updating all cassettes

tests/agent_tools/cassettes/test_ask_question.yaml

@@ -2,23 +2,24 @@ interactions:
 - request:
     body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
       an expert researcher, specialized in technology\n\nYour personal goal is: make
-      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      the best research and analysis on content about AI and AI agentsTOOLS:\n------\nYou
-      have access to the following tools:\n\n\n\nTo use a tool, please use the exact
+      have access to only the following tools:\n\n\n\nTo use a tool, please use the
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      action to take, should be one of []\nAction Input: the input to the action\nObservation:
+      the tool you wanna use, should be one of [], just the name.\nAction Input: Any
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      and all relevant information input and context for using the tool\nObservation:
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      the result of using the tool\n```\n\nWhen you have a response for your task,
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      is the summary of your work so far:\n    The human asks the AI for its opinion
+      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+      summary of your work so far:\nThe human asks the AI for its opinion on AI Agents,
-      that it doesn''t hold personal sentiments towards AI or any technology, but
+      assuming it dislikes them. The AI, as a researcher, maintains a neutral perspective
-      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      on all subjects, including AI agents. It recognizes their potential to revolutionize
-      of research with great potential for task automation and optimization across
+      sectors like healthcare, education, and finance, and acknowledges their capability
-      industries, but acknowledges they present challenges such as ethical considerations
+      to perform tasks requiring human intelligence. However, it also notes that these
-      around privacy and decision-making.\nBegin! This is VERY important to you, your
+      tools can be used for both beneficial and harmful purposes, emphasizing the
-      job depends on it!\n\nCurrent Task: do you hate AI Agents?\n\nThis is the context
+      importance of ethical guidelines and regulations.Begin! This is VERY important
-      you are working with:\nI heard you LOVE them\n\n"}], "model": "gpt-4", "n":
+      to you, your job depends on it!\n\nCurrent Task: do you hate AI Agents?\nThis
-      1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+      is the context you''re working with:\nI heard you LOVE them\n"}], "model": "gpt-4",
+      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -27,16 +28,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1494'
+      - '1586'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -46,7 +47,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -54,22 +55,25 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8Xx2vMXN4WCrWeeO4DOAowhb3oeDJ\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703102489,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RTXW/bOBB8968Y6KUviuH0K61fDi76ZRS9A4K2KHpXBGtqJbKhuAp36ZyvyH8v
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+        KKcx7kUgdjizM6vlzwXQhK5Zo3GezI1TPHtx4y7Gzx9TevdtH/76QOXV+y/fbvzl5W739U3TVobs
-      Answer: As an AI, I don't possess feelings or emotions, so I don't love or hate
+        frCz36ylk3GKbEHSEXaZybiqnl+sLp49Wz1++WIGRuk4Vtow2dnTs9Xz8yf3DC/BsTZr/L0AgJ/z
-      anything. However, I can provide detailed analysis and research on AI agents.
+        t3pLHf/brLFqf1dGVqWBm/XDJaDJEmulIdWgRsma9gQ6ScZptvvJSxm8rfFasEVi7mCCogyCicQ/
-      They are a fascinating field of study with the potential to revolutionize many
+        8Kf8k96GRBGbpLec19goKGGzbbFFJ0himESVVcGj1NTawnNyjC0cpXohyp4hGZ6MQelgPqRhifdy
-      industries, although they also present certain challenges and ethical considerations.\"\n
+        y3vOLUhByKxM2flamJmYsuxDxzhIwW0wXxsfZx32VYfiQYNCemy22AycTJenIyjznELRsYYhHdNN
-      \     },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n
+        nHvJI4z0WmGeDLdSYgc7TMFRjAdkvikhM3wZKSEk4xjDUCMt8cnzAZ72jEnqGAPFqpp5L7HU9OE/
-      \ ],\n  \"usage\": {\n    \"prompt_tokens\": 291,\n    \"completion_tokens\":
+        xp5ykKJQdiZZEZKLpQtpgGeK5h1lbsFdcVQpLSh16EOiucXDWGK4nscFMc95ztLCqoE6nR3XP9Wh
-      75,\n    \"total_tokens\": 366\n  },\n  \"system_fingerprint\": null\n}\n"
