interactions: - request: body: '{"trace_id": "99e7c20c-e861-4933-a4cb-d7a2f5949fc4", "execution_type": "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null, "crew_name": "crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level": "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count": 0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-05T12:57:54.329170+00:00"}, "ephemeral_trace_id": "99e7c20c-e861-4933-a4cb-d7a2f5949fc4"}' headers: Accept: - '*/*' Accept-Encoding: - gzip, deflate, zstd Connection: - keep-alive Content-Length: - '488' Content-Type: - application/json User-Agent: - CrewAI-CLI/1.3.0 X-Crewai-Version: - 1.3.0 method: POST uri: https://app.crewai.com/crewai_plus/api/v1/tracing/ephemeral/batches response: body: string: '{"id":"da3e20ff-96b0-4815-b356-a25fcfb43292","ephemeral_trace_id":"99e7c20c-e861-4933-a4cb-d7a2f5949fc4","execution_type":"crew","crew_name":"crew","flow_name":null,"status":"running","duration_ms":null,"crewai_version":"1.3.0","total_events":0,"execution_context":{"crew_fingerprint":null,"crew_name":"crew","flow_name":null,"crewai_version":"1.3.0","privacy_level":"standard"},"created_at":"2025-11-05T12:57:54.615Z","updated_at":"2025-11-05T12:57:54.615Z","access_code":"TRACE-9bbeba92f1","user_identifier":null}' headers: Connection: - keep-alive Content-Length: - '515' Content-Type: - application/json; charset=utf-8 Date: - Wed, 05 Nov 2025 12:57:54 GMT cache-control: - no-store content-security-policy: - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/ https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net https://js.hscollectedforms.net https://js.usemessages.com https://snap.licdn.com https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data: *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com; connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/* https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com https://api.hubspot.com https://forms.hscollectedforms.net https://api.hubapi.com https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509 https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self'' *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com https://drive.google.com https://slides.google.com https://accounts.google.com https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/ https://www.youtube.com https://share.descript.com' etag: - W/"ce1f6a4680ba6e63a8bfb949f2a8d5ff" expires: - '0' permissions-policy: - camera=(), microphone=(self), geolocation=() pragma: - no-cache referrer-policy: - strict-origin-when-cross-origin strict-transport-security: - max-age=63072000; includeSubDomains vary: - Accept x-content-type-options: - nosniff x-frame-options: - SAMEORIGIN x-permitted-cross-domain-policies: - none x-request-id: - 6d1d9b58-75ce-46a8-8f6c-9599dff3535b x-runtime: - '0.077951' x-xss-protection: - 1; mode=block status: code: 201 message: Created - 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: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\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 [learn_about_ai], 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: Write and then review an small paragraph on AI until it''s AMAZING\n\nThis is the expected criteria for your final answer: The final paragraph.