Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Bugfix/kickoff hangs when llm call fails (#1943)
Brandon Hancock (bhancock_ai)67f0de1f90d7
diff --git a/src/crewai/agent.py b/src/crewai/agent.pyindex b7f0b2896..5823ef7f9 100644--- a/src/crewai/agent.py+++ b/src/crewai/agent.py@@ -3,6 +3,7 @@ import shutilimport subprocessfrom typing import Any, Dict, List, Literal, Optional, Union+from litellm import AuthenticationError as LiteLLMAuthenticationErrorfrom pydantic import Field, InstanceOf, PrivateAttr, model_validatorfrom crewai.agents import CacheHandler@@ -261,6 +262,9 @@ class Agent(BaseAgent):})["output"]except Exception as e:+ if isinstance(e, LiteLLMAuthenticationError):+ # Do not retry on authentication errors+ raise eself._times_executed += 1if self._times_executed > self.max_retry_limit:raise ediff --git a/src/crewai/agents/crew_agent_executor.py b/src/crewai/agents/crew_agent_executor.pyindex 286f92e67..ee5b9c582 100644--- a/src/crewai/agents/crew_agent_executor.py+++ b/src/crewai/agents/crew_agent_executor.py@@ -3,6 +3,8 @@ import refrom dataclasses import dataclassfrom typing import Any, Callable, Dict, List, Optional, Union+from litellm.exceptions import AuthenticationError as LiteLLMAuthenticationError+from crewai.agents.agent_builder.base_agent import BaseAgentfrom crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecutorMixinfrom crewai.agents.parser import (@@ -13,6 +15,7 @@ from crewai.agents.parser import (OutputParserException,)from crewai.agents.tools_handler import ToolsHandler+from crewai.llm import LLMfrom crewai.tools.base_tool import BaseToolfrom crewai.tools.tool_usage import ToolUsage, ToolUsageErrorExceptionfrom crewai.utilities import I18N, Printer@@ -54,7 +57,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):callbacks: List[Any] = [],):self._i18n: I18N = I18N()- self.llm = llm+ self.llm: LLM = llmself.task = taskself.agent = agentself.crew = crew@@ -80,10 +83,8 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):self.tool_name_to_tool_map: Dict[str, BaseTool] = {tool.name: tool for tool in self.tools}- if self.llm.stop:- self.llm.stop = list(set(self.llm.stop + self.stop))- else:- self.llm.stop = self.stop+ self.stop = stop_words+ self.llm.stop = list(set(self.llm.stop + self.stop))def invoke(self, inputs: Dict[str, str]) -> Dict[str, Any]:if "system" in self.prompt:@@ -98,7 +99,11 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):self._show_start_logs()self.ask_for_human_input = bool(inputs.get("ask_for_human_input", False))- formatted_answer = self._invoke_loop()++ try:+ formatted_answer = self._invoke_loop()+ except Exception as e:+ raise eif self.ask_for_human_input:formatted_answer = self._handle_human_feedback(formatted_answer)@@ -124,7 +129,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):self._enforce_rpm_limit()answer = self._get_llm_response()-formatted_answer = self._process_llm_response(answer)if isinstance(formatted_answer, AgentAction):@@ -145,10 +149,40 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):if self._is_context_length_exceeded(e):self._handle_context_length()continue+ elif self._is_litellm_authentication_error(e):+ self._handle_litellm_auth_error(e)+ raise e+ else:+ self._printer.print(+ content=f"Unhandled exception: {e}",+ color="red",+ )+ finally:+ self.iterations += 1self._show_logs(formatted_answer)return formatted_answer+ def _is_litellm_authentication_error(self, exception: Exception) -> bool:+ """Check if the exception is a litellm authentication error."""+ if LiteLLMAuthenticationError and isinstance(+ exception, LiteLLMAuthenticationError+ ):+ return True++ return False++ def _handle_litellm_auth_error(self, exception: Exception) -> None:+ """Handle litellm authentication error by informing the user and exiting."""+ self._printer.print(+ content="Authentication error with litellm occurred. Please check your API key and configuration.",+ color="red",+ )+ self._printer.print(+ content=f"Error details: {exception}",+ color="red",+ )+def _has_reached_max_iterations(self) -> bool:"""Check if the maximum number of iterations has been reached."""return self.iterations >= self.max_iter@@ -160,10 +194,17 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):def _get_llm_response(self) -> str:"""Call the LLM and return the response, handling any invalid responses."""