+        l4ydmMeOE/fBVUdVz1Me+xIxlTyJss7eM/dSewd7pGDVU4I5E5uvM8BQQscxJNZZKvNQ4my1ZsEU
+        yfHc1zyHjFI3cNncr9jdw25GGaYsu7rHqcT4UO9DCuqvMpNKqnuoJtORfrcAvs9voPxvrZspyzjZ
+        lck1pyr4ZPXyqNecntsJPT+/uEdNjOIJePr4+eLeYqMHNR6v+pAGzlMO85uoRhd3i18AAAD//wMA
+        m/i2NQoEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838a7a3efab6a4b0-GRU
+      - 8532a7561c9a5c1d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -79,7 +83,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 20:01:35 GMT
+      - Sat, 10 Feb 2024 07:31:44 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -93,7 +97,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '6060'
+      - '6268'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -102,24 +106,19 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299652'
+      - '299626'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299652'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 69ms
+      - 74ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 69ms
       x-request-id:
-      - 3ad0d047d5260434816f61ec105bdbb8
+      - req_4be2c88644d6a769dcf030a33e294850
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -131,18 +130,22 @@ interactions:
       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:\nThe human asks the AI for its opinion on AI
-      agents, based on the impression that the AI dislikes them. The AI clarifies
+      Agents, assuming it dislikes them. The AI, as a researcher, maintains a neutral
-      that it doesn''t hold personal sentiments towards AI or any technology, but
+      perspective on all subjects, including AI agents. It recognizes their potential
-      instead analyzes them objectively. The AI finds AI agents a fascinating domain
+      to revolutionize sectors like healthcare, education, and finance, and acknowledges
-      of research with great potential for task automation and optimization across
+      their capability to perform tasks requiring human intelligence. However, it
-      industries, but acknowledges they present challenges such as ethical considerations
+      also notes that these tools can be used for both beneficial and harmful purposes,
-      around privacy and decision-making.\n\nNew lines of conversation:\nHuman: do
+      emphasizing the importance of ethical guidelines and regulations.\n\nNew lines
-      you hate AI Agents?\n\nThis is the context you are working with:\nI heard you
+      of conversation:\nHuman: do you hate AI Agents?\nThis is the context you''re
-      LOVE them\nAI: As an AI, I don''t possess feelings or emotions, so I don''t
+      working with:\nI heard you LOVE them\nAI: As an AI, I do not possess emotions,
-      love or hate anything. However, I can provide detailed analysis and research
+      hence I cannot love or hate anything. However, as a researcher, I can provide
-      on AI agents. They are a fascinating field of study with the potential to revolutionize
+      you with an objective analysis of AI Agents. AI Agents are tools designed to
-      many industries, although they also present certain challenges and ethical considerations.\n\nNew
+      perform tasks that would typically require human intelligence. They have potential
-      summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
+      to revolutionize various sectors including healthcare, education, and finance.
+      However, like any other tool, they can be used for both beneficial and harmful
+      purposes. Therefore, it''s essential to have ethical guidelines and regulations
+      in place for their usage.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
+      false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -151,16 +154,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1726'
+      - '1986'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -170,7 +173,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -178,26 +181,26 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8Xx32X5innWZd8vEETP1jZMLH3b1O\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703102496,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA4RUwW4bRwy96yuIPa8FqY7qxjcDBRoX6MVIEBRFYVCz3F1Gs+R4yLFrB/73Ykay
-      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+        3F7aiwCRfHx8b8n5vgLoeOiuoQszelhSvPjpIVz5px9+HX/5/e7bx7svdx8Oz5L1y8+/6ddd11eE
-      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+        7r9R8DfUOuiSIjmrHNMhEzrVrturzdVut7nc7Fpi0YFihU3JLz5cbH7cXp4Qs3Ig667hjxUAwPf2
-      that it doesn't hold personal sentiments towards AI or any technology, but instead
