fix: type checking

.gitignore

@@ -11,5 +11,4 @@ chroma.sqlite3
 old_en.json
 db/
 test.py
-rc-tests/*
-*.pkl
+rc-tests/*

README.md

@@ -195,47 +195,6 @@ Please refer to the [Connect crewAI to LLMs](https://docs.crewai.com/how-to/LLM-
 
 **CrewAI's Advantage**: CrewAI is built with production in mind. It offers the flexibility of Autogen's conversational agents and the structured process approach of ChatDev, but without the rigidity. CrewAI's processes are designed to be dynamic and adaptable, fitting seamlessly into both development and production workflows.
 
-
-## Training
-
-The training feature in CrewAI allows you to train your AI agents using the command-line interface (CLI). By running the command `crewai train -n <n_iterations>`, you can specify the number of iterations for the training process.
-
-During training, CrewAI utilizes techniques to optimize the performance of your agents along with human feedback. This helps the agents improve their understanding, decision-making, and problem-solving abilities.
-
-To use the training feature, follow these steps:
-
-1. Open your terminal or command prompt.
-2. Navigate to the directory where your CrewAI project is located.
-3. Run the following command:
-
-```shell
-crewai train -n <n_iterations>
-```
-
-Replace `<n_iterations>` with the desired number of training iterations. This determines how many times the agents will go through the training process.
-
-Remember to also replace the placeholder inputs with the actual values you want to use on the main.py file in the `train` function.
-
-```python
-def train():
-    """
-    Train the crew for a given number of iterations.
-    """
-    inputs = {"topic": "AI LLMs"}
-    try:
-        ProjectCreationCrew().crew().train(n_iterations=int(sys.argv[1]), inputs=inputs)
-    ...
-```
-
-It is important to note that the training process may take some time, depending on the complexity of your agents and will also require your feedback on each iteration.
-
-Once the training is complete, your agents will be equipped with enhanced capabilities and knowledge, ready to tackle complex tasks and provide more consistent and valuable insights.
-
-Remember to regularly update and retrain your agents to ensure they stay up-to-date with the latest information and advancements in the field.
-
-Happy training with CrewAI!
-
-
 ## Contribution
 
 CrewAI is open-source and we welcome contributions. If you're looking to contribute, please:

docs/core-concepts/Agents.md

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

poetry.lock

@@ -6092,4 +6092,4 @@ tools = ["crewai-tools"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.10,<=3.13"
-content-hash = "f1e540dc2b356a2592149e8ff2cc03540e4b0f99e1ce0521b5ff139d5e0ed105"
+content-hash = "f1e540dc2b356a2592149e8ff2cc03540e4b0f99e1ce0521b5ff139d5e0ed105"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "crewai"
-version = "0.35.0"
+version = "0.32.2"
 description = "Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks."
 authors = ["Joao Moura <joao@crewai.com>"]
 readme = "README.md"
@@ -21,7 +21,7 @@ opentelemetry-sdk = "^1.22.0"
 opentelemetry-exporter-otlp-proto-http = "^1.22.0"
 instructor = "1.3.3"
 regex = "^2023.12.25"
-crewai-tools = { version = "^0.4.0", optional = true }
+crewai-tools = { version = "^0.3.0", optional = true }
 click = "^8.1.7"
 python-dotenv = "^1.0.0"
 embedchain = "0.1.109"
@@ -43,7 +43,7 @@ mkdocs-material = { extras = ["imaging"], version = "^9.5.7" }
 mkdocs-material-extensions = "^1.3.1"
 pillow = "^10.2.0"
 cairosvg = "^2.7.1"
-crewai-tools = "^0.4.0"
+crewai-tools = "^0.3.0"
 
 [tool.poetry.group.test.dependencies]
 pytest = "^8.0.0"
@@ -60,4 +60,4 @@ exclude = ["cli/templates/main.py", "cli/templates/crew.py"]
 
 [build-system]
 requires = ["poetry-core"]
-build-backend = "poetry.core.masonry.api"
+build-backend = "poetry.core.masonry.api"

src/crewai/__init__.py

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

src/crewai/agent.py

@@ -1,5 +1,7 @@
 import os
-from typing import Any, List, Optional, Tuple
+import uuid
+from copy import deepcopy
+from typing import Any, Dict, List, Optional, Tuple
 
 from langchain.agents.agent import RunnableAgent
 from langchain.agents.tools import tool as LangChainTool
@@ -7,20 +9,27 @@ from langchain.tools.render import render_text_description
 from langchain_core.agents import AgentAction
 from langchain_core.callbacks import BaseCallbackHandler
 from langchain_openai import ChatOpenAI
+from pydantic import (
+    UUID4,
+    BaseModel,
+    ConfigDict,
+    Field,
+    InstanceOf,
+    PrivateAttr,
+    field_validator,
+    model_validator,
+)
+from pydantic_core import PydanticCustomError
 
-from pydantic import Field, InstanceOf, model_validator
-
-from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser
+from crewai.agents import CacheHandler, CrewAgentExecutor, CrewAgentParser, ToolsHandler
 from crewai.memory.contextual.contextual_memory import ContextualMemory
-from crewai.tools.agent_tools import AgentTools
-from crewai.utilities import Prompts, Converter
+from crewai.utilities import I18N, Logger, Prompts, RPMController
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
-from crewai.utilities.token_counter_callback import TokenCalcHandler
-from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.utilities.token_counter_callback import TokenCalcHandler, TokenProcess
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
-class Agent(BaseAgent):
+class Agent(BaseModel):
     """Represents an agent in a system.
 
     Each agent has a role, a goal, a backstory, and an optional language model (llm).
@@ -44,10 +53,57 @@ class Agent(BaseAgent):
             callbacks: A list of callback functions from the langchain library that are triggered during the agent's execution process
     """
 
+    __hash__ = object.__hash__  # type: ignore
+    _logger: Logger = PrivateAttr()
+    _rpm_controller: RPMController = PrivateAttr(default=None)
+    _request_within_rpm_limit: Any = PrivateAttr(default=None)
+    _token_process: TokenProcess = TokenProcess()
+
+    formatting_errors: int = 0
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+    id: UUID4 = Field(
+        default_factory=uuid.uuid4,
+        frozen=True,
+        description="Unique identifier for the object, not set by user.",
+    )
+    role: str = Field(description="Role of the agent")
+    goal: str = Field(description="Objective of the agent")
+    backstory: str = Field(description="Backstory of the agent")
+    cache: bool = Field(
+        default=True,
+        description="Whether the agent should use a cache for tool usage.",
+    )
+    config: Optional[Dict[str, Any]] = Field(
+        description="Configuration for the agent",
+        default=None,
+    )
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the agent execution to be respected.",
+    )
+    verbose: bool = Field(
+        default=False, description="Verbose mode for the Agent Execution"
+    )
+    allow_delegation: bool = Field(
+        default=True, description="Allow delegation of tasks to agents"
+    )
+    tools: Optional[List[Any]] = Field(
+        default_factory=list, description="Tools at agents disposal"
+    )
+    max_iter: Optional[int] = Field(
+        default=25, description="Maximum iterations for an agent to execute a task"
+    )
     max_execution_time: Optional[int] = Field(
         default=None,
         description="Maximum execution time for an agent to execute a task",
     )
+    agent_executor: InstanceOf[CrewAgentExecutor] = Field(
+        default=None, description="An instance of the CrewAgentExecutor class."
+    )
+    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
+    tools_handler: InstanceOf[ToolsHandler] = Field(
+        default=None, description="An instance of the ToolsHandler class."
+    )
     cache_handler: InstanceOf[CacheHandler] = Field(
         default=None, description="An instance of the CacheHandler class."
     )
@@ -55,6 +111,7 @@ class Agent(BaseAgent):
         default=None,
         description="Callback to be executed after each step of the agent execution.",
     )
+    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
     llm: Any = Field(
         default_factory=lambda: ChatOpenAI(
             model=os.environ.get("OPENAI_MODEL_NAME", "gpt-4o")
@@ -76,18 +133,47 @@ class Agent(BaseAgent):
     response_template: Optional[str] = Field(
         default=None, description="Response format for the agent."
     )
-
     allow_code_execution: Optional[bool] = Field(
         default=False, description="Enable code execution for the agent."
     )
 
+    _original_role: str | None = None
+    _original_goal: str | None = None
+    _original_backstory: str | None = None
+
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
         super().__init__(**config, **data)
 
+    @field_validator("id", mode="before")
+    @classmethod
+    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+        if v:
+            raise PydanticCustomError(
+                "may_not_set_field", "This field is not to be set by the user.", {}
+            )
+
+    @model_validator(mode="after")
+    def set_attributes_based_on_config(self) -> "Agent":
+        """Set attributes based on the agent configuration."""
+        if self.config:
+            for key, value in self.config.items():
+                setattr(self, key, value)
+        return self
+
+    @model_validator(mode="after")
+    def set_private_attrs(self):
+        """Set private attributes."""
+        self._logger = Logger(self.verbose)
+        if self.max_rpm and not self._rpm_controller:
+            self._rpm_controller = RPMController(
+                max_rpm=self.max_rpm, logger=self._logger
+            )
+        return self
+
     @model_validator(mode="after")
     def set_agent_executor(self) -> "Agent":
-        """Ensure agent executor and token process is set."""
+        """set agent executor is set."""
         if hasattr(self.llm, "model_name"):
             token_handler = TokenCalcHandler(self.llm.model_name, self._token_process)
 
@@ -124,8 +210,7 @@ class Agent(BaseAgent):
             Output of the agent
         """
         if self.tools_handler:
-            # type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
-            self.tools_handler.last_used_tool = {}
+            self.tools_handler.last_used_tool = {}  # type: ignore # Incompatible types in assignment (expression has type "dict[Never, Never]", variable has type "ToolCalling")
 
         task_prompt = task.prompt()
 
@@ -145,8 +230,9 @@ class Agent(BaseAgent):
                 task_prompt += self.i18n.slice("memory").format(memory=memory)
 
         tools = tools or self.tools
-        # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
-        parsed_tools = self._parse_tools(tools or [])
+
+        parsed_tools = self._parse_tools(tools)  # type: ignore # Argument 1 to "_parse_tools" of "Agent" has incompatible type "list[Any] | None"; expected "list[Any]"
+
         self.create_agent_executor(tools=tools)
         self.agent_executor.tools = parsed_tools
         self.agent_executor.task = task
@@ -166,22 +252,33 @@ class Agent(BaseAgent):
                 "tools": self.agent_executor.tools_description,
             }
         )["output"]
+
         if self.max_rpm:
             self._rpm_controller.stop_rpm_counter()
+
         return result
 
-    def format_log_to_str(
-        self,
-        intermediate_steps: List[Tuple[AgentAction, str]],
-        observation_prefix: str = "Observation: ",
-        llm_prefix: str = "",
-    ) -> str:
-        """Construct the scratchpad that lets the agent continue its thought process."""
-        thoughts = ""
-        for action, observation in intermediate_steps:
-            thoughts += action.log
-            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
-        return thoughts
+    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
+        """Set the cache handler for the agent.
+
+        Args:
+            cache_handler: An instance of the CacheHandler class.
+        """
+        self.tools_handler = ToolsHandler()
+        if self.cache:
+            self.cache_handler = cache_handler
+            self.tools_handler.cache = cache_handler
+        self.create_agent_executor()
+
+    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
+        """Set the rpm controller for the agent.
+
+        Args:
+            rpm_controller: An instance of the RPMController class.
+        """
+        if not self._rpm_controller:
+            self._rpm_controller = rpm_controller
+            self.create_agent_executor()
 
     def create_agent_executor(self, tools=None) -> None:
         """Create an agent executor for the agent.
@@ -237,32 +334,75 @@ class Agent(BaseAgent):
         )
 
         stop_words = [self.i18n.slice("observation")]
-
         if self.response_template:
             stop_words.append(
                 self.response_template.split("{{ .Response }}")[1].strip()
             )
 
         bind = self.llm.bind(stop=stop_words)
-
         inner_agent = agent_args | execution_prompt | bind | CrewAgentParser(agent=self)
         self.agent_executor = CrewAgentExecutor(
             agent=RunnableAgent(runnable=inner_agent), **executor_args
         )
 
-    def get_delegation_tools(self, agents: List[BaseAgent]):
-        agent_tools = AgentTools(agents=agents)
-        tools = agent_tools.tools()
-        return tools
+    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
+        """Interpolate inputs into the agent description and backstory."""
+        if self._original_role is None:
+            self._original_role = self.role
+        if self._original_goal is None:
+            self._original_goal = self.goal
+        if self._original_backstory is None:
+            self._original_backstory = self.backstory
 
-    def get_output_converter(self, llm, text, model, instructions):
-        return Converter(llm=llm, text=text, model=model, instructions=instructions)
+        if inputs:
+            self.role = self._original_role.format(**inputs)
+            self.goal = self._original_goal.format(**inputs)
+            self.backstory = self._original_backstory.format(**inputs)
 
