Add RPM control to both agents and crews (#133)

* moving file into utilities
* creating Logger and RPMController
* Adding support for RPM to agents and crew

src/crewai/agent.py

@@ -24,8 +24,7 @@ from crewai.agents import (
     CrewAgentOutputParser,
     ToolsHandler,
 )
-from crewai.i18n import I18N
+from crewai.utilities import I18N, Logger, Prompts, RPMController
-from crewai.prompts import Prompts
 
 
 class Agent(BaseModel):
@@ -42,11 +41,14 @@ class Agent(BaseModel):
             llm: The language model that will run the agent.
             max_iter: Maximum number of iterations for an agent to execute a task.
             memory: Whether the agent should have memory or not.
+            max_rpm: Maximum number of requests per minute for the agent execution to be respected.
             verbose: Whether the agent execution should be in verbose mode.
             allow_delegation: Whether the agent is allowed to delegate tasks to other agents.
     """
 
     __hash__ = object.__hash__
+    _logger: Logger = PrivateAttr()
+    _rpm_controller: RPMController = PrivateAttr(default=None)
     _request_within_rpm_limit: Any = PrivateAttr(default=None)
 
     model_config = ConfigDict(arbitrary_types_allowed=True)
@@ -58,6 +60,10 @@ class Agent(BaseModel):
     role: str = Field(description="Role of the agent")
     goal: str = Field(description="Objective of the agent")
     backstory: str = Field(description="Backstory of the agent")
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the agent execution to be respected.",
+    )
     memory: bool = Field(
         default=True, description="Whether the agent should have memory or not"
     )
@@ -101,6 +107,15 @@ class Agent(BaseModel):
                 "may_not_set_field", "This field is not to be set by the user.", {}
             )
 
+    @model_validator(mode="after")
+    def set_private_attrs(self):
+        self._logger = Logger(self.verbose)
+        if self.max_rpm and not self._rpm_controller:
+            self._rpm_controller = RPMController(
+                max_rpm=self.max_rpm, logger=self._logger
+            )
+        return self
+
     @model_validator(mode="after")
     def check_agent_executor(self) -> "Agent":
         if not self.agent_executor:
@@ -128,7 +143,7 @@ class Agent(BaseModel):
         tools = tools or self.tools
         self.agent_executor.tools = tools
 
-        return self.agent_executor.invoke(
+        result = self.agent_executor.invoke(
             {
                 "input": task,
                 "tool_names": self.__tools_names(tools),
@@ -137,14 +152,20 @@ class Agent(BaseModel):
             RunnableConfig(callbacks=[self.tools_handler]),
         )["output"]
 
+        if self.max_rpm:
+            self._rpm_controller.stop_rpm_counter()
+
+        return result
+
     def set_cache_handler(self, cache_handler) -> None:
         self.cache_handler = cache_handler
         self.tools_handler = ToolsHandler(cache=self.cache_handler)
         self.__create_agent_executor()
 
-    def set_request_within_rpm_limit(self, ensure_function) -> None:
+    def set_rpm_controller(self, rpm_controller) -> None:
-        self._request_within_rpm_limit = ensure_function
+        if not self._rpm_controller:
-        self.__create_agent_executor()
+            self._rpm_controller = rpm_controller
+            self.__create_agent_executor()
 
     def __create_agent_executor(self) -> CrewAgentExecutor:
         """Create an agent executor for the agent.
@@ -164,9 +185,13 @@ class Agent(BaseModel):
             "verbose": self.verbose,
             "handle_parsing_errors": True,
             "max_iterations": self.max_iter,
-            "request_within_rpm_limit": self._request_within_rpm_limit,
         }
 
+        if self._rpm_controller:
+            executor_args[
+                "request_within_rpm_limit"
+            ] = self._rpm_controller.check_or_wait
+
         if self.memory:
             summary_memory = ConversationSummaryMemory(
                 llm=self.llm, input_key="input", memory_key="chat_history"

src/crewai/agents/exceptions.py

@@ -1,6 +1,6 @@
 from langchain_core.exceptions import OutputParserException
 
-from crewai.i18n import I18N
+from crewai.utilities import I18N
 
 
 class TaskRepeatedUsageException(OutputParserException):

src/crewai/agents/executor.py

@@ -12,8 +12,8 @@ from langchain_core.tools import BaseTool
 from langchain_core.utils.input import get_color_mapping
 
 from crewai.agents.cache.cache_hit import CacheHit
-from crewai.i18n import I18N
 from crewai.tools.cache_tools import CacheTools
+from crewai.utilities import I18N
 
 
 class CrewAgentExecutor(AgentExecutor):

src/crewai/agents/output_parser.py

@@ -7,7 +7,7 @@ from langchain_core.agents import AgentAction, AgentFinish
 from crewai.agents.cache import CacheHandler, CacheHit
 from crewai.agents.exceptions import TaskRepeatedUsageException
 from crewai.agents.tools_handler import ToolsHandler
-from crewai.i18n import I18N
+from crewai.utilities import I18N
 