\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"}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1356' content-type: - application/json host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - '600' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//nFbdjltFDL7fp7DOTUHKRku73S17F6pWioRAgoL42Sp15jjnmM6xh/lJ NlSVeAiekCdBnpNszkJRETf5GY89n+3vG8+7M4CG2+YGGtdjdkPw589//OGr58PLb3a7iy9f3F1+ 99M3T574b18Evfz+7lkzMw9d/0IuH73mTofgKbPKaHaRMJNF/ez66vGTy+vL68tqGLQlb25dyOeX ev744vHl+cWz84urg2Ov7Cg1N/DzGQDAu/ppEKWlu+YGLmbHlYFSwo6am/tNAE1UbysNpsQpo+Rm djI6lUxSUb958+ZWXvVauj7fwCuFXeRMgAI44G8sHQSM2EUMPajAYjmDJQhRC1mhw9xThJYysqcW WDYaB7T0AddaMuSeIJVaozksH3kPJVFdzaoecIvsce3tL3jCKDBopIPzYjm/lYWzcDejdVUNK+Tj OiwllHwD797fytfrRHGL4/ZFzLxhx+hhKZm8547EEXyyWH4KnEZgPBQ/otUN9GVAAZ5uDlEdpUQJ 1nsY0PUslGZAKZBF9nuwfpdMEdI+ZRrSHF71lKaeLM6Xlkb8LN0MImHS8WeIuvY0nCf123GBoqNg kGaA0oJH6Qp2BEVaitbIlqWbw2JpSSAMxWduOTkOngXjHpLjin3HuYdEW4roAUOIiq439Km4HjAd 85kAa4nC5K+dL1TMXyjvNL5NM9j1bO6x+hkWwHaL4mggyZYtDCh7YGlLypEpGdZHyRB4drXYCSJK R7CJOgCWrINJBFxJWQcrJcUtu0qJQ+wWoq41s0szyBElGc3s7F53sKPatIguj0lncr2o125fuwGU e3bogYcJBEsuqKmAR5O5qwANwevekqlJqnRqB1mJS0rVlaWyZ7G07g9FOO/nt1KFdPi619MSRHfQ 49ZUsDE+WuCpTPLHFTe/lZcs6GEhaUfxI9yOFCKl2gxDuYkqmSlOGS46qmQGR0IBjlKthUzkjpo4 lbIWzGknnHl7z+/KxWUGEhMCVsJbnJa25DXUMurmKA5wGKrYdWNEPzYxY3prboZhH6xVfg+Rfi0c 6QOqPDH4g5KqjX0oqzl8sYceo4yI/yfzF8tTOZhSpUekrfpi1eLauS1G1pLASqgx/fn7H5XkPaHP vTMPC105r7WOWWHDYhyvFrL6Z2Sxyh3vkgcCsxiiRlW/B5IexdnBGijWnqIHOhDNVZQyURbdBYr1 ekiwLiPD0Se1gg0hWyAXSyXWlPAYtRg409EYcaKSgxpa7jjbTdPRHBZpVIdklmKUULBCbWkGnNNE d1khUuoxEGiJsNPorXsH/q4190B3OaLGdrzdNASN2TR3TC5E3VR4rkfvSTpKoxqnAy/SpiS0eSvF +4kBRTSPV4KN2tcHy/v74eq1Mzalv7k2GxZO/Wokng3SlDU01fr+DOB1HeLlwVxuxiqvsr6letzj 66sxXnN6Nkysnx9GfJM1oz8Znl4d3R4EXI1jOE3eAY2zO789uZ4eDVha1onhbJL2P+F8KPa95v5L +JPB2XyjdhUitewepnzaFsmeDP+27b7MFXBzGBgru+esFS1tsPjxxdOMd89qw9JRDJHHZ88mrK6e Pr26bJ+t8Wlz9v7sLwAAAP//AwB2mKgL/wkAAA== headers: CF-RAY: - 999c85037ab70f3e-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:01 GMT Server: - cloudflare Set-Cookie: - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 13:28:01 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '6669' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '6691' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29688' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 624ms x-request-id: - req_REDACTED status: code: 200 message: OK - request: body: '{"messages":[{"role":"user","content":"SYSTEM: The schema should have the following structure, only two keys:\n- tool_name: str\n- arguments: dict (always a dictionary, with all arguments being passed)\n\nExample:\n{\"tool_name\": \"tool name\", \"arguments\": {\"arg_name1\": \"value\", \"arg_name2\": 2}}\n\nUSER: Only tools available:\n###\nTool Name: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid output schema:\n\n### TEXT \n```\nThought: To write an amazing paragraph on AI, I need to gather detailed information about the subject. I''ll use the tool available to learn more about AI.