-    def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:
+    def increment_formatting_errors(self) -> None:
+        """Count the formatting errors of the agent."""
+        self.formatting_errors += 1
+
+    def format_log_to_str(
+        self,
+        intermediate_steps: List[Tuple[AgentAction, str]],
+        observation_prefix: str = "Observation: ",
+        llm_prefix: str = "",
+    ) -> str:
+        """Construct the scratchpad that lets the agent continue its thought process."""
+        thoughts = ""
+        for action, observation in intermediate_steps:
+            thoughts += action.log
+            thoughts += f"\n{observation_prefix}{observation}\n{llm_prefix}"
+        return thoughts
+
+    def copy(self):
+        """Create a deep copy of the Agent."""
+        exclude = {
+            "id",
+            "_logger",
+            "_rpm_controller",
+            "_request_within_rpm_limit",
+            "_token_process",
+            "agent_executor",
+            "tools",
+            "tools_handler",
+            "cache_handler",
+        }
+
+        copied_data = self.model_dump(exclude=exclude)
+        copied_data = {k: v for k, v in copied_data.items() if v is not None}
+
+        copied_agent = Agent(**copied_data)
+        copied_agent.tools = deepcopy(self.tools)
+
+        return copied_agent
+
+    def _parse_tools(self, tools: List[Any]) -> List[LangChainTool]:  # type: ignore # Function "langchain_core.tools.tool" is not valid as a type
         """Parse tools to be used for the task."""
+        # tentatively try to import from crewai_tools import BaseTool as CrewAITool
         tools_list = []
         try:
-            # tentatively try to import from crewai_tools import BaseTool as CrewAITool
             from crewai_tools import BaseTool as CrewAITool
 
             for tool in tools:

src/crewai/agents/agent_builder/base_agent.py

@@ -1,256 +0,0 @@
-from copy import deepcopy
-import uuid
-from typing import Any, Dict, List, Optional
-from abc import ABC, abstractmethod
-from pydantic import (
-    UUID4,
-    BaseModel,
-    Field,
-    InstanceOf,
-    field_validator,
-    model_validator,
-    ConfigDict,
-    PrivateAttr,
-)
-from pydantic_core import PydanticCustomError
-
-from crewai.utilities import I18N, RPMController, Logger
-from crewai.agents import CacheHandler, ToolsHandler
-from crewai.utilities.token_counter_callback import TokenProcess
-
-
-class BaseAgent(ABC, BaseModel):
-    """Abstract Base Class for all third party agents compatible with CrewAI.
-
-    Attributes:
-        id (UUID4): Unique identifier for the agent.
-        role (str): Role of the agent.
-        goal (str): Objective of the agent.
-        backstory (str): Backstory of the agent.
-        cache (bool): Whether the agent should use a cache for tool usage.
-        config (Optional[Dict[str, Any]]): Configuration for the agent.
-        verbose (bool): Verbose mode for the Agent Execution.
-        max_rpm (Optional[int]): Maximum number of requests per minute for the agent execution.
-        allow_delegation (bool): Allow delegation of tasks to agents.
-        tools (Optional[List[Any]]): Tools at the agent's disposal.
-        max_iter (Optional[int]): Maximum iterations for an agent to execute a task.
-        agent_executor (InstanceOf): An instance of the CrewAgentExecutor class.
-        llm (Any): Language model that will run the agent.
-        crew (Any): Crew to which the agent belongs.
-        i18n (I18N): Internationalization settings.
-        cache_handler (InstanceOf[CacheHandler]): An instance of the CacheHandler class.
-        tools_handler (InstanceOf[ToolsHandler]): An instance of the ToolsHandler class.
-
-
-    Methods:
-        execute_task(task: Any, context: Optional[str] = None, tools: Optional[List[Any]] = None) -> str:
-            Abstract method to execute a task.
-        create_agent_executor(tools=None) -> None:
-            Abstract method to create an agent executor.
-        _parse_tools(tools: List[Any]) -> List[Any]:
-            Abstract method to parse tools.
-        get_delegation_tools(agents: List["BaseAgent"]):
-            Abstract method to set the agents task tools for handling delegation and question asking to other agents in crew.
-        get_output_converter(llm, model, instructions):
-            Abstract method to get the converter class for the agent to create json/pydantic outputs.
-        interpolate_inputs(inputs: Dict[str, Any]) -> None:
-            Interpolate inputs into the agent description and backstory.
-        set_cache_handler(cache_handler: CacheHandler) -> None:
-            Set the cache handler for the agent.
-        increment_formatting_errors() -> None:
-            Increment formatting errors.
-        copy() -> "BaseAgent":
-            Create a copy of the agent.
-        set_rpm_controller(rpm_controller: RPMController) -> None:
-            Set the rpm controller for the agent.
-        set_private_attrs() -> "BaseAgent":
-            Set private attributes.
-    """
-
-    __hash__ = object.__hash__  # type: ignore
-    _logger: Logger = PrivateAttr()
-    _rpm_controller: RPMController = PrivateAttr(default=None)
-    _request_within_rpm_limit: Any = PrivateAttr(default=None)
-    formatting_errors: int = 0
-    model_config = ConfigDict(arbitrary_types_allowed=True)
-    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
-    role: str = Field(description="Role of the agent")
-    goal: str = Field(description="Objective of the agent")
-    backstory: str = Field(description="Backstory of the agent")
-    cache: bool = Field(
-        default=True, description="Whether the agent should use a cache for tool usage."
-    )
-    config: Optional[Dict[str, Any]] = Field(
-        description="Configuration for the agent", default=None
-    )
-    verbose: bool = Field(
-        default=False, description="Verbose mode for the Agent Execution"
-    )
-    max_rpm: Optional[int] = Field(
-        default=None,
-        description="Maximum number of requests per minute for the agent execution to be respected.",
-    )
-    allow_delegation: bool = Field(
-        default=True, description="Allow delegation of tasks to agents"
-    )
-    tools: Optional[List[Any]] = Field(
-        default_factory=list, description="Tools at agents' disposal"
-    )
-    max_iter: Optional[int] = Field(
-        default=25, description="Maximum iterations for an agent to execute a task"
-    )
-    agent_executor: InstanceOf = Field(
-        default=None, description="An instance of the CrewAgentExecutor class."
-    )
-    llm: Any = Field(
-        default=None, description="Language model that will run the agent."
-    )
-    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-    cache_handler: InstanceOf[CacheHandler] = Field(
-        default=None, description="An instance of the CacheHandler class."
-    )
-    tools_handler: InstanceOf[ToolsHandler] = Field(
-        default=None, description="An instance of the ToolsHandler class."
-    )
-
-    _original_role: str | None = None
-    _original_goal: str | None = None
-    _original_backstory: str | None = None
-    _token_process: TokenProcess = TokenProcess()
-
-    def __init__(__pydantic_self__, **data):
-        config = data.pop("config", {})
-        super().__init__(**config, **data)
-
-    @model_validator(mode="after")
-    def set_config_attributes(self):
-        if self.config:
-            for key, value in self.config.items():
-                setattr(self, key, value)
-        return self
-
-    @field_validator("id", mode="before")
-    @classmethod
-    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
-        if v:
-            raise PydanticCustomError(
-                "may_not_set_field", "This field is not to be set by the user.", {}
-            )
-
-    @model_validator(mode="after")
-    def set_attributes_based_on_config(self) -> "BaseAgent":
-        """Set attributes based on the agent configuration."""
-        if self.config:
-            for key, value in self.config.items():
-                setattr(self, key, value)
-        return self
-
-    @model_validator(mode="after")
-    def set_private_attrs(self):
-        """Set private attributes."""
-        self._logger = Logger(self.verbose)
-        if self.max_rpm and not self._rpm_controller:
-            self._rpm_controller = RPMController(
-                max_rpm=self.max_rpm, logger=self._logger
-            )
-        if not self._token_process:
-            self._token_process = TokenProcess()
-        return self
-
-    @abstractmethod
-    def execute_task(
-        self,
-        task: Any,
-        context: Optional[str] = None,
-        tools: Optional[List[Any]] = None,
-    ) -> str:
-        pass
-
-    @abstractmethod
-    def create_agent_executor(self, tools=None) -> None:
-        pass
-
-    @abstractmethod
-    def _parse_tools(self, tools: List[Any]) -> List[Any]:
-        pass
-
-    @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]):
-        """Set the task tools that init BaseAgenTools class."""
-        pass
-
-    @abstractmethod
-    def get_output_converter(
-        self, llm: Any, text: str, model: type[BaseModel] | None, instructions: str
-    ):
-        """Get the converter class for the agent to create json/pydantic outputs."""
-        pass
-
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
-        """Interpolate inputs into the agent description and backstory."""
-        if self._original_role is None:
-            self._original_role = self.role
-        if self._original_goal is None:
-            self._original_goal = self.goal
-        if self._original_backstory is None:
-            self._original_backstory = self.backstory
-
-        if inputs:
-            self.role = self._original_role.format(**inputs)
-            self.goal = self._original_goal.format(**inputs)
-            self.backstory = self._original_backstory.format(**inputs)
-
-    def set_cache_handler(self, cache_handler: CacheHandler) -> None:
-        """Set the cache handler for the agent.
-
-        Args:
-            cache_handler: An instance of the CacheHandler class.
-        """
-        self.tools_handler = ToolsHandler()
-        if self.cache:
-            self.cache_handler = cache_handler
-            self.tools_handler.cache = cache_handler
-        self.create_agent_executor()
-
-    def increment_formatting_errors(self) -> None:
-        print("Formatting errors incremented")
-
-    def copy(self):
-        exclude = {
-            "id",
-            "_logger",
-            "_rpm_controller",
-            "_request_within_rpm_limit",
-            "token_process",
-            "agent_executor",
-            "tools",
-            "tools_handler",
-            "cache_handler",
-            "crew",
-            "llm",
-        }
-
-        copied_data = self.model_dump(exclude=exclude, exclude_unset=True)
-        copied_agent = self.__class__(**copied_data)
-
-        # Copy mutable attributes separately
-        copied_agent.tools = deepcopy(self.tools)
-        copied_agent.config = deepcopy(self.config)
-
-        # Preserve original values for interpolation
-        copied_agent._original_role = self._original_role
-        copied_agent._original_goal = self._original_goal
-        copied_agent._original_backstory = self._original_backstory
-
-        return copied_agent
-
-    def set_rpm_controller(self, rpm_controller: RPMController) -> None:
-        """Set the rpm controller for the agent.
-
-        Args:
-            rpm_controller: An instance of the RPMController class.
-        """
-        if not self._rpm_controller:
-            self._rpm_controller = rpm_controller
-            self.create_agent_executor()

src/crewai/agents/agent_builder/base_agent_executor_mixin.py

@@ -1,65 +0,0 @@
-import time
-
-from crewai.memory.entity.entity_memory_item import EntityMemoryItem
-from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
-from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
-from crewai.utilities.converter import ConverterError
-from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
-
-
-class CrewAgentExecutorMixin:
-    def _should_force_answer(self) -> bool:
-        return (
-            self.iterations == self.force_answer_max_iterations
-        ) and not self.have_forced_answer
-
-    def _create_short_term_memory(self, output) -> None:
-        if (
-            self.crew
-            and self.crew.memory
-            and "Action: Delegate work to coworker" not in output.log
-        ):
-            memory = ShortTermMemoryItem(
-                data=output.log,
-                agent=self.crew_agent.role,
-                metadata={
-                    "observation": self.task.description,
-                },
-            )
-            self.crew._short_term_memory.save(memory)
-
-    def _create_long_term_memory(self, output) -> None:
-        if self.crew and self.crew.memory:
-            ltm_agent = TaskEvaluator(self.crew_agent)
-            evaluation = ltm_agent.evaluate(self.task, output.log)
-
-            if isinstance(evaluation, ConverterError):
-                return
-
-            long_term_memory = LongTermMemoryItem(
-                task=self.task.description,
-                agent=self.crew_agent.role,
-                quality=evaluation.quality,
-                datetime=str(time.time()),
-                expected_output=self.task.expected_output,
-                metadata={
-                    "suggestions": evaluation.suggestions,
-                    "quality": evaluation.quality,
-                },
-            )
-            self.crew._long_term_memory.save(long_term_memory)
-
-            for entity in evaluation.entities:
-                entity_memory = EntityMemoryItem(
-                    name=entity.name,
-                    type=entity.type,
-                    description=entity.description,
-                    relationships="\n".join([f"- {r}" for r in entity.relationships]),
-                )
-                self.crew._entity_memory.save(entity_memory)
-
-    def _ask_human_input(self, final_answer: dict) -> str:
-        """Get human input."""
-        return input(
-            self._i18n.slice("getting_input").format(final_answer=final_answer)
-        )