 FINAL_ANSWER_ACTION = "Final Answer:"
 FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE = (

src/crewai/crew.py

@@ -1,8 +1,6 @@
 import json
-import threading
-import time
 import uuid
-from typing import Any, ClassVar, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Union
 
 from pydantic import (
     UUID4,
@@ -19,10 +17,10 @@ from pydantic_core import PydanticCustomError
 
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
-from crewai.i18n import I18N
 from crewai.process import Process
 from crewai.task import Task
 from crewai.tools.agent_tools import AgentTools
+from crewai.utilities import I18N, Logger, RPMController
 
 
 class Crew(BaseModel):
@@ -37,23 +35,26 @@ class Crew(BaseModel):
         config: Configuration settings for the crew.
         cache_handler: Handles caching for the crew's operations.
         max_rpm: Maximum number of requests per minute for the crew execution to be respected.
-        rpm: Current number of requests per minute for the crew execution.
         id: A unique identifier for the crew instance.
     """
 
     __hash__ = object.__hash__
-    _timer: Optional[threading.Timer] = PrivateAttr(default=None)
+    _rpm_controller: RPMController = PrivateAttr()
-    lock: ClassVar[threading.Lock] = threading.Lock()
+    _logger: Logger = PrivateAttr()
-    rpm: ClassVar[int] = 0
+    _cache_handler: Optional[InstanceOf[CacheHandler]] = PrivateAttr(
-    max_rpm: Optional[int] = Field(default=None)
+        default=CacheHandler()
+    )
     model_config = ConfigDict(arbitrary_types_allowed=True)
     tasks: List[Task] = Field(default_factory=list)
     agents: List[Agent] = Field(default_factory=list)
     process: Process = Field(default=Process.sequential)
     verbose: Union[int, bool] = Field(default=0)
     config: Optional[Union[Json, Dict[str, Any]]] = Field(default=None)
-    cache_handler: Optional[InstanceOf[CacheHandler]] = Field(default=CacheHandler())
     id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
+    max_rpm: Optional[int] = Field(
+        default=None,
+        description="Maximum number of requests per minute for the crew execution to be respected.",
+    )
     language: str = Field(
         default="en",
         description="Language used for the crew, defaults to English.",
@@ -74,9 +75,10 @@ class Crew(BaseModel):
         return json.loads(v) if isinstance(v, Json) else v
 
     @model_validator(mode="after")
-    def set_reset_counter(self):
+    def set_private_attrs(self):
-        if self.max_rpm:
+        self._cache_handler = CacheHandler()
-            self._reset_request_count()
+        self._logger = Logger(self.verbose)
+        self._rpm_controller = RPMController(max_rpm=self.max_rpm, logger=self._logger)
         return self
 
     @model_validator(mode="after")
@@ -94,8 +96,8 @@ class Crew(BaseModel):
 
         if self.agents:
             for agent in self.agents:
-                agent.set_cache_handler(self.cache_handler)
+                agent.set_cache_handler(self._cache_handler)
-                agent.set_request_within_rpm_limit(self.ensure_request_within_rpm_limit)
+                agent.set_rpm_controller(self._rpm_controller)
         return self
 
     def _setup_from_config(self):
@@ -116,28 +118,9 @@ class Crew(BaseModel):
         del task_config["agent"]
         return Task(**task_config, agent=task_agent)
 
