool
+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 .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: Optional[List[Tool]] = Field(
-		description="Tools the agent are limited to use for this task.",
-		default=[]
-	)
+    """Class that represent a task to be executed."""
 
-	@root_validator(pre=False)
-	def _set_tools(_cls, values):
-		if (values.get('agent')) and not (values.get('tools')):
-			values['tools'] = values.get('agent').tools
-		return values
+    __hash__ = object.__hash__
+    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.",
+    )
+    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.",
+    )
 
-	def execute(self, context: str = None) -> str:
-		"""
-		Execute the task.
-			Returns:
-				output (str): 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.")
+    @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):
+        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:
+            result = self.agent.execute_task(
+                task=self.description, context=context, tools=self.tools
+            )
+
+            self.output = TaskOutput(description=self.description, result=result)
+            return result
+        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/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(" ")[0:10])
+        self.summary = f"{excerpt}..."
+        return self

crewai/tools/agent_tools.py

@@ -1,57 +1,76 @@
-from typing import List, Any
-from pydantic.v1 import BaseModel, Field
 from textwrap import dedent
-from langchain.tools import Tool
+from typing import List
+
+from langchain.tools import Tool
+from pydantic import BaseModel, Field
+
+from crewai.agent import Agent
 
-from ..agent import Agent
 
 class AgentTools(BaseModel):
-	"""Tools for generic agent."""
-	agents: List[Agent] = Field(description="List of agents in this crew.")
+    """Default tools around agent delegation"""
 
-	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`.
-				""")
-			),
-		]
+    agents: List[Agent] = Field(description="List of agents in this crew.")
 
-	def delegate_work(self, command):
-		"""Useful to delegate a specific task to a coworker."""
-		return self.__execute(command)
+    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 co-worker you want to ask it to (one of the options),
+                the task and all actual context you have for the task.
+                For example, `coworker|task|context`.
+                """
+                ),
+            ),
+            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 co-worker you want to ask it to (one of the options),
+                the question and all actual context you have for the question.
+                For example, `coworker|question|context`.
+                """
+                ),
+            ),
+        ]
 
-	def ask_question(self, command):
-		"""Useful to ask a question, opinion or take from a coworker."""
-		return self.__execute(command)
+    def delegate_work(self, command):
+        """Useful to delegate a specific task to a coworker."""
+        return self.__execute(command)
 
-	def __execute(self, command):
-		"""Execute the command."""
-		agent, task, information = command.split("|")
-		if not agent or not task or not information:
-			return "Error executing tool. Missing 3 pipe (|) separated values."
-		
-		agent = [available_agent for available_agent in self.agents if available_agent.role == agent]
-		
-		if len(agent) == 0:
-			return "Error executing tool. Co-worker not found, double check the co-worker."
+    def ask_question(self, command):
+        """Useful to ask a question, opinion or take from a coworker."""
+        return self.__execute(command)
 
-		agent = agent[0]
-		result = agent.execute_task(task, information)	
-		return result
+    def __execute(self, command):
+        """Execute the command."""
+        try:
+            agent, task, context = command.split("|")
+        except ValueError:
+            return "\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"
+
+        if not agent or not task or not context:
+            return "\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 = [
+            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])}.\n"
+
+        agent = agent[0]
+        result = agent.execute_task(task, context)
+        return result

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)

pyproject.toml

@@ -1,7 +1,7 @@
 
 [tool.poetry]
 name = "crewai"
-version = "0.1.2"
+version = "0.1.23"
 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"
@@ -12,14 +12,25 @@ Documentation = "https://github.com/joaomdmoura/CrewAI/wiki/Index"
 Repository = "https://github.com/joaomdmoura/crewai"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1,<4.0"
+python = ">=3.9,<4.0"
 pydantic = "^2.4.2"
-langchain = "^0.0.335"
-openai = "^0.28.1"
+langchain = "^0.0.354"
+openai = "^1.5.0"
+
+[tool.poetry.group.dev.dependencies]
+isort = "^5.13.2"
+black = "^23.12.1"
+autoflake = "^2.2.1"
+pre-commit = "^3.6.0"
+
+[tool.isort]
+profile = "black"
+known_first_party = ["crewai"]
 
 [tool.poetry.group.test.dependencies]
 pytest = "^7.4"
 pytest-vcr = "^1.0.2"
+python-dotenv = "1.0.0"
 
 [build-system]
 requires = ["poetry-core"]

tests/agent_test.py

@@ -1,109 +1,204 @@
 """Test Agent creation and execution basic functionality."""
 
 import pytest
-
 from langchain.chat_models import ChatOpenAI as OpenAI
 
-from ..crewai import Agent
+from crewai.agent import Agent
+from crewai.agents.cache import CacheHandler
+
 
 def test_agent_creation():
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory"
-	)
+    agent = Agent(role="test role", goal="test goal", backstory="test backstory")
+
+    assert agent.role == "test role"
+    assert agent.goal == "test goal"
+    assert agent.backstory == "test backstory"
+    assert agent.tools == []
 
-	assert agent.role == "test role"
-	assert agent.goal == "test goal"
-	assert agent.backstory == "test backstory"
-	assert agent.tools == []
 
 def test_agent_default_values():
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory"
-	)
+    agent = Agent(role="test role", goal="test goal", backstory="test backstory")
+
+    assert isinstance(agent.llm, OpenAI)
+    assert agent.llm.model_name == "gpt-4"
+    assert agent.llm.temperature == 0.7
+    assert agent.llm.verbose == False
+    assert agent.allow_delegation == True
 
-	assert isinstance(agent.llm, OpenAI)
-	assert agent.llm.model_name == "gpt-4"
-	assert agent.llm.temperature == 0.7
-	assert agent.llm.verbose == False
-	assert agent.allow_delegation == True
 
 def test_custom_llm():
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory",
-		llm=OpenAI(
-			temperature=0,
-			model="gpt-3.5"
-		)
-	)
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        llm=OpenAI(temperature=0, model="gpt-4"),
+    )
 
-	assert isinstance(agent.llm, OpenAI)
-	assert agent.llm.model_name == "gpt-3.5"
-	assert agent.llm.temperature == 0
+    assert isinstance(agent.llm, OpenAI)
+    assert agent.llm.model_name == "gpt-4"
+    assert agent.llm.temperature == 0
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_without_memory():
+    no_memory_agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        memory=False,
+        llm=OpenAI(temperature=0, model="gpt-4"),
+    )
+
+    memory_agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        memory=True,
+        llm=OpenAI(temperature=0, model="gpt-4"),
+    )
+
+    result = no_memory_agent.execute_task("How much is 1 + 1?")
+
+    assert result == "1 + 1 equals 2."
+    assert no_memory_agent.agent_executor.memory is None
+    assert memory_agent.agent_executor.memory is not None
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution():
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory",
-		allow_delegation=False
-	)
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        allow_delegation=False,
+    )
 
-	output = agent.execute_task("How much is 1 + 1?")
-	assert output == "1 + 1 = 2"
+    output = agent.execute_task("How much is 1 + 1?")
+    assert output == "2"
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_tools():
-	from langchain.tools import tool
+    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. 
-			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)
+    @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.
+        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)
 
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory",
-		tools=[multiplier],
-		allow_delegation=False
-	)
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        tools=[multiplier],
+        allow_delegation=False,
+    )
 
-	output = agent.execute_task("What is 3 times 4")
-	assert output == "3 times 4 is 12"
+    output = agent.execute_task("What is 3 times 4")
+    assert output == "12"
 
-@pytest.mark.vcr()
+
+@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.
+        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.
+        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)
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        tools=[multiplier],
+        allow_delegation=False,
+        verbose=True,
+    )
+
+    assert agent.tools_handler.last_used_tool == {}
+    output = agent.execute_task("What is 3 times 5?")
+    tool_usage = {
+        "tool": "multiplier",
+        "input": "3,5",
+    }
+
+    assert output == "3 times 5 is 15."
+    assert agent.tools_handler.last_used_tool == 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 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)
+
+    cache_handler = CacheHandler()
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        tools=[multiplier],
+        allow_delegation=False,
+        cache_handler=cache_handler,
+        verbose=True,
+    )
+
+    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-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_with("multiplier", "2,6")
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_agent_execution_with_specific_tools():
-	from langchain.tools import tool
+    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. 
-			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)
+    @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.
+        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)
 
-	agent = Agent(
-		role="test role",
-		goal="test goal",
-		backstory="test backstory",
-		allow_delegation=False
-	)
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        allow_delegation=False,
+    )
 
-	output = agent.execute_task(
-		task="What is 3 times 4",
-		tools=[multiplier]
-	)
-	assert output == "12"
+    output = agent.execute_task(task="What is 3 times 4", tools=[multiplier])
+    assert output == "3 times 4 is 12."

tests/agent_tools/agent_tools_test.py

@@ -1,46 +1,74 @@
 """Test Agent creation and execution basic functionality."""
 
 import pytest
-from ...crewai import Agent
-from ...crewai.tools.agent_tools import AgentTools
+
+from crewai.agent import Agent
+from crewai.tools.agent_tools import AgentTools
 
 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",
-	allow_delegation=False
+    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",
+    allow_delegation=False,
 )
 tools = AgentTools(agents=[researcher])
 
 
-@pytest.mark.vcr()
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_delegate_work():
-	result = tools.delegate_work(
-		command="researcher|share your take on AI Agents|I heard you hate them"
-	)
+    result = tools.delegate_work(
+        command="researcher|share your take on AI Agents|I heard you hate them"
+    )
 
-	assert result == "As a technology researcher, it's important to maintain objectivity. AI agents have their own merits and demerits. On the positive side, they can automate routine tasks, improve efficiency, and enable new forms of communication and decision-making. However, there are potential downsides, like job displacement due to automation and concerns about privacy and security. It's not accurate to say that I hate them, but rather, I recognize the potential implications - both positive and negative - of their use."
+    assert (
+        result
+        == "I apologize if my previous statements have given you the impression that I hate AI agents. As a technology researcher, I don't hold personal sentiments towards AI or any other technology. Rather, I analyze them objectively based on their capabilities, applications, and implications. AI agents, in particular, are a fascinating domain of research. They hold tremendous potential in automating and optimizing various tasks across industries. However, like any other technology, they come with their own set of challenges, such as ethical considerations around privacy and decision-making. My objective is to understand these technologies in depth and provide a balanced view."
+    )
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_ask_question():
-	result = tools.ask_question(
-		command="researcher|do you hate AI Agents?|I heard you LOVE them"
-	)
+    result = tools.ask_question(
+        command="researcher|do you hate AI Agents?|I heard you LOVE them"
+    )
+
+    assert (
+        result
+        == "As an AI, I don't possess feelings or emotions, so I don't love or hate anything. However, I can provide detailed analysis and research on AI agents. They are a fascinating field of study with the potential to revolutionize many industries, although they also present certain challenges and ethical considerations."
+    )
+
+
+def test_can_not_self_delegate():
+    # TODO: Add test for self delegation
+    pass
+
+
+def test_delegate_work_with_wrong_input():
+    result = tools.ask_question(command="writer|share your take on AI Agents")
+
+    assert (
+        result
+        == "\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"
+    )
 