\nAction: learn_about_ai\nAction Input: {}"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"InstructorToolCalling"}},"tools":[{"type":"function","function":{"name":"InstructorToolCalling","description":"Correctly extracted `InstructorToolCalling` with all the required parameters with correct types","parameters":{"properties":{"tool_name":{"description":"The name of the tool to be called.","title":"Tool Name","type":"string"},"arguments":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"description":"A dictionary of arguments to be passed to the tool.","title":"Arguments"}},"required":["arguments","tool_name"],"type":"object"}}}]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1486' content-type: - application/json host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-raw-response: - 'true' x-stainless-read-timeout: - '600.0' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFNda9swFH33rxD3ORlO6iTGbyXsI4WFdLRj2VyMIl87WmVJSPJYCfnv RXZqO2kG84MROjrnnnt0dQgIAZ5DQoDtqWOVFuPl9sf6Lv5ch/j4qDe4udl/F3q9+jb5+un+J4w8 Q+1+I3NvrA9MVVqg40q2MDNIHXrVyWI+vYkWUTxpgErlKDyt1G4cqfE0nEbjMB6H8xNxrzhDCwn5 FRBCyKH5e4syx7+QkHD0tlOhtbRESLpDhIBRwu8AtZZbR6WDUQ8yJR1K71rWQgwAp5TIGBWiL9x+ h8G6z4kKkd3dxl/W9XK7ug0fduvNNhLFx+f8Ph7Ua6VfdGOoqCXr8hng3X5yUYwQkLRquCtpnamZ U+ZBKbGkQnBZXggRAtSUdYXS+SbgkLZdeY0UkhQEUiMzulO1yyhPYZT2hBSSw/EIZ4LH4Nr6aZCa waK2VLyPk0qpHPVdNXk+nZBjd3VCldqonb2gQsElt/vMILVNImCd0q0tb6EpDvXZrYM2qtIuc+oZ m3LTxbzVg34oe3QyPYFOOSoGrDgeXdHLcnSUN2PRTSKjbI95T+0nktY5VwMgGHT93s017bZzLsv/ ke8BxlA7zDNtMOfsvOP+mEH/Zv91rEu5MQwWzR/OMHMcjb+JHAtai/Y5gX2xDqus4LJEow1v3hQU OpvPZvMoj3d0BsExeAUAAP//AwAU6/i4XAQAAA== headers: CF-RAY: - 999c852e882ff580-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:02 GMT Server: - cloudflare Set-Cookie: - __cf_bm=REDACTED; path=/; expires=Wed, 05-Nov-25 13:28:02 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None - _cfuvid=REDACTED; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '737' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '763' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29804' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 392ms x-request-id: - req_REDACTED status: code: 200 message: OK - request: body: '{"messages":[{"role":"user","content":"SYSTEM: The schema should have the following structure, only two keys:\n- tool_name: str\n- arguments: dict (always a dictionary, with all arguments being passed)\n\nExample:\n{\"tool_name\": \"tool name\", \"arguments\": {\"arg_name1\": \"value\", \"arg_name2\": 2}}\n\nUSER: Only tools available:\n###\nTool Name: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid output schema:\n\n### TEXT \n```\nThought: To write an amazing paragraph on AI, I need to gather detailed information about the subject. I''ll use the tool available to learn more about AI.