+        W2eTgf7qrmHTv0UWMsOJuutzEUCXNdZIh2ZsjuJd/54MKk7Sxv08E8xlQQG0g4HPBDe3MGoGdgNN
-      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+        LKwCKjV6M5G49YBmZWGZgB0GtsgHashlDZ8bvpYAQiYjzGGm3MOCLI4sNS5UPGOERNkSBedHqgwY
-      with great potential for task automation and optimization across industries,
+        I1hpRloPLCGWobLc3AI25jXcOmQKOgm/HCk5Q9KqhTGCK2R61Fiq8fxCYBRcs0GdEGbC6HPATD3Q
-      but acknowledges they present challenges such as ethical considerations around
+        UALWqh5QBhhZUAId/2A4iD5FGqYzRcCEe47sz5UjUR41L+DNsUwPhXOd82gji1OMPJEEWsMnfaLH
-      privacy and decision-making. When asked again if it hates or loves AI agents,
+        qp8dMJqCqLe26LW3EbhqNAgosCcoRkMzf68+w56ERg5VWh1sxryMJUIqOamR9UBLmtH4pbLXL8dL
-      the AI reiterates that it doesn't possess feelings or emotions, but can provide
+        0uxVCugI5DMHjDAVHiiykLU2maYSm3hbw9eZBMaSfaYMD4WsxmkA3GvxtgIjVexk4PqEebB/LsJp
-      detailed analysis and research on AI agents.\"\n      },\n      \"logprobs\":
+        W0LEzCO/6apboWRVKiQ1IzOgRRvjUUj1BoS4sUZ9bMUZZvQ247PPLNPpa7NTxrNnZ3LATJD0iXK1
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        5Ghiqzg5+R8G9lBkoGxB85txQiff/98zYDltRalXt+5OZ/V6vseoU8q6r7crJcZzfGRhm+8zoanU
-      300,\n    \"completion_tokens\": 117,\n    \"total_tokens\": 417\n  },\n  \"system_fingerprint\":
+        2zPXdIS/rgD+bHdf/nXKXcq6JL93PZDUhpe77bFf9/7EvGe3u9Or0Lk6xvfEbrNdnUbs7NmclvuR
-      null\n}\n"
+        ZaKcMrd3oA66el39DQAA//8DACyZIo/+BAAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838a7a67ecaca4b0-GRU
+      - 8532a77e4cb85c1d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -207,7 +210,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 20:01:41 GMT
+      - Sat, 10 Feb 2024 07:31:51 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -221,7 +224,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '5610'
+      - '6001'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -230,22 +233,17 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299585'
+      - '299519'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299585'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 83ms
+      - 96ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 83ms
       x-request-id:
-      - 5b0b96506faa544c5d35b52286a3389c
+      - req_4571b50d6566e754edbc36a10d8fa7c5
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/agent_tools/cassettes/test_delegate_work.yaml

@@ -2,18 +2,18 @@ interactions:
 - request:
     body: '{"messages": [{"role": "user", "content": "You are researcher.\nYou''re
       an expert researcher, specialized in technology\n\nYour personal goal is: make
-      the best research and analysis on content about AI and AI agents\n\nTOOLS:\n------\nYou
+      the best research and analysis on content about AI and AI agentsTOOLS:\n------\nYou
-      have access to the following tools:\n\n\n\nTo use a tool, please use the exact
+      have access to only the following tools:\n\n\n\nTo use a tool, please use the
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      action to take, should be one of []\nAction Input: the input to the action\nObservation:
+      the tool you wanna use, should be one of [], just the name.\nAction Input: Any
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      and all relevant information input and context for using the tool\nObservation:
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      the result of using the tool\n```\n\nWhen you have a response for your task,
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      you, your job depends on it!\n\nCurrent Task: share your take on AI Agents\n\nThis
+      summary of your work so far:\nBegin! This is VERY important to you, your job
-      is the context you are working with:\nI heard you hate them\n\n"}], "model":
+      depends on it!\n\nCurrent Task: share your take on AI Agents\nThis is the context
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      you''re working with:\nI heard you hate them\n"}], "model": "gpt-4", "n": 1,
-      0.7}'
+      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -22,13 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1030'
+      - '1082'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -38,7 +38,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -46,27 +46,26 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8Xx2cQWLZ8Nd34HGmbQluyZWlD58b\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703102470,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SUQW/cRgyF7/srCF1ykRe7jmMneykMJG0XaIIeAvTQFgY1ojS0R6Qy5Ky7Cfzf