-	assert result == "As a researcher, my feelings towards AI Agents are neutral. I neither love nor hate them. I study and analyze them objectively to understand their potential, capabilities, and limitations. While I appreciate the technological advancement they represent, my job is to approach them from an analytical and scientific perspective."
 
 def test_delegate_work_to_wrong_agent():
-	result = tools.ask_question(
-		command="writer|share your take on AI Agents|I heard you hate them"
-	)
+    result = tools.ask_question(
+        command="writer|share your take on AI Agents|I heard you hate them"
+    )
+
+    assert (
+        result
+        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher.\n"
+    )
 
-	assert result == "Error executing tool. Co-worker not found, double check the co-worker."
 
 def test_ask_question_to_wrong_agent():
-	result = tools.ask_question(
-		command="writer|do you hate AI Agents?|I heard you LOVE them"
-	)
-
-	assert result == "Error executing tool. Co-worker not found, double check the co-worker."
-
+    result = tools.ask_question(
+        command="writer|do you hate AI Agents?|I heard you LOVE them"
+    )
 
+    assert (
+        result
+        == "\nError executing tool. Co-worker mentioned on the Action Input not found, it must to be one of the following options: researcher.\n"
+    )

tests/agent_tools/cassettes/test_ask_question.yaml

@@ -0,0 +1,251 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
+      an expert researcher, specialized in technology\n\nYour personal goal is: make
+      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\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 []\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn''t hold personal sentiments towards AI or any technology, but
+      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      of research with great potential for task automation and optimization across
+      industries, but acknowledges they present challenges such as ethical considerations
+      around privacy and decision-making.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: do you hate AI Agents?\n\nThis is the context
+      you are working with:\nI heard you LOVE them\n\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:
+      - '1494'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8Xx2vMXN4WCrWeeO4DOAowhb3oeDJ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102489,\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: As an AI, I don't possess feelings or emotions, so I don't love or hate
+      anything. However, I can provide detailed analysis and research on AI agents.
+      They are a fascinating field of study with the potential to revolutionize many
+      industries, although they also present certain challenges and ethical considerations.\"\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 291,\n    \"completion_tokens\":
+      75,\n    \"total_tokens\": 366\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a7a3efab6a4b0-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 20:01:35 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:
+      - '6060'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299652'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299652'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 69ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 69ms
+      x-request-id:
+      - 3ad0d047d5260434816f61ec105bdbb8
+    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:\nThe human asks the AI for its opinion on AI
+      agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn''t hold personal sentiments towards AI or any technology, but
+      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      of research with great potential for task automation and optimization across
+      industries, but acknowledges they present challenges such as ethical considerations
+      around privacy and decision-making.\n\nNew lines of conversation:\nHuman: do
+      you hate AI Agents?\n\nThis is the context you are working with:\nI heard you
+      LOVE them\nAI: As an AI, I don''t possess feelings or emotions, so I don''t
+      love or hate anything. However, I can provide detailed analysis and research
+      on AI agents. They are a fascinating field of study with the potential to revolutionize
+      many industries, although they also present certain challenges and ethical considerations.\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:
+      - '1726'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8Xx32X5innWZd8vEETP1jZMLH3b1O\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102496,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn't hold personal sentiments towards AI or any technology, but instead
+      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+      with great potential for task automation and optimization across industries,
+      but acknowledges they present challenges such as ethical considerations around
+      privacy and decision-making. When asked again if it hates or loves AI agents,
+      the AI reiterates that it doesn't possess feelings or emotions, but can provide
+      detailed analysis and research on AI agents.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      300,\n    \"completion_tokens\": 117,\n    \"total_tokens\": 417\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a7a67ecaca4b0-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 20:01:41 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:
+      - '5610'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299585'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299585'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 83ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 83ms
+      x-request-id:
+      - 5b0b96506faa544c5d35b52286a3389c
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/agent_tools/cassettes/test_delegate_work.yaml

@@ -0,0 +1,250 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
+      an expert researcher, specialized in technology\n\nYour personal goal is: make
+      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\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 []\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: share your take on AI Agents\n\nThis
+      is the context you are working with:\nI heard you hate them\n\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:
+      - '1030'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8Xx2cQWLZ8Nd34HGmbQluyZWlD58b\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102470,\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: I apologize if my previous statements have given you the impression
+      that I hate AI agents. As a technology researcher, I don't hold personal sentiments
+      towards AI or any other technology. Rather, I analyze them objectively based
+      on their capabilities, applications, and implications. AI agents, in particular,
+      are a fascinating domain of research. They hold tremendous potential in automating
+      and optimizing various tasks across industries. However, like any other technology,
+      they come with their own set of challenges, such as ethical considerations around
+      privacy and decision-making. My objective is to understand these technologies
+      in depth and provide a balanced view.\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      211,\n    \"completion_tokens\": 134,\n    \"total_tokens\": 345\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a79c59ea7a4b0-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 20:01:23 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        path=/; expires=Wed, 20-Dec-23 20:31:23 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000;
+        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:
+      - '12923'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299769'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299769'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 46ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 46ms
+      x-request-id:
+      - 6468cdd7ae76aea910c72a503a58b8da
+    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: share
+      your take on AI Agents\n\nThis is the context you are working with:\nI heard
+      you hate them\nAI: I apologize if my previous statements have given you the
+      impression that I hate AI agents. As a technology researcher, I don''t hold
+      personal sentiments towards AI or any other technology. Rather, I analyze them
+      objectively based on their capabilities, applications, and implications. AI
+      agents, in particular, are a fascinating domain of research. They hold tremendous
+      potential in automating and optimizing various tasks across industries. However,
+      like any other technology, they come with their own set of challenges, such
+      as ethical considerations around privacy and decision-making. My objective is
+      to understand these technologies in depth and provide a balanced view.\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:
+      - '1622'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8Xx2pqWD01uG0roGJ4daSfvaXLchg\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703102483,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      that it doesn't hold personal sentiments towards AI or any technology, but instead
+      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+      with great potential for task automation and optimization across industries,
+      but acknowledges they present challenges such as ethical considerations around
+      privacy and decision-making.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 279,\n    \"completion_tokens\":
+      81,\n    \"total_tokens\": 360\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a7a17fbb9a4b0-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 20:01:29 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:
+      - '5872'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299610'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299610'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 77ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 77ms
+      x-request-id:
+      - bff02b569530c001aa9a2adba9adbeb9
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_execution.yaml

@@ -0,0 +1,224 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\n\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 []\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]\n```\n\t\tThis is the summary of your work so far:\n    \nBegin!
+      This is VERY important to you, your job depends on it!\n\nCurrent Task: How
+      much is 1 + 1?\n\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:
+      - '851'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuDsBh2o1JE49eouNIBWCE2vn9pB\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091636,\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: 2\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 181,\n    \"completion_tokens\":
+      17,\n    \"total_tokens\": 198\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83897143cca7a477-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=H9RUg933Wznv5vpw9KzjZyJZSXUer6tLsBPnCGaO5sY-1703091638-1-AQMrr8fshVzTPZkSf5UmVC0gg4mnCVMhRfsAVDwFMAcb9eo7Gj6h8TFKL6YGvGlR5eid/JQIY/YbP3d9k7VV+RA=;
+        path=/; expires=Wed, 20-Dec-23 17:30:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=G34V4_SI2mUudYSgDXesqo_OnsZMUghvvyGp95eog58-1703091638133-0-604800000;
+        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:
+      - '1879'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299812'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299812'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 37ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 37ms
+      x-request-id:
+      - 199af19ff2674901b03dbe9d166d7ffb
+    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: How much
+      is 1 + 1?\nAI: 2\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:
+      - '871'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=H9RUg933Wznv5vpw9KzjZyJZSXUer6tLsBPnCGaO5sY-1703091638-1-AQMrr8fshVzTPZkSf5UmVC0gg4mnCVMhRfsAVDwFMAcb9eo7Gj6h8TFKL6YGvGlR5eid/JQIY/YbP3d9k7VV+RA=;
+        _cfuvid=G34V4_SI2mUudYSgDXesqo_OnsZMUghvvyGp95eog58-1703091638133-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuDuhhGTeJIvAaVjt8lxngLaR7GV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091638,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to add 1 + 1, to
+      which the AI responds with 2.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 150,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 172\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83897152ad2ba477-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:41 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:
+      - '2860'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299798'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299798'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 40ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 40ms
+      x-request-id:
+      - 6acd80ebd8c2463aa09cbb1550d14de3
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_execution_with_specific_tools.yaml

@@ -0,0 +1,345 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\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 [multiplier]\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\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:
+      - '1199'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuE6OrjKKco53f0TIqPQEE3nWeNj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091650,\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:
+      multiplier\\nAction Input: 3,4\\n\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+      24,\n    \"total_tokens\": 284\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8389719d5cba0110-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:52 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        path=/; expires=Wed, 20-Dec-23 17:30:52 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000;
+        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:
+      - '2423'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299729'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299729'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 54ms
+      x-request-id:
+      - 8f99f43731fa878eaf0fcbf0719d1b3f
+    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 goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\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 [multiplier]\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\n\nObservation:
+      12\nThought: \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:
+      - '1305'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuE86Ud94rsOP7VA4Bgxo6RM5XE6\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091652,\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:
+      3 times 4 is 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 315\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971ae0f120110-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:55 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:
+      - '2334'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299703'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299703'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 59ms
+      x-request-id:
+      - 44304b182424a8acad8a3121817bea58
+    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: What
+      is 3 times 4\nAI: 3 times 4 is 12.\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:
+      - '885'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuEBWLslSBUMDHZRViwpoXcclYOk\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091655,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+      4, and the AI responds that 3 times 4 is 12.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      155,\n    \"completion_tokens\": 27,\n    \"total_tokens\": 182\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971be49500110-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:58 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:
+      - '2942'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299794'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299794'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 41ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 41ms
+      x-request-id:
+      - 546e9b3713f3ff2d7f9868133efaa3a7
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_execution_with_tools.yaml