\nAction: learn_about_ai\nAction Input: {}"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"InstructorToolCalling"}},"tools":[{"type":"function","function":{"name":"InstructorToolCalling","description":"Correctly extracted `InstructorToolCalling` with all the required parameters with correct types","parameters":{"properties":{"tool_name":{"description":"The name of the tool to be called.","title":"Tool Name","type":"string"},"arguments":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"description":"A dictionary of arguments to be passed to the tool.","title":"Arguments"}},"required":["arguments","tool_name"],"type":"object"}}}]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1486' content-type: - application/json cookie: - __cf_bm=REDACTED; _cfuvid=REDACTED host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-raw-response: - 'true' x-stainless-read-timeout: - '600.0' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFPRjpswEHznK6x9TqqEEoJ4a69Se7pepEptdVE5oY1ZiFNjE9u0d43y 7xWQA5JLpfKALI9ndna8PniMgcggZsC36HhZyenN+mF1N+crvF+X2ycM8r3aWPXlz114//s9TBqG 3uyIuxfWG67LSpITWnUwN4SOGtX5MvTfBssg8lug1BnJhlZUbhroqT/zg+ksms7CE3GrBScLMfvh McbYof03FlVGTxCz2eRlpyRrsSCI+0OMgdGy2QG0VliHysFkALlWjlTjWtVSjgCntUw5SjkU7r7D aD3khFKmn/e7cP9t9emD+B69W+9yXTgdPX28HdXrpJ+r1lBeK97nM8L7/fiiGGOgsGy5t8o6U3On zVet5Q1KKVRxIcQYoCnqkpRrmoBD0nXVaCQQJyAJjUpxo2uXokhgkgyEBOLD8Qhngkfv2vpxlJqh vLYoX8eJSmmHTVdtno8n5NhfndRFZfTGXlAhF0rYbWoIbZsIWKerzlZjoS0O9dmtQ2V0WbnU6Z/U lvOXYacHw1AO6Nw/gU47lCNWFE2u6KUZORTtWPSTyJFvKRuow0RinQk9ArxR16/dXNPuOheq+B/5 AeCcKkdZWhnKBD/veDhmqHmz/zrWp9waBkvml+CUOkGmuYmMcqxl95zAPltHZZoLVZCpjGjfFORV Gi4WYZBFG1yAd/T+AgAA//8DABCsRmNcBAAA headers: CF-RAY: - 999c8533ce42f580-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:02 GMT Server: - cloudflare Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '498' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '524' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29804' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 392ms x-request-id: - req_REDACTED 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: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\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 [learn_about_ai], 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: Write and then review an small paragraph on AI until it''s AMAZING\n\nThis is the expected criteria for your final answer: The final paragraph.\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":"```\nThought: To write an amazing paragraph on AI, I need to gather detailed information about the subject. I''ll use the tool available to learn more about AI.\nAction: learn_about_ai\nAction Input: {}\nObservation: I encountered an error: Failed to convert text into a Pydantic model due to validation error: 1 validation error for InstructorToolCalling\n JSON input should be string, bytes or bytearray [type=json_type, input_value=InstructorToolCalling(too...about_ai'', arguments={}), input_type=InstructorToolCalling]\n For further information visit https://errors.pydantic.dev/2.12/v/json_type\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 [learn_about_ai]\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```"}],"model":"gpt-4o"}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '2695' content-type: - application/json cookie: - __cf_bm=REDACTED; _cfuvid=REDACTED host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - '600' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFbbbhw3DH33VxDz1ALrhePYjuO3bYuiRi95SdEGdbDhSpwZxRpqKlLr