crewAI/tests/cassettes/test_agent_error_on_parsing_tool.yaml

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\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 expected
      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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '1374'
      content-type:
      - application/json
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIrzTIGOht7LtyCu63s9y6al9Wt0\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463811,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"I need to determine what action to take
      next to retrieve the final answer.  \\nAction: get_final_answer  \\nAction Input:
      {}  \",\n        \"refusal\": null,\n        \"annotations\": []\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    \"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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a2159f4c67b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:13 GMT
      Server:
      - cloudflare
      Set-Cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        path=/; expires=Tue, 01-Apr-25 00:00:13 GMT; domain=.api.openai.com; HttpOnly;
        Secure; SameSite=None
      - _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000;
        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '2066'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149999694'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_1311568b96e7fc639ff8dc1e0a43aa79
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: !!binary |
      CuoNCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSwQ0KEgoQY3Jld2FpLnRl
      bGVtZXRyeRKrCAoQqJ0LX3K2ujggGW8chWkxnhIIOKFYgK1mwk4qDENyZXcgQ3JlYXRlZDABOcih
      DV8ZBzIYQQhnHF8ZBzIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKGgoOcHl0aG9uX3Zl
      cnNpb24SCAoGMy4xMi44Si4KCGNyZXdfa2V5EiIKIDczYWFjMjg1ZTY3NDY2NjdmNzUxNDc2NzAw
      MDM0MTEwSjEKB2NyZXdfaWQSJgokNGRkNDQyYjItNjE2My00YWY2LTg1NjMtNzM1ZWJmNjIxOTNh
      ShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShEKC2NyZXdfbWVtb3J5EgIQAEoaChRjcmV3
      X251bWJlcl9vZl90YXNrcxICGAFKGwoVY3Jld19udW1iZXJfb2ZfYWdlbnRzEgIYAUo6ChBjcmV3
      X2ZpbmdlcnByaW50EiYKJGVlYWUyOTM3LWI0YzgtNGE5ZS04YWI4LWVjM2Y3ZGMxNDFmYko7Chtj
      cmV3X2ZpbmdlcnByaW50X2NyZWF0ZWRfYXQSHAoaMjAyNS0wMy0zMVQxNjozMDoxMS4yOTA0MjdK
      zgIKC2NyZXdfYWdlbnRzEr4CCrsCW3sia2V5IjogImUxNDhlNTMyMDI5MzQ5OWY4Y2ViZWE4MjZl
      NzI1ODJiIiwgImlkIjogIjMzNDNjZjgzLWFiNmEtNDk5OS04Mjc2LTA1ZGM0MTE0N2E1YiIsICJy
      b2xlIjogInRlc3Qgcm9sZSIsICJ2ZXJib3NlPyI6IHRydWUsICJtYXhfaXRlciI6IDEsICJtYXhf
      cnBtIjogbnVsbCwgImZ1bmN0aW9uX2NhbGxpbmdfbGxtIjogIiIsICJsbG0iOiAiZ3B0LTRvLW1p
      bmkiLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IGZhbHNlLCAiYWxsb3dfY29kZV9leGVjdXRpb24/
      IjogZmFsc2UsICJtYXhfcmV0cnlfbGltaXQiOiAyLCAidG9vbHNfbmFtZXMiOiBbXX1dSpACCgpj
      cmV3X3Rhc2tzEoECCv4BW3sia2V5IjogImY3YTlmN2JiMWFlZTRiNmVmMmM1MjZkMGE4YzJmMmFj
      IiwgImlkIjogImIxZjRhMGFhLTYwMmQtNGFjMy05ODllLTY0NDdmNDlmZjZjMSIsICJhc3luY19l
      eGVjdXRpb24/IjogZmFsc2UsICJodW1hbl9pbnB1dD8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAi
      dGVzdCByb2xlIiwgImFnZW50X2tleSI6ICJlMTQ4ZTUzMjAyOTM0OTlmOGNlYmVhODI2ZTcyNTgy
      YiIsICJ0b29sc19uYW1lcyI6IFsiZ2V0X2ZpbmFsX2Fuc3dlciJdfV16AhgBhQEAAQAAEoAEChCN
      K3bIxbl53On4qoM0P7BDEghZs7x1P32BHioMVGFzayBDcmVhdGVkMAE58PIvXxkHMhhBiKowXxkH
      MhhKLgoIY3Jld19rZXkSIgogNzNhYWMyODVlNjc0NjY2N2Y3NTE0NzY3MDAwMzQxMTBKMQoHY3Jl
      d19pZBImCiQ0ZGQ0NDJiMi02MTYzLTRhZjYtODU2My03MzVlYmY2MjE5M2FKLgoIdGFza19rZXkS
      IgogZjdhOWY3YmIxYWVlNGI2ZWYyYzUyNmQwYThjMmYyYWNKMQoHdGFza19pZBImCiRiMWY0YTBh
      YS02MDJkLTRhYzMtOTg5ZS02NDQ3ZjQ5ZmY2YzFKOgoQY3Jld19maW5nZXJwcmludBImCiRlZWFl
      MjkzNy1iNGM4LTRhOWUtOGFiOC1lYzNmN2RjMTQxZmJKOgoQdGFza19maW5nZXJwcmludBImCiRl
      MzJiYTMwZS00MDZmLTQ0ZmItOGM2Mi0wMmRkZTczZDIyNTJKOwobdGFza19maW5nZXJwcmludF9j
      cmVhdGVkX2F0EhwKGjIwMjUtMDMtMzFUMTY6MzA6MTEuMjkwMzc4SjsKEWFnZW50X2ZpbmdlcnBy
      aW50EiYKJDZiYjU4M2YxLWRkZTAtNDgwYy05YzZkLWRmNzQ0NTI1YTI3ZXoCGAGFAQABAAASegoQ
      2qsKnI/iz5YZxt5B55H/3BIITw7exxOBPXIqEFRvb2wgVXNhZ2UgRXJyb3IwATmI7cjnGQcyGEFA
      q9XnGQcyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSg8KA2xsbRIICgZncHQtNG96AhgB
      hQEAAQAA
    headers:
      Accept:
      - '*/*'
      Accept-Encoding:
      - gzip, deflate, zstd
      Connection:
      - keep-alive
      Content-Length:
      - '1773'
      Content-Type:
      - application/x-protobuf
      User-Agent:
      - OTel-OTLP-Exporter-Python/1.31.1
    method: POST
    uri: https://telemetry.crewai.com:4319/v1/traces
  response:
    body:
      string: "\n\0"
    headers:
      Content-Length:
      - '2'
      Content-Type:
      - application/x-protobuf
      Date:
      - Mon, 31 Mar 2025 23:30:14 GMT
    status:
      code: 200
      message: OK
- 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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '4193'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs3RZWE0pDm4saOP5a2j2pUORUD\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463815,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
      Answer: I must follow the predefined structure and utilize the get_final_answer
      tool to extract the necessary information.\\n```\",\n        \"refusal\": null,\n
      \       \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 878,\n    \"completion_tokens\":
      35,\n    \"total_tokens\": 913,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a2235a2467b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:16 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '1050'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149999028'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_a945851daba59247e89436242f50c663
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '4193'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs5hXcx2fn8tJmCAJHoKpvbM9C5\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463817,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: you should always think
      about what to do\\nAction: get_final_answer\\nAction Input: {}\",\n        \"refusal\":
      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 878,\n    \"completion_tokens\":
      23,\n    \"total_tokens\": 901,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a237ced067b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:17 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '760'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149999027'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_47c73df64cb410e71c6558fb111669b9