-    def ensure_request_within_rpm_limit(self):
-        if not self.max_rpm:
-            return True
-
-        with Crew.lock:
-            if Crew.rpm < self.max_rpm:
-                Crew.rpm += 1
-                return True
-            self._log("info", "Max RPM reached, waiting for next minute to start.")
-
-        return self._wait_for_next_minute()
-
-    def _wait_for_next_minute(self):
-        time.sleep(60)
-        with Crew.lock:
-            Crew.rpm = 0
-            return True
-
     def kickoff(self) -> str:
         """Starts the crew to work on its assigned tasks."""
         for agent in self.agents:
-            agent.cache_handler = self.cache_handler
             agent.i18n = I18N(language=self.language)
 
         if self.process == Process.sequential:
@@ -149,8 +132,12 @@ class Crew(BaseModel):
         for task in self.tasks:
             self._prepare_and_execute_task(task)
             task_output = task.execute(task_output)
-            self._log("debug", f"\n[{task.agent.role}] Task output: {task_output}\n\n")
+            self._logger.log(
-        self._stop_timer()
+                "debug", f"[{task.agent.role}] Task output: {task_output}\n\n"
+            )
+
+        if self.max_rpm:
+            self._rpm_controller.stop_rpm_counter()
         return task_output
 
     def _prepare_and_execute_task(self, task):
@@ -158,24 +145,5 @@ class Crew(BaseModel):
         if task.agent.allow_delegation:
             task.tools += AgentTools(agents=self.agents).tools()
 
-        self._log("debug", f"Working Agent: {task.agent.role}")
+        self._logger.log("debug", f"Working Agent: {task.agent.role}")
-        self._log("info", f"Starting Task: {task.description}")
+        self._logger.log("info", f"Starting Task: {task.description}")
-
-    def _log(self, level, message):
-        """Logs a message at the specified verbosity level."""
-        level_map = {"debug": 1, "info": 2}
-        verbose_level = (
-            2 if isinstance(self.verbose, bool) and self.verbose else self.verbose
-        )
-        if verbose_level and level_map[level] <= verbose_level:
-            print(f"\n{message}")
-
-    def _stop_timer(self):
-        if self._timer:
-            self._timer.cancel()
-
-    def _reset_request_count(self):
-        self._stop_timer()
-        self._timer = threading.Timer(60.0, self._reset_request_count)
-        self._timer.start()
-        Crew.rpm = 0

src/crewai/tools/agent_tools.py

@@ -4,7 +4,7 @@ from langchain.tools import Tool
 from pydantic import BaseModel, Field
 
 from crewai.agent import Agent
-from crewai.i18n import I18N
+from crewai.utilities import I18N
 
 
 class AgentTools(BaseModel):

src/crewai/utilities/__init__.py

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

src/crewai/utilities/i18n.py

@@ -17,7 +17,9 @@ class I18N(BaseModel):
         """Load translations from a JSON file based on the specified language."""
         try:
             dir_path = os.path.dirname(os.path.realpath(__file__))
-            prompts_path = os.path.join(dir_path, f"translations/{self.language}.json")
+            prompts_path = os.path.join(
+                dir_path, f"../translations/{self.language}.json"
+            )
 
             with open(prompts_path, "r") as f:
                 self._translations = json.load(f)

src/crewai/utilities/logger.py

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

src/crewai/utilities/prompts.py

@@ -3,7 +3,7 @@ from typing import ClassVar
 from langchain.prompts import PromptTemplate
 from pydantic import BaseModel, Field
 
-from .i18n import I18N
+from crewai.utilities import I18N
 
 
 class Prompts(BaseModel):

src/crewai/utilities/rpm_controller.py

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

tests/agent_test.py

@@ -6,9 +6,10 @@ import pytest
 from langchain.tools import tool
 from langchain_openai import ChatOpenAI as OpenAI
 
-from crewai.agent import Agent
+from crewai import Agent, Crew, Task
 from crewai.agents.cache import CacheHandler
 from crewai.agents.executor import CrewAgentExecutor
+from crewai.utilities import RPMController
 