OIH/vaBmb3YMNC++iBJ5yMPD4ZcjgCb45goa16O6YYzHP777+49fMXU/declnrxw/W+vzuiHd2/y n6fXpZnZi7T6SE63r+YuDWMkDYkns8uESub1xauL05dnr84uT6thSJ6iPetGPT5Lx6cnp2fHJ5fH Jxebh30KjqS5gn+OAAC+1J8GkT19aq7gZLY9GUgEO2qudpcAmpyinTQoEkSRtZntjS6xElfUHz58 uOG3fSpdr1dwDdKnEj2gKg2jQpHAHWhPEAkzL3GVii4xgKYUATsMDJqgQ+0pQ+A25QEtfUgMi+v5 DS+c/Xv15P32HK55LHoFXx5u+M1KKK9xur7IGtrgAka4ZqUYQ0fsCL5bXH8PmVrKYoENmac1xTQO xAqpBaOgKGWQe1EaBLRHBYcMI2XDB4pyuzlmwxvjPWT6t4RM0JcBGcJByDm87Ulo8yqwi8UTZEJJ HLibTZnVv8acVpGGY0lxPR1QdjRaRjOIyF3BjqCwp2yc+HoH2dd4GWtF5rC4BiXXc4qpCySAmaBo iOEzeUCXkwisMYdUDI4votmuaQLiHq1IY06OREhmhtegElBr5SR291NIw0gw9eunLXKZw+/o+sB0 kBWClJVQLe7iegZtckVIjGErf23xyngLGLuUg/bbqmOM6W7HSMVY/UKb01BhDHhreMmHmr3ACoW8 +faoOIe/gvaAfm15GcOWckWB4xiDw+mRFNcDCmDRxGmwyqypDy5aCWTArLATgkz5DxYSI/iAHSfR 4KZKZ5Iex23Xt0VLphmktqVsh4XHTI48sRrMcUxZCwetRLGHjKFKhrSv7l1iCZ7yBmjtf/McMoRh RKeWqiQXSO/nN1zluPl1oEpOd9DjmiomJiMX8/0jvWmCuxyUAGu9M/XEEtZUUeGAnw3ViBm7jGO/ k+fPgTHCguWO8v+oLkgNH5iTqXRNxiJroGzU71r2fgZ3PWX6WohWXk8SOiZf23UoEfU5zRnJG7VW Jqr0tiR/m/Qs7UdK2wlwDr9gZtPHTk5cBsqP9TQzHaZRwxA+kxxKapWi1G5+KilFdxvJnGi21iRw PcZI3JFMnbzp3eGJxoAGyp11kADCGNZJa+sMY2JinYHL2KpdfCowYlxF2jp8KjCT0MxIy7S6N6mZ i6lpyB+qzmZcEHBFLcox+Y4OCK3MZ2TZ8WHfA2QvDkeCO5Nol1Nhv8o0BTlU52wzNOv5twt0I/pn lTqHhRg/9iELXDbTb20jbQZBLTWpw4KTCazO9wHzbS3WY9Guio0pScbwMKrAOmgNJq6IVNEmhqCy k3QYDibPNEpNvpMFndHVY57oghG1B013mL1dnia9S8zkbIBM82US/uEXOlNbBG1B4BLjgQGZk06x bTd4v7E87LaBmDrTgjx52rSBg/TLSTz25RdNY1OtD0cA7+vWUR4tEs1UkqWmW6rhzi9eT/6a/Z6z t748fbGxqvXv3nD5erOsPHa49KQYohwsLo1D15PfP91vOVh8SAeGo4O0v4bznO/d3PgW93uDsy84 +eVeLs9dy/SxMvr8tV2ZK+DG9pzgaGmz06jw1GKJ04rWTNNy2QbuKI85THtaOy4vzs8vzvzlCs+b o4ej/wAAAP//AwBH9X6IsAoAAA== headers: CF-RAY: - 999c85379bea0f3e-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:11 GMT Server: - cloudflare Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '8186' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '8211' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29364' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 1.27s x-request-id: - req_REDACTED status: code: 200 message: OK - request: body: '{"messages":[{"role":"user","content":"SYSTEM: The schema should have the following structure, only two keys:\n- tool_name: str\n- arguments: dict (always a dictionary, with all arguments being passed)\n\nExample:\n{\"tool_name\": \"tool name\", \"arguments\": {\"arg_name1\": \"value\", \"arg_name2\": 2}}\n\nUSER: Only tools available:\n###\nTool Name: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid output schema:\n\n### TEXT \n```\nThought: I should attempt using the learn_about_ai tool again to gather information on AI.\nAction: learn_about_ai\nAction Input: {}"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"InstructorToolCalling"}},"tools":[{"type":"function","function":{"name":"InstructorToolCalling","description":"Correctly extracted `InstructorToolCalling` with all the required parameters with correct types","parameters":{"properties":{"tool_name":{"description":"The name of the tool to be called.","title":"Tool Name","type":"string"},"arguments":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"description":"A dictionary of arguments to be passed to the