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '6960'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs6Z7FbkaaEHZCks2aPg5RpB7p9\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463818,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I need to determine how
      to proceed in order to get the final answer.\\nAction: get_final_answer\\nAction
      Input: {}\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n
      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
      \ \"usage\": {\n    \"prompt_tokens\": 1474,\n    \"completion_tokens\": 29,\n
      \   \"total_tokens\": 1503,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a23dadf367b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:18 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '807'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149998375'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_116bd0a42b72845da93d150d06b3d074
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: !!binary |
      CrkBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSkAEKEgoQY3Jld2FpLnRl
      bGVtZXRyeRJ6ChBg77N3Xk6AOGtF6qHpgY/TEgjLb9iGJfRibCoQVG9vbCBVc2FnZSBFcnJvcjAB
      ObCyK+IaBzIYQSCCN+IaBzIYShsKDmNyZXdhaV92ZXJzaW9uEgkKBzAuMTA4LjBKDwoDbGxtEggK
      BmdwdC00b3oCGAGFAQABAAA=
    headers:
      Accept:
      - '*/*'
      Accept-Encoding:
      - gzip, deflate, zstd
      Connection:
      - keep-alive
      Content-Length:
      - '188'
      Content-Type:
      - application/x-protobuf
      User-Agent:
      - OTel-OTLP-Exporter-Python/1.31.1
    method: POST
    uri: https://telemetry.crewai.com:4319/v1/traces
  response:
    body:
      string: "\n\0"
    headers:
      Content-Length:
      - '2'
      Content-Type:
      - application/x-protobuf
      Date:
      - Mon, 31 Mar 2025 23:30:19 GMT
    status:
      code: 200
      message: OK
- 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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '6960'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs6TS0cl8Nktzxi2GavpYUOOcVV\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463818,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I need to pursue the action
      to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      1474,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 1500,\n    \"prompt_tokens_details\":
      {\n      \"cached_tokens\": 1408,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a2433d5567b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:19 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '1031'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149998375'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_772114061f86f1e4fc4d6af78e369c9c
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '9751'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs88CTLDSND5eByFBW2ge57fKNW\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463820,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I need to pursue the action
      to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      2076,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 2102,\n    \"prompt_tokens_details\":
      {\n      \"cached_tokens\": 1408,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 9293a24a5d9b67b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:20 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:
      - '724'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149997717'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_53b688c965fd8ea9aec538e23dc14d5f
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '9751'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs8PPr1kQwag3x7EeShzJwgKBHQ\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463820,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I need to pursue the action
      to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      2076,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 2102,\n    \"prompt_tokens_details\":
      {\n      \"cached_tokens\": 2048,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a24f5b6e67b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:21 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '970'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149997716'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 0s
      x-request-id:
      - req_003929761b6c31033aa046068854bb4d
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '12542'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIs9EQi1thZCKE6iowM7PKovOwHL\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463821,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I need to take action
      to get the final answer.\\nAction: get_final_answer\\nAction Input: {}\",\n
      \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
      2678,\n    \"completion_tokens\": 25,\n    \"total_tokens\": 2703,\n    \"prompt_tokens_details\":
      {\n      \"cached_tokens\": 2048,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-Cache-Status:
      - DYNAMIC
      CF-RAY:
      - 9293a2560b2367b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:22 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:
      - '954'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149997058'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 1ms
      x-request-id:
      - req_58701a68086507409e813a7fe23fa4a3
    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\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 expected
      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 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": "I need to determine what action to take next to retrieve
      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. 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": "I need
      to determine what action to take next to retrieve 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. 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```\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."}, {"role": "assistant", "content": "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: you should always think about what to
      do\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: you should always think about what to
      do\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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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."}, {"role": "assistant", "content": "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 need to pursue the action to get 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. 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 need to pursue the action to get 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. 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```\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-mini", "stop": ["\nObservation:"]}'