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

@@ -1,81 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import List, Optional, Union
-from pydantic import BaseModel, Field
-from crewai.agents.agent_builder.base_agent import BaseAgent
-from crewai.task import Task
-from crewai.utilities import I18N
-
-
-class BaseAgentTools(BaseModel, ABC):
-    """Default tools around agent delegation"""
-
-    agents: List[BaseAgent] = Field(description="List of agents in this crew.")
-    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-
-    @abstractmethod
-    def tools(self):
-        pass
-
-    def _get_coworker(self, coworker: Optional[str], **kwargs) -> Optional[str]:
-        coworker = coworker or kwargs.get("co_worker") or kwargs.get("coworker")
-        if coworker:
-            is_list = coworker.startswith("[") and coworker.endswith("]")
-            if is_list:
-                coworker = coworker[1:-1].split(",")[0]
-        return coworker
-
-    def delegate_work(
-        self, task: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to delegate a specific task to a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, task, context)
-
-    def ask_question(
-        self, question: str, context: str, coworker: Optional[str] = None, **kwargs
-    ):
-        """Useful to ask a question, opinion or take from a coworker passing all necessary context and names."""
-        coworker = self._get_coworker(coworker, **kwargs)
-        return self._execute(coworker, question, context)
-
-    def _execute(self, agent: Union[str, None], task: str, context: Union[str, None]):
-        """Execute the command."""
-        try:
-            if agent is None:
-                agent = ""
-
-            # It is important to remove the quotes from the agent name.
-            # The reason we have to do this is because less-powerful LLM's
-            # have difficulty producing valid JSON.
-            # As a result, we end up with invalid JSON that is truncated like this:
-            # {"task": "....", "coworker": "....
-            # when it should look like this:
-            # {"task": "....", "coworker": "...."}
-            agent_name = agent.casefold().replace('"', "").replace("\n", "")
-
-            agent = [
-                available_agent
-                for available_agent in self.agents
-                if available_agent.role.casefold().replace("\n", "") == agent_name
-            ]
-        except Exception as _:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        if not agent:
-            return self.i18n.errors("agent_tool_unexsiting_coworker").format(
-                coworkers="\n".join(
-                    [f"- {agent.role.casefold()}" for agent in self.agents]
-                )
-            )
-
-        agent = agent[0]
-        task = Task(
-            description=task,
-            agent=agent,
-            expected_output="Your best answer to your coworker asking you this, accounting for the context shared.",
-        )
-        return agent.execute_task(task, context)

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

@@ -1,48 +0,0 @@
-from abc import ABC, abstractmethod
-from typing import Any, Optional
-
-
-from pydantic import BaseModel, Field, PrivateAttr
-
-
-class OutputConverter(BaseModel, ABC):
-    """
-    Abstract base class for converting task results into structured formats.
-
-    This class provides a framework for converting unstructured text into
-    either Pydantic models or JSON, tailored for specific agent requirements.
-    It uses a language model to interpret and structure the input text based
-    on given instructions.
-
-    Attributes:
-        text (str): The input text to be converted.
-        llm (Any): The language model used for conversion.
-        model (Any): The target model for structuring the output.
-        instructions (str): Specific instructions for the conversion process.
-        max_attempts (int): Maximum number of conversion attempts (default: 3).
-    """
-
-    _is_gpt: bool = PrivateAttr(default=True)
-    text: str = Field(description="Text to be converted.")
-    llm: Any = Field(description="The language model to be used to convert the text.")
-    model: Any = Field(description="The model to be used to convert the text.")
-    instructions: str = Field(description="Conversion instructions to the LLM.")
-    max_attemps: Optional[int] = Field(
-        description="Max number of attemps to try to get the output formated.",
-        default=3,
-    )
-
-    @abstractmethod
-    def to_pydantic(self, current_attempt=1):
-        """Convert text to pydantic."""
-        pass
-
-    @abstractmethod
-    def to_json(self, current_attempt=1):
-        """Convert text to json."""
-        pass
-
-    @abstractmethod
-    def _is_gpt(self, llm):
-        """Return if llm provided is of gpt from openai."""
-        pass

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

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

src/crewai/agents/executor.py

@@ -7,20 +7,24 @@ from langchain.agents.agent import ExceptionTool
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain_core.agents import AgentAction, AgentFinish, AgentStep
 from langchain_core.exceptions import OutputParserException
-
+from langchain_core.pydantic_v1 import root_validator
 from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 from pydantic import InstanceOf
-from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixin
 
 from crewai.agents.tools_handler import ToolsHandler
+from crewai.memory.entity.entity_memory_item import EntityMemoryItem
+from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
+from crewai.memory.short_term.short_term_memory_item import ShortTermMemoryItem
 from crewai.tools.tool_usage import ToolUsage, ToolUsageErrorException
 from crewai.utilities import I18N
 from crewai.utilities.constants import TRAINING_DATA_FILE
+from crewai.utilities.converter import ConverterError
+from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.training_handler import CrewTrainingHandler
 
 
-class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
+class CrewAgentExecutor(AgentExecutor):
     _i18n: I18N = I18N()
     should_ask_for_human_input: bool = False
     llm: Any = None
@@ -42,6 +46,61 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
     prompt_template: Optional[str] = None
     response_template: Optional[str] = None
 
+    @root_validator()
+    def set_force_answer_max_iterations(cls, values: Dict) -> Dict:
+        values["force_answer_max_iterations"] = values["max_iterations"] - 2
+        return values
+
+    def _should_force_answer(self) -> bool:
+        return (
+            self.iterations == self.force_answer_max_iterations
+        ) and not self.have_forced_answer
+
+    def _create_short_term_memory(self, output) -> None:
+        if (
+            self.crew
+            and self.crew.memory
+            and "Action: Delegate work to coworker" not in output.log
+        ):
+            memory = ShortTermMemoryItem(
+                data=output.log,
+                agent=self.crew_agent.role,
+                metadata={
+                    "observation": self.task.description,
+                },
+            )
+            self.crew._short_term_memory.save(memory)
+
+    def _create_long_term_memory(self, output) -> None:
+        if self.crew and self.crew.memory:
+            ltm_agent = TaskEvaluator(self.crew_agent)
+            evaluation = ltm_agent.evaluate(self.task, output.log)
+
+            if isinstance(evaluation, ConverterError):
+                return
+
+            long_term_memory = LongTermMemoryItem(
+                task=self.task.description,
+                agent=self.crew_agent.role,
+                quality=evaluation.quality,
+                datetime=str(time.time()),
+                expected_output=self.task.expected_output,
+                metadata={
+                    "suggestions": evaluation.suggestions,
+                    "quality": evaluation.quality,
+                },
+            )
+            self.crew._long_term_memory.save(long_term_memory)
+
+            for entity in evaluation.entities:
+                entity_memory = EntityMemoryItem(
+                    name=entity.name,
+                    type=entity.type,
+                    description=entity.description,
+                    relationships="\n".join([f"- {r}" for r in entity.relationships]),
+                )
+                self.crew._entity_memory.save(entity_memory)
+
     def _call(
         self,
         inputs: Dict[str, str],
@@ -251,6 +310,12 @@ class CrewAgentExecutor(AgentExecutor, CrewAgentExecutorMixin):
                     )
             yield AgentStep(action=agent_action, observation=observation)
 
+    def _ask_human_input(self, final_answer: dict) -> str:
+        """Get human input."""
+        return input(
+            self._i18n.slice("getting_input").format(final_answer=final_answer)
+        )
+
     def _handle_crew_training_output(
         self, output: AgentFinish, human_feedback: str | None = None
     ) -> None:

src/crewai/cli/templates/pyproject.toml

@@ -6,7 +6,7 @@ authors = ["Your Name <you@example.com>"]
 
 [tool.poetry.dependencies]
 python = ">=3.10,<=3.13"
-crewai = { extras = ["tools"], version = "^0.35.0" }
+crewai = { extras = ["tools"], version = "^0.32.2" }
 
 [tool.poetry.scripts]
 {{folder_name}} = "{{folder_name}}.main:run"

src/crewai/crew.py

@@ -18,7 +18,6 @@ from pydantic import (
 from pydantic_core import PydanticCustomError
 
 from crewai.agent import Agent
-from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache import CacheHandler
 from crewai.memory.entity.entity_memory import EntityMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
@@ -72,7 +71,7 @@ class Crew(BaseModel):
     cache: bool = Field(default=True)
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
-    agents: List[BaseAgent] = Field(default_factory=list)
+    agents: List[Agent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
     verbose: Union[int, bool] = Field(default=0)
     memory: bool = Field(
@@ -94,7 +93,7 @@ class Crew(BaseModel):
     manager_llm: Optional[Any] = Field(
         description="Language model that will run the agent.", default=None
     )
-    manager_agent: Optional[BaseAgent] = Field(
+    manager_agent: Optional[Any] = Field(
         description="Custom agent that will be used as manager.", default=None
     )
     manager_callbacks: Optional[List[InstanceOf[BaseCallbackHandler]]] = Field(
@@ -281,25 +280,20 @@ class Crew(BaseModel):
         inputs: Optional[Dict[str, Any]] = {},
     ) -> Union[str, Dict[str, Any]]:
         """Starts the crew to work on its assigned tasks."""
-        self._execution_span = self._telemetry.crew_execution_span(self, inputs)
-        # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
-        self._interpolate_inputs(inputs)
+        self._execution_span = self._telemetry.crew_execution_span(self)
+
+        self._interpolate_inputs(inputs)  # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
         self._set_tasks_callbacks()
 
         i18n = I18N(prompt_file=self.prompt_file)
 
         for agent in self.agents:
-            # type: ignore # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
             agent.i18n = i18n
-            # type: ignore[attr-defined] # Argument 1 to "_interpolate_inputs" of "Crew" has incompatible type "dict[str, Any] | None"; expected "dict[str, Any]"
-            agent.crew = self  # type: ignore[attr-defined]
-            # TODO: Create an AgentFunctionCalling protocol for future refactoring
-            if (
-                hasattr(agent, "function_calling_llm")
-                and not agent.function_calling_llm
-            ):
+            agent.crew = self
+
+            if not agent.function_calling_llm:
                 agent.function_calling_llm = self.function_calling_llm
-            if hasattr(agent, "step_callback") and not agent.step_callback:
+            if not agent.step_callback:
                 agent.step_callback = self.step_callback
 
             agent.create_agent_executor()
@@ -309,20 +303,19 @@ class Crew(BaseModel):
         if self.process == Process.sequential:
             result = self._run_sequential_process()
         elif self.process == Process.hierarchical:
-            # type: ignore # Unpacking a string is disallowed
-            result, manager_metrics = self._run_hierarchical_process()
-            # type: ignore # Cannot determine type of "manager_metrics"
-            metrics.append(manager_metrics)
+            result, manager_metrics = self._run_hierarchical_process()  # type: ignore # Unpacking a string is disallowed
+            metrics.append(manager_metrics)  # type: ignore # Cannot determine type of "manager_metrics"
         else:
             raise NotImplementedError(
                 f"The process '{self.process}' is not implemented yet."
             )
+
         metrics = metrics + [
             agent._token_process.get_summary() for agent in self.agents
         ]
-
         self.usage_metrics = {
-            key: sum([m[key] for m in metrics if m is not None]) for key in metrics[0]
+            key: sum([m[key] for m in metrics if m is not None])  # type: ignore # List comprehension has incompatible type List[Any | str]; expected List[bool]
+            for key in metrics[0]
         }
 
         return result
@@ -370,14 +363,13 @@ class Crew(BaseModel):
     def _run_sequential_process(self) -> str:
         """Executes tasks sequentially and returns the final output."""
         task_output = ""
-        token_usage = []
         for task in self.tasks:
             if task.agent.allow_delegation:  # type: ignore #  Item "None" of "Agent | None" has no attribute "allow_delegation"
                 agents_for_delegation = [
                     agent for agent in self.agents if agent != task.agent
                 ]
                 if len(self.agents) > 1 and len(agents_for_delegation) > 0:
-                    task.tools += task.agent.get_delegation_tools(agents_for_delegation)
+                    task.tools += AgentTools(agents=agents_for_delegation).tools()
 
             role = task.agent.role if task.agent is not None else "None"
             self._logger.log("debug", f"== Working Agent: {role}", color="bold_purple")
@@ -389,6 +381,7 @@ class Crew(BaseModel):
                 self._file_handler.log(
                     agent=role, task=task.description, status="started"
                 )
+
             output = task.execute(context=task_output)
 
             if not task.async_execution:
@@ -396,18 +389,15 @@ class Crew(BaseModel):
 
             role = task.agent.role if task.agent is not None else "None"
             self._logger.log("debug", f"== [{role}] Task output: {task_output}\n\n")
-            token_summ = task.agent._token_process.get_summary()
-
-            token_usage.append(token_summ)
 
             if self.output_log_file:
                 self._file_handler.log(agent=role, task=task_output, status="completed")
 
-        token_usage_formatted = self.aggregate_token_usage(token_usage)
         self._finish_execution(task_output)
 