tool.","title":"Arguments"}},"required":["arguments","tool_name"],"type":"object"}}}]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1422' content-type: - application/json cookie: - __cf_bm=REDACTED; _cfuvid=REDACTED host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-raw-response: - 'true' x-stainless-read-timeout: - '600.0' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFPRbtowFH3nK6z7DBOkAdq8rZU2darKtLVbu6WKLs5N8ObYlu2sUMS/ T0loEiiTlofI8vE599zj6+2AMRApRAz4Cj0vjBxdPT7c3tHHD9mjX1zTN67X68UXeXl7+X5tL2BY MfTyF3H/ynrHdWEkeaFVA3NL6KlSncxnwVk4Dy8mNVDolGRFy40fhXoUjINwND4fjWd74koLTg4i 9nPAGGPb+l9ZVCmtIWLj4etOQc5hThC1hxgDq2W1A+iccB6Vh2EHcq08qcq1KqXsAV5rmXCUsivc fNveussJpUwebj7fYLB+MffP4fevd+XzRi5+8PtPvXqN9MbUhrJS8TafHt7uR0fFGAOFRc29Vs7b kntt77SWVyilUPmREGOANi8LUr5qArZx01WlEUMUgyS0KsGlLn2CIoZh3BFiiLa7HRwI7gan1k+9 1CxlpUP5Nk5USnusuqrzfNoju/bqpM6N1Ut3RIVMKOFWiSV0dSLgvDaNrcpCXRzKg1sHY3VhfOL1 b6rLBbOzRg+6oezQSbAHvfYoe6z5dHhCL0nJo6jHop1EjnxFaUftJhLLVOgeMOh1/dbNKe2mc6Hy /5HvAM7JeEoTYykV/LDj7pil6s3+61ibcm0YHNk/glPiBdnqJlLKsJTNcwK3cZ6KJBMqJ2usqN8U ZCaZTaezMD1f4hQGu8FfAAAA//8DADWXbfNcBAAA headers: CF-RAY: - 999c856bfaa2adf8-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:11 GMT Server: - cloudflare Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '442' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '457' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29820' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 360ms x-request-id: - req_REDACTED status: code: 200 message: OK - request: body: '{"messages":[{"role":"user","content":"SYSTEM: The schema should have the following structure, only two keys:\n- tool_name: str\n- arguments: dict (always a dictionary, with all arguments being passed)\n\nExample:\n{\"tool_name\": \"tool name\", \"arguments\": {\"arg_name1\": \"value\", \"arg_name2\": 2}}\n\nUSER: Only tools available:\n###\nTool Name: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\n\nReturn a valid schema for the tool, the tool name must be exactly equal one of the options, use this text to inform the valid output schema:\n\n### TEXT \n```\nThought: I should attempt using the learn_about_ai tool again to gather information on AI.\nAction: learn_about_ai\nAction Input: {}"}],"model":"gpt-4o","tool_choice":{"type":"function","function":{"name":"InstructorToolCalling"}},"tools":[{"type":"function","function":{"name":"InstructorToolCalling","description":"Correctly extracted `InstructorToolCalling` with all the required parameters with correct types","parameters":{"properties":{"tool_name":{"description":"The name of the tool to be called.","title":"Tool Name","type":"string"},"arguments":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"description":"A dictionary of arguments to be passed to the tool.","title":"Arguments"}},"required":["arguments","tool_name"],"type":"object"}}}]}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '1422' content-type: - application/json cookie: - __cf_bm=REDACTED; _cfuvid=REDACTED host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-raw-response: - 'true' x-stainless-read-timeout: - '600.0' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFNdj9owEHznV1j7DBUfAa55a6lUndQeVXWtriqnaHE2wT3HtuxNC4f4 