    headers:
      accept:
      - application/json
      accept-encoding:
      - gzip, deflate, zstd
      connection:
      - keep-alive
      content-length:
      - '12542'
      content-type:
      - application/json
      cookie:
      - __cf_bm=1S5GqtdZlw2N3SJ7L2plaSLL9C98N6SHFF2yfiNNhvE-1743463813-1.0.1.1-KwGBgTXoXjtVlkPtShw19TBHDFEUx.2QH7PXFHEcrV4HQpDEYC2huBlyfVkkr4bTtDVenmctavjBmNoQM12Ie9yRkMNwey3SwOK.1et3PlE;
        _cfuvid=gEx9GW83E.zW51Yz4hCsodDQ2f9_PiDrVILLKkDa.6M-1743463813602-0.0.1.1-604800000
      host:
      - api.openai.com
      user-agent:
      - OpenAI/Python 1.68.2
      x-stainless-arch:
      - arm64
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - MacOS
      x-stainless-package-version:
      - 1.68.2
      x-stainless-raw-response:
      - 'true'
      x-stainless-read-timeout:
      - '600.0'
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.8
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    content: "{\n  \"id\": \"chatcmpl-BHIsBMTtfSuUn9wxvCtunG64V1bHD\",\n  \"object\":
      \"chat.completion\",\n  \"created\": 1743463823,\n  \"model\": \"gpt-4o-mini-2024-07-18\",\n
      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
      \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal
      Answer: I am unable to provide a final answer due to a continuous error when
      trying to retrieve it using the get_final_answer tool.\\n```\",\n        \"refusal\":
      null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 2678,\n    \"completion_tokens\":
      41,\n    \"total_tokens\": 2719,\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_b376dfbbd5\"\n}\n"
    headers:
      CF-RAY:
      - 9293a25ceb3867b9-SJC
      Connection:
      - keep-alive
      Content-Encoding:
      - gzip
      Content-Type:
      - application/json
      Date:
      - Mon, 31 Mar 2025 23:30:24 GMT
      Server:
      - cloudflare
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - nosniff
      access-control-expose-headers:
      - X-Request-ID
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - crewai-iuxna1
      openai-processing-ms:
      - '1095'
      openai-version:
      - '2020-10-01'
      strict-transport-security:
      - max-age=31536000; includeSubDomains; preload
      x-ratelimit-limit-requests:
      - '30000'
      x-ratelimit-limit-tokens:
      - '150000000'
      x-ratelimit-remaining-requests:
      - '29999'
      x-ratelimit-remaining-tokens:
      - '149997058'
      x-ratelimit-reset-requests:
      - 2ms
      x-ratelimit-reset-tokens:
      - 1ms
      x-request-id:
      - req_f3e522c8e419cab62842ddcee0e80b7b
    http_version: HTTP/1.1
    status_code: 200
- request:
    body: '{"name": "llama3.2:3b"}'
    headers:
      accept:
      - '*/*'
      accept-encoding:
      - gzip, deflate
      connection:
      - keep-alive
      content-length:
      - '23'
      content-type:
      - application/json
      host:
      - localhost:11434
      user-agent:
      - litellm/1.68.0
    method: POST
    uri: http://localhost:11434/api/show
  response:
    body:
      string: "{\"license\":\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version
        Release Date: September 25, 2024\\n\\n\u201CAgreement\u201D means the terms
        and conditions for use, reproduction, distribution \\nand modification of
        the Llama Materials set forth herein.\\n\\n\u201CDocumentation\u201D means
        the specifications, manuals and documentation accompanying Llama 3.2\\ndistributed
        by Meta at https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D
        or \u201Cyou\u201D means you, or your employer or any other person or entity
        (if you are \\nentering into this Agreement on such person or entity\u2019s
        behalf), of the age required under\\napplicable laws, rules or regulations
        to provide legal consent and that has legal authority\\nto bind your employer
        or such other person or entity if you are entering in this Agreement\\non
        their behalf.\\n\\n\u201CLlama 3.2\u201D means the foundational large language
        models and software and algorithms, including\\nmachine-learning model code,
        trained model weights, inference-enabling code, training-enabling code,\\nfine-tuning
        enabling code and other elements of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
        Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and
        Documentation (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
        or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located
        in or, \\nif you are an entity, your principal place of business is in the
        EEA or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside
        of the EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below
        or by using or distributing any portion or element of the Llama Materials,\\nyou
        agree to be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
        \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
        and royalty-free limited license under Meta\u2019s intellectual property or
        other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
        distribute, copy, create derivative works \\nof, and make modifications to
        the Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i.
        If you distribute or make available the Llama Materials (or any derivative
        works thereof), \\nor a product or service (including another AI model) that
        contains any of them, you shall (A) provide\\na copy of this Agreement with
        any such Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
        a related website, user interface, blogpost, about page, or product documentation.
        If you use the\\nLlama Materials or any outputs or results of the Llama Materials
        to create, train, fine tune, or\\notherwise improve an AI model, which is
        distributed or made available, you shall also include \u201CLlama\u201D\\nat
        the beginning of any such AI model name.\\n\\n        ii. If you receive Llama
        Materials, or any derivative works thereof, from a Licensee as part\\nof an
        integrated end user product, then Section 2 of this Agreement will not apply
        to you. \\n\\n        iii. You must retain in all copies of the Llama Materials
        that you distribute the \\nfollowing attribution notice within a \u201CNotice\u201D
        text file distributed as a part of such copies: \\n\u201CLlama 3.2 is licensed
        under the Llama 3.2 Community License, Copyright \xA9 Meta Platforms,\\nInc.