-        # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
-        return self._format_output(task_output, token_usage_formatted)
+        token_usage = task.agent._token_process.get_summary()  # type: ignore # Item "None" of "Agent | None" has no attribute "_token_process"
+
+        return self._format_output(task_output, token_usage)  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
 
     def _run_hierarchical_process(self) -> Union[str, Dict[str, Any]]:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
@@ -418,7 +408,7 @@ class Crew(BaseModel):
             manager = self.manager_agent
             if len(manager.tools) > 0:
                 raise Exception("Manager agent should not have tools")
-            manager.tools = self.manager_agent.get_delegation_tools(self.agents)
+            manager.tools = AgentTools(agents=self.agents).tools()
         else:
             manager = Agent(
                 role=i18n.retrieve("hierarchical_manager_agent", "role"),
@@ -430,7 +420,6 @@ class Crew(BaseModel):
             )
 
         task_output = ""
-        token_usage = []
         for task in self.tasks:
             self._logger.log("debug", f"Working Agent: {manager.role}")
             self._logger.log("info", f"Starting Task: {task.description}")
@@ -444,10 +433,8 @@ class Crew(BaseModel):
                 agent=manager, context=task_output, tools=manager.tools
             )
 
-            self._logger.log("debug", f"[{manager.role}] Task output: {task_output}")
-            if hasattr(task, "agent._token_process"):
-                token_summ = task.agent._token_process.get_summary()
-                token_usage.append(token_summ)
+            self._logger.log("debug", f"[{manager.role}] Task ouptput: {task_output}")
+
             if self.output_log_file:
                 self._file_handler.log(
                     agent=manager.role, task=task_output, status="completed"
@@ -455,13 +442,9 @@ class Crew(BaseModel):
 
         self._finish_execution(task_output)
 
-        # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
         manager_token_usage = manager._token_process.get_summary()
-        token_usage.append(manager_token_usage)
-        token_usage_formatted = self.aggregate_token_usage(token_usage)
-
-        return self._format_output(
-            task_output, token_usage_formatted
+        return self._format_output(  # type: ignore # Incompatible return value type (got "tuple[str, Any]", expected "str")
+            task_output, manager_token_usage
         ), manager_token_usage
 
     def copy(self):
@@ -509,12 +492,11 @@ class Crew(BaseModel):
             )
             for task in self.tasks
         ]
-        # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
-        for agent in self.agents:
-            agent.interpolate_inputs(inputs)
+
+        [agent.interpolate_inputs(inputs) for agent in self.agents]  # type: ignore # "interpolate_inputs" of "Agent" does not return a value (it only ever returns None)
 
     def _format_output(
-        self, output: str, token_usage: Optional[Dict[str, Any]] = None
+        self, output: str, token_usage: Optional[Dict[str, Any]]
     ) -> Union[str, Dict[str, Any]]:
         """
         Formats the output of the crew execution.
@@ -536,9 +518,3 @@ class Crew(BaseModel):
 
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"
-
-    def aggregate_token_usage(self, token_usage_list: List[Dict[str, Any]]):
-        return {
-            key: sum([m[key] for m in token_usage_list if m is not None])
-            for key in token_usage_list[0]
-        }

src/crewai/task.py

@@ -6,14 +6,12 @@ from copy import deepcopy
 from typing import Any, Dict, List, Optional, Type
 
 from langchain_openai import ChatOpenAI
-from opentelemetry.trace import Span
 from pydantic import UUID4, BaseModel, Field, field_validator, model_validator
 from pydantic_core import PydanticCustomError
 
-from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.agent import Agent
 from crewai.tasks.task_output import TaskOutput
-from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities import I18N, ConverterError, Printer
+from crewai.utilities import I18N, Converter, ConverterError, Printer
 from crewai.utilities.pydantic_schema_parser import PydanticSchemaParser
 
 
@@ -44,6 +42,7 @@ class Task(BaseModel):
     tools_errors: int = 0
     delegations: int = 0
     i18n: I18N = I18N()
+    thread: Optional[threading.Thread] = None
     prompt_context: Optional[str] = None
     description: str = Field(description="Description of the actual task.")
     expected_output: str = Field(
@@ -56,7 +55,7 @@ class Task(BaseModel):
     callback: Optional[Any] = Field(
         description="Callback to be executed after the task is completed.", default=None
     )
-    agent: Optional[BaseAgent] = Field(
+    agent: Optional[Agent] = Field(
         description="Agent responsible for execution the task.", default=None
     )
     context: Optional[List["Task"]] = Field(
@@ -96,11 +95,8 @@ class Task(BaseModel):
         default=False,
     )
 
-    _telemetry: Telemetry
-    _execution_span: Span | None = None
     _original_description: str | None = None
     _original_expected_output: str | None = None
-    _thread: threading.Thread | None = None
 
     def __init__(__pydantic_self__, **data):
         config = data.pop("config", {})
@@ -122,12 +118,6 @@ class Task(BaseModel):
             return value[1:]
         return value
 
-    @model_validator(mode="after")
-    def set_private_attrs(self) -> "Task":
-        """Set private attributes."""
-        self._telemetry = Telemetry()
-        return self
-
     @model_validator(mode="after")
     def set_attributes_based_on_config(self) -> "Task":
         """Set attributes based on the agent configuration."""
@@ -155,21 +145,9 @@ class Task(BaseModel):
             )
         return self
 
-    def wait_for_completion(self) -> str | BaseModel:
-        """Wait for asynchronous task completion and return the output."""
-        assert self.async_execution, "Task is not set to be executed asynchronously."
-
-        if self._thread:
-            self._thread.join()
-            self._thread = None
-
-        assert self.output, "Task output is not set."
-
-        return self.output.exported_output
-
     def execute(  # type: ignore # Missing return statement
         self,
-        agent: BaseAgent | None = None,
+        agent: Agent | None = None,
         context: Optional[str] = None,
         tools: Optional[List[Any]] = None,
     ) -> str:
@@ -179,8 +157,6 @@ class Task(BaseModel):
             Output of the task.
         """
 
-        self._execution_span = self._telemetry.task_started(self)
-
         agent = agent or self.agent
         if not agent:
             raise Exception(
@@ -188,25 +164,22 @@ class Task(BaseModel):
             )
 
         if self.context:
-            # type: ignore # Incompatible types in assignment (expression has type "list[Never]", variable has type "str | None")
-            context = []
+            context = []  # type: ignore # Incompatible types in assignment (expression has type "list[Never]", variable has type "str | None")
             for task in self.context:
                 if task.async_execution:
-                    task.wait_for_completion()
-                if task.output:
-                    # type: ignore # Item "str" of "str | None" has no attribute "append"
-                    context.append(task.output.raw_output)
-            # type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
-            context = "\n".join(context)
+                    task.thread.join()  # type: ignore # Item "None" of "Thread | None" has no attribute "join"
+                if task and task.output:
+                    context.append(task.output.raw_output)  # type: ignore # Item "str" of "str | None" has no attribute "append"
+            context = "\n".join(context)  # type: ignore # Argument 1 to "join" of "str" has incompatible type "str | None"; expected "Iterable[str]"
 
         self.prompt_context = context
         tools = tools or self.tools
 
         if self.async_execution:
-            self._thread = threading.Thread(
+            self.thread = threading.Thread(
                 target=self._execute, args=(agent, self, context, tools)
             )
-            self._thread.start()
+            self.thread.start()
         else:
             result = self._execute(
                 task=self,
@@ -222,9 +195,9 @@ class Task(BaseModel):
             context=context,
             tools=tools,
         )
+
         exported_output = self._export_output(result)
 
-        # type: ignore # the responses are usually str but need to figure out a more elegant solution here
         self.output = TaskOutput(
             description=self.description,
             exported_output=exported_output,
@@ -235,10 +208,6 @@ class Task(BaseModel):
         if self.callback:
             self.callback(self.output)
 
-        if self._execution_span:
-            self._telemetry.task_ended(self._execution_span, self)
-            self._execution_span = None
-
         return exported_output
 
     def prompt(self) -> str:
@@ -290,7 +259,7 @@ class Task(BaseModel):
             [task.copy() for task in self.context] if self.context else None
         )
         cloned_agent = self.agent.copy() if self.agent else None
-        cloned_tools = deepcopy(self.tools) if self.tools else []
+        cloned_tools = deepcopy(self.tools) if self.tools else None
 
         copied_task = Task(
             **copied_data,
@@ -309,34 +278,29 @@ class Task(BaseModel):
 
             # try to convert task_output directly to pydantic/json
             try:
-                # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
-                exported_result = model.model_validate_json(result)
+                exported_result = model.model_validate_json(result)  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
                 if self.output_json:
-                    # type: ignore # "str" has no attribute "model_dump"
-                    return exported_result.model_dump()
+                    return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
                 return exported_result
             except Exception:
                 # sometimes the response contains valid JSON in the middle of text
                 match = re.search(r"({.*})", result, re.DOTALL)
                 if match:
                     try:
-                        # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
-                        exported_result = model.model_validate_json(match.group(0))
+                        exported_result = model.model_validate_json(match.group(0))  # type: ignore # Item "None" of "type[BaseModel] | None" has no attribute "model_validate_json"
                         if self.output_json:
-                            # type: ignore # "str" has no attribute "model_dump"
-                            return exported_result.model_dump()
+                            return exported_result.model_dump()  # type: ignore # "str" has no attribute "model_dump"
                         return exported_result
                     except Exception:
                         pass
 
-            # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_llm"
-            llm = getattr(self.agent, "function_calling_llm", None) or self.agent.llm
+            llm = self.agent.function_calling_llm or self.agent.llm  # type: ignore # Item "None" of "Agent | None" has no attribute "function_calling_llm"
+
             if not self._is_gpt(llm):
-                # type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
-                model_schema = PydanticSchemaParser(model=model).get_schema()
+                model_schema = PydanticSchemaParser(model=model).get_schema()  # type: ignore # Argument "model" to "PydanticSchemaParser" has incompatible type "type[BaseModel] | None"; expected "type[BaseModel]"
                 instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
-            converter = self.agent.get_output_converter(
+            converter = Converter(
                 llm=llm, text=result, model=model, instructions=instructions
             )
 
@@ -354,8 +318,7 @@ class Task(BaseModel):
 
         if self.output_file:
             content = (
-                # type: ignore # "str" has no attribute "json"
-                exported_result if not self.output_pydantic else exported_result.json()
+                exported_result if not self.output_pydantic else exported_result.json()  # type: ignore # "str" has no attribute "json"
             )
             self._save_file(content)
 
@@ -365,14 +328,12 @@ class Task(BaseModel):
         return isinstance(llm, ChatOpenAI) and llm.openai_api_base is None
 
     def _save_file(self, result: Any) -> None:
-        # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
-        directory = os.path.dirname(self.output_file)
+        directory = os.path.dirname(self.output_file)  # type: ignore # Value of type variable "AnyOrLiteralStr" of "dirname" cannot be "str | None"
 
         if directory and not os.path.exists(directory):
             os.makedirs(directory)
 
-        # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
-        with open(self.output_file, "w", encoding="utf-8") as file:
+        with open(self.output_file, "w", encoding="utf-8") as file:  # type: ignore # Argument 1 to "open" has incompatible type "str | None"; expected "int | str | bytes | PathLike[str] | PathLike[bytes]"
             file.write(result)
         return None
 

src/crewai/telemetry/telemetry.py

@@ -1,10 +1,8 @@
-from __future__ import annotations
-
 import asyncio
 import json
 import os
 import platform
-from typing import TYPE_CHECKING, Any
+from typing import Any
 
 import pkg_resources
 from opentelemetry import trace
@@ -12,11 +10,7 @@ from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExport
 from opentelemetry.sdk.resources import SERVICE_NAME, Resource
 from opentelemetry.sdk.trace import TracerProvider
 from opentelemetry.sdk.trace.export import BatchSpanProcessor
-from opentelemetry.trace import Span, Status, StatusCode
-
-if TYPE_CHECKING:
-    from crewai.crew import Crew
-    from crewai.task import Task
+from opentelemetry.trace import Status, StatusCode
 
 
 class Telemetry:
@@ -94,6 +88,9 @@ class Telemetry:
                 self._add_attribute(span, "python_version", platform.python_version())
                 self._add_attribute(span, "crew_id", str(crew.id))
                 self._add_attribute(span, "crew_process", crew.process)
+                self._add_attribute(
+                    span, "crew_language", crew.prompt_file if crew.i18n else "None"
+                )
                 self._add_attribute(span, "crew_memory", crew.memory)
                 self._add_attribute(span, "crew_number_of_tasks", len(crew.tasks))
                 self._add_attribute(span, "crew_number_of_agents", len(crew.agents))
@@ -105,8 +102,6 @@ class Telemetry:
                             {
                                 "id": str(agent.id),
                                 "role": agent.role,
-                                "goal": agent.goal,
-                                "backstory": agent.backstory,
                                 "verbose?": agent.verbose,
                                 "max_iter": agent.max_iter,
                                 "max_rpm": agent.max_rpm,
@@ -128,16 +123,8 @@ class Telemetry:
                         [
                             {
                                 "id": str(task.id),
-                                "description": task.description,
-                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
-                                "human_input?": task.human_input,
                                 "agent_role": task.agent.role if task.agent else "None",
-                                "context": (
-                                    [task.description for task in task.context]
-                                    if task.context
-                                    else None
-                                ),
                                 "tools_names": [
                                     tool.name.casefold() for tool in task.tools
                                 ],
@@ -156,38 +143,6 @@ class Telemetry:
             except Exception:
                 pass
 