71USjgSOSs1DZHk8s7Pj9b4nBKgUYgFygywLpweLHw9397sH9S2Mvqy/796XzJ8/PG/ZjZbREvoV w65/keQX1htpC6eJlTUNLD0hU6U6ms/Gk2gevR3VQGFT0hUtdzyI7GA8HEeD4c1gODsSN1ZJChCL nz0hhNjX/8qiSWkLsRj2X3YKCgFzgvh0SAjwVlc7gCGowGgY+i0orWEylWtTat0B2FqdSNS6Ldx8 +866zQm1TqJPT3Lx9S4ab9FM9J/sdps/f3y3xE69RnrnakNZaeQpnw5+2o8vigkBBouae2sC+1Ky 9ffW6gVqrUx+ISQEoM/LggxXTcB+1XRVaawgXoEm9CbBtS05QbWC/qolrCDeHw5wJnjoXVs/dlLz lJUB9es40RjLWHVV5/l4RA6nq9M2d96uwwUVMmVU2CSeMNSJQGDrGluVhbo4lGe3Ds7bwnHC9onq cuPZpNGDdihbdDQ+gmwZdYc1n/av6CUpMap6LE6TKFFuKG2p7URimSrbAXqdrl+7uabddK5M/j/y LSAlOaY0cZ5SJc87bo95qt7sv46dUq4NQyD/W0lKWJGvbiKlDEvdPCcIu8BUJJkyOXnnVf2mIHPJ bDqdRenNGqfQO/T+AgAA//8DAH8H0iVcBAAA headers: CF-RAY: - 999c856feb83adf8-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:12 GMT Server: - cloudflare Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '405' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '422' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '29820' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 360ms x-request-id: - req_REDACTED 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: learn_about_ai\nTool Arguments: {}\nTool Description: Useful for when you need to learn about AI to write an paragraph about it.\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 [learn_about_ai], 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: Write and then review an small paragraph on AI until it''s AMAZING\n\nThis is the expected criteria for your final answer: The final paragraph.\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":"```\nThought: To write an amazing paragraph on AI, I need to gather detailed information about the subject. I''ll use the tool available to learn more about AI.\nAction: learn_about_ai\nAction Input: {}\nObservation: I encountered an error: Failed to convert text into a Pydantic model due to validation error: 1 validation error for InstructorToolCalling\n JSON input should be string, bytes or bytearray [type=json_type, input_value=InstructorToolCalling(too...about_ai'', arguments={}), input_type=InstructorToolCalling]\n For further information visit https://errors.pydantic.dev/2.12/v/json_type\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 [learn_about_ai]\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 should attempt using the learn_about_ai tool again to gather information on AI.\nAction: learn_about_ai\nAction Input: {}\nObservation: I encountered an error: Failed to convert text into a Pydantic model due to validation error: 1 validation error for InstructorToolCalling\n JSON input should be string, bytes or bytearray [type=json_type, input_value=InstructorToolCalling(too...about_ai'', arguments={}), input_type=InstructorToolCalling]\n For further information visit https://errors.pydantic.dev/2.12/v/json_type\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 [learn_about_ai]\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 should attempt using the learn_about_ai tool again to gather information on AI.