@@ -0,0 +1,344 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\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 [multiplier]\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\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:
+      - '1199'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuDxosP85Kqo6mU6biIggZ5c828i\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091641,\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:
+      multiplier\\nAction Input: 3,4\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 283\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83897166eba7a5fd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:44 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        path=/; expires=Wed, 20-Dec-23 17:30:44 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000;
+        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:
+      - '2718'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299729'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299729'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 54ms
+      x-request-id:
+      - 1714a9f5a2141d30f72506facf616944
+    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 goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      input if you wanted to multiply 1 by 2.\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 [multiplier]\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation:
+      12\nThought: \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:
+      - '1303'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuE0tWsbI9QDkRau6rzSUZfuqhFN\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091644,\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:
+      12\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+      15,\n    \"total_tokens\": 308\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971796af6a5fd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:46 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:
+      - '2355'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299704'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299704'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 59ms
+      x-request-id:
+      - a3de9d34f17496d9bdd2ae9360f6054a
+    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: What
+      is 3 times 4\nAI: 12\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:
+      - '871'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuE3Di6FRdNAetXNfWs6OWyRAfkf\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091647,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+      4 and the AI responds with 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 149,\n    \"completion_tokens\":
+      20,\n    \"total_tokens\": 169\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971899954a5fd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:00:49 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:
+      - '2698'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299798'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299798'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 40ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 40ms
+      x-request-id:
+      - ddbd97cea4ec099c21c00ca922157ae1
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_without_memory.yaml

@@ -0,0 +1,113 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      tools:\n\n\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 []\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]\n```\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: How much is 1 + 1?\n\n"}], "model": "gpt-4", "n": 1,
+      "stop": ["\nObservation"], "stream": false, "temperature": 0.0}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '799'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwKQzRwByjmOhHcKQk32biG9bslO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099730,\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: 1 + 1 equals 2.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 169,\n    \"completion_tokens\":
+      24,\n    \"total_tokens\": 193\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a36e258f71a90-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:15:33 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=MXonvOWhzu2xzqqQW6loCrPxpu3htpmRm9QULnV6Uic-1703099733-1-AXiceGXQ09SeMmJaW7hk60DzeZec+Bojjr+ptfpQQRQa0K6o+0oZS2Nhjv6TgYOas6QVkjTabKLwlzoS7qAeJoM=;
+        path=/; expires=Wed, 20-Dec-23 19:45:33 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=0hRVC1wV9ReH4cnY21jU6QE6m7DIZOjDOkZSBykI7yI-1703099733905-0-604800000;
+        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:
+      - '3423'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299825'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299825'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 35ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 35ms
+      x-request-id:
+      - b8aea1a1a2f28a89da6e56213d29152c
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_creation.yaml

@@ -0,0 +1,610 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
+      to the following tools:\n\n\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 []\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: Give me a list of 5 interesting
+      ideas to explore for na article, what makes them unique and interesting.\n\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:
+      - '1173'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuEFy7ANTsR0yPJ75zQoqJ6ihEkP\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091659,\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\\n\\nFinal
+      Answer: \\n\\n1. **The Evolution of AI: From Old Concepts to New Frontiers**
+      - This topic would explore the history of AI from its earliest concepts in philosophy
+      and mathematics to the cutting-edge technologies of today. This would be interesting
+      as it gives the readers an understanding of how far we have come and where we
+      might go next.\\n\\n2. **AI Agents in Healthcare: The Future of Medicine** -
+      This topic addresses the unique ways AI is being used in healthcare, from diagnosing
+      diseases to predicting patient outcomes. It's interesting because it highlights
+      how AI technology can make significant impacts on our health and well-being.\\n\\n3.
+      **AI and Ethics: Navigating the Moral Landscape of Artificial Intelligence**
+      - This could be an engaging piece that delves into the ethical implications
+      of AI, such as privacy concerns, job displacement, and decision-making biases.
+      This is a unique topic because it invites readers to consider the societal implications
+      of AI.\\n\\n4. **Demystifying AI Algorithms: A Deep Dive into Machine Learning**
+      - This would be a technical article explaining how popular machine learning
+      algorithms work, including neural networks and reinforcement learning. This
+      topic is interesting as it provides insights into the 'black box' of AI for
+      a non-technical audience.\\n\\n5. **AI Startups: The Game Changers of the Tech
+      Industry** - This article would profile promising AI startups and their innovative
+      products or services. What makes this topic unique is that it gives a glimpse
+      into the entrepreneurial side of AI, showcasing how startups are driving the
+      AI revolution.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 238,\n    \"completion_tokens\":
+      320,\n    \"total_tokens\": 558\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838971d4593501aa-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:01:38 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=lhXyDHHBBKgFgSeDJK7E90moYsVyXxwqYmoAjsR8zds-1703091698-1-AYOGE4WrbSFLThbY9Taz64kS7u1A9etNqu5IlAbOO60eV5UT/UaDydp38qZtI5dS17GuIFB6ZLTm9Ap/IHZJjJw=;
+        path=/; expires=Wed, 20-Dec-23 17:31:38 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000;
+        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:
+      - '38911'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299731'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299731'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 53ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 53ms
+      x-request-id:
+      - 18a794039177925024548a3eec1133fe
+    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: Give
+      me a list of 5 interesting ideas to explore for na article, what makes them
+      unique and interesting.\nAI: 1. **The Evolution of AI: From Old Concepts to
+      New Frontiers** - This topic would explore the history of AI from its earliest
+      concepts in philosophy and mathematics to the cutting-edge technologies of today.
+      This would be interesting as it gives the readers an understanding of how far
+      we have come and where we might go next.\n\n2. **AI Agents in Healthcare: The
+      Future of Medicine** - This topic addresses the unique ways AI is being used
+      in healthcare, from diagnosing diseases to predicting patient outcomes. It''s
+      interesting because it highlights how AI technology can make significant impacts
+      on our health and well-being.\n\n3. **AI and Ethics: Navigating the Moral Landscape
+      of Artificial Intelligence** - This could be an engaging piece that delves into
+      the ethical implications of AI, such as privacy concerns, job displacement,
+      and decision-making biases. This is a unique topic because it invites readers
+      to consider the societal implications of AI.\n\n4. **Demystifying AI Algorithms:
+      A Deep Dive into Machine Learning** - This would be a technical article explaining
+      how popular machine learning algorithms work, including neural networks and
+      reinforcement learning. This topic is interesting as it provides insights into
+      the ''black box'' of AI for a non-technical audience.\n\n5. **AI Startups: The
+      Game Changers of the Tech Industry** - This article would profile promising
+      AI startups and their innovative products or services. What makes this topic
+      unique is that it gives a glimpse into the entrepreneurial side of AI, showcasing
+      how startups are driving the AI revolution.\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:
+      - '2547'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=lhXyDHHBBKgFgSeDJK7E90moYsVyXxwqYmoAjsR8zds-1703091698-1-AYOGE4WrbSFLThbY9Taz64kS7u1A9etNqu5IlAbOO60eV5UT/UaDydp38qZtI5dS17GuIFB6ZLTm9Ap/IHZJjJw=;
+        _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuEsg8v9ayaeSLfl3wwNDslKQohR\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091698,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI for five interesting
+      and unique article ideas. The AI suggests: 1) an exploration of the evolution
+      of AI, from its earliest concepts to current technologies, 2) a look into the
+      use of AI in healthcare and how it's shaping the future of medicine, 3) an investigation
+      into the ethical implications of AI, 4) a technical explanation of how popular
+      machine learning algorithms work, and 5) a profile on AI startups and their
+      potentially revolutionary products or services.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      465,\n    \"completion_tokens\": 101,\n    \"total_tokens\": 566\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838972c91b0201aa-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:01:51 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:
+      - '13153'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299380'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299380'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 123ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 123ms
+      x-request-id:
+      - f498095d127271d7e782bd4e2d81158f
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re
+      a senior writer, specialized in technology, software engineering, AI and startups.
+      You work as a freelancer and are now working on writing content for a new customer.\n\nYour
+      personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\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 []\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: Write a 1 amazing paragraph highlight
+      for each idea that showcases how good an article about this topic could be.
+      Return the list of ideas with their paragraph and your notes.\n\nThis is the
+      context you are working with:\n1. **The Evolution of AI: From Old Concepts to
+      New Frontiers** - This topic would explore the history of AI from its earliest
+      concepts in philosophy and mathematics to the cutting-edge technologies of today.
+      This would be interesting as it gives the readers an understanding of how far
+      we have come and where we might go next.\n\n2. **AI Agents in Healthcare: The
+      Future of Medicine** - This topic addresses the unique ways AI is being used
+      in healthcare, from diagnosing diseases to predicting patient outcomes. It''s
+      interesting because it highlights how AI technology can make significant impacts
+      on our health and well-being.\n\n3. **AI and Ethics: Navigating the Moral Landscape
+      of Artificial Intelligence** - This could be an engaging piece that delves into
+      the ethical implications of AI, such as privacy concerns, job displacement,
+      and decision-making biases. This is a unique topic because it invites readers
+      to consider the societal implications of AI.\n\n4. **Demystifying AI Algorithms:
+      A Deep Dive into Machine Learning** - This would be a technical article explaining
+      how popular machine learning algorithms work, including neural networks and
+      reinforcement learning. This topic is interesting as it provides insights into
+      the ''black box'' of AI for a non-technical audience.\n\n5. **AI Startups: The
+      Game Changers of the Tech Industry** - This article would profile promising
+      AI startups and their innovative products or services. What makes this topic
+      unique is that it gives a glimpse into the entrepreneurial side of AI, showcasing
+      how startups are driving the AI revolution.\n\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:
+      - '2846'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuF6yxj7DBxOklkSGxNnET4eRRMX\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091712,\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\\n\\nFinal
+      Answer: \\n\\n1. **The Evolution of AI: From Old Concepts to New Frontiers**
+      - Journey with us as we traverse the fascinating timeline of artificial intelligence
+      - from its philosophical and mathematical infancy to the sophisticated, problem-solving
+      tool it has become today. This riveting account will not only educate but also
+      inspire, as we delve deep into the milestones that brought us here and shine
+      a beacon on the potential that lies ahead.\\n\\n2. **AI Agents in Healthcare:
+      The Future of Medicine** - Imagine a world where illnesses are diagnosed before
+      symptoms appear, where patient outcomes are not mere guesses but accurate predictions.
+      This is the world AI is crafting in healthcare - a revolution that's saving
+      lives and changing the face of medicine as we know it. This article will spotlight
+      this transformative journey, underlining the profound impact AI is having on
+      our health and well-being.\\n\\n3. **AI and Ethics: Navigating the Moral Landscape
+      of Artificial Intelligence** - As AI becomes an integral part of our lives,
+      it brings along a plethora of ethical dilemmas. This thought-provoking piece
+      will navigate the complex moral landscape of AI, addressing critical concerns
+      like privacy, job displacement, and decision-making biases. It serves as a much-needed
+      discussion platform for the societal implications of AI, urging us to look beyond
+      the technology and into the mirror.\\n\\n4. **Demystifying AI Algorithms: A
+      Deep Dive into Machine Learning** - Ever wondered what goes on behind the scenes
+      of AI? This enlightening article will break down the complex world of machine
+      learning algorithms into digestible insights, unraveling the mystery of AI's
+      'black box'. It's a rare opportunity for the non-technical audience to appreciate
+      the inner workings of AI, fostering a deeper understanding of this revolutionary
+      technology.\\n\\n5. **AI Startups: The Game Changers of the Tech Industry**
+      - In the world of tech, AI startups are the bold pioneers charting new territories.
+      This article will spotlight these game changers, showcasing how their innovative
+      products and services are driving the AI revolution. It's a unique opportunity
+      to catch a glimpse of the entrepreneurial side of AI, offering inspiration for
+      the tech enthusiasts and dreamers alike.\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      557,\n    \"completion_tokens\": 447,\n    \"total_tokens\": 1004\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8389731f9e14a537-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:02:52 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=PQ1Zoj5GxgZ_f0jkeDUljP5RPxAZ6R1vF57KNYCX8.A-1703091772-1-Aff/FYwzB8VsF9SCkzi9xE9Bag3EFcofaPDkYfW14mpZhHsepfU/zuQ5DEXLBI3CXpUkQJ7wRW42b7ZCV04BY2Y=;
+        path=/; expires=Wed, 20-Dec-23 17:32:52 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000;
+        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:
+      - '60517'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299316'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299316'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 136ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 136ms
+      x-request-id:
+      - 00735e9e054e84ca1a977e11ae706469
+    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: Write
+      a 1 amazing paragraph highlight for each idea that showcases how good an article
+      about this topic could be. Return the list of ideas with their paragraph and
+      your notes.\n\nThis is the context you are working with:\n1. **The Evolution
+      of AI: From Old Concepts to New Frontiers** - This topic would explore the history
+      of AI from its earliest concepts in philosophy and mathematics to the cutting-edge
+      technologies of today. This would be interesting as it gives the readers an
+      understanding of how far we have come and where we might go next.\n\n2. **AI
+      Agents in Healthcare: The Future of Medicine** - This topic addresses the unique
+      ways AI is being used in healthcare, from diagnosing diseases to predicting
+      patient outcomes. It''s interesting because it highlights how AI technology
+      can make significant impacts on our health and well-being.\n\n3. **AI and Ethics:
+      Navigating the Moral Landscape of Artificial Intelligence** - This could be
+      an engaging piece that delves into the ethical implications of AI, such as privacy
+      concerns, job displacement, and decision-making biases. This is a unique topic
+      because it invites readers to consider the societal implications of AI.\n\n4.
+      **Demystifying AI Algorithms: A Deep Dive into Machine Learning** - This would
+      be a technical article explaining how popular machine learning algorithms work,
+      including neural networks and reinforcement learning. This topic is interesting
+      as it provides insights into the ''black box'' of AI for a non-technical audience.\n\n5.
+      **AI Startups: The Game Changers of the Tech Industry** - This article would
+      profile promising AI startups and their innovative products or services. What
+      makes this topic unique is that it gives a glimpse into the entrepreneurial
+      side of AI, showcasing how startups are driving the AI revolution.\nAI: 1. **The
+      Evolution of AI: From Old Concepts to New Frontiers** - Journey with us as we
+      traverse the fascinating timeline of artificial intelligence - from its philosophical
+      and mathematical infancy to the sophisticated, problem-solving tool it has become
+      today. This riveting account will not only educate but also inspire, as we delve
+      deep into the milestones that brought us here and shine a beacon on the potential
+      that lies ahead.\n\n2. **AI Agents in Healthcare: The Future of Medicine** -
+      Imagine a world where illnesses are diagnosed before symptoms appear, where
+      patient outcomes are not mere guesses but accurate predictions. This is the
+      world AI is crafting in healthcare - a revolution that''s saving lives and changing
+      the face of medicine as we know it. This article will spotlight this transformative
+      journey, underlining the profound impact AI is having on our health and well-being.\n\n3.
+      **AI and Ethics: Navigating the Moral Landscape of Artificial Intelligence**
+      - As AI becomes an integral part of our lives, it brings along a plethora of
+      ethical dilemmas. This thought-provoking piece will navigate the complex moral
+      landscape of AI, addressing critical concerns like privacy, job displacement,
+      and decision-making biases. It serves as a much-needed discussion platform for
+      the societal implications of AI, urging us to look beyond the technology and
+      into the mirror.\n\n4. **Demystifying AI Algorithms: A Deep Dive into Machine
+      Learning** - Ever wondered what goes on behind the scenes of AI? This enlightening
+      article will break down the complex world of machine learning algorithms into
+      digestible insights, unraveling the mystery of AI''s ''black box''. It''s a
+      rare opportunity for the non-technical audience to appreciate the inner workings
+      of AI, fostering a deeper understanding of this revolutionary technology.\n\n5.
+      **AI Startups: The Game Changers of the Tech Industry** - In the world of tech,
+      AI startups are the bold pioneers charting new territories. This article will
+      spotlight these game changers, showcasing how their innovative products and
+      services are driving the AI revolution. It''s a unique opportunity to catch
+      a glimpse of the entrepreneurial side of AI, offering inspiration for the tech
+      enthusiasts and dreamers alike.\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:
+      - '4927'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=PQ1Zoj5GxgZ_f0jkeDUljP5RPxAZ6R1vF57KNYCX8.A-1703091772-1-Aff/FYwzB8VsF9SCkzi9xE9Bag3EFcofaPDkYfW14mpZhHsepfU/zuQ5DEXLBI3CXpUkQJ7wRW42b7ZCV04BY2Y=;
+        _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XuG5bK3Oe1gVXJLOjuo2AMBa83Du\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703091773,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to write a paragraph
+      for each of five AI-related topics, highlighting how each could make for an
+      interesting article. The proposed topics are: the history of AI, AI's role in
+      healthcare, ethical considerations in AI, understanding AI algorithms, and AI
+      startups. The AI provides detailed overviews for each topic, emphasizing the
+      evolution and impact of AI, the transformative role of AI in healthcare, the
+      ethical dilemmas faced in AI development and use, the intricacies of AI algorithms,
+      and the pioneering role of AI startups in the tech industry.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      917,\n    \"completion_tokens\": 112,\n    \"total_tokens\": 1029\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8389749b9cc5a537-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 17:02:59 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:
+      - '6202'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '298788'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '298788'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 242ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 242ms
+      x-request-id:
+      - c96a3bc39be7375a244224b958575e22
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_verbose_levels_output.yaml