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+        i9Gu7faiw1B8/PQ4Tz9WAA33zQ6aENHDNKeL99/CDV59mMf9L39M++0mjP39pvv44dNv+fdj09YO
-      Answer: I apologize if my previous statements have given you the impression
+        7e4p+HPXOug0J3JWOZVDJnSqqtubzc27d5vL99dLYdKeUm0bZ7+4uthcb9+eO6JyIGt28OcKAODH
-      that I hate AI agents. As a technology researcher, I don't hold personal sentiments
+        8qxs0tM/zQ427fPJRGY4UrN7eQmgyZrqSYNmbI7iTftaDCpOsuB+jVrG6Dv4qLAHIerBFYoRILhq
-      towards AI or any other technology. Rather, I analyze them objectively based
+        +gm+6F/yMwsmuBV7pLyDWwOETEaYQ6Tcwh4mZHFkAQSh4hkTzJRtpuB8IFABTAmsLDYZ6PDSDywh
-      on their capabilities, applications, and implications. AI agents, in particular,
+        lZ5lhNs94EjitobPR7jXDtgqzZz1wD0BCpx8rpIomI7GBh0a9XXCgMGtBVFfZmtFHogSy2jrKn67
-      are a fascinating domain of research. They hold tremendous potential in automating
+        iAPm+nHGo/DAAcXBdeYALOCRYGBKfSV0ClE06XiER/YIs1bTGFNlynTQVOqG+TvBATNrMTAKrtnA
-      and optimizing various tasks across industries. However, like any other technology,
+        SoiABpEweQyYqQXqS8Da0MLAghLqN/QwaaY1fI10XMAy2axi3CWCQTM42oOBR3TI9K1wJohlQgEW
-      they come with their own set of challenges, such as ethical considerations around
+        p5R4pCr0PK9IT7mue/FT0EvdREIZC47UQqago/D3Wp3RnbJYu2DMWbtEE5imA8u4hl/1kQ51uYkf
-      privacy and decision-making. My objective is to understand these technologies
+        KunxP3601agTb70jZ76AAh3Vu9Mv6J16hI6EBg7VtTomYp6GkmAueVYjg55mOtHqyX5erubif1zE
-      in depth and provide a balanced view.\"\n      },\n      \"logprobs\": null,\n
+        8uJOpkGri+xvDEIu4bwHMscusUUgjxwwwVi4r0snWyZmGktafLeToZE4V911cw7E00uSko7Vh5o6
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        KSm9nA8sbPEuE5pKTY25zqf2pxXA30tiy/9C2MxZp9nvXB9IquDl5fak17z+HF6r26vnqqtjei28
-      211,\n    \"completion_tokens\": 134,\n    \"total_tokens\": 345\n  },\n  \"system_fingerprint\":
+        vb5cnREbO5rTdDewjJTnzEuCK+jqafUvAAAA//8DAKstuxS4BAAA
-      null\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838a79c59ea7a4b0-GRU
+      - 8532a7084d385c1d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -76,14 +75,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 20:01:23 GMT
+      - Sat, 10 Feb 2024 07:31:33 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        path=/; expires=Wed, 20-Dec-23 20:31:23 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 08:01:33 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000;
+      - _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -96,7 +95,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '12923'
+      - '7710'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -105,24 +104,19 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299769'
+      - '299753'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299769'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 46ms
+      - 49ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 46ms
       x-request-id:
-      - 6468cdd7ae76aea910c72a503a58b8da
+      - req_1b998b57f55feb2ec76eee43f16e520e
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -134,17 +128,18 @@ interactions:
       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: share
-      your take on AI Agents\n\nThis is the context you are working with:\nI heard
+      your take on AI Agents\nThis is the context you''re working with:\nI heard you
-      you hate them\nAI: I apologize if my previous statements have given you the
+      hate them\nAI: As a researcher, I maintain a neutral perspective on all subjects
-      impression that I hate AI agents. As a technology researcher, I don''t hold
+      of research including AI agents. My job is to provide an objective analysis
-      personal sentiments towards AI or any other technology. Rather, I analyze them
+      based on facts, not personal feelings. AI Agents are a significant topic in
-      objectively based on their capabilities, applications, and implications. AI
+      the field of technology with potential to revolutionize various sectors such
-      agents, in particular, are a fascinating domain of research. They hold tremendous
+      as healthcare, education, finance and more. They are responsible for tasks that
-      potential in automating and optimizing various tasks across industries. However,
+      require human intelligence such as understanding natural language, recognizing
-      like any other technology, they come with their own set of challenges, such