        All Rights Reserved.\u201D\\n\\n        iv. Your use of the Llama Materials
        must comply with applicable laws and regulations\\n(including trade compliance
        laws and regulations) and adhere to the Acceptable Use Policy for\\nthe Llama
        Materials (available at https://www.llama.com/llama3_2/use-policy), which
        is hereby \\nincorporated by reference into this Agreement.\\n  \\n2. Additional
        Commercial Terms. If, on the Llama 3.2 version release date, the monthly active
        users\\nof the products or services made available by or for Licensee, or
        Licensee\u2019s affiliates, \\nis greater than 700 million monthly active
        users in the preceding calendar month, you must request \\na license from
        Meta, which Meta may grant to you in its sole discretion, and you are not
        authorized to\\nexercise any of the rights under this Agreement unless or
        until Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer
        of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
        OUTPUT AND \\nRESULTS THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS,
        WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY
        KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF
        TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
        YOU ARE SOLELY RESPONSIBLE\\nFOR DETERMINING THE APPROPRIATENESS OF USING
        OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED\\nWITH
        YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\\n\\n4. Limitation
        of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY
        THEORY OF LIABILITY, \\nWHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,
        OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, \\nFOR ANY LOST PROFITS OR ANY
        INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES,
        EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
        ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n    a. No trademark
        licenses are granted under this Agreement, and in connection with the Llama
        Materials, \\nneither Meta nor Licensee may use any name or mark owned by
        or associated with the other or any of its affiliates, \\nexcept as required
        for reasonable and customary use in describing and redistributing the Llama
        Materials or as \\nset forth in this Section 5(a). Meta hereby grants you
        a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
        \\nto comply with the last sentence of Section 1.b.i. You will comply with
        Meta\u2019s brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
        All goodwill arising out of your use of the Mark \\nwill inure to the benefit
        of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
        derivatives made by or for Meta, with respect to any\\n    derivative works
        and modifications of the Llama Materials that are made by you, as between
        you and Meta,\\n    you are and will be the owner of such derivative works
        and modifications.\\n\\n    c. If you institute litigation or other proceedings
        against Meta or any entity (including a cross-claim or\\n    counterclaim
        in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results,
        or any portion\\n    of any of the foregoing, constitutes infringement of
        intellectual property or other rights owned or licensable\\n    by you, then
        any licenses granted to you under this Agreement shall terminate as of the
        date such litigation or\\n    claim is filed or instituted. You will indemnify
        and hold harmless Meta from and against any claim by any third\\n    party
        arising out of or related to your use or distribution of the Llama Materials.\\n\\n6.
        Term and Termination. The term of this Agreement will commence upon your acceptance
        of this Agreement or access\\nto the Llama Materials and will continue in
        full force and effect until terminated in accordance with the terms\\nand
        conditions herein. Meta may terminate this Agreement if you are in breach
        of any term or condition of this\\nAgreement. Upon termination of this Agreement,
        you shall delete and cease use of the Llama Materials. Sections 3,\\n4 and
        7 shall survive the termination of this Agreement. \\n\\n7. Governing Law
        and Jurisdiction. This Agreement will be governed and construed under the
        laws of the State of \\nCalifornia without regard to choice of law principles,
        and the UN Convention on Contracts for the International\\nSale of Goods does
        not apply to this Agreement. The courts of California shall have exclusive
        jurisdiction of\\nany dispute arising out of this Agreement.\\n**Llama 3.2**
        **Acceptable Use Policy**\\n\\nMeta is committed to promoting safe and fair
        use of its tools and features, including Llama 3.2. If you access or use Llama
        3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D). The
        most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
        Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You
        agree you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1.
        Violate the law or others\u2019 rights, including to:\\n    1. Engage in,
        promote, generate, contribute to, encourage, plan, incite, or further illegal
        or unlawful activity or content, such as:\\n        1. Violence or terrorism\\n
        \       2. Exploitation or harm to children, including the solicitation, creation,
        acquisition, or dissemination of child exploitative content or failure to
        report Child Sexual Abuse Material\\n        3. Human trafficking, exploitation,
        and sexual violence\\n        4. The illegal distribution of information or
        materials to minors, including obscene materials, or failure to employ legally
        required age-gating in connection with such information or materials.\\n        5.
        Sexual solicitation\\n        6. Any other criminal activity\\n    1. Engage
        in, promote, incite, or facilitate the harassment, abuse, threatening, or
        bullying of individuals or groups of individuals\\n    2. Engage in, promote,
        incite, or facilitate discrimination or other unlawful or harmful conduct
        in the provision of employment, employment benefits, credit, housing, other
        economic benefits, or other essential goods and services\\n    3. Engage in
        the unauthorized or unlicensed practice of any profession including, but not
        limited to, financial, legal, medical/health, or related professional practices\\n
        \   4. Collect, process, disclose, generate, or infer private or sensitive
        information about individuals, including information about individuals\u2019
        identity, health, or demographic information, unless you have obtained the
        right to do so in accordance with applicable law\\n    5. Engage in or facilitate
        any action or generate any content that infringes, misappropriates, or otherwise
        violates any third-party rights, including the outputs or results of any products
        or services using the Llama Materials\\n    6. Create, generate, or facilitate
        the creation of malicious code, malware, computer viruses or do anything else
        that could disable, overburden, interfere with or impair the proper working,
        integrity, operation or appearance of a website or computer system\\n    7.
        Engage in any action, or facilitate any action, to intentionally circumvent
        or remove usage restrictions or other safety measures, or to enable functionality
        disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in
        the planning or development of activities that present a risk of death or
        bodily harm to individuals, including use of Llama 3.2 related to the following:\\n
        \   8. Military, warfare, nuclear industries or applications, espionage, use
        for materials or activities that are subject to the International Traffic
        Arms Regulations (ITAR) maintained by the United States Department of State
        or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical
        Weapons Convention Implementation Act of 1997\\n    9. Guns and illegal weapons
        (including weapon development)\\n    10. Illegal drugs and regulated/controlled
        substances\\n    11. Operation of critical infrastructure, transportation
        technologies, or heavy machinery\\n    12. Self-harm or harm to others, including
        suicide, cutting, and eating disorders\\n    13. Any content intended to incite
        or promote violence, abuse, or any infliction of bodily harm to an individual\\n3.