-    def task_started(self, task: Task) -> Span | None:
-        """Records task started in a crew."""
-        if self.ready:
-            try:
-                tracer = trace.get_tracer("crewai.telemetry")
-                span = tracer.start_span("Task Execution")
-
-                self._add_attribute(span, "task_id", str(task.id))
-                self._add_attribute(span, "formatted_description", task.description)
-                self._add_attribute(
-                    span, "formatted_expected_output", task.expected_output
-                )
-
-                return span
-            except Exception:
-                pass
-
-        return None
-
-    def task_ended(self, span: Span, task: Task):
-        """Records task execution in a crew."""
-        if self.ready:
-            try:
-                self._add_attribute(
-                    span, "output", task.output.raw_output if task.output else ""
-                )
-
-                span.set_status(Status(StatusCode.OK))
-                span.end()
-            except Exception:
-                pass
-
     def tool_repeated_usage(self, llm: Any, tool_name: str, attempts: int):
         """Records the repeated usage 'error' of a tool by an agent."""
         if self.ready:
@@ -252,7 +207,7 @@ class Telemetry:
             except Exception:
                 pass
 
-    def crew_execution_span(self, crew: Crew, inputs: dict[str, Any] | None):
+    def crew_execution_span(self, crew):
         """Records the complete execution of a crew.
         This is only collected if the user has opted-in to share the crew.
         """
@@ -266,7 +221,6 @@ class Telemetry:
                     pkg_resources.get_distribution("crewai").version,
                 )
                 self._add_attribute(span, "crew_id", str(crew.id))
-                self._add_attribute(span, "inputs", json.dumps(inputs))
                 self._add_attribute(
                     span,
                     "crew_agents",
@@ -284,7 +238,7 @@ class Telemetry:
                                 "llm": json.dumps(self._safe_llm_attributes(agent.llm)),
                                 "delegation_enabled?": agent.allow_delegation,
                                 "tools_names": [
-                                    tool.name.casefold() for tool in agent.tools or []
+                                    tool.name.casefold() for tool in agent.tools
                                 ],
                             }
                             for agent in crew.agents
@@ -299,17 +253,16 @@ class Telemetry:
                             {
                                 "id": str(task.id),
                                 "description": task.description,
-                                "expected_output": task.expected_output,
                                 "async_execution?": task.async_execution,
-                                "human_input?": task.human_input,
+                                "output": task.expected_output,
                                 "agent_role": task.agent.role if task.agent else "None",
                                 "context": (
                                     [task.description for task in task.context]
                                     if task.context
-                                    else None
+                                    else "None"
                                 ),
                                 "tools_names": [
-                                    tool.name.casefold() for tool in task.tools or []
+                                    tool.name.casefold() for tool in task.tools
                                 ],
                             }
                             for task in crew.tasks

src/crewai/tools/agent_tools.py

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

src/crewai/utilities/converter.py

@@ -1,11 +1,9 @@
 import json
+from typing import Any, Optional
 
 from langchain.schema import HumanMessage, SystemMessage
 from langchain_openai import ChatOpenAI
-from pydantic import model_validator
-from crewai.agents.agent_builder.utilities.base_output_converter_base import (
-    OutputConverter,
-)
+from pydantic import BaseModel, Field, PrivateAttr, model_validator
 
 
 class ConverterError(Exception):
@@ -16,9 +14,19 @@ class ConverterError(Exception):
         self.message = message
 
 
-class Converter(OutputConverter):
+class Converter(BaseModel):
     """Class that converts text into either pydantic or json."""
 
+    _is_gpt: bool = PrivateAttr(default=True)
+    text: str = Field(description="Text to be converted.")
+    llm: Any = Field(description="The language model to be used to convert the text.")
+    model: Any = Field(description="The model to be used to convert the text.")
+    instructions: str = Field(description="Conversion instructions to the LLM.")
+    max_attemps: Optional[int] = Field(
+        description="Max number of attemps to try to get the output formated.",
+        default=3,
+    )
+
     @model_validator(mode="after")
     def check_llm_provider(self):
         if not self._is_gpt(self.llm):

src/crewai/utilities/token_counter_callback.py

@@ -4,7 +4,31 @@ import tiktoken
 from langchain.callbacks.base import BaseCallbackHandler
 from langchain.schema import LLMResult
 
-from crewai.agents.agent_builder.utilities.base_token_process import TokenProcess
+
+class TokenProcess:
+    total_tokens: int = 0
+    prompt_tokens: int = 0
+    completion_tokens: int = 0
+    successful_requests: int = 0
+
+    def sum_prompt_tokens(self, tokens: int):
+        self.prompt_tokens = self.prompt_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_completion_tokens(self, tokens: int):
+        self.completion_tokens = self.completion_tokens + tokens
+        self.total_tokens = self.total_tokens + tokens
+
+    def sum_successful_requests(self, requests: int):
+        self.successful_requests = self.successful_requests + requests
+
+    def get_summary(self) -> Dict[str, Any]:
+        return {
+            "total_tokens": self.total_tokens,
+            "prompt_tokens": self.prompt_tokens,
+            "completion_tokens": self.completion_tokens,
+            "successful_requests": self.successful_requests,
+        }
 
 
 class TokenCalcHandler(BaseCallbackHandler):

tests/agent_test.py

@@ -12,7 +12,6 @@ from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
 from crewai.agents.parser import CrewAgentParser
-
 from crewai.tools.tool_calling import InstructorToolCalling
 from crewai.tools.tool_usage import ToolUsage
 from crewai.utilities import RPMController

tests/cassettes/test_crew_full_ouput.yaml

@@ -400561,4 +400561,4 @@ interactions:
     status:
       code: 200
       message: OK
-version: 1
+version: 1