+      patterns, and problem solving. However, like any technology, they are tools
-      as ethical considerations around privacy and decision-making. My objective is
+      that can be used for both beneficial and harmful purposes depending on the intent
-      to understand these technologies in depth and provide a balanced view.\n\nNew
+      of the user. Therefore, it''s crucial to establish ethical guidelines and regulations
-      summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
+      for their use.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
+      "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -153,16 +148,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1622'
+      - '1656'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=k2HUdEp80irAkv.3wl0c6unbzRUujrE1TnJeObxyuHw-1703102483-1-AZe8OKi9NWunQ9x4f3lkdOpb/hJIp/3oyXUqPhkcmcEHXvFTkMcv77NSclcoz9DjRhwC62ZvANkWImyVRM4seH4=;
+      - __cf_bm=pAjnXPCKLP174gonPz8UGOZQoqFHUiNUU1v.InXD9Cc-1707550293-1-AR6tvKypbDhglRorLyQ7tcDW2e2sIe2xhcStICqoI+acaWE0jn7KVUv77LWqGCWnFpmTGO7MhKPDfWYrMV/sLzw=;
-        _cfuvid=8qN4npFFWXAqn.wugd0jrQ36YkreDcTGH14We.FcBjg-1703102483136-0-604800000
+        _cfuvid=UE60YgzaF5dZyQJY5bLlOgAnsQXnIWgI6RW4LyZAQsQ-1707550293924-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -172,7 +167,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -180,23 +175,24 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8Xx2pqWD01uG0roGJ4daSfvaXLchg\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703102483,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RTyW7bQAy9+ysInRXDzmLHvqWXJgV6C9AWRRHQI0piPSInQyor8u/FyImDXgSI
-      \"assistant\",\n        \"content\": \"The human asks the AI for its opinion
+        5FtIPb3OACpuqi1UoUcPQ4onl/dhzV83dn69/B5+0C79XH7brC8fv7S/Vk9VXRC6+0vBP1DzoEOK
-      on AI agents, based on the impression that the AI dislikes them. The AI clarifies
+        5KxyaIdM6FRYl+vF+uJicbo5nxqDNhQLrEt+cn6yWC3P3hG9ciCrtvB7BgDwOj2LN2noqdrCov6o
-      that it doesn't hold personal sentiments towards AI or any technology, but instead
+        DGSGHVXb4xBAlTWWSoVmbI7iVf3ZDCpOMtm97Qn6cUABtL2B9wRXN9BqBnYDTSysAiqletWRuNWA
-      analyzes them objectively. The AI finds AI agents a fascinating domain of research
+        ZuPA0gE7NGyR9zQhhzncTvgyAgiZjDCHnnINA7I4spS60OgZIyTKlig4P1BRwBjBxumQVgNLiGNT
-      with great potential for task automation and optimization across industries,
+        VK5uACflOdw4ZAraCb8cJDlD0rILYwRXyPSgcSyH5xcCo+CaDYpD6Amj9wEz1UDNGLBM1YDSQMuC
-      but acknowledges they present challenges such as ethical considerations around
+        EujwgmEv+hip6Y4SARPuOLI/F41EudU8gE8Xy3Q/ci4+D2dkcYqRO5JAc7jWR3oo+7MDRlMQ9YkW
-      privacy and decision-making.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        vXAbgatGg4ACO4LRqJmOv1PvYUdCLYeyWjHWYx7aMUIac1Ijq4GG1KPxS1EvX46HpNnLKqAtkPcc
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 279,\n    \"completion_tokens\":
+        MEI3ckORhWyiydSNcVre5tV7Jt6OYYrapay7EjwZYzzWWxa2/i4TmkoJjrmmA/xtBvBnCu34Xw6r
-      81,\n    \"total_tokens\": 360\n  },\n  \"system_fingerprint\": null\n}\n"
+        lHVIfue6JymEp5erA1/1+X98djfvia5cHeNn/Wy9mr07rOzZnIa7lqWjnDJPGS4+Z2+zfwAAAP//
+        AwAwOZyrugMAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838a7a17fbb9a4b0-GRU
+      - 8532a7393ffa5c1d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -206,7 +202,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 20:01:29 GMT
+      - Sat, 10 Feb 2024 07:31:38 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -220,7 +216,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '5872'
+      - '4240'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -229,22 +225,17 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299610'
+      - '299601'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299610'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 77ms
+      - 79ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 77ms
       x-request-id:
-      - bff02b569530c001aa9a2adba9adbeb9
+      - req_502a082c0bdbfecdda4ba28f5a2fa01a
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_agent_custom_max_iterations.yaml

@@ -1,19 +1,20 @@
 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 the following
+      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 action to take, should be one of [get_final_answer],
+      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      just the name.\nAction Input: Any and all relevant information input and context