\nAction: learn_about_ai\nAction Input: {}\nObservation: I encountered an error: Failed to convert text into a Pydantic model due to validation error: 1 validation error for InstructorToolCalling\n JSON input should be string, bytes or bytearray [type=json_type, input_value=InstructorToolCalling(too...about_ai'', arguments={}), input_type=InstructorToolCalling]\n For further information visit https://errors.pydantic.dev/2.12/v/json_type\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 [learn_about_ai]\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"}' headers: accept: - application/json accept-encoding: - gzip, deflate, zstd connection: - keep-alive content-length: - '5419' content-type: - application/json cookie: - __cf_bm=REDACTED; _cfuvid=REDACTED host: - api.openai.com user-agent: - OpenAI/Python 1.109.1 x-stainless-arch: - arm64 x-stainless-async: - 'false' x-stainless-lang: - python x-stainless-os: - MacOS x-stainless-package-version: - 1.109.1 x-stainless-read-timeout: - '600' x-stainless-retry-count: - '0' x-stainless-runtime: - CPython x-stainless-runtime-version: - 3.12.9 method: POST uri: https://api.openai.com/v1/chat/completions response: body: string: !!binary | H4sIAAAAAAAAAwAAAP//jFVda1tHEH33rxjuUwuy8VfsxG+iUBAUt9CUNjRBjHZHd8feO3M7OytF CfnvZa9kW2lT6IsQc3bOnPm8n08AOo7dHXQhoYdhzKc/vPvj/rdf3s3LbrSf7rd6/+vV9cPv8ub+ 5/jxvps1D109UPAnr7Ogw5jJWWUPByN0aqwXtzeXV9e3128uJ2DQSLm59aOfXuvp5fnl9en569Pz m4NjUg5Uujv48wQA4PP02yRKpI/dHZzPniwDlYI9dXfPjwA609wsHZbCxVG8m72AQcVJJtVvk9Y+ +R0sYMs5g+gWRtMNRwJPBCsqDqOWwqtMMKJhbzgmUIH5AlZYKLb/ww50K/Aous0Uezp7L+/lRxbM MJeyJbuDuTmvOTBmWIhTztyTBILv5ovvgQsYbTTXVjr+xNJP0VuVTGCrliOsdkCCq9zAAUNioQKu MJKt1QZwLI8FPKGD70YOmPMOjP6qbASpDijAR4HP4G2iQgc3Q+kJ1qYDVIlkrWaxRRL0apgho/QV ewKUCEZB+4POEd3JZJIy4GMzRQpcWKVMjzOhSTNP7PRxJOO9gPmiJR6NNyQtPYwblEARMPdq7GnY M2ywOOCgVbyAriGi4wwwZ9023rIrTsMkgIfWvKl1bE+VaZygGzJwHugMFl4AxzFzQN+rNDrEmIIZ U5wBSRvmNj9NOlOOBUoNCbBAIsyeAhrNYJvIqKWCHAuwQGTsRSe3yIWwUJk1bVhdRQetBTaUOORm 3yYOCapz5k8TiysIbrhH35d6wEc6KqjKNBimGM9gXppHm2aWuh+GNkQbmgF7G+OBy8EsaaoCrdsI koTd7LlWT+Sn++7NprBuKGUaK5ZYixsf1GYCzEXbTrQMQ8KcSXpqA5zbrk/hPHEoM3jQVavBmDHQ QOIH7kQgRBHWamC6qsWhUKjGvoOBsFSjMo0nrKtXo9bz+QKSth64NarYyjhqW+O2UY122t/Mj5R3 MGbcAUKwOi1cuwatNSXh2FRrNSgamHx3dnwYjNa1YLtLUnM+AlBEfT8t7SR9OCBfno9Q1n40XZV/ uHZrFi5paYRFpR2c4jp2E/rlBODDdOzqV/era40bfen6SFO4i4ubyz1h93Jfj+Db2wPq6piPgKur N7NvUC4jOXIuRxezCxgSxRffl/OKNbIeASdHif9bz7e498mz9P+H/gUIgUanuByNIoevc355ZtQ+ QP/17LnQk+CukG040NKZrDUj0hpr3n8buv0ZWa5ZerLReP+BWI/Lm1evbq7j6xW+6k6+nPwNAAD/ /wMAnDB2cCkHAAA= headers: CF-RAY: - 999c85731a4f0f3e-EWR Connection: - keep-alive Content-Encoding: - gzip Content-Type: - application/json Date: - Wed, 05 Nov 2025 12:58:18 GMT Server: - cloudflare Strict-Transport-Security: - max-age=31536000; includeSubDomains; preload 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: - user-REDACTED openai-processing-ms: - '5822' openai-project: - proj_REDACTED openai-version: - '2020-10-01' x-envoy-upstream-service-time: - '5849' x-openai-proxy-wasm: - v0.1 x-ratelimit-limit-requests: - '500' x-ratelimit-limit-tokens: - '30000' x-ratelimit-remaining-requests: - '499' x-ratelimit-remaining-tokens: - '28711' x-ratelimit-reset-requests: - 120ms x-ratelimit-reset-tokens: - 2.578s x-request-id: - req_REDACTED status: code: 200 message: OK version: 1