tests/cassettes/test_save_task_pydantic_output.yaml

@@ -1,111 +1,114 @@
 interactions:
 - request:
     body: !!binary |
-      CqcuCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS/i0KEgoQY3Jld2FpLnRl
-      bGVtZXRyeRKNAQoQWsK2m2g3VyJHWaXnQym/VhIII86T/ZrUN8EqClRvb2wgVXNhZ2UwATnYaVBJ
-      jjbPF0FYJVFJjjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHwoJdG9vbF9uYW1lEhIK
-      EGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYARKNAQoQ6Z32Q3lxb6RU5NbYTjLU
-      SxIIqcY2PQT6l3gqClRvb2wgVXNhZ2UwATnAus9KjjbPF0EYU9BKjjbPF0oaCg5jcmV3YWlfdmVy
-      c2lvbhIICgYwLjMwLjZKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1w
-      dHMSAhgBegIYARKNAQoQwek7gO4ckm9Jvn6BwHW9QxII3T6AbeLq7EIqClRvb2wgVXNhZ2UwATlY
-      cF9PjjbPF0GoM2BPjjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHwoJdG9vbF9uYW1l
-      EhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYARLKAQoQxj4ww0iUXwfHLphC
-      57m2khIIjJFrK75dr+gqEFRvb2wgVXNhZ2UgRXJyb3IwATlQt3hRjjbPF0GIfnlRjjbPF0oaCg5j
-      cmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKZgoDbGxtEl8KXXsibmFtZSI6IG51bGwsICJtb2RlbF9u
-      YW1lIjogImdwdC00LTAxMjUtcHJldmlldyIsICJ0ZW1wZXJhdHVyZSI6IDAuNywgImNsYXNzIjog
-      IkNoYXRPcGVuQUkifXoCGAESygEKEArpOi/Us2A3PpB8Gii7j88SCPzLVYFtDQSsKhBUb29sIFVz
-      YWdlIEVycm9yMAE56MF6Uo42zxdBaH17Uo42zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42
-      SmYKA2xsbRJfCl17Im5hbWUiOiBudWxsLCAibW9kZWxfbmFtZSI6ICJncHQtNC0wMTI1LXByZXZp
-      ZXciLCAidGVtcGVyYXR1cmUiOiAwLjcsICJjbGFzcyI6ICJDaGF0T3BlbkFJIn16AhgBEsoBChBt
-      yk7Qq7Sgw6WMHkcEj6WfEgijl4wq3/wt7SoQVG9vbCBVc2FnZSBFcnJvcjABOeAyk1OONs8XQdja
-      k1OONs8XShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzAuNkpmCgNsbG0SXwpdeyJuYW1lIjogbnVs
-      bCwgIm1vZGVsX25hbWUiOiAiZ3B0LTQtMDEyNS1wcmV2aWV3IiwgInRlbXBlcmF0dXJlIjogMC43
-      LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIYARJiChAmBkQ6MDSlxvmv4YVRGzmdEgj1PJQNKV6C
-      sCoQVG9vbCBVc2FnZSBFcnJvcjABOfgzEleONs8XQQjYEleONs8XShoKDmNyZXdhaV92ZXJzaW9u
-      EggKBjAuMzAuNnoCGAESjQEKEAwZ3MFe3tvKT/3fZgpV4ywSCEicyz0QPrdVKgpUb29sIFVzYWdl
-      MAE5CPdvWI42zxdBWLpwWI42zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42Sh8KCXRvb2xf
-      bmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAESjQEKEGIhNyFGf0X0
-      iubEVUn96JASCCPQkQmTahyuKgpUb29sIFVzYWdlMAE5gFEoWo42zxdBgEspWo42zxdKGgoOY3Jl
-      d2FpX3ZlcnNpb24SCAoGMC4zMC42Sh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4K
-      CGF0dGVtcHRzEgIYAXoCGAESjQEKECluqAOjM96Xcuo2pY/AxrUSCE2CDrSmkuFVKgpUb29sIFVz
-      YWdlMAE5YJvZW442zxdBoLTaW442zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42Sh8KCXRv
-      b2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAESYgoQ3rypXzEG
-      OaBuogXtWu23OxIIJU2tAn4rSesqEFRvb2wgVXNhZ2UgRXJyb3IwATmAst9fjjbPF0GgfeBfjjbP
-      F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZ6AhgBEpcBChCoJakn4gJ/bsmLqhOQ+pzJEggZ
-      FE39y55kSSoKVG9vbCBVc2FnZTABOdAenmKONs8XQdAYn2KONs8XShoKDmNyZXdhaV92ZXJzaW9u
-      EggKBjAuMzAuNkopCgl0b29sX25hbWUSHAoaRGVsZWdhdGUgd29yayB0byBjby13b3JrZXJKDgoI
-      YXR0ZW1wdHMSAhgBegIYARKWAQoQbG8DmDglapO/4qWaAMeMhhII+ZHmV8V3pYsqClRvb2wgVXNh
-      Z2UwATlwxGFojjbPF0Goi2JojjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKKAoJdG9v
-      bF9uYW1lEhsKGUFzayBxdWVzdGlvbiB0byBjby13b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYARKL
-      AQoQA3elhWektmDyQtq61PMfARIInyy2MM6Y3gwqClRvb2wgVXNhZ2UwATnoK/drjjbPF0EI9/dr
-      jjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHQoJdG9vbF9uYW1lEhAKDmxlYXJuX2Fi
-      b3V0X0FJSg4KCGF0dGVtcHRzEgIYAXoCGAESiwEKEGOUc3nLZT3TTF1UqTEf3aYSCAIG5j6E1JLk
-      KgpUb29sIFVzYWdlMAE5wIxYbY42zxdBuDRZbY42zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4z
-      MC42Sh0KCXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAF6AhgBEmIK
-      ELpJQh4iRyb0LtlYOjZkn+8SCCPJgujx+G0+KhBUb29sIFVzYWdlIEVycm9yMAE5ULmabo42zxdB
-      wE2bbo42zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42egIYARLzAQoQFQ74Wok+KKV4rR5E
-      kSYVMRIIJRc3G0tgxY4qClRvb2wgVXNhZ2UwATlYx7FzjjbPF0EYorJzjjbPF0oaCg5jcmV3YWlf
-      dmVyc2lvbhIICgYwLjMwLjZKHQoJdG9vbF9uYW1lEhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVt
-      cHRzEgIYAUpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTMuNS10
-      dXJiby0wMTI1IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIY
-      ARLzAQoQnJMORTVCM7CSablsUBxMJxIIQCKuv5AXvFEqClRvb2wgVXNhZ2UwATl4LDp1jjbPF0EQ
-      5Dp1jjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHQoJdG9vbF9uYW1lEhAKDmxlYXJu
-      X2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAUpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVs
-      X25hbWUiOiAiZ3B0LTMuNS10dXJiby0wMTI1IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3Mi
-      OiAiQ2hhdE9wZW5BSSJ9egIYARLzAQoQAfw9BLcOs9bjmKBOkNP2pRII8jFQggGaAhsqClRvb2wg
-      VXNhZ2UwATlAbQJ3jjbPF0HwIAN3jjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHQoJ
-      dG9vbF9uYW1lEhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAUpmCgNsbG0SXwpdeyJu
-      YW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTMuNS10dXJiby0wMTI1IiwgInRlbXBlcmF0
-      dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIYARKXAQoQuzP2zqalo852qSEZJPoW
-      /RIInedZySqvqygqClRvb2wgVXNhZ2UwATkYAGWujjbPF0Go4mWujjbPF0oaCg5jcmV3YWlfdmVy
-      c2lvbhIICgYwLjMwLjZKKQoJdG9vbF9uYW1lEhwKGkRlbGVnYXRlIHdvcmsgdG8gY28td29ya2Vy
-      Sg4KCGF0dGVtcHRzEgIYAXoCGAESlwEKEATlyOCYjHSp1K3QoCeqMmUSCP/SCa7gOMy+KgpUb29s
-      IFVzYWdlMAE5QKeKuY42zxdBqGaLuY42zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42SikK
-      CXRvb2xfbmFtZRIcChpEZWxlZ2F0ZSB3b3JrIHRvIGNvLXdvcmtlckoOCghhdHRlbXB0cxICGAF6
-      AhgBEpcBChDCNHUdgM9SPykW9jZLAszpEgjxF3ox7N4UJyoKVG9vbCBVc2FnZTABOeDPiMqONs8X
-      QdCiicqONs8XShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzAuNkopCgl0b29sX25hbWUSHAoaRGVs
-      ZWdhdGUgd29yayB0byBjby13b3JrZXJKDgoIYXR0ZW1wdHMSAhgBegIYARKHAQoQ79rs2SVt97mT
-      uX/cWDscnBII6rrlGA8RtbMqClRvb2wgVXNhZ2UwATkYFcz6jjbPF0FQ3Mz6jjbPF0oaCg5jcmV3
-      YWlfdmVyc2lvbhIICgYwLjMwLjZKGQoJdG9vbF9uYW1lEgwKCm11bHRpcGxpZXJKDgoIYXR0ZW1w
-      dHMSAhgBegIYARKHAQoQVP9tyrp7Wv9IolbUgao9uBII8inECsdSecYqClRvb2wgVXNhZ2UwATl4
-      JZH8jjbPF0GIyZH8jjbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKGQoJdG9vbF9uYW1l
-      EgwKCm11bHRpcGxpZXJKDgoIYXR0ZW1wdHMSAhgBegIYARJiChCQ/ikD6wODQRRK4sOy00xbEgh3
-      W3X41OAJQSoQVG9vbCBVc2FnZSBFcnJvcjABOXi4pf+ONs8XQeB3pv+ONs8XShoKDmNyZXdhaV92
-      ZXJzaW9uEggKBjAuMzAuNnoCGAESYgoQ53JWAKq1hJb9rscUFhC6GhIIPzTRaeMJnJYqEFRvb2wg
-      VXNhZ2UgRXJyb3IwATkIPJsAjzbPF0GQzJsAjzbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMw
-      LjZ6AhgBEvMBChC/rx/MIKAdxGOMAfLmXNJoEghCqOptNDfKXSoKVG9vbCBVc2FnZTABOaAAQwuP
-      Ns8XQejuQwuPNs8XShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzAuNkodCgl0b29sX25hbWUSEAoO
-      bGVhcm5fYWJvdXRfQUlKDgoIYXR0ZW1wdHMSAhgBSmYKA2xsbRJfCl17Im5hbWUiOiBudWxsLCAi
-      bW9kZWxfbmFtZSI6ICJncHQtMy41LXR1cmJvLTAxMjUiLCAidGVtcGVyYXR1cmUiOiAwLjcsICJj
-      bGFzcyI6ICJDaGF0T3BlbkFJIn16AhgBEsoBChAJc/cdYOh6bOxXLE4BSMa0Egg1m5FL4NyjeCoQ
-      VG9vbCBVc2FnZSBFcnJvcjABOXiAigyPNs8XQZhLiwyPNs8XShoKDmNyZXdhaV92ZXJzaW9uEggK
-      BjAuMzAuNkpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTMuNS10
-      dXJiby0wMTI1IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIY
-      ARLzAQoQIwsE8AeUGx2Zlpsj/8cIpxIIGiYkqh1O8V8qClRvb2wgVXNhZ2UwATmIou0NjzbPF0EI
-      Xu4NjzbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHQoJdG9vbF9uYW1lEhAKDmxlYXJu
-      X2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAUpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVs
-      X25hbWUiOiAiZ3B0LTMuNS10dXJiby0wMTI1IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3Mi
-      OiAiQ2hhdE9wZW5BSSJ9egIYARLzAQoQzE4sWSyDKyW+MsjMu3qaURII0Ek+EFuG+pQqClRvb2wg
-      VXNhZ2UwATl4knUPjzbPF0FYPnYPjzbPF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKHQoJ
-      dG9vbF9uYW1lEhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0dGVtcHRzEgIYAUpmCgNsbG0SXwpdeyJu
-      YW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTMuNS10dXJiby0wMTI1IiwgInRlbXBlcmF0
-      dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIYARKIAQoQV5Ebj7z0WSmnDL6cuEwc
-      aRIIjQwTYaUnU+0qClRvb2wgVXNhZ2UwATmoPboXjzbPF0Eo+boXjzbPF0oaCg5jcmV3YWlfdmVy
-      c2lvbhIICgYwLjMwLjZKGgoJdG9vbF9uYW1lEg0KC3JldHVybl9kYXRhSg4KCGF0dGVtcHRzEgIY
-      AXoCGAESlwEKEC6MfuEYt3qySHDPP/fGhDoSCME60nPc2PP5KgpUb29sIFVzYWdlMAE5kBWpIo82
-      zxdBmOSpIo82zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42SikKCXRvb2xfbmFtZRIcChpE
-      ZWxlZ2F0ZSB3b3JrIHRvIGNvLXdvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBEo8BChAW4yhha9hM
-      Bq622l4ljFgrEgiqbqTTWlbblCoKVG9vbCBVc2FnZTABOcgCViiPNs8XQVjlViiPNs8XShoKDmNy
-      ZXdhaV92ZXJzaW9uEggKBjAuMzAuNkohCgl0b29sX25hbWUSFAoSbXVsdGlwbGNhdGlvbl90b29s
-      Sg4KCGF0dGVtcHRzEgIYAXoCGAESjwEKEDMq2VDCq4/7QaQhcHACuUQSCN8bD12jrjruKgpUb29s
-      IFVzYWdlMAE5OAsOKo82zxdBSK8OKo82zxdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMC42SiEK
-      CXRvb2xfbmFtZRIUChJtdWx0aXBsY2F0aW9uX3Rvb2xKDgoIYXR0ZW1wdHMSAhgBegIYARKPAQoQ
-      7Q6do5ZLFG1iUnTRbk8ZOBIISweZORdlmm8qClRvb2wgVXNhZ2UwATngLc4rjzbPF0HY1c4rjzbP
-      F0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMwLjZKIQoJdG9vbF9uYW1lEhQKEm11bHRpcGxjYXRp
-      b25fdG9vbEoOCghhdHRlbXB0cxICGAF6AhgBEo8BChDAqYWXAeTztQaza44KbHvPEgjLnc1ioqFZ
-      2yoKVG9vbCBVc2FnZTABOWAPky2PNs8XQaCrky2PNs8XShoKDmNyZXdhaV92ZXJzaW9uEggKBjAu
-      MzAuNkohCgl0b29sX25hbWUSFAoSbXVsdGlwbGNhdGlvbl90b29sSg4KCGF0dGVtcHRzEgIYAXoC
-      GAE=
+      CvkvCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS0C8KEgoQY3Jld2FpLnRl
+      bGVtZXRyeRKTAQoQLqw+EjxvbTuuw2uK+Z1VwBIIQ7i0ygfU4ncqClRvb2wgVXNhZ2UwATmI4vtU
+      X+vcF0HYpfxUX+vcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJKHwoJdG9vbF9uYW1lEhIK
+      EGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABKTAQoQ5gXS9qaPUXIZ
+      HrfMjoNLTBIIbYzD2CnTapMqClRvb2wgVXNhZ2UwATnQkFRWX+vcF0EoKVVWX+vcF0oaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjMyLjJKHwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoI
+      YXR0ZW1wdHMSAhgBegIYAYUBAAEAABKTAQoQ2qhuTH7MsHdQcTba5VsvnhIITr+y+m0u0l8qClRv
+      b2wgVXNhZ2UwATkgFJtaX+vcF0EQ55taX+vcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJK
+      HwoJdG9vbF9uYW1lEhIKEGdldF9maW5hbF9hbnN3ZXJKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEA
+      ABLQAQoQqRrtPlT4tPSoyC0r7b4LKxIIQeUfZL/g8XcqEFRvb2wgVXNhZ2UgRXJyb3IwATloU8Fc
+      X+vcF0G4FsJcX+vcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJKZgoDbGxtEl8KXXsibmFt
+      ZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC00LTAxMjUtcHJldmlldyIsICJ0ZW1wZXJhdHVy
+      ZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAAS0AEKEKBXCmTXjZRJFp2i
+      rTVc0HASCHda+ZbetuNrKhBUb29sIFVzYWdlIEVycm9yMAE5CNWoXV/r3BdBuIipXV/r3BdKGgoO
+      Y3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySmYKA2xsbRJfCl17Im5hbWUiOiBudWxsLCAibW9kZWxf
+      bmFtZSI6ICJncHQtNC0wMTI1LXByZXZpZXciLCAidGVtcGVyYXR1cmUiOiAwLjcsICJjbGFzcyI6
+      ICJDaGF0T3BlbkFJIn16AhgBhQEAAQAAEtABChDRyJwJBHmQbpjeqiqVKVXtEggwlO2x4+8/7SoQ
+      VG9vbCBVc2FnZSBFcnJvcjABOZDWpV5f69wXQXCCpl5f69wXShoKDmNyZXdhaV92ZXJzaW9uEggK
+      BjAuMzIuMkpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTQtMDEy
+      NS1wcmV2aWV3IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9egIY
+      AYUBAAEAABJoChBYSTS4T56qn9uV/7fuGXJeEghoO+P9EPF9mioQVG9vbCBVc2FnZSBFcnJvcjAB
+      OeC54mFf69wXQVBO42Ff69wXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMnoCGAGFAQABAAAS
+      kwEKEBSvIa1MLNQ87IQBMQO+bJwSCHBHin2QwJ06KgpUb29sIFVzYWdlMAE5SIgZY1/r3BdBuBwa
+      Y1/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh8KCXRvb2xfbmFtZRISChBnZXRfZmlu
+      YWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASkwEKELCH9rRBT8NoumB9Poc1RV8S
+      CAuveHZDPucwKgpUb29sIFVzYWdlMAE5WNIcZV/r3BdBALEdZV/r3BdKGgoOY3Jld2FpX3ZlcnNp
+      b24SCAoGMC4zMi4ySh8KCXRvb2xfbmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRz
+      EgIYAXoCGAGFAQABAAASkwEKEH+Cq1vI2oyP7OvOUhPFEmISCEI78UcGQbDYKgpUb29sIFVzYWdl
+      MAE58H9sZl/r3BdBYBRtZl/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh8KCXRvb2xf
+      bmFtZRISChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASaAoQSypk
+      rhDcn8HjHzB1fE06IxII14WesmPDQIIqEFRvb2wgVXNhZ2UgRXJyb3IwATnIf+ZpX+vcF0EgGOdp
+      X+vcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJ6AhgBhQEAAQAAEpwBChBcqrWqs8O3kz0u
+      WtxW6Q2PEghUJQXvLBsS3ioKVG9vbCBVc2FnZTABOdDdVWxf69wXQeCBVmxf69wXShoKDmNyZXdh
+      aV92ZXJzaW9uEggKBjAuMzIuMkooCgl0b29sX25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dv
+      cmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpsBChAP+DwhzLsJsu/moyVCYJZLEgikfOou
+      Ui5xEyoKVG9vbCBVc2FnZTABOUB0i3Ff69wXQcAvjHFf69wXShoKDmNyZXdhaV92ZXJzaW9uEggK
+      BjAuMzIuMkonCgl0b29sX25hbWUSGgoYQXNrIHF1ZXN0aW9uIHRvIGNvd29ya2VySg4KCGF0dGVt