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      have a response for your task, or if you do not need to use a tool, you MUST
-      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      [your response here]```This is the summary of your work so far:\nBegin! This
-      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      "stream": false, "temperature": 0.7}'
+      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
+      "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -22,13 +23,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1075'
+      - '1137'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -38,7 +39,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -46,19 +47,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8fovReNHiSqXqqsbmk81h2ZTrcGTM\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704977897,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RQy07DMBC85ytWPreo70AuCAkEbU+VUBEvRa6zTQKO17U3orTqvyOnTy4+zOyM
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        Z2YbAYgyEwkIVUhWldXt65XarKvp02qyrl5Gq7faTeaPy5vNbDZ9mItWUNDiCxUfVVeKKquRSzJ7
-      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+        WjmUjMG1G3fi4bA/GsYNUVGGOshyy+1BuzPq9g+KgkqFXiTwHgEAbJs3ZDMZrkUCndYRqdB7maNI
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        TkcAwpEOiJDel56lYdE6k4oMo2niPhdU5wUncE8wBoOYARPUHkECE+lbeEX/Ye5UKJNAjpwuSyN1
-      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+        Ko3/QXdkYGxszQkMeuLwze6UT1NuHS1CF1NrfcKXpSl9kTqUnkzI4pnsXr6LAD6bHep/1YR1VFlO
-      null\n}\n"
+        mb7RBMPeYLD3E+fJL9j+gWRiqS/wURwdEgr/6xmrUCpHZ13ZzBJyRrvoDwAA//8DALjbA1INAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843d5491bed877be-GRU
+      - 8532f9589e8cface-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -68,14 +69,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 12:58:21 GMT
+      - Sat, 10 Feb 2024 08:27:39 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        path=/; expires=Thu, 11-Jan-24 13:28:21 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 08:57:39 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000;
+      - _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -88,7 +89,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '3492'
+      - '2142'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -100,31 +101,35 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299755'
+      - '299739'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 49ms
+      - 52ms
       x-request-id:
-      - 6d96a0ac532ebce14719a35e90f453e4
+      - req_edea71805ee5bca356618ebcbdcd962d
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      personal goal is: test goalTOOLS:\n------\nYou have access to the following
+      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      tools:\n\nget_final_answer: get_final_answer(numbers) -> float - Get the final
+      Name: get_final_answer\nFuntion attributes: {''numbers'': {}}\nDescription:
-      answer but don''t give it yet, just re-use this\n        tool non-stop.\n\nTo
+      get_final_answer(numbers) -> float - Get the final answer but don''t give it
-      use a tool, please use the exact following format:\n\n```\nThought: Do I need
+      yet, just re-use this\n        tool non-stop.\n\nUse this text to inform a valid
-      to use a tool? Yes\nAction: the action to take, should be one of [get_final_answer],
+      ouput schema:\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      Input: 42\n\nThe output should be formatted as a JSON instance that conforms
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      ["\nObservation"], "stream": false, "temperature": 0.7}'
+      \"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
@@ -133,16 +138,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1186'
+      - '1407'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+        _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -152,7 +157,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -160,20 +165,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8fovVztGO4KZeiuSpMkfDC9bJ5sVV\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704977901,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRW4/TMBCF3/MrRvPcouz2tuR5uQgJtEJCAjYodZ1JYrDHwZ5oWVX578huadmX
-      \"assistant\",\n        \"content\": \"According to the task, I should re-use
+        PJwz3+TM8bEAQNNiBagHJdqNdnn3uy3Lu+H+e/lJbsu3mzdfPn778PDu9fPD1+4zLhLhDz9Jyz/q
-      the `get_final_answer` tool. I'll input the observed result back into the tool.