        Intentionally deceive or mislead others, including use of Llama 3.2 related
        to the following:\\n    14. Generating, promoting, or furthering fraud or
        the creation or promotion of disinformation\\n    15. Generating, promoting,
        or furthering defamatory content, including the creation of defamatory statements,
        images, or other content\\n    16. Generating, promoting, or further distributing
        spam\\n    17. Impersonating another individual without consent, authorization,
        or legal right\\n    18. Representing that the use of Llama 3.2 or outputs
        are human-generated\\n    19. Generating or facilitating false online engagement,
        including fake reviews and other means of fake online engagement\\n4. Fail
        to appropriately disclose to end users any known dangers of your AI system\\n5.
        Interact with third party tools, models, or software designed to generate
        unlawful content or engage in unlawful or harmful conduct and/or represent
        that the outputs of such tools, models, or software are associated with Meta
        or Llama 3.2\\n\\nWith respect to any multimodal models included in Llama
        3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License
        Agreement are not being granted to you if you are an individual domiciled
        in, or a company with a principal place of business in, the European Union.
        This restriction does not apply to end users of a product or service that
        incorporates any such multimodal models.\\n\\nPlease report any violation
        of this Policy, software \u201Cbug,\u201D or other problems that could lead
        to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
        Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
        Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
        Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
        Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
        3.2: LlamaUseReport@meta.com\",\"modelfile\":\"# Modelfile generated by \\\"ollama
        show\\\"\\n# To build a new Modelfile based on this, replace FROM with:\\n#
        FROM llama3.2:3b\\n\\nFROM /Users/joaomoura/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff\\nTEMPLATE
        \\\"\\\"\\\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
        Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end
        }}\\n{{- if .Tools }}When you receive a tool call response, use the output
        to format an answer to the orginal user question.\\n\\nYou are a helpful assistant
        with tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range
        $i, $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
        if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
        if and $.Tools $last }}\\n\\nGiven the following functions, please respond
        with a JSON for a function call with its proper arguments that best answers
        the given prompt.\\n\\nRespond in the format {\\\"name\\\": function name,
        \\\"parameters\\\": dictionary of argument name and its value}. Do not use
        variables.\\n\\n{{ range $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
        else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last
        }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
        end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
        if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
        }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else
        }}\\n\\n{{ .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{
        end }}\\n{{- else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
        .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
        end }}\\n{{- end }}\\n{{- end }}\\\"\\\"\\\"\\nPARAMETER stop \\u003c|start_header_id|\\u003e\\nPARAMETER
        stop \\u003c|end_header_id|\\u003e\\nPARAMETER stop \\u003c|eot_id|\\u003e\\nLICENSE
        \\\"LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\\nLlama 3.2 Version Release Date:
        September 25, 2024\\n\\n\u201CAgreement\u201D means the terms and conditions
        for use, reproduction, distribution \\nand modification of the Llama Materials
        set forth herein.\\n\\n\u201CDocumentation\u201D means the specifications,
        manuals and documentation accompanying Llama 3.2\\ndistributed by Meta at
        https://llama.meta.com/doc/overview.\\n\\n\u201CLicensee\u201D or \u201Cyou\u201D
        means you, or your employer or any other person or entity (if you are \\nentering
        into this Agreement on such person or entity\u2019s behalf), of the age required
        under\\napplicable laws, rules or regulations to provide legal consent and
        that has legal authority\\nto bind your employer or such other person or entity
        if you are entering in this Agreement\\non their behalf.\\n\\n\u201CLlama
        3.2\u201D means the foundational large language models and software and algorithms,
        including\\nmachine-learning model code, trained model weights, inference-enabling
        code, training-enabling code,\\nfine-tuning enabling code and other elements
        of the foregoing distributed by Meta at \\nhttps://www.llama.com/llama-downloads.\\n\\n\u201CLlama
        Materials\u201D means, collectively, Meta\u2019s proprietary Llama 3.2 and
        Documentation (and \\nany portion thereof) made available under this Agreement.\\n\\n\u201CMeta\u201D
        or \u201Cwe\u201D means Meta Platforms Ireland Limited (if you are located
        in or, \\nif you are an entity, your principal place of business is in the
        EEA or Switzerland) \\nand Meta Platforms, Inc. (if you are located outside
        of the EEA or Switzerland). \\n\\n\\nBy clicking \u201CI Accept\u201D below
        or by using or distributing any portion or element of the Llama Materials,\\nyou
        agree to be bound by this Agreement.\\n\\n\\n1. License Rights and Redistribution.\\n\\n
        \   a. Grant of Rights. You are granted a non-exclusive, worldwide, \\nnon-transferable
        and royalty-free limited license under Meta\u2019s intellectual property or
        other rights \\nowned by Meta embodied in the Llama Materials to use, reproduce,
        distribute, copy, create derivative works \\nof, and make modifications to
        the Llama Materials.  \\n\\n    b. Redistribution and Use.  \\n\\n        i.
        If you distribute or make available the Llama Materials (or any derivative
        works thereof), \\nor a product or service (including another AI model) that
        contains any of them, you shall (A) provide\\na copy of this Agreement with
        any such Llama Materials; and (B) prominently display \u201CBuilt with Llama\u201D\\non
        a related website, user interface, blogpost, about page, or product documentation.