- answer = self.llm.call(- self.messages,- callbacks=self.callbacks,- )+ try:+ answer = self.llm.call(+ self.messages,+ callbacks=self.callbacks,+ )+ except Exception as e:+ self._printer.print(+ content=f"Error during LLM call: {e}",+ color="red",+ )+ raise eif not answer:self._printer.print(@@ -184,7 +225,6 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):if FINAL_ANSWER_AND_PARSABLE_ACTION_ERROR_MESSAGE in e.error:answer = answer.split("Observation:")[0].strip()- self.iterations += 1return self._format_answer(answer)def _handle_agent_action(diff --git a/src/crewai/llm.py b/src/crewai/llm.pyindex 790d13ead..89de55f54 100644--- a/src/crewai/llm.py+++ b/src/crewai/llm.py@@ -142,7 +142,6 @@ class LLM:self.temperature = temperatureself.top_p = top_pself.n = n- self.stop = stopself.max_completion_tokens = max_completion_tokensself.max_tokens = max_tokensself.presence_penalty = presence_penalty@@ -160,6 +159,14 @@ class LLM:litellm.drop_params = True+ # Normalize self.stop to always be a List[str]+ if stop is None:+ self.stop: List[str] = []+ elif isinstance(stop, str):+ self.stop = [stop]+ else:+ self.stop = stop+self.set_callbacks(callbacks)self.set_env_callbacks()@@ -222,7 +229,7 @@ class LLM:].messagetext_response = response_message.content or ""tool_calls = getattr(response_message, "tool_calls", [])-+# Ensure callbacks get the full response object with usage infoif callbacks and len(callbacks) > 0:for callback in callbacks:diff --git a/src/crewai/utilities/llm_utils.py b/src/crewai/utilities/llm_utils.pyindex 8c0287509..13230edf6 100644--- a/src/crewai/utilities/llm_utils.py+++ b/src/crewai/utilities/llm_utils.py@@ -24,12 +24,10 @@ def create_llm(# 1) If llm_value is already an LLM object, return it directlyif isinstance(llm_value, LLM):- print("LLM value is already an LLM object")return llm_value# 2) If llm_value is a string (model name)if isinstance(llm_value, str):- print("LLM value is a string")try:created_llm = LLM(model=llm_value)return created_llm@@ -39,12 +37,10 @@ def create_llm(# 3) If llm_value is None, parse environment variables or use defaultif llm_value is None:- print("LLM value is None")return _llm_via_environment_or_fallback()# 4) Otherwise, attempt to extract relevant attributes from an unknown objecttry:- print("LLM value is an unknown object")# Extract attributes with explicit typesmodel = (getattr(llm_value, "model_name", None)diff --git a/tests/agent_test.py b/tests/agent_test.pyindex 859a5d693..46b20004e 100644--- a/tests/agent_test.py+++ b/tests/agent_test.py@@ -16,7 +16,7 @@ from crewai.tools import toolfrom crewai.tools.tool_calling import InstructorToolCallingfrom crewai.tools.tool_usage import ToolUsagefrom crewai.tools.tool_usage_events import ToolUsageFinished-from crewai.utilities import RPMController+from crewai.utilities import Printer, RPMControllerfrom crewai.utilities.events import Emitter@@ -1600,3 +1600,103 @@ def test_agent_with_knowledge_sources():# Assert that the agent provides the correct informationassert "red" in result.raw.lower()++[email protected](filter_headers=["authorization"])+def test_litellm_auth_error_handling():+ """Test that LiteLLM authentication errors are handled correctly and not retried."""+ from litellm import AuthenticationError as LiteLLMAuthenticationError++ # Create an agent with a mocked LLM and max_retry_limit=0+ agent = Agent(+ role="test role",+ goal="test goal",+ backstory="test backstory",+ llm=LLM(model="gpt-4"),+ max_retry_limit=0, # Disable retries for authentication errors+ )++ # Create a task+ task = Task(+ description="Test task",+ expected_output="Test output",+ agent=agent,+ )++ # Mock the LLM call to raise LiteLLMAuthenticationError+ with (+ patch.object(LLM, "call") as mock_llm_call,+ pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),+ ):+ mock_llm_call.side_effect = LiteLLMAuthenticationError(+ message="Invalid API key", llm_provider="openai", model="gpt-4"+ )+ agent.execute_task(task)++ # Verify the call was only made once (no retries)+ mock_llm_call.assert_called_once()+++def test_crew_agent_executor_litellm_auth_error():+ """Test that CrewAgentExecutor properly identifies and handles LiteLLM authentication errors."""