@@ -0,0 +1,702 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
+      to the following tools:\n\n\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 [], 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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: Write about AI advancements.\n\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:
+      - '1113'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=u_fUK0MqnLcrbhMkg8kKMfrSZpALgzClvD984s71oU8-1703091698056-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8bQsRQf90BTHpHqddg5XG2sg4rtmq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703932143,\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:
+      Use Google Scholar\\nAction Input: Search for recent research papers on AI advancements\"\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 225,\n    \"completion_tokens\":
+      29,\n    \"total_tokens\": 254\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d999768d421d2e-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 30 Dec 2023 10:29:04 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=OlUZJKYA638vLuLRXpnvHsuQGjjNUEUPLyqPk3Xgr7k-1703932144-1-ASbmQtFM69cq3p8WvAULs1c92cQqV4Hj6AQj5D+8d2YbxDrPwADZ4dAPrO1SbsGfaEUgCtY9Hbm1XCp/n7sUEW0=;
+        path=/; expires=Sat, 30-Dec-23 10:59:04 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000;
+        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:
+      - '1122'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299747'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299747'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 50ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 50ms
+      x-request-id:
+      - de0d60f246779b2ce8deb72a46100999
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
+      to the following tools:\n\n\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 [], 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]\n```\n\t\tThis
+      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      you, your job depends on it!\n\nCurrent Task: Write about AI advancements.\nThought:
+      Do I need to use a tool? Yes\nAction: Use Google Scholar\nAction Input: Search
+      for recent research papers on AI advancements\nObservation: Use Google Scholar
+      is not a valid tool, try one of [].\nThought: \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:
+      - '1326'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000;
+        __cf_bm=OlUZJKYA638vLuLRXpnvHsuQGjjNUEUPLyqPk3Xgr7k-1703932144-1-ASbmQtFM69cq3p8WvAULs1c92cQqV4Hj6AQj5D+8d2YbxDrPwADZ4dAPrO1SbsGfaEUgCtY9Hbm1XCp/n7sUEW0=
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8bQsSUIlFRKysiZmNykEJYHaXX2Su\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703932144,\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:
+      The field of artificial intelligence (AI) has seen numerous advancements in
+      recent years. The technology has become more sophisticated and capable due to
+      developments in machine learning algorithms and increased computational power.\\n\\nOne
+      significant advancement is in the area of natural language processing (NLP).
+      AI algorithms are now capable of understanding and generating human language
+      more accurately. This has led to the development of more advanced chatbots and
+      virtual assistants that can understand context, sentiment, and even sarcasm.\\n\\nAnother
+      key advancement is in the field of machine learning. Deep learning, a subset
+      of machine learning, has seen tremendous growth. It uses artificial neural networks
+      with various abstraction layers to simulate the human brain, allowing the AI
+      to learn from large amounts of data. This has led to significant improvements
+      in image and speech recognition and has allowed for the development of self-driving
+      cars.\\n\\nAI has also made strides in the field of robotics. Robots are now
+      more autonomous and can learn from their environment, allowing them to adapt
+      to different scenarios. This is particularly useful in industries like manufacturing
+      and logistics.\\n\\nLastly, advancements in AI have also led to the development
+      of more sophisticated predictive models. These are used in a variety of fields,
+      from predicting weather patterns to stock market trends. The ability to accurately
+      predict future events based on historical data is a powerful tool that can have
+      wide-ranging implications. \\n\\nTo conclude, the advancements in AI have opened
+      up numerous possibilities across various sectors. However, these advancements
+      also come with challenges, particularly in the areas of ethics and data privacy.
+      As we continue to push the boundaries of what AI can achieve, it is crucial
+      to address these concerns to ensure that the technology is used responsibly.\"\n
+      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 275,\n    \"completion_tokens\":
+      341,\n    \"total_tokens\": 616\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d9997f69c91d2e-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 30 Dec 2023 10:29:21 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:
+      - '17002'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299695'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299695'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 61ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 61ms
+      x-request-id:
+      - c128a7ecfe8990bfc73a1f7ff595a2f6
+    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: Write
+      about AI advancements.\nAI: The field of artificial intelligence (AI) has seen
+      numerous advancements in recent years. The technology has become more sophisticated
+      and capable due to developments in machine learning algorithms and increased
+      computational power.\n\nOne significant advancement is in the area of natural
+      language processing (NLP). AI algorithms are now capable of understanding and
+      generating human language more accurately. This has led to the development of
+      more advanced chatbots and virtual assistants that can understand context, sentiment,
+      and even sarcasm.\n\nAnother key advancement is in the field of machine learning.
+      Deep learning, a subset of machine learning, has seen tremendous growth. It
+      uses artificial neural networks with various abstraction layers to simulate
+      the human brain, allowing the AI to learn from large amounts of data. This has
+      led to significant improvements in image and speech recognition and has allowed
+      for the development of self-driving cars.\n\nAI has also made strides in the
+      field of robotics. Robots are now more autonomous and can learn from their environment,
+      allowing them to adapt to different scenarios. This is particularly useful in
+      industries like manufacturing and logistics.\n\nLastly, advancements in AI have
+      also led to the development of more sophisticated predictive models. These are
+      used in a variety of fields, from predicting weather patterns to stock market
+      trends. The ability to accurately predict future events based on historical
+      data is a powerful tool that can have wide-ranging implications. \n\nTo conclude,
+      the advancements in AI have opened up numerous possibilities across various
+      sectors. However, these advancements also come with challenges, particularly
+      in the areas of ethics and data privacy. As we continue to push the boundaries
+      of what AI can achieve, it is crucial to address these concerns to ensure that
+      the technology is used responsibly.\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:
+      - '2789'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000;
+        __cf_bm=OlUZJKYA638vLuLRXpnvHsuQGjjNUEUPLyqPk3Xgr7k-1703932144-1-ASbmQtFM69cq3p8WvAULs1c92cQqV4Hj6AQj5D+8d2YbxDrPwADZ4dAPrO1SbsGfaEUgCtY9Hbm1XCp/n7sUEW0=
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8bQskWvLAJ1fYi1pr0zhuBF1HO0L2\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703932162,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to write about
+      AI advancements. The AI explains that developments in machine learning and increased
+      computational power have led to significant progress in AI technology. Key advancements
+      include improvements in natural language processing, deep learning, robotics,
+      and predictive models. These advancements have led to the creation of more sophisticated
+      chatbots, virtual assistants, image and speech recognition, self-driving cars,
+      and autonomous robots. Despite these advancements, the AI also notes the challenges
+      associated with AI, including ethical and data privacy issues.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 471,\n    \"completion_tokens\": 100,\n
+      \   \"total_tokens\": 571\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d999eb1f821d2e-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 30 Dec 2023 10:29:28 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:
+      - '6188'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299320'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299320'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 135ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 135ms
+      x-request-id:
+      - 4b79a71f1f2a49e466f61343cfa2b543
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Researcher.\nYou''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.\n\nYour personal goal is: Make the best research
+      and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou have access
+      to the following tools:\n\n\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 [], 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]\n```\n\t\tThis
+      is the summary of your work so far:\n    The human asks the AI to write about
+      AI advancements. The AI explains that developments in machine learning and increased
+      computational power have led to significant progress in AI technology. Key advancements
+      include improvements in natural language processing, deep learning, robotics,
+      and predictive models. These advancements have led to the creation of more sophisticated
+      chatbots, virtual assistants, image and speech recognition, self-driving cars,
+      and autonomous robots. Despite these advancements, the AI also notes the challenges
+      associated with AI, including ethical and data privacy issues.\nBegin! This
+      is VERY important to you, your job depends on it!\n\nCurrent Task: Write about
+      AI advancements.\n\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:
+      - '1715'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000;
+        __cf_bm=OlUZJKYA638vLuLRXpnvHsuQGjjNUEUPLyqPk3Xgr7k-1703932144-1-ASbmQtFM69cq3p8WvAULs1c92cQqV4Hj6AQj5D+8d2YbxDrPwADZ4dAPrO1SbsGfaEUgCtY9Hbm1XCp/n7sUEW0=
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8bQsq1r7k6279XJwzh3QWNbAxg0Ed\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703932168,\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\\n\\nFinal
+      Answer: Artificial Intelligence (AI) has been making significant advancements
+      in the last decade, revolutionizing various sectors including technology, healthcare,
+      finance, and transportation. One of the key advancements in AI is the development
+      and refinement of machine learning algorithms. Machine learning, a subset of
+      AI, allows computers to learn from data and make predictions or decisions without
+      being explicitly programmed. \\n\\nThe introduction of Deep Learning, a subfield
+      of machine learning, has been a game-changer. It mimics the workings of the
+      human brain in processing data for use in decision making. Deep Learning is
+      primarily responsible for the advancements in tasks that involve image and speech
+      recognition.\\n\\nNatural Language Processing (NLP) has also seen substantial
+      improvements. NLP is a branch of AI that gives machines the ability to read,
+      understand, and derive meaning from human languages. It's the technology used
+      in voice-assistant devices like Amazon's Alexa and Apple's Siri.\\n\\nIn the
+      field of robotics, AI has made it possible to create robots that can understand
+      and respond to their environment. This has led to the creation of autonomous
+      vehicles and drones.\\n\\nPredictive models are another area where AI has made
+      significant strides. These models are used in various fields, from predicting
+      weather patterns to stock market trends and user behavior in technology applications.\\n\\nDespite
+      the significant advancements, AI technology also poses several challenges. The
+      ethical implications of AI are a major concern, particularly in areas like facial
+      recognition and decision-making algorithms. Data privacy is another issue, especially
+      with the increasing use of AI in handling sensitive information.\\n\\nIn conclusion,
+      while AI has seen incredible advancements and has the potential to revolutionize
+      various industries, there are also significant challenges that need to be addressed
+      to ensure its ethical and responsible use.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      325,\n    \"completion_tokens\": 356,\n    \"total_tokens\": 681\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d99a14dcd41d2e-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 30 Dec 2023 10:29:39 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:
+      - '10741'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299596'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299596'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 80ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 80ms
+      x-request-id:
+      - ad489cb01822a7221278cc4aca438ced
+    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:\nThe human asks the AI to write about AI advancements.
+      The AI explains that developments in machine learning and increased computational
+      power have led to significant progress in AI technology. Key advancements include
+      improvements in natural language processing, deep learning, robotics, and predictive
+      models. These advancements have led to the creation of more sophisticated chatbots,
+      virtual assistants, image and speech recognition, self-driving cars, and autonomous
+      robots. Despite these advancements, the AI also notes the challenges associated
+      with AI, including ethical and data privacy issues.\n\nNew lines of conversation:\nHuman:
+      Write about AI advancements.\nAI: Artificial Intelligence (AI) has been making
+      significant advancements in the last decade, revolutionizing various sectors
+      including technology, healthcare, finance, and transportation. One of the key
+      advancements in AI is the development and refinement of machine learning algorithms.
+      Machine learning, a subset of AI, allows computers to learn from data and make
+      predictions or decisions without being explicitly programmed. \n\nThe introduction
+      of Deep Learning, a subfield of machine learning, has been a game-changer. It
+      mimics the workings of the human brain in processing data for use in decision
+      making. Deep Learning is primarily responsible for the advancements in tasks
+      that involve image and speech recognition.\n\nNatural Language Processing (NLP)
+      has also seen substantial improvements. NLP is a branch of AI that gives machines
+      the ability to read, understand, and derive meaning from human languages. It''s
+      the technology used in voice-assistant devices like Amazon''s Alexa and Apple''s
+      Siri.\n\nIn the field of robotics, AI has made it possible to create robots
+      that can understand and respond to their environment. This has led to the creation
+      of autonomous vehicles and drones.\n\nPredictive models are another area where
+      AI has made significant strides. These models are used in various fields, from
+      predicting weather patterns to stock market trends and user behavior in technology
+      applications.\n\nDespite the significant advancements, AI technology also poses
+      several challenges. The ethical implications of AI are a major concern, particularly
+      in areas like facial recognition and decision-making algorithms. Data privacy
+      is another issue, especially with the increasing use of AI in handling sensitive
+      information.\n\nIn conclusion, while AI has seen incredible advancements and
+      has the potential to revolutionize various industries, there are also significant
+      challenges that need to be addressed to ensure its ethical and responsible use.\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:
+      - '3444'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=BMxGwK4wPoN6Cq5150swBY7QbtTvmWU2.p39x.cUidg-1703932144438-0-604800000;
+        __cf_bm=OlUZJKYA638vLuLRXpnvHsuQGjjNUEUPLyqPk3Xgr7k-1703932144-1-ASbmQtFM69cq3p8WvAULs1c92cQqV4Hj6AQj5D+8d2YbxDrPwADZ4dAPrO1SbsGfaEUgCtY9Hbm1XCp/n7sUEW0=
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8bQt1FyzTtuAbCMxkMxdzVK1M2QhO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703932179,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asked the AI to write about
+      AI advancements. The AI highlighted key developments in machine learning and
+      increased computational power that have led to significant progress in AI technology.
+      These advancements include improvements in natural language processing, deep
+      learning, robotics, and predictive models, which have enabled the creation of
+      sophisticated chatbots, virtual assistants, image and speech recognition, self-driving
+      cars, and autonomous robots. The AI further explained that AI has revolutionized
+      various sectors including technology, healthcare, finance, and transportation.
+      Machine learning allows computers to make predictions or decisions based on
+      data, and deep learning mimics human brain processing for decision making. Natural
+      Language Processing allows machines to understand human languages, and AI has
+      enabled the creation of responsive robots and predictive models for various
+      applications. Despite these advancements, the AI also noted the challenges associated
+      with AI, including ethical implications and data privacy issues. In conclusion,
+      while AI has seen incredible advancements, there are significant challenges
+      that need to be addressed to ensure its ethical and responsible use.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 584,\n    \"completion_tokens\": 198,\n
+      \   \"total_tokens\": 782\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d99a598ebe1d2e-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 30 Dec 2023 10:29:51 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:
+      - '11197'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299156'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299156'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 168ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 168ms
+      x-request-id:
+      - 8f64b23c4bfaa33e56e4e5ed52e113c1
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_crew_with_delegating_agents.yaml

