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: 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
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '1353'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
        _cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
      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-A81dBo5r2nWAvfAeKvkQePo1xr4b7\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726476257,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"Thought: I should use the get_final_answer
      tool to obtain 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\":
      26,\n    \"total_tokens\": 300,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
      0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3f92e12a1b2233-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 16 Sep 2024 08:44:17 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:
      - '364'
      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:
      - '29999682'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_5c29cd8664e9e690925d94ebc473d603
    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: 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": "Thought: I should use
      the get_final_answer tool to obtain The final answer.\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. 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
      Answer: 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
      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:
      - '2349'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1SckBhvJ18Dazp6bi8DEKYeiS9Q4.6_6i3nmLBw9b6g-1726476036-1.0.1.1-TnN4UpDXA33YXCVCUWOaZ12vGIg_o5NpJQEUHgjn6XdUgb7M0ND8PdkTfkd8rrxG5XFlPRMzI54GxZ0FeUY9xw;
        _cfuvid=0Rs4xTPk7h7OIXuSbTgMVVD9JSoZeKMwnygKHoHQo3k-1726476036297-0.0.1.1-604800000
      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-A81dCt0gksdnPkvgVhu5410k09MYV\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726476258,\n  \"model\": \"gpt-4o-2024-05-13\",\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\": 482,\n    \"completion_tokens\":
      6,\n    \"total_tokens\": 488,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
      0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3f92e53b2a2233-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 16 Sep 2024 08:44:18 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:
      - '226'
      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:
      - '29999446'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 1ms
      x-request-id:
      - req_fc90b97faad1b9af36997b5e74a427b1
    http_version: HTTP/1.1
    status_code: 200
version: 1