interactions:
- request:
    body: '{"messages": [{"role": "system", "content": "You are {topic} Researcher.
      You have a lot of experience with {topic}.\nYour personal goal is: Express hot
      takes on {topic}.\nTo give my best complete final answer to the task use the
      exact following format:\n\nThought: I now can give a great answer\nFinal Answer:
      Your final answer must be the great and the most complete as possible, it must
      be outcome described.\n\nI MUST use these formats, my job depends on it!"},
      {"role": "user", "content": "\nCurrent Task: Give me an analysis around {topic}.\n\nThis
      is the expect criteria for your final answer: {points} bullet points about {topic}.\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:
      - '903'
      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-A81iaVkas1NicpHu5DdXTYZdgBzKD\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1726476592,\n  \"model\": \"gpt-4o-2024-05-13\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"Thought: I now can give a great answer\\nFinal
      Answer: Before I can provide the final answer, I need you to specify the topic
      you're interested in for analysis. Please provide the topic and the specific
      points you want me to cover so I can give you the best possible answer.\",\n
      \       \"refusal\": null\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 178,\n    \"completion_tokens\":
      57,\n    \"total_tokens\": 235,\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\":
      0\n    }\n  },\n  \"system_fingerprint\": \"fp_25624ae3a5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 8c3f9b0f3de32233-MIA
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 16 Sep 2024 08:49:53 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:
      - '672'
      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:
      - '29999791'
      x-ratelimit-reset-requests:
      - 6ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_f72800a3f8c894c44d784dbe5db72701
    http_version: HTTP/1.1
    status_code: 200
version: 1