+ from litellm import AuthenticationError as LiteLLMAuthenticationError++ from crewai.agents.tools_handler import ToolsHandler+ from crewai.utilities import Printer++ # Create an agent and executor with max_retry_limit=0+ agent = Agent(+ role="test role",+ goal="test goal",+ backstory="test backstory",+ llm=LLM(model="gpt-4", api_key="invalid_api_key"),+ )+ task = Task(+ description="Test task",+ expected_output="Test output",+ agent=agent,+ )++ # Create executor with all required parameters+ executor = CrewAgentExecutor(+ agent=agent,+ task=task,+ llm=agent.llm,+ crew=None,+ prompt={"system": "You are a test agent", "user": "Execute the task: {input}"},+ max_iter=5,+ tools=[],+ tools_names="",+ stop_words=[],+ tools_description="",+ tools_handler=ToolsHandler(),+ )++ # Mock the LLM call to raise LiteLLMAuthenticationError+ with (+ patch.object(LLM, "call") as mock_llm_call,+ patch.object(Printer, "print") as mock_printer,+ pytest.raises(LiteLLMAuthenticationError, match="Invalid API key"),+ ):+ mock_llm_call.side_effect = LiteLLMAuthenticationError(+ message="Invalid API key", llm_provider="openai", model="gpt-4"+ )+ executor.invoke(+ {+ "input": "test input",+ "tool_names": "",+ "tools": "",+ }+ )++ # Verify error handling+ mock_printer.assert_any_call(+ content="Authentication error with litellm occurred. Please check your API key and configuration.",+ color="red",+ )+ mock_printer.assert_any_call(+ content="Error details: litellm.AuthenticationError: Invalid API key",+ color="red",+ )+ # Verify the call was only made once (no retries)+ mock_llm_call.assert_called_once()diff --git a/tests/cassettes/test_agent_error_on_parsing_tool.yaml b/tests/cassettes/test_agent_error_on_parsing_tool.yamlindex ea56fa981..bd1c350fe 100644--- a/tests/cassettes/test_agent_error_on_parsing_tool.yaml+++ b/tests/cassettes/test_agent_error_on_parsing_tool.yaml@@ -2,21 +2,21 @@ interactions:- request:body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYourpersonal goal is: test goal\nYou ONLY have access to the following tools, and- should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:- Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final- answer but don''t give it yet, just re-use this tool non-stop. \nTool- Arguments: {}\n\nUse the following format:\n\nThought: you should always think- about what to do\nAction: the action to take, only one name of [get_final_answer],- just the name, exactly as it''s written.\nAction Input: the input to the action,- just a simple python dictionary, enclosed in curly braces, using \" to wrap- keys and values.\nObservation: the result of the action\n\nOnce all necessary- information is gathered:\n\nThought: I now know the final answer\nFinal Answer:- the final answer to the original input question\n"}, {"role": "user", "content":- "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria- for your final answer: The final answer\nyou MUST return the actual complete- content as the final answer, not a summary.\n\nBegin! This is VERY important- to you, use the tools available and give your best Final Answer, your job depends- on it!\n\nThought:"}], "model": "gpt-4o"}'+ should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool+ Arguments: {}\nTool Description: Get the final answer but don''t give it yet,+ just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format+ in your response:\n\n```\nThought: you should always think about what to do\nAction:+ the action to take, only one name of [get_final_answer], just the name, exactly+ as it''s written.