        If you use the\\nLlama Materials or any outputs or results of the Llama Materials
        to create, train, fine tune, or\\notherwise improve an AI model, which is
        distributed or made available, you shall also include \u201CLlama\u201D\\nat
        the beginning of any such AI model name.\\n\\n        ii. If you receive Llama
        Materials, or any derivative works thereof, from a Licensee as part\\nof an
        integrated end user product, then Section 2 of this Agreement will not apply
        to you. \\n\\n        iii. You must retain in all copies of the Llama Materials
        that you distribute the \\nfollowing attribution notice within a \u201CNotice\u201D
        text file distributed as a part of such copies: \\n\u201CLlama 3.2 is licensed
        under the Llama 3.2 Community License, Copyright \xA9 Meta Platforms,\\nInc.
        All Rights Reserved.\u201D\\n\\n        iv. Your use of the Llama Materials
        must comply with applicable laws and regulations\\n(including trade compliance
        laws and regulations) and adhere to the Acceptable Use Policy for\\nthe Llama
        Materials (available at https://www.llama.com/llama3_2/use-policy), which
        is hereby \\nincorporated by reference into this Agreement.\\n  \\n2. Additional
        Commercial Terms. If, on the Llama 3.2 version release date, the monthly active
        users\\nof the products or services made available by or for Licensee, or
        Licensee\u2019s affiliates, \\nis greater than 700 million monthly active
        users in the preceding calendar month, you must request \\na license from
        Meta, which Meta may grant to you in its sole discretion, and you are not
        authorized to\\nexercise any of the rights under this Agreement unless or
        until Meta otherwise expressly grants you such rights.\\n\\n3. Disclaimer
        of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
        OUTPUT AND \\nRESULTS THEREFROM ARE PROVIDED ON AN \u201CAS IS\u201D BASIS,
        WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\\nALL WARRANTIES OF ANY
        KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES\\nOF
        TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
        YOU ARE SOLELY RESPONSIBLE\\nFOR DETERMINING THE APPROPRIATENESS OF USING
        OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED\\nWITH
        YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\\n\\n4. Limitation
        of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY
        THEORY OF LIABILITY, \\nWHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY,
        OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, \\nFOR ANY LOST PROFITS OR ANY
        INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES,
        EVEN \\nIF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF
        ANY OF THE FOREGOING.\\n\\n5. Intellectual Property.\\n\\n    a. No trademark
        licenses are granted under this Agreement, and in connection with the Llama
        Materials, \\nneither Meta nor Licensee may use any name or mark owned by
        or associated with the other or any of its affiliates, \\nexcept as required
        for reasonable and customary use in describing and redistributing the Llama
        Materials or as \\nset forth in this Section 5(a). Meta hereby grants you
        a license to use \u201CLlama\u201D (the \u201CMark\u201D) solely as required
        \\nto comply with the last sentence of Section 1.b.i. You will comply with
        Meta\u2019s brand guidelines (currently accessible \\nat https://about.meta.com/brand/resources/meta/company-brand/).
        All goodwill arising out of your use of the Mark \\nwill inure to the benefit
        of Meta.\\n\\n    b. Subject to Meta\u2019s ownership of Llama Materials and
        derivatives made by or for Meta, with respect to any\\n    derivative works
        and modifications of the Llama Materials that are made by you, as between
        you and Meta,\\n    you are and will be the owner of such derivative works
        and modifications.\\n\\n    c. If you institute litigation or other proceedings
        against Meta or any entity (including a cross-claim or\\n    counterclaim
        in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results,
        or any portion\\n    of any of the foregoing, constitutes infringement of
        intellectual property or other rights owned or licensable\\n    by you, then
        any licenses granted to you under this Agreement shall terminate as of the
        date such litigation or\\n    claim is filed or instituted. You will indemnify
        and hold harmless Meta from and against any claim by any third\\n    party
        arising out of or related to your use or distribution of the Llama Materials.\\n\\n6.
        Term and Termination. The term of this Agreement will commence upon your acceptance
        of this Agreement or access\\nto the Llama Materials and will continue in
        full force and effect until terminated in accordance with the terms\\nand
        conditions herein. Meta may terminate this Agreement if you are in breach
        of any term or condition of this\\nAgreement. Upon termination of this Agreement,
        you shall delete and cease use of the Llama Materials. Sections 3,\\n4 and
        7 shall survive the termination of this Agreement. \\n\\n7. Governing Law
        and Jurisdiction. This Agreement will be governed and construed under the
        laws of the State of \\nCalifornia without regard to choice of law principles,
        and the UN Convention on Contracts for the International\\nSale of Goods does
        not apply to this Agreement. The courts of California shall have exclusive
        jurisdiction of\\nany dispute arising out of this Agreement.\\\"\\nLICENSE
        \\\"**Llama 3.2** **Acceptable Use Policy**\\n\\nMeta is committed to promoting
        safe and fair use of its tools and features, including Llama 3.2. If you access
        or use Llama 3.2, you agree to this Acceptable Use Policy (\u201C**Policy**\u201D).
        The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\\n\\n**Prohibited
        Uses**\\n\\nWe want everyone to use Llama 3.2 safely and responsibly. You
        agree you will not use, or allow others to use, Llama 3.2 to:\\n\\n\\n\\n1.
        Violate the law or others\u2019 rights, including to:\\n    1. Engage in,
        promote, generate, contribute to, encourage, plan, incite, or further illegal
        or unlawful activity or content, such as:\\n        1. Violence or terrorism\\n
        \       2. Exploitation or harm to children, including the solicitation, creation,
        acquisition, or dissemination of child exploitative content or failure to
        report Child Sexual Abuse Material\\n        3. Human trafficking, exploitation,
        and sexual violence\\n        4. The illegal distribution of information or
        materials to minors, including obscene materials, or failure to employ legally
        required age-gating in connection with such information or materials.\\n        5.
