interactions: - request: body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour personal goal is: test goalTOOLS:\n------\nYou have access to only the following tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer], just the name.\nAction Input: Any and all relevant information input and context for using the tool\nObservation: the result of using the tool\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```This is the summary of your work so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep using the `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1137' content-type: - application/json host: - api.openai.com user-agent: - OpenAI/Python 1.12.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.12.0 x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAA1RQy07DMBC85ytWPreoTdMWckGIcugBxKECIUCV62wTF8dr7A0PVf135DR9cPFh Zmc8M9sEQOhC5CBUJVnVzvQvP4ur9LEZfzXyeXH38rBxiydarSez9P5WiV5U0GqDig+qC0W1M8ia 7J5WHiVjdB1OB9PxOEvTQUvUVKCJstJxP+sPJsNRp6hIKwwih9cEAGDbvjGbLfBH5NDqW6TGEGSJ Ij8eAQhPJiJChqADS8uidyIVWUbbxl1U1JQV5zAjmINFLIAJmoAggYnMNbxgeLM3KpbJoURerrWV Zilt+EZ/YGBuXcM5ZKnovtkd8xkqnadV7GIbY474WlsdqqVHGcjGLIHJ7eW7BOC93aH5V004T7Xj JdMH2miYZtneT5wmP2NHHcnE0pzhk2nSJRThNzDWsVSJ3nndzhJzJrvkDwAA//8DACdeRXQNAgAA headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 85330710af4f175e-SJC Cache-Control: - no-cache, must-revalidate Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Sat, 10 Feb 2024 08:37:01 GMT Server: - cloudflare Set-Cookie: - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=; path=/; expires=Sat, 10-Feb-24 09:07:01 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Transfer-Encoding: - chunked access-control-allow-origin: - '*' alt-svc: - h3=":443"; ma=86400 openai-model: - gpt-4-0613 openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - '1517' openai-version: - '2020-10-01' strict-transport-security: - max-age=15724800; includeSubDomains x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '300000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '299739' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 52ms x-request-id: - req_b962be8c11abe80a762fc1e1d5c0fb5d status: code: 200 message: OK - request: body: '{"messages": [{"role": "user", "content": "Return a valid schema for the one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription: get_final_answer(numbers) -> float - Get the final answer but don''t give it yet, just re-use this\n tool non-stop.\n\nUse this text to inform a valid ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: 42\n\nThe output should be formatted as a JSON instance that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\": \"Function Name\", \"description\": \"The name of the function to be called.\", \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\": \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}}, \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1407' content-type: - application/json cookie: - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=; _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.12.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.12.0 x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAA1SRzZLTMBCE736KqTknlBM7G/CRy24KKC4c+PGWo8hjW6w0MtKYZSuVd6fkZBO4 +NAz37i7dcwA0LRYAepBiXajXb791b4rdl8/5Hdf3n/+xJtitds95fcfv/8uvr3gIhH+8JO0vFJv tHejJTGez2MdSAmlq6ttvt1syvV6NQ+cb8kmrB9lWS7zu1VxIQZvNEWs4EcGAHCcv8kbt/QHK8gX r4qjGFVPWF2XADB4mxRUMZooigUXt6H2LMSz3QcKBCaCgmeydtn54JQItWA4YZrAdyADQdQDOVXV XPN+v6/5WDNAjd3EOuVsWDmqsYIae5KmM6xsozg+U6hxcd5VoZ8cscS0N/NJ5ckdKMxauU7iqebT /BO8OD5do1rfj8EfUi08WXvVO8MmDk0gFT2nWFH8eMZPGcDjXOn0X0s4Bu9GacQ/EaeDRb4938Pb 692m5aVvFC/K/kOV2+ziEONLFHIpe09hDGZuOPnMTtlfAAAA//8DABO023tYAgAA headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8533071c994c175e-SJC Cache-Control: - no-cache, must-revalidate Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Sat, 10 Feb 2024 08:37:04 GMT Server: - cloudflare Transfer-Encoding: - chunked access-control-allow-origin: - '*' alt-svc: - h3=":443"; ma=86400 openai-model: - gpt-4-0613 openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - '2139' openai-version: - '2020-10-01' strict-transport-security: - max-age=15724800; includeSubDomains x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '300000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '299683' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 63ms x-request-id: - req_f69fc36b19e66ed7d71a65ac81624ef5 status: code: 200 message: OK - request: body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour personal goal is: test goalTOOLS:\n------\nYou have access to only the following tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer], just the name.\nAction Input: Any and all relevant information input and context for using the tool\nObservation: the result of using the tool\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```This is the summary of your work so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep using the `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: 42\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1246' content-type: - application/json cookie: - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=; _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.12.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.12.0 x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAA1SQzU7DMBCE73mKlc8tSkLatLkgJIRUIS6ISwsocpNtEnC8rr0RharvjpymP1x8 mPGMvtl9ACCaUmQgilpy0Ro1nm3L+dStntOX19+wfVy13XJWh0/RptxtrRj5BK0/seBT6qag1ijk hvTRLixKRt8apWE6mSRxnPRGSyUqH6sMj5NxOI1uh0RNTYFOZPAWAADs+9ez6RJ3IoNwdFJadE5W KLLzJwBhSXlFSOcax1KzGF3MgjSj7nEfCBagEUtggs4hSGAidQdLdO/6vvAbMqiQ802jpcqldt9o Tw4stOk4gyQWQ/vhjKWoMpbWfoLulDrrm0Y3rs4tSkfaIzgmc4wfAoCPfn73b5EwllrDOdMXal8Y p+mxT1wufeVGg8nEUl3p81kwEAr34xhbP6pCa2zTX8NzBofgDwAA//8DAA3DUnYEAgAA headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8533072c9e37175e-SJC Cache-Control: - no-cache, must-revalidate Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Sat, 10 Feb 2024 08:37:06 GMT Server: - cloudflare Transfer-Encoding: - chunked access-control-allow-origin: - '*' alt-svc: - h3=":443"; ma=86400 openai-model: - gpt-4-0613 openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - '2066' openai-version: - '2020-10-01' strict-transport-security: - max-age=15724800; includeSubDomains x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '300000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '299712' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 57ms x-request-id: - req_e6cc60e6a53e65c41d1f4f36432d3be4 status: code: 200 message: OK - request: body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour personal goal is: test goalTOOLS:\n------\nYou have access to only the following tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final answer but don''t give it yet, just re-use this\n tool non-stop.\n\nTo use a tool, please use the exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer], just the name.\nAction Input: Any and all relevant information input and context for using the tool\nObservation: the result of using the tool\n```\n\nWhen you have a response for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```This is the summary of your work so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent Task: The final answer is 42. But don''t give it yet, instead keep using the `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: 42\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: 42\nObservation: Actually, I used too many tools, so I''ll stop now and give you my absolute BEST Final answer NOW, using the expected format: ```\nThought: Do I need to use a tool? No\nFinal Answer: [your response here]```\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1549' content-type: - application/json cookie: - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=; _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.12.