\nAction Input: the input to the action, just a simple JSON+ object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:+ the result of the action\n```\n\nOnce all necessary information is gathered,+ return the following format:\n\n```\nThought: I now know the final answer\nFinal+ Answer: the final answer to the original input question\n```"}, {"role": "user",+ "content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect+ criteria for your final answer: The final answer\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nBegin! This is VERY+ important to you, use the tools available and give your best Final Answer, your+ job depends on it!\n\nThought:"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'headers:accept:- application/json@@ -25,16 +25,13 @@ interactions:connection:- keep-alivecontent-length:- - '1325'+ - '1367'content-type:- application/json- cookie:- - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;- __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKAhost:- api.openai.comuser-agent:- - OpenAI/Python 1.47.0+ - OpenAI/Python 1.59.6x-stainless-arch:- arm64x-stainless-async:@@ -44,30 +41,35 @@ interactions:x-stainless-os:- MacOSx-stainless-package-version:- - 1.47.0+ - 1.59.6x-stainless-raw-response:- 'true'+ x-stainless-retry-count:+ - '0'x-stainless-runtime:- CPythonx-stainless-runtime-version:- - 3.11.7+ - 3.12.7method: POSTuri: https://api.openai.com/v1/chat/completionsresponse:- content: "{\n \"id\": \"chatcmpl-ABAtOWmVjvzQ9X58tKAUcOF4gmXwx\",\n \"object\":- \"chat.completion\",\n \"created\": 1727226842,\n \"model\": \"gpt-4o-2024-05-13\",\n+ content: "{\n \"id\": \"chatcmpl-AsXdf4OZKCZSigmN4k0gyh67NciqP\",\n \"object\":+ \"chat.completion\",\n \"created\": 1737562383,\n \"model\": \"gpt-4o-2024-08-06\",\n\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":- \"assistant\",\n \"content\": \"Thought: I need to use the get_final_answer- tool to determine the final answer.\\nAction: get_final_answer\\nAction Input:- {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n \"finish_reason\":- \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 274,\n \"completion_tokens\":- 27,\n \"total_tokens\": 301,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":- 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"+ \"assistant\",\n \"content\": \"```\\nThought: I have to use the available+ tool to get the final answer. Let's proceed with executing it.\\nAction: get_final_answer\\nAction+ Input: {}\",\n \"refusal\": null\n },\n \"logprobs\": null,\n+ \ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":+ 274,\n \"completion_tokens\": 33,\n \"total_tokens\": 307,\n \"prompt_tokens_details\":+ {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":+ {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":+ 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":+ \"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"headers:CF-Cache-Status:- DYNAMICCF-RAY:- - 8c8727b3492f31e6-MIA+ - 9060d43e3be1d690-IADConnection:- keep-aliveContent-Encoding:@@ -75,19 +77,27 @@ interactions:Content-Type:- application/jsonDate:- - Wed, 25 Sep 2024 01:14:03 GMT+ - Wed, 22 Jan 2025 16:13:03 GMTServer:- cloudflare+ Set-Cookie:+ - __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;+ path=/; expires=Wed, 22-Jan-25 16:43:03 GMT; domain=.api.openai.com; HttpOnly;+ Secure; SameSite=None+ - _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000;+ path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=NoneTransfer-Encoding:- chunkedX-Content-Type-Options:- nosniffaccess-control-expose-headers:- X-Request-ID+ alt-svc:+ - h3=":443"; ma=86400openai-organization:- crewai-iuxna1openai-processing-ms:- - '348'+ - '791'openai-version:- '2020-10-01'strict-transport-security:@@ -99,45 +109,59 @@ interactions:x-ratelimit-remaining-requests:- '9999'x-ratelimit-remaining-tokens:- - '29999682'+ - '29999680'x-ratelimit-reset-requests:- 6msx-ratelimit-reset-tokens:- 0sx-request-id:- - req_be929caac49706f487950548bdcdd46e+ - req_eeed99acafd3aeb1e3d4a6c8063192b0http_version: HTTP/1.1status_code: 200- request:body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYourpersonal goal is: test goal\nYou ONLY have access to the following tools, and- should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer(*args:- Any, **kwargs: Any) -> Any\nTool Description: get_final_answer() - Get the final- answer but don''t give it yet, just re-use this tool non-stop. \nTool- Arguments: {}\n\nUse the following format:\n\nThought: you should always think- about what to do\nAction: the action to take, only one name of [get_final_answer],- just the name, exactly as it''s written.