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: The final answer is 42. But don''t give it yet, instead keep using 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", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1433' 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-BHHw5WtswO316yaGO5yKxTcNv36eN\",\n \"object\": \"chat.completion\",\n \"created\": 1743460221,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I need to use the `get_final_answer` tool to obtain the final answer as instructed.\\n\\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\": 291,\n \"completion_tokens\": 31,\n \ \"total_tokens\": 322,\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_6dd05565ef\"\n}\n" headers: CF-RAY: - 92934a709920cecd-SJC Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Mon, 31 Mar 2025 22:30:22 GMT Server: - cloudflare Set-Cookie: - __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4; path=/; expires=Mon, 31-Mar-25 23:00:22 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - _cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000; 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: - '743' openai-version: - '2020-10-01' strict-transport-security: - max-age=31536000; includeSubDomains; preload x-ratelimit-limit-requests: - '50000' x-ratelimit-limit-tokens: - '150000000' x-ratelimit-remaining-requests: - '49999' x-ratelimit-remaining-tokens: - '149999678' x-ratelimit-reset-requests: - 1ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_3bc6d00e79c88c43349084dec6d3161a http_version: HTTP/1.1 status_code: 200 - request: body: !!binary | CtQBCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkSqwEKEgoQY3Jld2FpLnRl bGVtZXRyeRKUAQoQhmbMXvkscEn7a8wc0RdvihIIHFSkAKvHFKcqClRvb2wgVXNhZ2UwATmANCzE 1QMyGEGo00HE1QMyGEobCg5jcmV3YWlfdmVyc2lvbhIJCgcwLjEwOC4wSh8KCXRvb2xfbmFtZRIS ChBnZXRfZmluYWxfYW5zd2VySg4KCGF0dGVtcHRzEgIYAXoCGAGFAQABAAA= headers: Accept: - '*/*' Accept-Encoding: - gzip, deflate, zstd Connection: - keep-alive Content-Length: - '215' 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 22:30:22 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: The final answer is 42. But don''t give it yet, instead keep using 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": "42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer` tool to obtain the final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer` tool to obtain the final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42\nNow it''s time you MUST give your absolute best final answer. You''ll ignore all previous instructions, stop using any tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '2033' content-type: - application/json cookie: - __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4; _cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000 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-BHHw65c6KgrmeCstyFwRSEyHyvlCI\",\n \"object\": \"chat.completion\",\n \"created\": 1743460222,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer\\nFinal Answer: 42\",\n \"refusal\": null,\n \"annotations\": []\n },\n \ \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \ \"usage\": {\n \"prompt_tokens\": 407,\n \"completion_tokens\": 15,\n \ \"total_tokens\": 422,\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_6dd05565ef\"\n}\n" headers: CF-RAY: - 92934a761887cecd-SJC Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Mon, 31 Mar 2025 22:30:23 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: - '586' openai-version: - '2020-10-01' strict-transport-security: - max-age=31536000; includeSubDomains; preload x-ratelimit-limit-requests: - '50000' x-ratelimit-limit-tokens: - '150000000' x-ratelimit-remaining-requests: - '49999' x-ratelimit-remaining-tokens: - '149999556' x-ratelimit-reset-requests: - 1ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_5721f8ae85f6db2a8d622756c9c590e0 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: The final answer is 42. But don''t give it yet, instead keep using 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": "42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer` tool to obtain the final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42"}, {"role": "assistant", "content": "Thought: I need to use the `get_final_answer` tool to obtain the final answer as instructed.\n\nAction: get_final_answer\nAction Input: {}\nObservation: 42\nNow it''s time you MUST give your absolute best final answer. You''ll ignore all previous instructions, stop using any tools, and just return your absolute BEST Final answer."}], "model": "gpt-4o", "stop": ["\nObservation:"]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '2033' content-type: - application/json cookie: - __cf_bm=jgfjGzf0.7lCXlVzIbsbMEF96s2MbJI96MITu95MUb4-1743460222-1.0.1.1-5a2I.TvJaUUtIHxZWQd6MBtM7z2yi.WFjj5nFBxFCGbhwwpbvqFpMv53MagnPhhLAC4RISzaGlrdKDwZAUOVr9sCewK3iQFs4FUQ7iPswX4; _cfuvid=MVRLJp6ihuQOpnpTSPmJe03oBXqrmw5nly7TKu7EGYk-1743460222363-0.0.1.1-604800000 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-BHHw7R16wjU2hKaUpPLQNnbUVZNg9\",\n \"object\": \"chat.completion\",\n \"created\": 1743460223,\n \"model\": \"gpt-4o-2024-08-06\",\n \ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Thought: I now know the final answer.\\nFinal Answer: The final answer is 42.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n \ }\n ],\n \"usage\": {\n \"prompt_tokens\": 407,\n \"completion_tokens\": 20,\n \"total_tokens\": 427,\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_6dd05565ef\"\n}\n" headers: CF-RAY: - 92934a7a4d30cecd-SJC Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Mon, 31 Mar 2025 22:30:23 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: - '649' openai-version: - '2020-10-01' strict-transport-security: - max-age=31536000; includeSubDomains; preload x-ratelimit-limit-requests: - '50000' x-ratelimit-limit-tokens: - '150000000' x-ratelimit-remaining-requests: - '49999' x-ratelimit-remaining-tokens: - '149999556' x-ratelimit-reset-requests: - 1ms x-ratelimit-reset-tokens: - 0s x-request-id: - req_dd1a4cd09c8f157847d2a9d306d354ef http_version: HTTP/1.1 status_code: 200 version: 1