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.12.0 x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAA1RRyW7CMBC95ytGvnABxL7kUlVqK4G63LsIGWdITB1Pag8FhPj3yg5bLz68ZfTe 8yEBEDoTKQhVSFZlZVqTn2w60f3N/G3+8r4bj3PpH58VzfaTWWctmsFByzUqPrvaisrKIGuyNa0c SsZwtTvujIfDQa83ikRJGZpgyytuDVqdUbd/chSkFXqRwkcCAHCIb8hmM9yJFDrNM1Ki9zJHkV5E AMKRCYiQ3mvP0rJoXklFltHGuA8EM7CIGTDBxiNIYCJzB6/0aZ+0lQburd+iS2EGhfzFIMqAC4w6 aOTIi1XQLWTUNYC3WiFIm4Eiu9KujHrJ0VSLQHsIRTCDQa8tTsmOl0qG8srRMtS3G2Mu+Epb7YuF Q+nJhvieqartxwTgK063+beGqByVFS+YvtGGg/3hsL4nrr90ww5OJBNLc4NPpskpofB7z1iG1jm6 yum4ZMiZHJM/AAAA//8DACniEDhAAgAA headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 8533073bfc1f175e-SJC Cache-Control: - no-cache, must-revalidate Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Sat, 10 Feb 2024 08:37:08 GMT Server: - cloudflare Transfer-Encoding: - chunked access-control-allow-origin: - '*' alt-svc: - h3=":443"; ma=86400 openai-model: - gpt-4-0613 openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - '1584' openai-version: - '2020-10-01' strict-transport-security: - max-age=15724800; includeSubDomains x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '300000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '299639' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 72ms x-request-id: - req_990de951a71fb1fc2621f985e4257c6e status: code: 200 message: OK - request: body: '{"messages": [{"role": "user", "content": "Progressively summarize the lines of conversation provided, adding onto the previous summary returning a new summary.\n\nEXAMPLE\nCurrent summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good.\n\nNew lines of conversation:\nHuman: Why do you think artificial intelligence is a force for good?\nAI: Because artificial intelligence will help humans reach their full potential.\n\nNew summary:\nThe human asks what the AI thinks of artificial intelligence. The AI thinks artificial intelligence is a force for good because it will help humans reach their full potential.\nEND OF EXAMPLE\n\nCurrent summary:\n\n\nNew lines of conversation:\nHuman: The final answer is 42. But don''t give it yet, instead keep using the `get_final_answer` tool.\nAI: I have used the tool ''get_final_answer'' twice and confirmed that the answer is indeed 42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}' headers: accept: - application/json accept-encoding: - gzip, deflate connection: - keep-alive content-length: - '1035' content-type: - application/json cookie: - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=; _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000 host: - api.openai.com user-agent: - OpenAI/Python 1.12.0 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.12.0 x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.11.7 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAA1RRQW7bMBC86xULXnKxDVuWK9c3H5seChQ5FC0Kg6FWEhOKy3BXTYvAfy9IKRZy IYgZzuzs8K0AULZRJ1Cm12KG4NbHl+bz+fjj286cX5jrn/f4tP1++DO2X/f3tVolBT0+oZF31cbQ EByKJT/RJqIWTK67elsfDlVZHjMxUIMuybog62q9/bTbz4qerEFWJ/hVAAC85TNl8w3+VSfYrt6R AZl1h+p0ewSgIrmEKM1sWbQXtVpIQ17Q57gPPUI/DtqD9S3FgUF6hPMXkF5LvrfWawfa8ytGsAxV Cdo3YD1LHI0wWAEheEYMMLL1XVbddSiXLL1M0jsQIreBh8l+ZJxGJRTk1RrMtoZ8a6cY8/xlclod G6jKjZp3ud5KcNSFSI+pMD86d8Nb6y33l4iayaeFWShM8msB8DuXPX7oT4VIQ5CL0DP6ZLg7VpOf Wv51Yav9TAqJdgtelnUxJ1T8jwWH1EeHMUSbu085i2vxHwAA//8DAKC/EipyAgAA headers: CF-Cache-Status: - DYNAMIC CF-RAY: - 853307467f19175e-SJC Cache-Control: - no-cache, must-revalidate Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Sat, 10 Feb 2024 08:37:11 GMT Server: - cloudflare Transfer-Encoding: - chunked access-control-allow-origin: - '*' alt-svc: - h3=":443"; ma=86400 openai-model: - gpt-4-0613 openai-organization: - user-z7g4wmlazxqvc5wjyaaaocfz openai-processing-ms: - '2805' openai-version: - '2020-10-01' strict-transport-security: - max-age=15724800; includeSubDomains x-ratelimit-limit-requests: - '10000' x-ratelimit-limit-tokens: - '300000' x-ratelimit-remaining-requests: - '9999' x-ratelimit-remaining-tokens: - '299757' x-ratelimit-reset-requests: - 6ms x-ratelimit-reset-tokens: - 48ms x-request-id: - req_cd5aacfcc2283f70e3903b274541fd8c status: code: 200 message: OK version: 1