        Sexual solicitation\\n        6. Any other criminal activity\\n    1. Engage
        in, promote, incite, or facilitate the harassment, abuse, threatening, or
        bullying of individuals or groups of individuals\\n    2. Engage in, promote,
        incite, or facilitate discrimination or other unlawful or harmful conduct
        in the provision of employment, employment benefits, credit, housing, other
        economic benefits, or other essential goods and services\\n    3. Engage in
        the unauthorized or unlicensed practice of any profession including, but not
        limited to, financial, legal, medical/health, or related professional practices\\n
        \   4. Collect, process, disclose, generate, or infer private or sensitive
        information about individuals, including information about individuals\u2019
        identity, health, or demographic information, unless you have obtained the
        right to do so in accordance with applicable law\\n    5. Engage in or facilitate
        any action or generate any content that infringes, misappropriates, or otherwise
        violates any third-party rights, including the outputs or results of any products
        or services using the Llama Materials\\n    6. Create, generate, or facilitate
        the creation of malicious code, malware, computer viruses or do anything else
        that could disable, overburden, interfere with or impair the proper working,
        integrity, operation or appearance of a website or computer system\\n    7.
        Engage in any action, or facilitate any action, to intentionally circumvent
        or remove usage restrictions or other safety measures, or to enable functionality
        disabled by Meta\\n2. Engage in, promote, incite, facilitate, or assist in
        the planning or development of activities that present a risk of death or
        bodily harm to individuals, including use of Llama 3.2 related to the following:\\n
        \   8. Military, warfare, nuclear industries or applications, espionage, use
        for materials or activities that are subject to the International Traffic
        Arms Regulations (ITAR) maintained by the United States Department of State
        or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical
        Weapons Convention Implementation Act of 1997\\n    9. Guns and illegal weapons
        (including weapon development)\\n    10. Illegal drugs and regulated/controlled
        substances\\n    11. Operation of critical infrastructure, transportation
        technologies, or heavy machinery\\n    12. Self-harm or harm to others, including
        suicide, cutting, and eating disorders\\n    13. Any content intended to incite
        or promote violence, abuse, or any infliction of bodily harm to an individual\\n3.
        Intentionally deceive or mislead others, including use of Llama 3.2 related
        to the following:\\n    14. Generating, promoting, or furthering fraud or
        the creation or promotion of disinformation\\n    15. Generating, promoting,
        or furthering defamatory content, including the creation of defamatory statements,
        images, or other content\\n    16. Generating, promoting, or further distributing
        spam\\n    17. Impersonating another individual without consent, authorization,
        or legal right\\n    18. Representing that the use of Llama 3.2 or outputs
        are human-generated\\n    19. Generating or facilitating false online engagement,
        including fake reviews and other means of fake online engagement\\n4. Fail
        to appropriately disclose to end users any known dangers of your AI system\\n5.
        Interact with third party tools, models, or software designed to generate
        unlawful content or engage in unlawful or harmful conduct and/or represent
        that the outputs of such tools, models, or software are associated with Meta
        or Llama 3.2\\n\\nWith respect to any multimodal models included in Llama
        3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License
        Agreement are not being granted to you if you are an individual domiciled
        in, or a company with a principal place of business in, the European Union.
        This restriction does not apply to end users of a product or service that
        incorporates any such multimodal models.\\n\\nPlease report any violation
        of this Policy, software \u201Cbug,\u201D or other problems that could lead
        to a violation of this Policy through one of the following means:\\n\\n\\n\\n*
        Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues\\u0026h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\\n*
        Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\\n*
        Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\\n*
        Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama
        3.2: LlamaUseReport@meta.com\\\"\\n\",\"parameters\":\"stop                           \\\"\\u003c|start_header_id|\\u003e\\\"\\nstop
        \                          \\\"\\u003c|end_header_id|\\u003e\\\"\\nstop                           \\\"\\u003c|eot_id|\\u003e\\\"\",\"template\":\"\\u003c|start_header_id|\\u003esystem\\u003c|end_header_id|\\u003e\\n\\nCutting
        Knowledge Date: December 2023\\n\\n{{ if .System }}{{ .System }}\\n{{- end
        }}\\n{{- if .Tools }}When you receive a tool call response, use the output
        to format an answer to the orginal user question.\\n\\nYou are a helpful assistant
        with tool calling capabilities.\\n{{- end }}\\u003c|eot_id|\\u003e\\n{{- range
        $i, $_ := .Messages }}\\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\\n{{-
        if eq .Role \\\"user\\\" }}\\u003c|start_header_id|\\u003euser\\u003c|end_header_id|\\u003e\\n{{-
        if and $.Tools $last }}\\n\\nGiven the following functions, please respond
        with a JSON for a function call with its proper arguments that best answers
        the given prompt.\\n\\nRespond in the format {\\\"name\\\": function name,
        \\\"parameters\\\": dictionary of argument name and its value}. Do not use
        variables.\\n\\n{{ range $.Tools }}\\n{{- . }}\\n{{ end }}\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{-
        else }}\\n\\n{{ .Content }}\\u003c|eot_id|\\u003e\\n{{- end }}{{ if $last
        }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
        end }}\\n{{- else if eq .Role \\\"assistant\\\" }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n{{-
        if .ToolCalls }}\\n{{ range .ToolCalls }}\\n{\\\"name\\\": \\\"{{ .Function.Name
        }}\\\", \\\"parameters\\\": {{ .Function.Arguments }}}{{ end }}\\n{{- else
        }}\\n\\n{{ .Content }}\\n{{- end }}{{ if not $last }}\\u003c|eot_id|\\u003e{{
        end }}\\n{{- else if eq .Role \\\"tool\\\" }}\\u003c|start_header_id|\\u003eipython\\u003c|end_header_id|\\u003e\\n\\n{{
        .Content }}\\u003c|eot_id|\\u003e{{ if $last }}\\u003c|start_header_id|\\u003eassistant\\u003c|end_header_id|\\u003e\\n\\n{{
        end }}\\n{{- end }}\\n{{- end }}\",\"details\":{\"parent_model\":\"\",\"format\":\"gguf\",\"family\":\"llama\",\"families\":[\"llama\"],\"parameter_size\":\"3.2B\",\"quantization_level\":\"Q4_K_M\"},\"model_info\":{\"general.architecture\":\"llama\",\"general.basename\":\"Llama-3.2\",\"general.file_type\":15,\"general.finetune\":\"Instruct\",\"general.languages\":null,\"general.parameter_count\":3212749888,\"general.quantization_version\":2,\"general.size_label\":\"3B\",\"general.tags\":null,\"general.type\":\"model\",\"llama.attention.head_count\":24,\"llama.attention.head_count_kv\":8,\"llama.attention.key_length\":128,\"llama.attention.layer_norm_rms_epsilon\":0.00001,\"llama.attention.value_length\":128,\"llama.block_count\":28,\"llama.context_length\":131072,\"llama.embedding_length\":3072,\"llama.feed_forward_length\":8192,\"llama.rope.dimension_count\":128,\"llama.rope.freq_base\":500000,\"llama.vocab_size\":128256,\"tokenizer.ggml.bos_token_id\":128000,\"tokenizer.ggml.eos_token_id\":128009,\"tokenizer.ggml.merges\":null,\"tokenizer.ggml.model\":\"gpt2\",\"tokenizer.ggml.pre\":\"llama-bpe\",\"tokenizer.ggml.token_type\":null,\"tokenizer.ggml.tokens\":null},\"tensors\":[{\"name\":\"rope_freqs.weight\",\"type\":\"F32\",\"shape\":[64]},{\"name\":\"token_embd.weight\",\"type\":\"Q6_K\",\"shape\":[3072,128256]},{\"name\":\"blk.0.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.0.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.0.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.0.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.0.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.0.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.0.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.0.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.0.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.1.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.1.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.1.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.1.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.1.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.1.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.1.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.1.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.1.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.10.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.10.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.10.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.10.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.10.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.10.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.10.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.10.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.10.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.11.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.11.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.11.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.11.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.11.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.11.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.11.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.11.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.11.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.12.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.12.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.12.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.12.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.12.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.12.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.12.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.12.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.12.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.13.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.13.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.13.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.13.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.13.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.13.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.13.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.13.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.13.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.14.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.14.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.14.