+      cHRzEgIYAXoCGAGFAQABAAASkQEKEPb3Mf1VqY8Vf6+29dlFhWgSCM1ReYxiVApJKgpUb29sIFVz
+      YWdlMAE5sPqldF/r3BdBeKqmdF/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRv
+      b2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAF6AhgBhQEAAQAAEpEBChCq
+      FQcV1PqHVRas5I37hdYPEgjBm90KS4QjuioKVG9vbCBVc2FnZTABOfjr3nVf69wXQWiA33Vf69wX
+      ShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMkodCgl0b29sX25hbWUSEAoObGVhcm5fYWJvdXRf
+      QUlKDgoIYXR0ZW1wdHMSAhgBegIYAYUBAAEAABJoChCAUmAdKEw8ldIXchj4l5FTEggACxwRIm8M
+      TioQVG9vbCBVc2FnZSBFcnJvcjABOcgJ/3Zf69wXQZiO/3Zf69wXShoKDmNyZXdhaV92ZXJzaW9u
+      EggKBjAuMzIuMnoCGAGFAQABAAAS+QEKELqY0vdf9nhQ5xC3jQVvMZ0SCDx91QCyVM3EKgpUb29s
+      IFVzYWdlMAE5aALQe1/r3BdBQNnQe1/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0K
+      CXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsi
+      bmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJh
+      dHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAAS+QEKEOvcp2bL70Uh
+      ppRRgSDfGocSCAbAS5eR0Zf0KgpUb29sIFVzYWdlMAE5GLEzfV/r3BdBsGg0fV/r3BdKGgoOY3Jl
+      d2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghh
+      dHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0z
+      LjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUki
+      fXoCGAGFAQABAAAS+QEKEJJrId+mXE5JtfjeU884CCASCOokJijVUg9ZKgpUb29sIFVzYWdlMAE5
+      OIzSfl/r3BdB6D/Tfl/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRvb2xfbmFt
+      ZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFtZSI6IG51
+      bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVyZSI6IDAu
+      NywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAASnAEKEGbTvSmCEq1hfmW2vRFmS7oS
+      CADTIi8+Q/0uKgpUb29sIFVzYWdlMAE5EFJ9s1/r3BdBYBV+s1/r3BdKGgoOY3Jld2FpX3ZlcnNp
+      b24SCAoGMC4zMi4ySigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4K
+      CGF0dGVtcHRzEgIYAXoCGAGFAQABAAASnAEKEKJQrO/iuhlVNO1rDNHiMRcSCPTkQpOzD6cQKgpU
+      b29sIFVzYWdlMAE54DiFvV/r3BdB8NyFvV/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4y
+      SigKCXRvb2xfbmFtZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIY
+      AXoCGAGFAQABAAASnAEKEEfqaRZKKFFTpce+qADatWsSCC+o088u72sxKgpUb29sIFVzYWdlMAE5
+      iG7ryV/r3BdBqDnsyV/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySigKCXRvb2xfbmFt
+      ZRIbChlEZWxlZ2F0ZSB3b3JrIHRvIGNvd29ya2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAAS
+      jQEKEOop1HWbNPE8YlD5deGfOSMSCKmtMdk4L2TXKgpUb29sIFVzYWdlMAE5MIld9F/r3BdBWCle
+      9F/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4yShkKCXRvb2xfbmFtZRIMCgptdWx0aXBs
+      aWVySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASjQEKEIeyHGVjE8c+y9tC4zDzNYkSCK1EdMCk
+      DinyKgpUb29sIFVzYWdlMAE5yJLx9V/r3BdBgBvy9V/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoG
+      MC4zMi4yShkKCXRvb2xfbmFtZRIMCgptdWx0aXBsaWVySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQAB
+      AAASaAoQkg972Qk74fczD5e/SDXg1BII02eF0/y/vDwqEFRvb2wgVXNhZ2UgRXJyb3IwATnoC8T4
+      X+vcF0FYoMT4X+vcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJ6AhgBhQEAAQAAEmgKEK+/
+      ep8MyIKryHi4B9MJgFoSCPmxA6f5KaeDKhBUb29sIFVzYWdlIEVycm9yMAE56Gaa+V/r3BdBuOua
+      +V/r3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4yegIYAYUBAAEAABL5AQoQHOvurczFRHPh
+      zLdotvB2DxIILtVN6gvO/fIqClRvb2wgVXNhZ2UwATlwXUgEYOvcF0F4LEkEYOvcF0oaCg5jcmV3
+      YWlfdmVyc2lvbhIICgYwLjMyLjJKHQoJdG9vbF9uYW1lEhAKDmxlYXJuX2Fib3V0X0FJSg4KCGF0
+      dGVtcHRzEgIYAUpmCgNsbG0SXwpdeyJuYW1lIjogbnVsbCwgIm1vZGVsX25hbWUiOiAiZ3B0LTMu
+      NS10dXJiby0wMTI1IiwgInRlbXBlcmF0dXJlIjogMC43LCAiY2xhc3MiOiAiQ2hhdE9wZW5BSSJ9
+      egIYAYUBAAEAABLQAQoQ1OGo2qdk9xb9UdNmtGuYoBIIRRfFWBesYaYqEFRvb2wgVXNhZ2UgRXJy
+      b3IwATmIP3AFYOvcF0GY43AFYOvcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJKZgoDbGxt
+      El8KXXsibmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0
+      ZW1wZXJhdHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAAS+QEKEGr8
+      23SE3ifiBzkxMmmqLDwSCKa4vwo9iDeyKgpUb29sIFVzYWdlMAE5KEypBmDr3BdB2P+pBmDr3BdK
+      GgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRvb2xfbmFtZRIQCg5sZWFybl9hYm91dF9B
+      SUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFtZSI6IG51bGwsICJtb2RlbF9uYW1lIjog
+      ImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVyZSI6IDAuNywgImNsYXNzIjogIkNoYXRP
+      cGVuQUkifXoCGAGFAQABAAAS+QEKEKuHQQTWEfqoLrsTS3MWk4ISCNLBrrxWfjj+KgpUb29sIFVz
+      YWdlMAE52CQGCGDr3BdB0MwGCGDr3BdKGgoOY3Jld2FpX3ZlcnNpb24SCAoGMC4zMi4ySh0KCXRv
+      b2xfbmFtZRIQCg5sZWFybl9hYm91dF9BSUoOCghhdHRlbXB0cxICGAFKZgoDbGxtEl8KXXsibmFt
+      ZSI6IG51bGwsICJtb2RlbF9uYW1lIjogImdwdC0zLjUtdHVyYm8tMDEyNSIsICJ0ZW1wZXJhdHVy
+      ZSI6IDAuNywgImNsYXNzIjogIkNoYXRPcGVuQUkifXoCGAGFAQABAAASjgEKEEl2jlSHosTDCf2T
+      kVMJdVoSCFKYTaQ7uA7tKgpUb29sIFVzYWdlMAE5+LNjD2Dr3BdBgERkD2Dr3BdKGgoOY3Jld2Fp
+      X3ZlcnNpb24SCAoGMC4zMi4yShoKCXRvb2xfbmFtZRINCgtyZXR1cm5fZGF0YUoOCghhdHRlbXB0
+      cxICGAF6AhgBhQEAAQAAEpwBChDFje+vrdxywaCpwxd9V7gUEgj/t8gVyNqfXSoKVG9vbCBVc2Fn
+      ZTABOdhv2Bdg69wXQbgb2Rdg69wXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMkooCgl0b29s
+      X25hbWUSGwoZRGVsZWdhdGUgd29yayB0byBjb3dvcmtlckoOCghhdHRlbXB0cxICGAF6AhgBhQEA
+      AQAAEpUBChAEeGlBlALsLna/xMJS3tAVEgjguQVwVm9whyoKVG9vbCBVc2FnZTABOVgP+yBg69wX
+      QYCv+yBg69wXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMkohCgl0b29sX25hbWUSFAoSbXVs
+      dGlwbGNhdGlvbl90b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAASlQEKEArasdHN2QN534bW
+      INqT3I4SCGw3ZpVwofeNKgpUb29sIFVzYWdlMAE5INaDImDr3BdBqGaEImDr3BdKGgoOY3Jld2Fp
+      X3ZlcnNpb24SCAoGMC4zMi4ySiEKCXRvb2xfbmFtZRIUChJtdWx0aXBsY2F0aW9uX3Rvb2xKDgoI
+      YXR0ZW1wdHMSAhgBegIYAYUBAAEAABKVAQoQLSMocWp+gqCwmkQ2VSYxYBII6+65jDuqdT0qClRv
+      b2wgVXNhZ2UwATkozR4kYOvcF0HIWR8kYOvcF0oaCg5jcmV3YWlfdmVyc2lvbhIICgYwLjMyLjJK
+      IQoJdG9vbF9uYW1lEhQKEm11bHRpcGxjYXRpb25fdG9vbEoOCghhdHRlbXB0cxICGAF6AhgBhQEA
+      AQAAEpUBChCcXc1N49pCK+Se0QpX8SNMEgiHCiPHjpZP9CoKVG9vbCBVc2FnZTABOZitsyVg69wX
+      QZBVtCVg69wXShoKDmNyZXdhaV92ZXJzaW9uEggKBjAuMzIuMkohCgl0b29sX25hbWUSFAoSbXVs
+      dGlwbGNhdGlvbl90b29sSg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA=
     headers:
       Accept:
       - '*/*'
@@ -114,11 +117,11 @@ interactions:
       Connection:
       - keep-alive
       Content-Length:
-      - '5930'
+      - '6140'
       Content-Type:
       - application/x-protobuf
       User-Agent:
-      - OTel-OTLP-Exporter-Python/1.24.0
+      - OTel-OTLP-Exporter-Python/1.25.0
     method: POST
     uri: https://telemetry.crewai.com:4319/v1/traces
   response:
@@ -130,23 +133,23 @@ interactions:
       Content-Type:
       - application/x-protobuf
       Date:
-      - Tue, 14 May 2024 01:26:13 GMT
+      - Thu, 27 Jun 2024 17:05:57 GMT
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are Scorer. You''re an expert
-      scorer, specialized in scoring titles.\nYour personal goal is: Score the titleTo
-      give my best complete final answer to the task use the exact following format:\n\nThought:
-      I now can give a great answer\nFinal Answer: my best complete final answer to
-      the task.\nYour final answer must be the great and the most complete as possible,
-      it must be outcome described.\n\nI MUST use these formats, my job depends on
-      it!\nCurrent Task: Give me an integer score between 1-5 for the following title:
-      ''The impact of AI in the future of work''\n\nThis is the expect criteria for
-      your final answer: The score of the title. \n you MUST return the actual complete
-      content as the final answer, not a summary.\n\nBegin! This is VERY important
-      to you, use the tools available and give your best Final Answer, your job depends
-      on it!\n\nThought:\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+    body: '{"messages": [{"content": "You are Scorer. You''re an expert scorer, specialized
+      in scoring titles.\nYour personal goal is: Score the titleTo give my best complete
+      final answer to the task use the exact following format:\n\nThought: I now can
+      give a great answer\nFinal Answer: my best complete final answer to the task.\nYour
+      final answer must be the great and the most complete as possible, it must be
+      outcome described.\n\nI MUST use these formats, my job depends on it!\nCurrent
+      Task: Give me an integer score between 1-5 for the following title: ''The impact
+      of AI in the future of work''\n\nThis is the expect criteria for your final
+      answer: The score of the title. \n you MUST return the actual complete content
+      as the final answer, not a summary.\n\nBegin! This is VERY important to you,
+      use the tools available and give your best Final Answer, your job depends on
+      it!\n\nThought:\n", "role": "user"}], "model": "gpt-4o", "n": 1, "stop": ["\nObservation"],
       "stream": true, "temperature": 0.7}'
     headers:
       accept:
@@ -156,13 +159,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '996'
+      - '997'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.29.0
+      - OpenAI/Python 1.35.5
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -172,277 +175,73 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.29.0
+      - 1.35.5
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.11.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
-      string: 'data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
+      string: 'data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"After"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Thought"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        considering"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        relevance"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        depth"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        potential"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        interest"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        topic"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        as"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        well"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        as"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        clarity"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        and"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        simplicity"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        title"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        ''"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"The"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        impact"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        AI"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        future"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        work"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''.\n\n"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        Answer"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        Based"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        on"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        my"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        evaluation"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":","},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
         I"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        now"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        can"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
         give"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        title"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        ''"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"The"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        impact"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        AI"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        in"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        the"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        future"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        work"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"''"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
         a"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        score"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        great"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        answer"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"\n"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"Final"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
+        Answer"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":":"},"logprobs":null,"finish_reason":null}]}
+
+
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"
         "},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{"content":"4"},"logprobs":null,"finish_reason":null}]}
 