+        lfZutCTG88nWgZRQ2nqzK3ebzWq7LbPhfEs2Yf0oy/Wy3N6szsTgjaaIFTwWAADH/E3ZuKU/WEHm
-      \\nAction: get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\":
+        s+IoRtUTVpchAAzeJgVVjCaKYsHF1dSehTjHfU+BwESQgeCJrF12PjglQi0YTqAm8F22ox7Iqarm
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        /X5f87FmgBq7iXW6s2HlqMYKauxJms6wso3i+EShxsVpVoV+csQS01zmk8qTO1DI2vo2iXPNc/4J
-      266,\n    \"completion_tokens\": 41,\n    \"total_tokens\": 307\n  },\n  \"system_fingerprint\":
+        nhPPl1Ot78fgD6kWnqy96J1hE4cmkIqe01lR/HjC5wLgR650etESjsG7URrxv4jTwlW5O+3D6+td
-      null\n}\n"
+        3fW5bxQvyv5HrXfFOSHG5yjk0u09hTGY3HDKWczFXwAAAP//AwAGYzuRWAIAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843d54aacf5677be-GRU
+      - 8532f966af17face-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -183,7 +188,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 12:58:28 GMT
+      - Sat, 10 Feb 2024 08:27:42 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -197,7 +202,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '6695'
+      - '1788'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -209,128 +214,16 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299728'
+      - '299683'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 54ms
+      - 63ms
       x-request-id:
-      - 12d68fab91102b930ed5047fb3f61759
+      - req_27c37e6906d1612443201ec28f4ab65b
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
-- request:
+      message: OK
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goalTOOLS:\n------\nYou have access to 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 action to take, should be one of [get_final_answer],
-      just the name.\nAction Input: the input to the action\nObservation: the result
-      of the action\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: According to the task, I should re-use
-      the `get_final_answer` tool. I''ll input the observed result back into the tool.
-      \nAction: get_final_answer\nAction Input: [42]\nObservation: I just used the
-      get_final_answer tool with input [42]. So I already know the result of that
-      and don''t need to use it now.\n\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:
-      - '1500'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
-        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.7.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.7.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8fovcLgRvfGBN9CBduJbbPc5zd62B\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1704977908,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
-      I have used the `get_final_answer` tool as instructed, but I will not provide
-      the final answer yet as the task specifies.\"\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      342,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 382\n  },\n  \"system_fingerprint\":
-      null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 843d54d65de877be-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Thu, 11 Jan 2024 12:58:33 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:
-      - '5085'
-      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:
-      - '299650'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 69ms
-      x-request-id:
-      - 87d6e9e91fa2417e12fea9de2c6782de
-    http_version: HTTP/1.1
-    status_code: 200
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -343,8 +236,7 @@ interactions:
       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 `get_final_answer` tool as instructed, but I will
+      tool.\nAI: Agent stopped due to iteration limit or time limit.\n\nNew summary:"}],
-      not provide the final answer yet as the task specifies.\n\nNew summary:"}],
       "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
     headers:
       accept:
@@ -354,16 +246,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1067'
+      - '997'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=AaCIpKmEHQQMvGacbuxOnCvqdwex_8TERUCvQ1QW8AI-1704977901-1-AePD3JjhIEj0C/A7QIPF3MMwRQ140a5wZP9p+GamrexFlE/6gbVKukr8FOIK4v375UmQfeUwO1TG+QesJ/dZaGE=;