 
 def test_agent_creation():
@@ -252,3 +253,124 @@ def test_agent_moved_on_after_max_iterations():
             == "I have used the tool multiple times and the final answer remains 42."
         )
         private_mock.assert_called_once()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_respect_the_max_rpm_set(capsys):
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=5,
+        max_rpm=1,
+        verbose=True,
+        allow_delegation=False,
+    )
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        output = agent.execute_task(
+            task="The final answer is 42. But don't give it yet, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+        )
+        assert (
+            output
+            == "I've used the `get_final_answer` tool multiple times and it consistently returns the number 42."
+        )
+        captured = capsys.readouterr()
+        assert "Max RPM reached, waiting for next minute to start." in captured.out
+        moveon.assert_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_respect_the_max_rpm_set_over_crew_rpm(capsys):
+    from unittest.mock import patch
+
+    from langchain.tools import tool
+
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_iter=4,
+        max_rpm=10,
+        verbose=True,
+    )
+
+    task = Task(
+        description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
+        tools=[get_final_answer],
+        agent=agent,
+    )
+
+    crew = Crew(agents=[agent], tasks=[task], max_rpm=1, verbose=2)
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        crew.kickoff()
+        captured = capsys.readouterr()
+        assert "Max RPM reached, waiting for next minute to start." not in captured.out
+        moveon.assert_not_called()
+
+
+@pytest.mark.vcr(filter_headers=["authorization"])
+def test_agent_without_max_rpm_respet_crew_rpm(capsys):
+    from unittest.mock import patch
+
+    from langchain.tools import tool
+
+    @tool
+    def get_final_answer(numbers) -> float:
+        """Get the final answer but don't give it yet, just re-use this
+        tool non-stop."""
+        return 42
+
+    agent1 = Agent(
+        role="test role",
+        goal="test goal",
+        backstory="test backstory",
+        max_rpm=10,
+        verbose=True,
+    )
+
+    agent2 = Agent(
+        role="test role2",
+        goal="test goal2",
+        backstory="test backstory2",
+        max_iter=2,
+        verbose=True,
+    )
+
+    tasks = [
+        Task(
+            description="Just say hi.",
+            agent=agent1,
+        ),
+        Task(
+            description="Don't give a Final Answer, instead keep using the `get_final_answer` tool.",
+            tools=[get_final_answer],
+            agent=agent2,
+        ),
+    ]
+
+    crew = Crew(agents=[agent1, agent2], tasks=tasks, max_rpm=1, verbose=2)
+
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
+        moveon.return_value = True
+        crew.kickoff()
+        captured = capsys.readouterr()
+        assert "Action: get_final_answer" in captured.out
+        assert "Max RPM reached, waiting for next minute to start." in captured.out
+        moveon.assert_called_once()

tests/cassettes/test_agent_respect_the_max_rpm_set.yaml

@@ -0,0 +1,663 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1080'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfw8fvQxNLkF3ttE8Bm7s8rjYFq\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184512,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      234,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 258\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108e32c171abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:54 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        path=/; expires=Sat, 13-Jan-24 22:51:54 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1681'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299754'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - a25e71b234c622c7dc8010927635a75c
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1191'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfyCtYEPuuA9KzlWJko8Sc4ItXo\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184514,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      267,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 289\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108ef48b01abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1020'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299726'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 54ms
+      x-request-id:
+      - 2cb025cb28aa59d282888aa8daa8a745
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: "}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1293'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggfzAey5AALxtUqKehw6R7nBfyZv\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184515,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      297,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 319\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845108f7794d1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:21:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1662'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299702'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 59ms
+      x-request-id:
+      - 96578e7d658dcea71f927eb3700da70d
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [42]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1395'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg2v1bp5IaLU8TDmqcDgXiqXOTd\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184518,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      327,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 349\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845109052e951abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1840'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299678'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 64ms
+      x-request-id:
+      - 24c5fedfa1d1b427cc01a498f46fe60f
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      just the name.\nAction Input: the input to the action\nObservation: the result
+      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [42]\nObservation: 42\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [42]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [42]\nObservation: I''ve used too many tools for this task. I''m going
+      to give you my absolute BEST Final answer now and not use any more tools.\nThought:
+      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1618'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg4hc3SCoIfjLWgJVTHwj91kcWv\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184520,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used the `get_final_answer` tool multiple times and it consistently returns
+      the number 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 383,\n    \"completion_tokens\":
+      34,\n    \"total_tokens\": 417\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845109124bdd1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:03 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3318'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299623'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 75ms
+      x-request-id:
+      - c4eb234f14d03df86e41f35ff90b9708
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
+      tool.\nAI: I''ve used the `get_final_answer` tool multiple times and it consistently
+      returns the number 42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1041'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=N43k0gHErA0PBuIXY9IHQyia.HGfApTZKpYsN4S4E8s-1705184514-1-AQrOw6bC8j+KAeTt3IquXJN8QBK/oqZwqkQ1DG2CFnb3u2VkEs58RczmbK2+3luwjUlNNK5xihxOzOe1hFlIkfc=;
+        _cfuvid=tLKPNNCaE7nA1vSgk2uC9AN4gynXRvlaHmfacNL.ncY-1705184514404-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggg8PkiU1uRkwllwEfuGqBztgSqW\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705184524,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI to keep using
+      the `get_final_answer` tool, stating that the final answer is 42. The AI confirms
+      that it has used the `get_final_answer` tool multiple times and it consistently
+      returns the number 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 184,\n    \"completion_tokens\":
+      51,\n    \"total_tokens\": 235\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451092a2daf1abd-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:22:07 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '3505'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299755'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - 7db26cd36db9105a336c4975a978ad37
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_respect_the_max_rpm_set_over_crew_rpm.yaml