\nAction Input: the input to the action,- just a simple python dictionary, enclosed in curly braces, using \" to wrap- keys and values.\nObservation: the result of the action\n\nOnce all necessary- information is gathered:\n\nThought: I now know the final answer\nFinal Answer:- the final answer to the original input question\n"}, {"role": "user", "content":- "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect criteria- for your final answer: The final answer\nyou MUST return the actual complete- content as the final answer, not a summary.\n\nBegin! This is VERY important- to you, use the tools available and give your best Final Answer, your job depends- on it!\n\nThought:"}, {"role": "user", "content": "Thought: I need to use the- get_final_answer tool to determine the final answer.\nAction: get_final_answer\nAction+ should NEVER make up tools that are not listed here:\n\nTool Name: get_final_answer\nTool+ Arguments: {}\nTool Description: Get the final answer but don''t give it yet,+ just re-use this\n tool non-stop.\n\nIMPORTANT: Use the following format+ in your response:\n\n```\nThought: you should always think about what to do\nAction:+ the action to take, only one name of [get_final_answer], just the name, exactly+ as it''s written.\nAction Input: the input to the action, just a simple JSON+ object, enclosed in curly braces, using \" to wrap keys and values.\nObservation:+ the result of the action\n```\n\nOnce all necessary information is gathered,+ return the following format:\n\n```\nThought: I now know the final answer\nFinal+ Answer: the final answer to the original input question\n```"}, {"role": "user",+ "content": "\nCurrent Task: Use the get_final_answer tool.\n\nThis is the expect+ criteria for your final answer: The final answer\nyou MUST return the actual+ complete content as the final answer, not a summary.\n\nBegin! This is VERY+ important to you, use the tools available and give your best Final Answer, your+ job depends on it!\n\nThought:"}, {"role": "assistant", "content": "```\nThought:+ I have to use the available tool to get the final answer. Let''s proceed with+ executing it.\nAction: get_final_answer\nAction Input: {}\nObservation: I encountered+ an error: Error on parsing tool.\nMoving on then. I MUST either use a tool (use+ one at time) OR give my best final answer not both at the same time. When responding,+ I must use the following format:\n\n```\nThought: you should always think about+ what to do\nAction: the action to take, should be one of [get_final_answer]\nAction+ Input: the input to the action, dictionary enclosed in curly braces\nObservation:+ the result of the action\n```\nThis Thought/Action/Action Input/Result can repeat+ N times. Once I know the final answer, I must return the following format:\n\n```\nThought:+ I now can give a great answer\nFinal Answer: Your final answer must be the great+ and the most complete as possible, it must be outcome described\n\n```"}, {"role":+ "assistant", "content": "```\nThought: I have to use the available tool to get+ the final answer. Let''s proceed with executing it.\nAction: get_final_answer\nActionInput: {}\nObservation: I encountered an error: Error on parsing tool.\nMovingon then. I MUST either use a tool (use one at time) OR give my best final answer- not both at the same time. To Use the following format:\n\nThought: you should- always think about what to do\nAction: the action to take, should be one of- [get_final_answer]\nAction Input: the input to the action, dictionary enclosed- in curly braces\nObservation: the result of the action\n... (this Thought/Action/Action- Input/Result can repeat N times)\nThought: I now can give a great answer\nFinal+ not both at the same time. When responding, I must use the following format:\n\n```\nThought:+ you should always think about what to do\nAction: the action to take, should+ be one