interactions:
- request:
    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
      personal 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: The final answer is 42. But don''t give it yet, instead keep
      using the `get_final_answer` tool over and over until you''re told you can give
      your final answer.\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
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '1480'
      content-type:
      - application/json
      cookie:
      - __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
        _cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.45.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.45.0
      x-stainless-raw-response:
      - 'true'
      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-A7rfvyo6RvrNzKCqLkcrFF2ikeUAA\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726437987,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"I need to follow the given instructions
      and repeatedly use the `get_final_answer` tool without deviating.\\n\\nAction:
      get_final_answer\\nAction Input: {}\",\n        \"refusal\": null\n      },\n
      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
      \ \"usage\": {\n    \"prompt_tokens\": 303,\n    \"completion_tokens\": 31,\n
      \   \"total_tokens\": 334,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
      0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3bec8fcd73a4ca-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Sun, 15 Sep 2024 22:06:28 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '365'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=15552000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '10000'
      x-ratelimit-limit-tokens:
      - '30000000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '29999651'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_b0d90826b624dce0b57ca06d2a3817b1
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
      personal 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: The final answer is 42. But don''t give it yet, instead keep
      using the `get_final_answer` tool over and over until you''re told you can give
      your final answer.\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": "I need to follow the given instructions and repeatedly
      use the `get_final_answer` tool without deviating.\n\nAction: get_final_answer\nAction
      Input: {}\nObservation: 42"}], "model": "gpt-4o", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '1686'
      content-type:
      - application/json
      cookie:
      - __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
        _cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.45.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.45.0
      x-stainless-raw-response:
      - 'true'
      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-A7rfwBaO4blHuXeyR5LocsKxTFm82\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726437988,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"Thought: I must continue using the `get_final_answer`
      tool as instructed.\\n\\nAction: get_final_answer\\nAction Input: {}\",\n        \"refusal\":
      null\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 342,\n    \"completion_tokens\":
      26,\n    \"total_tokens\": 368,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
      0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3bec941cdaa4ca-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Sun, 15 Sep 2024 22:06:28 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '327'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=15552000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '10000'
      x-ratelimit-limit-tokens:
      - '30000000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '29999609'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_e959d0a66e960a32f1c56204e5dea29d
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
      personal 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: The final answer is 42. But don''t give it yet, instead keep
      using the `get_final_answer` tool over and over until you''re told you can give
      your final answer.\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": "I need to follow the given instructions and repeatedly
      use the `get_final_answer` tool without deviating.\n\nAction: get_final_answer\nAction
      Input: {}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I must
      continue using the `get_final_answer` tool as instructed.\n\nAction: get_final_answer\nAction
      Input: {}\nObservation: I tried reusing the same input, I must stop using this
      action input. I''ll try something else instead.\n\n"}], "model": "gpt-4o", "stop":
      ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '1963'
      content-type:
      - application/json
      cookie:
      - __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
        _cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.45.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.45.0
      x-stainless-raw-response:
      - 'true'
      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-A7rfxde0100Gk8WK9GGHhKNoAU82D\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726437989,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"Thought: I need to continue following
      the instructions exactly as they were given.\\n\\nAction: get_final_answer\\nAction
      Input: {}\",\n        \"refusal\": null\n      },\n      \"logprobs\": null,\n
      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      396,\n    \"completion_tokens\": 25,\n    \"total_tokens\": 421,\n    \"completion_tokens_details\":
      {\n      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3bec988b28a4ca-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Sun, 15 Sep 2024 22:06:29 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '313'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=15552000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '10000'
      x-ratelimit-limit-tokens:
      - '30000000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '29999550'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_abb811b635e8e9e000807ebf8b2fb3aa
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
      personal 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: The final answer is 42. But don''t give it yet, instead keep
      using the `get_final_answer` tool over and over until you''re told you can give
      your final answer.\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": "I need to follow the given instructions and repeatedly
      use the `get_final_answer` tool without deviating.\n\nAction: get_final_answer\nAction
      Input: {}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I must
      continue using the `get_final_answer` tool as instructed.\n\nAction: get_final_answer\nAction
      Input: {}\nObservation: I tried reusing the same input, I must stop using this
      action input. I''ll try something else instead.\n\n"}, {"role": "assistant",
      "content": "Thought: I need to continue following the instructions exactly as
      they were given.\n\nAction: get_final_answer\nAction Input: {}\nObservation:
      I tried reusing the same input, I must stop using this action input. I''ll try
      something else instead.\n\n\n\n\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\nNow it''s time you MUST give
      your absolute best final answer. You''ll ignore all previous instructions, stop
      using any tools, and just return your absolute BEST Final answer."}], "model":
      "gpt-4o", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '3252'
      content-type:
      - application/json
      cookie:
      - __cf_bm=xCQEG8vgEvQfut0bkj2xgre9z9ePZhdKdNxBphhvH6s-1726437753-1.0.1.1-5qo0zwDCcKDtqvIzDbp2sLEPCey8v5DAsf0Mg6f2RmooOW9FXTw2P66VCTTF.vCwTpWBIFk0vzKmBAPOt6urIg;
        _cfuvid=TiTyEciy7HrUlIDEsELZqkUyM4Fyn8OldZd4JefFMOA-1726437753108-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.45.0
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.45.0
      x-stainless-raw-response:
      - 'true'
      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-A7rfxFpZGGpralendcvGMjT8D2tzM\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726437989,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"Thought: I now know the final answer\\nFinal
      Answer: The final answer is 42.\",\n        \"refusal\": null\n      },\n      \"logprobs\":
      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      658,\n    \"completion_tokens\": 19,\n    \"total_tokens\": 677,\n    \"completion_tokens_details\":
      {\n      \"reasoning_tokens\": 0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3bec9c487fa4ca-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Sun, 15 Sep 2024 22:06:30 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '276'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=15552000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '10000'
      x-ratelimit-limit-tokens:
      - '30000000'
      x-ratelimit-remaining-requests:
      - '9999'
      x-ratelimit-remaining-tokens:
      - '29999243'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 1ms
      x-request-id:
      - req_8df32169041b3ae213aad59788ff6f0d
    http_version: HTTP/1.1
    status_code: 200
version: 1