@@ -0,0 +1,591 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\n"}], "model":
+      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1849'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwdlPGCjfSTQ9UYZ6FscyUha1T1\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185547,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1, 2, 3]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      410,\n    \"completion_tokens\": 30,\n    \"total_tokens\": 440\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451222a0daa023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:09 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        path=/; expires=Sat, 13-Jan-24 23:09:09 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1730'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299562'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 87ms
+      x-request-id:
+      - d2103c8ce4517885db35be6518e966cd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1965'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwghkojjlEuyvKZu4kPfOsqCGLh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185550,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4, 5, 6]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      449,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 477\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845122365b01023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:11 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1718'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299535'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 93ms
+      x-request-id:
+      - 9578b64bcbc4f8b489a7ba4df8e10136
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4, 5, 6]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2072'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwiHUPtP0zST5G9y9gq6L8xn7gO\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185552,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7, 8, 9]\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      485,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 513\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 84512244bdb0023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:13 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1439'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299509'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 98ms
+      x-request-id:
+      - 3ee6b071c3a4c976c4955dc66589b96e
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the task and all actual context you have for the task.\nFor
+      example, `coworker|task|context`.\nAsk question to co-worker: Useful to ask
+      a question, opinion or take from on of the following co-workers: test role.\nThe
+      input to this tool should be a pipe (|) separated text of length 3 (three),
+      representing the co-worker you want to ask it to (one of the options), the question
+      and all actual context you have for the question.\n For example, `coworker|question|context`.\n\nTo
+      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer,
+      Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
+      Input: the input to the action\nObservation: the result of the action\n```\n\nWhen
+      you have a response for your task, or if you do not need to use a tool, you
+      MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
+      [your response here]This is the summary of your work so far:\nBegin! This is
+      VERY important to you, your job depends on it!\n\nCurrent Task: Don''t give
+      a Final Answer, instead keep using the `get_final_answer` tool.\nThought: Do
+      I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [1, 2, 3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4, 5, 6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [7, 8, 9]\nObservation: I''ve used too many
+      tools for this task. I''m going to give you my absolute BEST Final answer now
+      and not use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2300'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwkNsNUjt0ChmyTHpqYq62HOuXV\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185554,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used too many tools for this task. I'm going to give you my absolute BEST
+      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      547,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 589\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 84512250bd7d023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:16 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2057'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299452'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 109ms
+      x-request-id:
+      - 1e3a6677139fb5c15cbb33f1b3154845
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nAI: I''ve
+      used too many tools for this task. I''m going to give you my absolute BEST Final
+      answer now and not use any more tools.\n\nNew summary:"}], "model": "gpt-4",
+      "n": 1, "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1049'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=rVM3HcQbZEwpOTwcpe7kl9QQYRs6WfN.nkQmw.sY1xg-1705185549-1-ATyblmW1bvTVkY3o9M+aZOU5lnMZ0R5ThR8QblVINArZXsnS39YH+NGcdAiT04v1fq+OTnj7lrwBulOgZqYUxKY=;
+        _cfuvid=3PdaxLthL4xZPggd16y46lBPKNh_Xt_xeL_2BrNr9xU-1705185549778-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8ggwmU48hiYTdhe5slzvm2Tuyuky3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705185556,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer, but to continue using the 'get_final_answer' tool. Despite this,
+      the AI expresses that it has used many tools for the task and decides to provide
+      its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      185,\n    \"completion_tokens\": 54,\n    \"total_tokens\": 239\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8451225f7ee6023d-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 13 Jan 2024 22:39:19 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2941'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299753'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 49ms
+      x-request-id:
+      - be72b34cee55b48a285458167d9a4909
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/cassettes/test_agent_without_max_rpm_respet_crew_rpm.yaml