@@ -0,0 +1,677 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\n\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to
+      delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO,
+      Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated
+      text of length\n\t\t\t\tthree, representing the role you want to delegate it
+      to,  the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk
+      Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof
+      the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this
+      tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing
+      the role you want to ask it to,  the question and \n\t\t\t\tinformation necessary.
+      For example, `coworker|question|information`.\n\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]\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]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Produce and amazing 1 paragraph draft of an article
+      about AI Agents.\n\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:
+      - '1907'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwL0C0AeNFxBDtNxKvF4g4SpBHMy\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099766,\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:
+      Delegate Work to Co-Worker\\nAction Input: Senior Writer|Create a compelling
+      and engaging 1 paragraph draft of an article about AI Agents|Provide a brief
+      yet comprehensive overview of AI agents, their uses, and implications in the
+      current world. Make sure to emphasize their potential and the role they can
+      play in the future. The tone should be informative but captivating. \"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 415,\n    \"completion_tokens\": 88,\n
+      \   \"total_tokens\": 503\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a37c488c8a51d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:16:16 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=;
+        path=/; expires=Wed, 20-Dec-23 19:46:16 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000;
+        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:
+      - '9246'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299559'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299559'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 88ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 88ms
+      x-request-id:
+      - a893482a313d58b1b40f4af679855361
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are Senior Writer.\nYou''re
+      a senior writer, specialized in technology, software engineering, AI and startups.
+      You work as a freelancer and are now working on writing content for a new customer.\n\nYour
+      personal goal is: Write the best content about AI and AI agents.\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\n\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 []\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]\n```\n\t\tThis
+      is the summary of your work so far:\n    The human asks the AI to write a paragraph
+      for each of five AI-related topics, highlighting how each could make for an
+      interesting article. The proposed topics are: the history of AI, AI''s role
+      in healthcare, ethical considerations in AI, understanding AI algorithms, and
+      AI startups. The AI provides detailed overviews for each topic, emphasizing
+      the evolution and impact of AI, the transformative role of AI in healthcare,
+      the ethical dilemmas faced in AI development and use, the intricacies of AI
+      algorithms, and the pioneering role of AI startups in the tech industry.\nBegin!
+      This is VERY important to you, your job depends on it!\n\nCurrent Task: Create
+      a compelling and engaging 1 paragraph draft of an article about AI Agents\n\nThis
+      is the context you are working with:\nProvide a brief yet comprehensive overview
+      of AI agents, their uses, and implications in the current world. Make sure to
+      emphasize their potential and the role they can play in the future. The tone
+      should be informative but captivating.\n\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:
+      - '1969'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwLAvsNLsRlvTVGewBsy2sHjUuvo\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099776,\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\\n\\nFinal
+      Answer: \\\"AI agents, the digital masterminds at the heart of the 21st-century
+      revolution, are shaping a new era of intelligence and innovation. They are autonomous
+      entities, capable of observing their environment, making decisions, and acting
+      on them, all in pursuit of a specific goal. From streamlining operations in
+      logistics to personalizing customer experiences in retail, AI agents are transforming
+      how businesses operate. But their potential extends far beyond the corporate
+      world. They are the sentinels protecting our digital frontiers, the virtual
+      assistants making our lives easier, and the unseen hands guiding autonomous
+      vehicles. As this technology evolves, AI agents will play an increasingly central
+      role in our world, ushering in an era of unprecedented efficiency, personalization,
+      and productivity. But with great power comes great responsibility, and understanding
+      and harnessing this potential responsibly will be one of our greatest challenges
+      and opportunities in the coming years.\\\"\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      391,\n    \"completion_tokens\": 194,\n    \"total_tokens\": 585\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a3801ecc3a632-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:16:33 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4=;
+        path=/; expires=Wed, 20-Dec-23 19:46:33 GMT; 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:
+      - '16857'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299534'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299534'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 93ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 93ms
+      x-request-id:
+      - d158efaaade6655137aaa299ea674831
+    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:\nThe human asks the AI to write a paragraph for
+      each of five AI-related topics, highlighting how each could make for an interesting
+      article. The proposed topics are: the history of AI, AI''s role in healthcare,
+      ethical considerations in AI, understanding AI algorithms, and AI startups.
+      The AI provides detailed overviews for each topic, emphasizing the evolution
+      and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas
+      faced in AI development and use, the intricacies of AI algorithms, and the pioneering
+      role of AI startups in the tech industry.\n\nNew lines of conversation:\nHuman:
+      Create a compelling and engaging 1 paragraph draft of an article about AI Agents\n\nThis
+      is the context you are working with:\nProvide a brief yet comprehensive overview
+      of AI agents, their uses, and implications in the current world. Make sure to
+      emphasize their potential and the role they can play in the future. The tone
+      should be informative but captivating.\nAI: \"AI agents, the digital masterminds
+      at the heart of the 21st-century revolution, are shaping a new era of intelligence
+      and innovation. They are autonomous entities, capable of observing their environment,
+      making decisions, and acting on them, all in pursuit of a specific goal. From
+      streamlining operations in logistics to personalizing customer experiences in
+      retail, AI agents are transforming how businesses operate. But their potential
+      extends far beyond the corporate world. They are the sentinels protecting our
+      digital frontiers, the virtual assistants making our lives easier, and the unseen
+      hands guiding autonomous vehicles. As this technology evolves, AI agents will
+      play an increasingly central role in our world, ushering in an era of unprecedented
+      efficiency, personalization, and productivity. But with great power comes great
+      responsibility, and understanding and harnessing this potential responsibly
+      will be one of our greatest challenges and opportunities in the coming years.\"\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:
+      - '2786'
+      content-type:
+      - application/json
+      cookie:
+      - _cfuvid=qVpxYVGQ_iwAkrQrePYbf52GMURpsQ__qprXXMk79wI-1703091772665-0-604800000;
+        __cf_bm=lM319LPDEnvF96Mm4S90dEPrAGj1BHp.EoL8Zh1oCkU-1703099793-1-AS7kVNRnez1R9AZHZcWMDEIHZ3+Ay1dO+6ucbsMG+Euq+B+uku7GPY+Yz9hBZVDn+UTIJAw5aBsQH3U34sHaie4=
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwLRKqCp8gf0ELMrLkRepygaoLrI\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099793,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to write a paragraph
+      for each of five AI-related topics: the history of AI, AI's role in healthcare,
+      ethical considerations in AI, understanding AI algorithms, and AI startups.
+      The AI provides detailed overviews for each topic, emphasizing the evolution
+      and impact of AI, the transformative role of AI in healthcare, the ethical dilemmas
+      faced in AI development and use, the intricacies of AI algorithms, and the pioneering
+      role of AI startups in the tech industry. The human then asks the AI to draft
+      a paragraph about AI Agents. The AI creates an engaging overview of AI agents,
+      discussing their roles, potential, and implications in the current world, highlighting
+      their transformative impact on various sectors and their potential for the future
+      while noting the importance of responsibly harnessing this potential.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 498,\n    \"completion_tokens\": 158,\n
+      \   \"total_tokens\": 656\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a386d398da632-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:16:50 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:
+      - '16935'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299320'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299320'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 136ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 136ms
+      x-request-id:
+      - c4705d7c284541ec74df0a25eb51aa7f
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are CEO.\nYou''re an long
+      time CEO of a content creation agency with a Senior Writer on the team. You''re
+      now working on a new project and want to make sure the content produced is amazing.\n\nYour
+      personal goal is: Make sure the writers in your company produce amazing content.\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nDelegate Work to Co-Worker: Useful to
+      delegate a specific task to one of the \n\t\t\t\tfollowing co-workers: [CEO,
+      Senior Writer].\n\t\t\t\tThe input to this tool should be a pipe (|) separated
+      text of length\n\t\t\t\tthree, representing the role you want to delegate it
+      to,  the task and \n\t\t\t\tinformation necessary. For example, `coworker|task|information`.\n\nAsk
+      Question to Co-Worker: Useful to ask a question, opinion or take from on\n\t\t\t\tof
+      the following co-workers: [CEO, Senior Writer]. \n\t\t\t\tThe input to this
+      tool should be a pipe (|) separated text of length \n\t\t\t\tthree, representing
+      the role you want to ask it to,  the question and \n\t\t\t\tinformation necessary.
+      For example, `coworker|question|information`.\n\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]\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]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Produce and amazing 1 paragraph draft of an article
+      about AI Agents.\nThought: Do I need to use a tool? Yes\nAction: Delegate Work
+      to Co-Worker\nAction Input: Senior Writer|Create a compelling and engaging 1
+      paragraph draft of an article about AI Agents|Provide a brief yet comprehensive
+      overview of AI agents, their uses, and implications in the current world. Make
+      sure to emphasize their potential and the role they can play in the future.
+      The tone should be informative but captivating. \nObservation: \"AI agents,
+      the digital masterminds at the heart of the 21st-century revolution, are shaping
+      a new era of intelligence and innovation. They are autonomous entities, capable
+      of observing their environment, making decisions, and acting on them, all in
+      pursuit of a specific goal. From streamlining operations in logistics to personalizing
+      customer experiences in retail, AI agents are transforming how businesses operate.
+      But their potential extends far beyond the corporate world. They are the sentinels
+      protecting our digital frontiers, the virtual assistants making our lives easier,
+      and the unseen hands guiding autonomous vehicles. As this technology evolves,
+      AI agents will play an increasingly central role in our world, ushering in an
+      era of unprecedented efficiency, personalization, and productivity. But with
+      great power comes great responsibility, and understanding and harnessing this
+      potential responsibly will be one of our greatest challenges and opportunities
+      in the coming years.\"\nThought: \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:
+      - '3352'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=;
+        _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwLixNfdsK3l1iSw7Uf11mrHwOwr\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099810,\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:
+      The Senior Writer has created a compelling and engaging 1 paragraph draft about
+      AI agents. The paragraph provides a brief yet comprehensive overview of AI agents,
+      their uses, and implications in the current world. It emphasizes their potential
+      and the role they can play in the future. The tone is informative but captivating,
+      meeting the objectives of the task.\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      688,\n    \"completion_tokens\": 80,\n    \"total_tokens\": 768\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a38d99b590199-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:17:02 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:
+      - '11599'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299200'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299200'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 160ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 160ms
+      x-request-id:
+      - 91515805acf37358b0e3b73fa4b302ed
+    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: Produce
+      and amazing 1 paragraph draft of an article about AI Agents.\nAI: The Senior
+      Writer has created a compelling and engaging 1 paragraph draft about AI agents.
+      The paragraph provides a brief yet comprehensive overview of AI agents, their
+      uses, and implications in the current world. It emphasizes their potential and
+      the role they can play in the future. The tone is informative but captivating,
+      meeting the objectives of the task.\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:
+      - '1282'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=o0Hi1R.X9SlINxIJTVmbndjXrZ0hKGumMHX9teXwypc-1703099776-1-AYizrWsw5e5xpAQYK2ILXGT8XFsMG/cUywCKEtgqcBAn361e23iU23y2rsxZge9SVmHfbz+ltf8zup2qIqhAfWM=;
+        _cfuvid=ps.JYe.5DT5QaG1hDuUb70tnVJo8IPWJrGrGEO_HUYA-1703099776177-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.0
+      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-8XwLutLT441lOLap9gUd0ttpfvq8b\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703099822,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to produce a draft
+      of an article about AI agents. The AI responds by creating a compelling and
+      engaging paragraph that provides a comprehensive overview of AI agents, their
+      uses, and implications in the current world, emphasizing their potential future
+      role.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 219,\n    \"completion_tokens\":
+      51,\n    \"total_tokens\": 270\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 838a39248aa10199-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 20 Dec 2023 19:17:10 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:
+      - '7304'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299695'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299695'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 61ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 61ms
+      x-request-id:
+      - 70b697c208659cf5af8ff46e2fc0ab69
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_logging_tool_usage.yaml