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.14.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.14.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.14.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.14.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.14.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.14.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.15.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.15.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.15.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.15.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.15.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.15.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.15.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.15.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.15.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.16.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.16.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.16.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.16.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.16.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.16.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.16.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.16.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.16.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.17.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.17.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.17.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.17.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.17.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.17.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.17.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.17.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.17.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.18.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.18.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.18.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.18.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.18.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.18.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.18.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.18.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.18.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.19.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.19.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.19.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.19.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.19.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.19.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.19.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.19.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.19.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.2.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.2.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.2.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.2.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.2.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.2.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.2.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.2.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.2.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.20.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.20.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.20.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.20.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.20.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.20.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.3.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.3.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.3.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.3.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.3.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.3.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.3.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.3.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.3.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.4.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.4.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.4.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.4.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.4.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.4.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.4.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.4.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.4.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.5.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.5.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.5.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.5.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.5.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.5.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.5.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.5.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.5.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.6.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.6.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.6.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.6.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.6.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.6.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.6.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.6.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.6.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.7.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.7.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.7.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.7.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.7.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.7.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.7.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.7.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.7.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.8.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.8.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.8.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.8.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.8.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.8.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.8.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.8.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.8.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.9.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.9.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.9.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.9.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.9.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.9.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.9.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.9.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.9.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.20.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.20.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.20.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.21.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.21.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.21.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.21.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.21.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.21.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.21.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.21.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.21.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.22.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.22.ffn_down.weight\",\"type\":\"Q4_K\",\"shape\":[8192,3072]},{\"name\":\"blk.22.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.22.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.22.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.22.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.22.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.22.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.22.attn_v.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.23.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.23.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.23.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.23.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.23.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.23.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.23.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.23.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.23.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.24.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.24.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.24.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.24.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.24.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.24.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.24.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.24.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.24.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.25.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.25.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.25.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.25.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.25.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.25.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.25.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.25.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.25.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.26.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.26.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.26.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.26.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.26.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.26.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.26.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.26.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.26.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"blk.27.attn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.27.ffn_down.weight\",\"type\":\"Q6_K\",\"shape\":[8192,3072]},{\"name\":\"blk.27.ffn_gate.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.27.ffn_up.weight\",\"type\":\"Q4_K\",\"shape\":[3072,8192]},{\"name\":\"blk.27.ffn_norm.weight\",\"type\":\"F32\",\"shape\":[3072]},{\"name\":\"blk.27.attn_k.weight\",\"type\":\"Q4_K\",\"shape\":[3072,1024]},{\"name\":\"blk.27.attn_output.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.27.attn_q.weight\",\"type\":\"Q4_K\",\"shape\":[3072,3072]},{\"name\":\"blk.27.attn_v.weight\",\"type\":\"Q6_K\",\"shape\":[3072,1024]},{\"name\":\"output_norm.weight\",\"type\":\"F32\",\"shape\":[3072]}],\"capabilities\":[\"completion\",\"tools\"],\"modified_at\":\"2025-02-20T18:55:09.150577031-08:00\"}"
    headers:
      Content-Type:
      - application/json; charset=utf-8
      Date:
      - Tue, 27 May 2025 08:12:39 GMT
      Transfer-Encoding:
      - chunked
    status:
      code: 200
      message: OK
version: 1