@@ -0,0 +1,816 @@
+interactions:
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
+      tools:\n\nDelegate work to co-worker: Useful to delegate a specific task to
+      one of the following co-workers: test role, test role2.\nThe input to this tool
+      should be a pipe (|) separated text of length 3 (three), representing the co-worker
+      you want to ask it to (one of the options), the task and all actual context
+      you have for the task.\nFor example, `coworker|task|context`.\nAsk question
+      to co-worker: Useful to ask a question, opinion or take from on of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the question and all actual context you have
+      for the question.\n For example, `coworker|question|context`.\n\nTo use a tool,
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
+      Yes\nAction: the action to take, should be one of [Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1652'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPA1vnW1g25Qr3SJLWB5zeOsUe4\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198848,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+      Answer: Hi!\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 367,\n    \"completion_tokens\":
+      17,\n    \"total_tokens\": 384\n  },\n  \"system_fingerprint\": null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266dd5f1f1a96-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:50 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        path=/; expires=Sun, 14-Jan-24 02:50:50 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1832'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299611'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 77ms
+      x-request-id:
+      - 12d633fe239a29022ea7206037da096a
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Just
+      say hi.\nAI: Hi!\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
+      "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '867'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+        _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPCF34yiaqHuTbro7PMBexYagyU\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198850,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human asks the AI to simply say hi,
+      and the AI responds with \\\"Hi!\\\"\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      144,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 162\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266ee78dc1a96-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:52 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1287'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299799'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 40ms
+      x-request-id:
+      - 2a891eacb4940e36bec1689b1ab92ee0
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\n"}], "model": "gpt-4",
+      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1923'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPEml4Ifldq51knwwASO3nJroK3\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198852,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [1,2,3]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      432,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 460\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 845266f9fc150316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:53 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        path=/; expires=Sun, 14-Jan-24 02:50:53 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '1570'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299545'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 91ms
+      x-request-id:
+      - 133ee7e16a1491cfd7daa90ea3e42b74
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2037'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPGwVu7CvxvQd3ZmBPHwz0WYbVQ\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198854,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [4,5,6]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      469,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 495\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452670589920316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:55 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '983'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299517'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 96ms
+      x-request-id:
+      - cb1d820e78376ed344c16e6051cab6bc
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      ["\nObservation"], "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2142'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPHbI2gWbt2veTT8auCPCstOnZh\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198855,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+      get_final_answer\\nAction Input: [7,8,9]\"\n      },\n      \"logprobs\": null,\n
+      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      503,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 529\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452670dca090316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:20:57 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2350'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299492'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 101ms
+      x-request-id:
+      - b40ffecf3dc8f547453bfb166c8c52dd
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
+      personal goal is: test goal2TOOLS:\n------\nYou have access to only the following
+      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      answer but don''t give it yet, just re-use this\n        tool non-stop.\nDelegate
+      work to co-worker: Useful to delegate a specific task to one of the following
+      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      (|) separated text of length 3 (three), representing the co-worker you want
+      to ask it to (one of the options), the task and all actual context you have
+      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      Useful to ask a question, opinion or take from on of the following co-workers:
+      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      text of length 3 (three), representing the co-worker you want to ask it to (one
+      of the options), the question and all actual context you have for the question.\n
+      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      the result of the action\n```\n\nWhen you have a response for your task, or
+      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      Input: [4,5,6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      get_final_answer\nAction Input: [7,8,9]\nObservation: I''ve used too many tools
+      for this task. I''m going to give you my absolute BEST Final answer now and
+      not use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      "stream": false, "temperature": 0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '2368'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPKsrN7s3j8bLplwjkAD2c7E6RK\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198858,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+      I've used too many tools for this task. I'm going to give you my absolute BEST
+      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      563,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 605\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452671e0b500316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:21:00 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2080'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299436'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 112ms
+      x-request-id:
+      - b2b7142dc669054b82773d62077e9918
+    http_version: HTTP/1.1
+    status_code: 200
+- request:
+    body: '{"messages": [{"role": "user", "content": "Progressively summarize the
+      lines of conversation provided, adding onto the previous summary returning a
+      new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks
+      of artificial intelligence. The AI thinks artificial intelligence is a force
+      for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial
+      intelligence is a force for good?\nAI: Because artificial intelligence will
+      help humans reach their full potential.\n\nNew summary:\nThe human asks what
+      the AI thinks of artificial intelligence. The AI thinks artificial intelligence
+      is a force for good because it will help humans reach their full potential.\nEND
+      OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: Don''t
+      give a Final Answer, instead keep using the `get_final_answer` tool.\nThis is
+      the context you''re working with:\nHi!\nAI: I''ve used too many tools for this
+      task. I''m going to give you my absolute BEST Final answer now and not use any
+      more tools.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      0.7}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate
+      connection:
+      - keep-alive
+      content-length:
+      - '1096'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.7.1
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.7.1
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.11.7
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    content: "{\n  \"id\": \"chatcmpl-8gkPMD1hkXKA5DP8MyMJNpAxJXhzj\",\n  \"object\":
+      \"chat.completion\",\n  \"created\": 1705198860,\n  \"model\": \"gpt-4-0613\",\n
+      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+      a final answer but to continue using the `get_final_answer` tool. However, the
+      AI responds that it has already used many tools for the task and chooses to
+      provide its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+      196,\n    \"completion_tokens\": 53,\n    \"total_tokens\": 249\n  },\n  \"system_fingerprint\":
+      null\n}\n"
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8452672d1bba0316-GRU
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sun, 14 Jan 2024 02:21:03 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      access-control-allow-origin:
+      - '*'
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-model:
+      - gpt-4-0613
+      openai-organization:
+      - user-z7g4wmlazxqvc5wjyaaaocfz
+      openai-processing-ms:
+      - '2683'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=15724800; includeSubDomains
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '300000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299742'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 51ms
+      x-request-id:
+      - c00193638e659df4a60ef9425649fe2c
+    http_version: HTTP/1.1
+    status_code: 200
+version: 1