@@ -0,0 +1,690 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\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 [multiplier],
+      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]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: What is 3 times 5?\n\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:
+      - '1231'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eDhOwdMJw0817wIqiD9MoXVRU8\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858225,\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:
+      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 264,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 287\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28cd70f9f1cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:07 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        path=/; expires=Fri, 29-Dec-23 14:27:07 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000;
+        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:
+      - '1725'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299717'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299717'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 56ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 56ms
+      x-request-id:
+      - 689757a1e38baf0844ec69f20525c5d7
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\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 [multiplier],
+      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]\n```\n\t\tThis is the summary
+      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: What is 3 times 5?\nThought: Do I need to use a tool?
+      Yes\nAction: multiplier\nAction Input: 3,5\nObservation: 15\nThought: \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:
+      - '1335'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eG2qnUr6SZcankL5AqkwIJvYFc\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858228,\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:
+      3 times 5 is 15.\"\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:
+      - 83d28ce3ab3b1cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:09 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:
+      - '1568'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299693'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299693'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 61ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 61ms
+      x-request-id:
+      - 66a02e3e08e3f6b5b29fb04cd19f50a0
+    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: What
+      is 3 times 5?\nAI: 3 times 5 is 15.\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:
+      - '886'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eIfmBgQoWGLW4jiQZTu3qzEBBL\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858230,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
+      times 5 and the AI responds that 3 times 5 is 15.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      155,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 181\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28cf118221cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:12 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:
+      - '2188'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299794'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299794'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 41ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 41ms
+      x-request-id:
+      - a644c703d416b1e4b06586e96e6d7297
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\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 [multiplier],
+      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]\n```\n\t\tThis is the summary
+      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
+      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\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:
+      - '1317'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eKehkNtTjrXJD0aFjiVUeXU7te\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858232,\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:
+      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 290,\n    \"completion_tokens\":
+      23,\n    \"total_tokens\": 313\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d007f461cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:14 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:
+      - '1885'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299697'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299697'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 60ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 60ms
+      x-request-id:
+      - 87959bfa6a029f7bcafb5095e66d4964
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      - Useful for when you need to multiply two numbers together.\n        The input
+      to this tool should be a comma separated list of numbers of\n        length
+      two, representing the two numbers you want to multiply together.\n        For
+      example, `1,2` would be the input if you wanted to multiply 1 by 2.\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 [multiplier],
+      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]\n```\n\t\tThis is the summary
+      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
+      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
+      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\nI just used the multiplier
+      tool with input 3,5. So I already knwo the result of that.\nObservation: Invalid
+      or incomplete response\nThought: \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:
+      - '1460'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eME5fg1w8QcXUnl0FBcqxJWy7u\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858234,\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:
+      3 times 5 is 15.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 324,\n    \"completion_tokens\":
+      22,\n    \"total_tokens\": 346\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d0fcfaf1cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:17 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:
+      - '2494'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299661'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299661'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 67ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 67ms
+      x-request-id:
+      - eb9704531634d4cd3c6652dff09914bc
+    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:\nThe human asks the AI to calculate 3 times 5
+      and the AI responds that 3 times 5 is 15.\n\nNew lines of conversation:\nHuman:
+      What is 3 times 5?\nAI: 3 times 5 is 15.\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:
+      - '972'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.6.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.6.1
+      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-8b7eP77MzprkbgjaMbeaEob0aDx39\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1703858237,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
+      times 5 twice, and both times the AI responds that 3 times 5 is 15.\"\n      },\n
+      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+      \ \"usage\": {\n    \"prompt_tokens\": 181,\n    \"completion_tokens\": 30,\n
+      \   \"total_tokens\": 211\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 83d28d211f591cd9-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 29 Dec 2023 13:57:20 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:
+      - '2967'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-limit-tokens_usage_based:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299771'
+      x-ratelimit-remaining-tokens_usage_based:
+      - '299771'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 45ms
+      x-ratelimit-reset-tokens_usage_based:
+      - 45ms
+      x-request-id:
+      - e3bbd11b2e9b28f76f8b43dc7a4d2b6d
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/conftest.py