 
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        out"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        of"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"
-        "},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"5"},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{"content":"."},"logprobs":null,"finish_reason":null}]}
-
-
-        data: {"id":"chatcmpl-9ObDhPtGi5k6ALX2jaFMR0vwXhSx0","object":"chat.completion.chunk","created":1715649973,"model":"gpt-4-0613","system_fingerprint":null,"choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
+        data: {"id":"chatcmpl-9emrFVxBDMfetsihHnas2Fd4viiHB","object":"chat.completion.chunk","created":1719507957,"model":"gpt-4o-2024-05-13","system_fingerprint":"fp_4008e3b719","choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
 
 
         data: [DONE]
@@ -453,20 +252,20 @@ interactions:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8837194f3860a686-MIA
+      - 89a7065b6911228b-SJC
       Connection:
       - keep-alive
       Content-Type:
       - text/event-stream; charset=utf-8
       Date:
-      - Tue, 14 May 2024 01:26:14 GMT
+      - Thu, 27 Jun 2024 17:05:57 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=o_N1eUBbqWWHvbE622tXs5BC9yN1X1bxp3npQXI46JU-1715649974-1.0.1.1-ALOCo.oJW08V4.F5WqVArJDbxakTERtLPfwUlDjTYrrg_WiJox.Pw_n.PnDfEdxa52BbaPI8M80h2S3wdJy2sw;
-        path=/; expires=Tue, 14-May-24 01:56:14 GMT; domain=.api.openai.com; HttpOnly;
+      - __cf_bm=V8sGOl1Y4f5Qu7trvPZAYe7AGA617GLKNhILzT6hbrc-1719507957-1.0.1.1-F.qdQAfjgBjTLxW4ciPK3Nt2jNdXguNNo.4_eOWYBNCmn2rSiWR4AeTxGn2ll2TgaFGHcoh9sWc__bk8cSIa3A;
+        path=/; expires=Thu, 27-Jun-24 17:35:57 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=vYif.qp5YND_OTGCG3IgxPXT3sqDTSpeVEIUapP.n.k-1715649974367-0.0.1.1-604800000;
+      - _cfuvid=9ZqY4IoIeegV9WIJ8ejAA9TRZrX2yM.crv4AqhuqVW4-1719507957363-0.0.1.1-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -475,37 +274,36 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '510'
+      - '87'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=15724800; includeSubDomains
+      - max-age=31536000; includeSubDomains
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '300000'
+      - '16000000'
       x-ratelimit-remaining-requests:
-      - '9997'
+      - '9999'
       x-ratelimit-remaining-tokens:
-      - '299098'
+      - '15999772'
       x-ratelimit-reset-requests:
-      - 13ms
+      - 6ms
       x-ratelimit-reset-tokens:
-      - 180ms
+      - 0s
       x-request-id:
-      - req_26f0f1e02a54a0aaf7e8b96ba7d56837
+      - req_5d3282a4dba2ac63ea035b3bf6a5c13f
     status:
       code: 200
       message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "Based on my evaluation, I give
-      the title ''The impact of AI in the future of work'' a score of 4 out of 5."},
-      {"role": "system", "content": "I''m gonna convert this raw text into valid JSON."}],
-      "model": "gpt-4", "tool_choice": {"type": "function", "function": {"name": "ScoreOutput"}},
-      "tools": [{"type": "function", "function": {"name": "ScoreOutput", "description":
-      "Correctly extracted `ScoreOutput` with all the required parameters with correct
-      types", "parameters": {"properties": {"score": {"title": "Score", "type": "integer"}},
-      "required": ["score"], "type": "object"}}}]}'
+    body: '{"messages": [{"role": "user", "content": "4"}, {"role": "system", "content":
+      "I''m gonna convert this raw text into valid JSON."}], "model": "gpt-4o", "tool_choice":
+      {"type": "function", "function": {"name": "ScoreOutput"}}, "tools": [{"type":
+      "function", "function": {"name": "ScoreOutput", "description": "Correctly extracted
+      `ScoreOutput` with all the required parameters with correct types", "parameters":
+      {"properties": {"score": {"title": "Score", "type": "integer"}}, "required":
+      ["score"], "type": "object"}}}]}'
     headers:
       accept:
       - application/json
@@ -514,16 +312,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '621'
+      - '519'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=o_N1eUBbqWWHvbE622tXs5BC9yN1X1bxp3npQXI46JU-1715649974-1.0.1.1-ALOCo.oJW08V4.F5WqVArJDbxakTERtLPfwUlDjTYrrg_WiJox.Pw_n.PnDfEdxa52BbaPI8M80h2S3wdJy2sw;
-        _cfuvid=vYif.qp5YND_OTGCG3IgxPXT3sqDTSpeVEIUapP.n.k-1715649974367-0.0.1.1-604800000
+      - __cf_bm=V8sGOl1Y4f5Qu7trvPZAYe7AGA617GLKNhILzT6hbrc-1719507957-1.0.1.1-F.qdQAfjgBjTLxW4ciPK3Nt2jNdXguNNo.4_eOWYBNCmn2rSiWR4AeTxGn2ll2TgaFGHcoh9sWc__bk8cSIa3A;
+        _cfuvid=9ZqY4IoIeegV9WIJ8ejAA9TRZrX2yM.crv4AqhuqVW4-1719507957363-0.0.1.1-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.29.0
+      - OpenAI/Python 1.35.5
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -533,28 +331,28 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.29.0
+      - 1.35.5
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.11.7
+      - 3.11.9
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
     body:
       string: !!binary |
-        g2QBAMTINfMxamd1CeMeEI6KoYFref5vBi4N2oOiMbVNv3QLhr1AppZoAgF1drbOzezQ65E14dmt
-        ADjNKcFsksRMO1Ud3qXHqqnW3c7ZUq/M23vj7mI9eXr198urN1YEQJvOiiz2xGsuBurUGghycvlZ
-        kVOi2W92e53hsN8X3tE2LxQlOHax2qk2es12r9OJnWZFoMSXAIBtaQTw3fsuJRqVVsQLQ6AEfgTQ
-        W1VQgkkI0xATE1kB5MLWTUqYUinhXLRW/WWJUuRQDm7ruUX6a6LU3/3z09v8MH9W3WF6MLi0g3h7
-        /LJO+pyQembtBoV6YJRiUFmdJIwANIme0FtPmfXFXRldGVUYAE38e0pw+22Ab4bM+uKbEp1vs6fq
-        xr2oYz/0+J5iGZUdO2/TsGA4o9YBfzeEjVGCIVpHY+0F8GPJammcS3Teahf/op0XJlCi2ejpBLhp
-        cghsmHJfPJATmc1mVwySYByBlb/R1IwL7/zUrrLYCwMD
+        A2kBAMTvp6ueppr36zWlPDGLEiUMsfWbugkuDdrjfExt05duwbBLw2xhoAkEVJatc7EwOfTJlTXh
+        3r0gQhpCEoLEa4LC6u5SFdV5+fV29lE+PKmz8/L0JMrOLtLbtbedoCOIwH6mgoYT77kYqCkbCHJy
+        +ZoKIWk4Hy6ng/lyuiBeKDhUGpIQ26Y74e5oMJp0B9PucMy8mnAaqBqSvgUR0b41IMLz9x1IGnRG
+        EWcMARL4EhEq1gqS4NV1WjeeadABZKLXjUoyrdbEqYZZO4GntXCoAvf9jK5+9bR2io+zVWZO4tX6
+        5mjtP/jTfBC14dGXTGh6ZmsXhTpiFGJQWpUUGCKC8Qr+p54DrtR929i2yQYRLP0hJGH/gzrgSv1A
+        Tv4xZ+2/6GO/GsL/VTUPmmNbsV8nHFHrAOeGsBFIQt2wFWP+C6JfE5Zbq5yArbiwjdNwrkwNSYsC
+        YM9kANg0ZX54IEPSFlOxRAJRBBacKDWxqmyVmnMDIusEajBfjsfjQQTxLwwD
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 88371965caa0a686-MIA
+      - 89a706621820228b-SJC
       Connection:
       - keep-alive
       Content-Encoding:
@@ -562,7 +360,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Tue, 14 May 2024 01:26:18 GMT
+      - Thu, 27 Jun 2024 17:05:58 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -572,25 +370,25 @@ interactions:
       openai-organization:
       - crewai-iuxna1
       openai-processing-ms:
-      - '994'
+      - '316'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
-      - max-age=15724800; includeSubDomains
+      - max-age=31536000; includeSubDomains
       x-ratelimit-limit-requests:
       - '10000'
       x-ratelimit-limit-tokens:
-      - '300000'
+      - '16000000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299944'
+      - '15999969'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 11ms
+      - 0s
       x-request-id:
-      - req_a9b61926ad5fdaf004dd4b99738bcadb
+      - req_abc65b2959a9fb14068d5e86757fec87
     status:
       code: 200
       message: OK

tests/crew_test.py

@@ -157,9 +157,9 @@ def test_hierarchical_process():
         manager_llm=ChatOpenAI(temperature=0, model="gpt-4"),
         tasks=[task],
     )
-    result = crew.kickoff()
+
     assert (
-        result
+        crew.kickoff()
         == "1. 'Demystifying AI: An in-depth exploration of Artificial Intelligence for the layperson' - In this piece, we will unravel the enigma of AI, simplifying its complexities into digestible information for the everyday individual. By using relatable examples and analogies, we will journey through the neural networks and machine learning algorithms that define AI, without the jargon and convoluted explanations that often accompany such topics.\n\n2. 'The Role of AI in Startups: A Game Changer?' - Startups today are harnessing the power of AI to revolutionize their businesses. This article will delve into how AI, as an innovative force, is shaping the startup ecosystem, transforming everything from customer service to product development. We'll explore real-life case studies of startups that have leveraged AI to accelerate their growth and disrupt their respective industries.\n\n3. 'AI and Ethics: Navigating the Complex Landscape' - AI brings with it not just technological advancements, but ethical dilemmas as well. This article will engage readers in a thought-provoking discussion on the ethical implications of AI, exploring issues like bias in algorithms, privacy concerns, job displacement, and the moral responsibility of AI developers. We will also discuss potential solutions and frameworks to address these challenges.\n\n4. 'Unveiling the AI Agents: The Future of Customer Service' - AI agents are poised to reshape the customer service landscape, offering businesses the ability to provide round-the-clock support and personalized experiences. In this article, we'll dive deep into the world of AI agents, examining how they work, their benefits and limitations, and how they're set to redefine customer interactions in the digital age.\n\n5. 'From Science Fiction to Reality: AI in Everyday Life' - AI, once a concept limited to the realm of sci-fi, has now permeated our daily lives. This article will highlight the ubiquitous presence of AI, from voice assistants and recommendation algorithms, to autonomous vehicles and smart homes. We'll explore how AI, in its various forms, is transforming our everyday experiences, making the future seem a lot closer than we imagined."
     )
 
@@ -388,10 +388,10 @@ def test_crew_full_ouput():
         "final_output": "Hello!",
         "tasks_outputs": [task1.output, task2.output],
         "usage_metrics": {
-            "total_tokens": 517,
-            "prompt_tokens": 466,
-            "completion_tokens": 51,
-            "successful_requests": 3,
+            "total_tokens": 348,
+            "prompt_tokens": 314,
+            "completion_tokens": 34,
+            "successful_requests": 2,
         },
     }
 
@@ -617,6 +617,7 @@ def test_delegation_is_not_enabled_if_there_are_only_one_agent():
     )
 
     crew = Crew(agents=[researcher], tasks=[task])
+
     with patch.object(Task, "execute") as execute:
         execute.return_value = "ok"
         crew.kickoff()
@@ -688,12 +689,12 @@ def test_agent_usage_metrics_are_captured_for_hierarchical_process():
     )
 
     result = crew.kickoff()
-    assert result == '"Howdy!"'
+    assert result == "Howdy!"
 
     assert crew.usage_metrics == {
-        "total_tokens": 1640,
-        "prompt_tokens": 1357,
-        "completion_tokens": 283,
+        "total_tokens": 1383,
+        "prompt_tokens": 1278,
+        "completion_tokens": 105,
         "successful_requests": 3,
     }
 

tests/task_test.py

@@ -367,6 +367,8 @@ def test_save_task_json_output():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_save_task_pydantic_output():
+    from langchain_openai import ChatOpenAI
+
     class ScoreOutput(BaseModel):
         score: int
 
@@ -375,6 +377,7 @@ def test_save_task_pydantic_output():
         goal="Score the title",
         backstory="You're an expert scorer, specialized in scoring titles.",
         allow_delegation=False,
+        llm=ChatOpenAI(model="gpt-4o"),
     )
 
     task = Task(
@@ -413,13 +416,13 @@ def test_increment_delegations_for_hierarchical_process():
         agents=[scorer],
         tasks=[task],
         process=Process.hierarchical,
-        manager_llm=ChatOpenAI(model="gpt-4-0125-preview"),
+        manager_llm=ChatOpenAI(model="gpt-4o"),
     )
 
     with patch.object(Task, "increment_delegations") as increment_delegations:
         increment_delegations.return_value = None
         crew.kickoff()
-        increment_delegations.assert_called_once
+        increment_delegations.assert_called_once()
 
 
 @pytest.mark.vcr(filter_headers=["authorization"])