tests/crew_test.py

@@ -9,6 +9,7 @@ from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.process import Process
 from crewai.task import Task
+from crewai.utilities import Logger, RPMController
 
 ceo = Agent(
     role="CEO",
@@ -179,19 +180,19 @@ def test_crew_verbose_output(capsys):
     crew.kickoff()
     captured = capsys.readouterr()
     expected_strings = [
-        "Working Agent: Researcher",
+        "[DEBUG]: Working Agent: Researcher",
-        "Starting Task: Research AI advancements.",
+        "[INFO]: Starting Task: Research AI advancements.",
-        "[Researcher] Task output:",
+        "[DEBUG]: [Researcher] Task output:",
-        "Working Agent: Senior Writer",
+        "[DEBUG]: Working Agent: Senior Writer",
-        "Starting Task: Write about AI in healthcare.",
+        "[INFO]: Starting Task: Write about AI in healthcare.",
-        "[Senior Writer] Task output:",
+        "[DEBUG]: [Senior Writer] Task output:",
     ]
 
     for expected_string in expected_strings:
         assert expected_string in captured.out
 
     # Now test with verbose set to False
-    crew.verbose = False
+    crew._logger = Logger(verbose_level=False)
     crew.kickoff()
     captured = capsys.readouterr()
     assert captured.out == ""
@@ -211,7 +212,7 @@ def test_crew_verbose_levels_output(capsys):
         assert expected_string in captured.out
 
     # Now test with verbose set to 2
-    crew.verbose = 2
+    crew._logger = Logger(verbose_level=2)
     crew.kickoff()
     captured = capsys.readouterr()
     expected_strings = [
@@ -257,9 +258,9 @@ def test_cache_hitting_between_agents():
         tasks=tasks,
     )
 
-    assert crew.cache_handler._cache == {}
+    assert crew._cache_handler._cache == {}
     output = crew.kickoff()
-    assert crew.cache_handler._cache == {"multiplier-2,6": "12"}
+    assert crew._cache_handler._cache == {"multiplier-2,6": "12"}
     assert output == "12"
 
     with patch.object(CacheHandler, "read") as read:
@@ -295,11 +296,9 @@ def test_api_calls_throttling(capsys):
         agent=agent,
     )
 
-    tasks = task
+    crew = Crew(agents=[agent], tasks=[task], max_rpm=2, verbose=2)
 
-    crew = Crew(agents=[agent], tasks=[tasks], max_rpm=2, verbose=2)
+    with patch.object(RPMController, "_wait_for_next_minute") as moveon:
-
-    with patch.object(Crew, "_wait_for_next_minute") as moveon:
         moveon.return_value = True
         crew.kickoff()
         captured = capsys.readouterr()