@@ -1,3 +1,4 @@
 # conftest.py
 from dotenv import load_dotenv
-load_result = load_dotenv(override=True)
+
+load_result = load_dotenv(override=True)

tests/crew_test.py

@@ -1,176 +1,268 @@
 """Test Agent creation and execution basic functionality."""
 
 import json
+
 import pytest
-from ..crewai import Agent, Crew, Task, Process
+
+from crewai.agent import Agent
+from crewai.agents.cache import CacheHandler
+from crewai.crew import Crew
+from crewai.process import Process
+from crewai.task import Task
 
 ceo = Agent(
-	role="CEO",
-	goal="Make sure the writers in your company produce amazing content.",
-	backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
-	allow_delegation=True
+    role="CEO",
+    goal="Make sure the writers in your company produce amazing content.",
+    backstory="You're an long time CEO of a content creation agency with a Senior Writer on the team. You're now working on a new project and want to make sure the content produced is amazing.",
+    allow_delegation=True,
 )
 
 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
+    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,
 )
 
 writer = Agent(
-	role="Senior Writer",
-	goal="Write the best content about AI and AI agents.",
-	backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
-	allow_delegation=False
+    role="Senior Writer",
+    goal="Write the best content about AI and AI agents.",
+    backstory="You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
+    allow_delegation=False,
 )
 
-def test_crew_config_conditional_requirement():
-	with pytest.raises(ValueError):
-		Crew(process=Process.sequential)
-	
-	config = json.dumps({
-		"agents": [
-			{
-				"role": "Senior 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."
-			},
-			{
-				"role": "Senior Writer",
-				"goal": "Write the best content about AI and AI agents.",
-				"backstory": "You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer."
-			}
-		],
-		"tasks": [
-			{
-				"description": "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-				"agent": "Senior Researcher"
-			},
-			{
-				"description": "Write a 1 amazing paragraph highlight for each idead that showcases how good an article about this topic could be, check references if necessary or search for more content but make sure it's unique, interesting and well written. Return the list of ideas with their paragraph and your notes.",
-				"agent": "Senior Writer"
-			}
-		]		
-	})
-	parsed_config = json.loads(config)
 
-	try:
-			crew = Crew(process=Process.sequential, config=config)			
-	except ValueError:
-			pytest.fail("Unexpected ValidationError raised")
-	
-	assert [agent.role for agent in crew.agents] == [agent['role'] for agent in parsed_config['agents']]
-	assert [task.description for task in crew.tasks] == [task['description'] for task in parsed_config['tasks']]
+def test_crew_config_conditional_requirement():
+    with pytest.raises(ValueError):
+        Crew(process=Process.sequential)
+
+    config = json.dumps(
+        {
+            "agents": [
+                {
+                    "role": "Senior 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.",
+                },
+                {
+                    "role": "Senior Writer",
+                    "goal": "Write the best content about AI and AI agents.",
+                    "backstory": "You're a senior writer, specialized in technology, software engineering, AI and startups. You work as a freelancer and are now working on writing content for a new customer.",
+                },
+            ],
+            "tasks": [
+                {
+                    "description": "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+                    "agent": "Senior Researcher",
+                },
+                {
+                    "description": "Write a 1 amazing paragraph highlight for each idead that showcases how good an article about this topic could be, check references if necessary or search for more content but make sure it's unique, interesting and well written. Return the list of ideas with their paragraph and your notes.",
+                    "agent": "Senior Writer",
+                },
+            ],
+        }
+    )
+    parsed_config = json.loads(config)
+
+    try:
+        crew = Crew(process=Process.sequential, config=config)
+    except ValueError:
+        pytest.fail("Unexpected ValidationError raised")
+
+    assert [agent.role for agent in crew.agents] == [
+        agent["role"] for agent in parsed_config["agents"]
+    ]
+    assert [task.description for task in crew.tasks] == [
+        task["description"] for task in parsed_config["tasks"]
+    ]
+
 
 def test_crew_config_with_wrong_keys():
-	no_tasks_config = json.dumps({
-		"agents": [
-			{
-				"role": "Senior 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."
-			}
-		]
-	})
+    no_tasks_config = json.dumps(
+        {
+            "agents": [
+                {
+                    "role": "Senior 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.",
+                }
+            ]
+        }
+    )
 
-	no_agents_config = json.dumps({
-		"tasks": [
-			{
-				"description": "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-				"agent": "Senior Researcher"
-			}
-		]		
-	})
-	with pytest.raises(ValueError):
-		Crew(process=Process.sequential, config='{"wrong_key": "wrong_value"}')
-	with pytest.raises(ValueError):
-		Crew(process=Process.sequential, config=no_tasks_config)
-	with pytest.raises(ValueError):
-		Crew(process=Process.sequential, config=no_agents_config)
+    no_agents_config = json.dumps(
+        {
+            "tasks": [
+                {
+                    "description": "Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+                    "agent": "Senior Researcher",
+                }
+            ]
+        }
+    )
+    with pytest.raises(ValueError):
+        Crew(process=Process.sequential, config='{"wrong_key": "wrong_value"}')
+    with pytest.raises(ValueError):
+        Crew(process=Process.sequential, config=no_tasks_config)
+    with pytest.raises(ValueError):
+        Crew(process=Process.sequential, config=no_agents_config)
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_creation():
-	tasks = [
-		Task(
-			description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-			agent=researcher
-		),
-		Task(
-			description="Write a 1 amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
-			agent=writer
-		)
-	]
+    tasks = [
+        Task(
+            description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
+            agent=researcher,
+        ),
+        Task(
+            description="Write a 1 amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
+            agent=writer,
+        ),
+    ]
 
-	crew = Crew(
-		agents=[researcher, writer],
-		process=Process.sequential,
-		tasks=tasks,
-	)
+    crew = Crew(
+        agents=[researcher, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
 
-	assert crew.kickoff() == """1. AI and Ethics: In a world that is increasingly being dominated by Artificial Intelligence, the question of ethics is ever more important. This article will delve into the complex intersection of AI and ethics, exploring how the decisions made by AI can impact society. From privacy concerns to the accountability of AI decisions, this piece will provide readers with a comprehensive understanding of the ethical dilemmas posed by AI.
+    assert (
+        crew.kickoff()
+        == """1. **The Evolution of AI: From Old Concepts to New Frontiers** - Journey with us as we traverse the fascinating timeline of artificial intelligence - from its philosophical and mathematical infancy to the sophisticated, problem-solving tool it has become today. This riveting account will not only educate but also inspire, as we delve deep into the milestones that brought us here and shine a beacon on the potential that lies ahead.
 