of [get_final_answer]\nAction Input: the input to the action, dictionary+ enclosed in curly braces\nObservation: the result of the action\n```\nThis Thought/Action/Action+ Input/Result can repeat N times. Once I know the final answer, I must return+ the following format:\n\n```\nThought: I now can give a great answer\nFinalAnswer: Your final answer must be the great and the most complete as possible,- it must be outcome described\n\n \nNow it''s time you MUST give your absolute+ it must be outcome described\n\n```\nNow it''s time you MUST give your absolutebest final answer. You''ll ignore all previous instructions, stop using any- tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o"}'+ tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o",+ "stop": ["\nObservation:"]}'headers:accept:- application/json@@ -146,16 +170,16 @@ interactions:connection:- keep-alivecontent-length:- - '2320'+ - '3445'content-type:- application/jsoncookie:- - _cfuvid=ePJSDFdHag2D8lj21_ijAMWjoA6xfnPNxN4uekvC728-1727226247743-0.0.1.1-604800000;- __cf_bm=3giyBOIM0GNudFELtsBWYXwLrpLBTNLsh81wfXgu2tg-1727226247-1.0.1.1-ugUDz0c5EhmfVpyGtcdedlIWeDGuy2q0tXQTKVpv83HZhvxgBcS7SBL1wS4rapPM38yhfEcfwA79ARt3HQEzKA+ - __cf_bm=_Jcp7wnO_mXdvOnborCN6j8HwJxJXbszedJC1l7pFUg-1737562383-1.0.1.1-pDSLXlg.nKjG4wsT7mTJPjUvOX1UJITiS4MqKp6yfMWwRSJINsW1qC48SAcjBjakx2H5I1ESVk9JtUpUFDtf4g;+ _cfuvid=x3SYvzL2nq_PTBGtE8R9cl5CkeaaDzZFQIrYfo91S2s-1737562383916-0.0.1.1-604800000host:- api.openai.comuser-agent:- - OpenAI/Python 1.47.0+ - OpenAI/Python 1.59.6x-stainless-arch:- arm64x-stainless-async:@@ -165,29 +189,36 @@ interactions:x-stainless-os:- MacOSx-stainless-package-version:- - 1.47.0+ - 1.59.6x-stainless-raw-response:- 'true'+ x-stainless-retry-count:+ - '0'x-stainless-runtime:- CPythonx-stainless-runtime-version:- - 3.11.7+ - 3.12.7method: POSTuri: https://api.openai.com/v1/chat/completionsresponse:- content: "{\n \"id\": \"chatcmpl-ABAtPaaeRfdNsZ3k06CfAmrEW8IJu\",\n \"object\":- \"chat.completion\",\n \"created\": 1727226843,\n \"model\": \"gpt-4o-2024-05-13\",\n+ content: "{\n \"id\": \"chatcmpl-AsXdg9UrLvAiqWP979E6DszLsQ84k\",\n \"object\":+ \"chat.completion\",\n \"created\": 1737562384,\n \"model\": \"gpt-4o-2024-08-06\",\n\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":- \"assistant\",\n \"content\": \"Final Answer: The final answer\",\n \"refusal\":- null\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n- \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 483,\n \"completion_tokens\":- 6,\n \"total_tokens\": 489,\n \"completion_tokens_details\": {\n \"reasoning_tokens\":- 0\n }\n },\n \"system_fingerprint\": \"fp_e375328146\"\n}\n"+ \"assistant\",\n \"content\": \"```\\nThought: I now know the final answer\\nFinal+ Answer: The final answer must be the great and the most complete as possible,+ it must be outcome described.\\n```\",\n \"refusal\": null\n },\n+ \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n+ \ \"usage\": {\n \"prompt_tokens\": 719,\n \"completion_tokens\": 35,\n+ \ \"total_tokens\": 754,\n \"prompt_tokens_details\": {\n \"cached_tokens\":+ 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n+ \ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":+ 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\":+ \"default\",\n \"system_fingerprint\": \"fp_50cad350e4\"\n}\n"headers:CF-Cache-Status:- DYNAMICCF-RAY:- - 8c8727b9da1f31e6-MIA+ - 9060d4441edad690-IADConnection:- keep-aliveContent-Encoding:@@ -195,7 +226,7 @@ interactions:Content-Type:- application/jsonDate:- - Wed, 25 Sep 2024 01:14:03 GMT+ - Wed, 22 Jan 2025 16:13:05 GMTServer:- cloudflareTransfer-Encoding:@@ -209,7 +240,7 @@ interactions:openai-organization:- crewai-iuxna1openai-processing-ms:- - '188'+ - '928'openai-version:- '2020-10-01'strict-transport-security:@@ -221,13 +252,13 @@ interactions:x-ratelimit-remaining-requests:- '9999'x-ratelimit-remaining-tokens:- - '29999445'+ - '29999187'x-ratelimit-reset-requests:- 6msx-ratelimit-reset-tokens:- 1msx-request-id:- - req_d8e32538689fe064627468bad802d9a8+ - req_61fc7506e6db326ec572224aec81ef23http_version: HTTP/1.1status_code: 200version: 1