-2. The Role of AI in Climate Change: Climate change is the defining issue of our time. This article will examine how AI is playing a pivotal role in combating this global challenge. From predicting climate patterns to optimizing renewable energy use, the piece will highlight how AI is not just a part of the problem, but also a crucial part of the solution.
+2. **AI Agents in Healthcare: The Future of Medicine** - Imagine a world where illnesses are diagnosed before symptoms appear, where patient outcomes are not mere guesses but accurate predictions. This is the world AI is crafting in healthcare - a revolution that's saving lives and changing the face of medicine as we know it. This article will spotlight this transformative journey, underlining the profound impact AI is having on our health and well-being.
 
-3. AI in Healthcare: The fusion of AI and healthcare holds a transformative potential. This article will explore how AI is revolutionizing healthcare, from improving diagnosis and treatment to enhancing patient care and hospital management. It will show how AI is not just improving healthcare outcomes but also driving a more efficient and patient-centered healthcare system.
+3. **AI and Ethics: Navigating the Moral Landscape of Artificial Intelligence** - As AI becomes an integral part of our lives, it brings along a plethora of ethical dilemmas. This thought-provoking piece will navigate the complex moral landscape of AI, addressing critical concerns like privacy, job displacement, and decision-making biases. It serves as a much-needed discussion platform for the societal implications of AI, urging us to look beyond the technology and into the mirror.
 
-4. The Future of AI and Work: The rise of AI has sparked a lively debate on its impact on jobs and the future of work. This article will explore this topic in-depth, examining both the potential job losses and the new opportunities created by AI. It will provide a balanced and insightful analysis of how AI is reshaping the world of work.
+4. **Demystifying AI Algorithms: A Deep Dive into Machine Learning** - Ever wondered what goes on behind the scenes of AI? This enlightening article will break down the complex world of machine learning algorithms into digestible insights, unraveling the mystery of AI's 'black box'. It's a rare opportunity for the non-technical audience to appreciate the inner workings of AI, fostering a deeper understanding of this revolutionary technology.
 
-5. AI in Space Exploration: The final frontier is not beyond the reach of AI. This article will spotlight the role of AI in space exploration, from analyzing vast amounts of astronomical data to autonomous spacecraft navigating the vast expanse of space. The piece will highlight how AI is not just aiding but also accelerating our quest to explore the universe."""
+5. **AI Startups: The Game Changers of the Tech Industry** - In the world of tech, AI startups are the bold pioneers charting new territories. This article will spotlight these game changers, showcasing how their innovative products and services are driving the AI revolution. It's a unique opportunity to catch a glimpse of the entrepreneurial side of AI, offering inspiration for the tech enthusiasts and dreamers alike."""
+    )
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_with_delegating_agents():
-	tasks = [
-		Task(
-			description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
-			agent=ceo
-		)
-	]
+    tasks = [
+        Task(
+            description="Produce and amazing 1 paragraph draft of an article about AI Agents.",
+            agent=ceo,
+        )
+    ]
 
-	crew = Crew(
-		agents=[ceo, writer],
-		process=Process.sequential,
-		tasks=tasks,
-	)
+    crew = Crew(
+        agents=[ceo, writer],
+        process=Process.sequential,
+        tasks=tasks,
+    )
 
-	assert crew.kickoff() == 'The Senior Writer produced an amazing paragraph about AI Agents: "Artificial Intelligence (AI) agents, the cutting-edge technology that is reshaping the digital landscape, are software entities that autonomously perform tasks to achieve specific goals. These agents, programmed to make decisions based on their environment, are the driving force behind a multitude of innovations, from self-driving cars to personalized recommendations in e-commerce. They are pushing boundaries in various sectors, mitigating human error, increasing efficiency, and revolutionizing customer experience. The importance of AI agents is underscored by their ability to adapt and learn, ushering in a new era of technology where machines can mimic, and often surpass, human intelligence. Understanding AI agents is akin to peering into the future, a future where technology is seamless, intuitive, and astoundingly smart."'
+    assert (
+        crew.kickoff()
+        == '"AI agents, the digital masterminds at the heart of the 21st-century revolution, are shaping a new era of intelligence and innovation. They are autonomous entities, capable of observing their environment, making decisions, and acting on them, all in pursuit of a specific goal. From streamlining operations in logistics to personalizing customer experiences in retail, AI agents are transforming how businesses operate. But their potential extends far beyond the corporate world. They are the sentinels protecting our digital frontiers, the virtual assistants making our lives easier, and the unseen hands guiding autonomous vehicles. As this technology evolves, AI agents will play an increasingly central role in our world, ushering in an era of unprecedented efficiency, personalization, and productivity. But with great power comes great responsibility, and understanding and harnessing this potential responsibly will be one of our greatest challenges and opportunities in the coming years."'
+    )
 
-@pytest.mark.vcr()
+
+@pytest.mark.vcr(filter_headers=["authorization"])
 def test_crew_verbose_output(capsys):
-		tasks = [
-				Task(
-						description="Research AI advancements.",
-						agent=researcher
-				),
-				Task(
-						description="Write about AI in healthcare.",
-						agent=writer
-				)
-		]
+    tasks = [
+        Task(description="Research AI advancements.", agent=researcher),
+        Task(description="Write about AI in healthcare.", agent=writer),
+    ]
 
-		crew = Crew(
-				agents=[researcher, writer],
-				tasks=tasks,
-				process=Process.sequential,
-				verbose=True
-		)
+    crew = Crew(
+        agents=[researcher, writer],
+        tasks=tasks,
+        process=Process.sequential,
+        verbose=True,
+    )
 
-		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:"
-		]
+    crew.kickoff()
+    captured = capsys.readouterr()
+    expected_strings = [
+        "Working Agent: Researcher",
+        "Starting Task: Research AI advancements.",
+        "[Researcher] Task output:",
+        "Working Agent: Senior Writer",
+        "Starting Task: Write about AI in healthcare.",
+        "[Senior Writer] Task output:",
+    ]
 
-		for expected_string in expected_strings:
-			assert expected_string in captured.out
+    for expected_string in expected_strings:
+        assert expected_string in captured.out
 
-		# Now test with verbose set to False
-		crew.verbose = False
-		crew.kickoff()
-		captured = capsys.readouterr()
-		assert captured.out == ""
+    # Now test with verbose set to False
+    crew.verbose = False
+    crew.kickoff()
+    captured = capsys.readouterr()
+    assert captured.out == ""
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_crew_verbose_levels_output(capsys):
+    tasks = [Task(description="Write about AI advancements.", agent=researcher)]
+
+    crew = Crew(agents=[researcher], tasks=tasks, process=Process.sequential, verbose=1)
+
+    crew.kickoff()
+    captured = capsys.readouterr()
+    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.kickoff()
+    captured = capsys.readouterr()
+    expected_strings = [
+        "Working Agent: Researcher",
+        "Starting Task: Write about AI advancements.",
+        "[Researcher] Task output:",
+    ]
+
+    for expected_string in expected_strings:
+        assert expected_string in captured.out
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_cache_hitting_between_agents():
+    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.
+        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)
+
+    tasks = [
+        Task(
+            description="What is 2 tims 6? Return only the number.",
+            tools=[multiplier],
+            agent=ceo,
+        ),
+        Task(
+            description="What is 2 times 6? Return only the number.",
+            tools=[multiplier],
+            agent=researcher,
+        ),
+    ]
+
+    crew = Crew(
+        agents=[ceo, researcher],
+        tasks=tasks,
+    )
+
+    assert crew.cache_handler._cache == {}
+    output = crew.kickoff()
+    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")

tests/task_test.py

@@ -1,57 +1,57 @@
 """Test Agent creation and execution basic functionality."""
 
-import pytest
-from ..crewai import Agent, Task
+
+from crewai.agent import Agent
+from crewai.task import Task
+
 
 def test_task_tool_reflect_agent_tools():
-	from langchain.tools import tool
+    from langchain.tools import tool
 
-	@tool
-	def fake_tool() -> None:
-		"Fake tool"
-		pass
-	
-	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.",
-		tools=[fake_tool],
-		allow_delegation=False
-	)
+    @tool
+    def fake_tool() -> None:
+        "Fake tool"
+
+    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.",
+        tools=[fake_tool],
+        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.",
+        agent=researcher,
+    )
+
+    assert task.tools == [fake_tool]
 
-	task = Task(
-		description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-		agent=researcher
-	)
-	
-	assert task.tools == [fake_tool]
 
 def test_task_tool_takes_precedence_ove_agent_tools():
-	from langchain.tools import tool
+    from langchain.tools import tool
 
-	@tool
-	def fake_tool() -> None:
-		"Fake tool"
-		pass
+    @tool
+    def fake_tool() -> None:
+        "Fake tool"
 
-	@tool
-	def fake_task_tool() -> None:
-		"Fake tool"
-		pass
-	
-	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.",
-		tools=[fake_tool],
-		allow_delegation=False
-	)
+    @tool
+    def fake_task_tool() -> None:
+        "Fake tool"
 
-	task = Task(
-		description="Give me a list of 5 interesting ideas to explore for na article, what makes them unique and interesting.",
-		agent=researcher,
-		tools=[fake_task_tool],
-		allow_delegation=False
-	)
-	
-	assert task.tools == [fake_task_tool]
+    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.",
+        tools=[fake_tool],
+        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.",
+        agent=researcher,
+        tools=[fake_task_tool],
+        allow_delegation=False,
+    )
+
+    assert task.tools == [fake_task_tool]