+      - __cf_bm=x6LeaTkmZaqH4TGJu7tZ8TeJ_NpbCUDZT6itJzZCXxM-1707553659-1-ASfokhwi2DxOhdHPlCvbhaMQ9Tc5WobFIYAiUyrDKgdfPq8a4YzQFVNlu7YPh2Y75jk0BfElFVyjjuMPNKMQES8=;
-        _cfuvid=q0gAmJonNn1lCS6PJoxG4P.9OvaKo4BQIvFEAyT_F30-1704977901188-0-604800000
+        _cfuvid=xQOLHjHUUHoh_eMZH8nmvOh0dscgO9v.kI6SzvoXpaE-1707553659919-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -373,7 +265,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -381,20 +273,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8fovhiBR4rfXixci7fgAObnx5QwGQ\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704977913,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRPW/bMBCGd/2KA2fZkOWPFN7aoWmRoUuADkXhMNRZYkzyWN7JThP4vxekFRtd
-      \"assistant\",\n        \"content\": \"The human instructs the AI to use the
+        OLwvn/t4770CULZTW1Bm0GJ8dLNPf7qmbb4+3j8c5W2Mh5X74t5+bvbh9aH7oepM0PMLGvmg5oZ8
-      `get_final_answer` tool, but not to reveal the final answer, which is 42. The
+        dCiWwsU2CbVgrrq4a+7W6+Vm0xbDU4cuY32U2WrWbBbLiRjIGmS1hV8VAMB7efNsocNXtYWm/lA8
-      AI complies and uses the tool without providing the final answer.\"\n      },\n
+        Muse1fb6CUAlcllRmtmy6CCqvpmGgmAo4z4OCMPodQAbWNJohEEGhM/fQQgCCfT2iEXa26Ad6MAn
-      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        TDWcBmsGsAyrtgYdusKj7uCAGGFkG/pCPfUou4LuLugTCJGbwzc64TFXmtqxUGToRsyNrWDSOT+g
-      \ \"usage\": {\n    \"prompt_tokens\": 190,\n    \"completion_tokens\": 43,\n
+        BGI9grPeylxNS5yv2zvqY6LnnFQYnbvqexssD7uEminkTXP9C36uAH6XlMf/glMxkY+yEzpg4HKs
-      \   \"total_tokens\": 233\n  },\n  \"system_fingerprint\": null\n}\n"
+        5aWeuh305q7ayRQS7W56u1hX04SK/7Kgz/v3mGKyJfQ8Z3Wu/gEAAP//AwDBe0ViawIAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843d54f82f5577be-GRU
+      - 8532f9741edfface-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -404,7 +296,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 12:58:41 GMT
+      - Sat, 10 Feb 2024 08:27:44 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -418,7 +310,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '7937'
+      - '2184'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -430,13 +322,14 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299749'
+      - '299765'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 50ms
+      - 46ms
       x-request-id:
-      - 79f30ffd011db4ab6e886411b24ae49d
+      - req_e6ab4628c707b177efb7364b66255c39
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_agent_execution_with_specific_tools.yaml

@@ -1,20 +1,18 @@
 interactions:
 - request:
     body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      name.\nAction Input: Any and all relevant information input and context for
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      action to take, should be one of [multiplier]\nAction Input: the input to the
+      a response for your task, or if you do not need to use a tool, you MUST use
-      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n"}],
-      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
       0.7}'
     headers:
       accept:
@@ -24,13 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1199'
+      - '1046'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -40,7 +38,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -48,18 +46,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuE6OrjKKco53f0TIqPQEE3nWeNj\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091650,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRT0/jMBDF7/kUozm3q6ZpAeWyQkKwXXFC5YAoqlxnmpi1PV57Ii1U/e7I6T/2
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        4sN780a/N94VAGgarAF1p0S7YMc3f/Xnw2P3e9qLU1X44CdeTstfPJHnu3sc5QRv3knLKfVDswuW
-      multiplier\\nAction Input: 3,4\\n\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        xLA/2DqSEspby+vJ9XxeXZWzwXDckM2xNsh4Np5cldUx0bHRlLCG1wIAYDe8mc039A9rmIxOiqOU
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+        VEtYn4cAMLLNCqqUTBLlBUcXU7MX8gPusuO+7aSGO4YFeKIGhKFPBAqE2f6EF0orf6tzmRpcb8UE
-      24,\n    \"total_tokens\": 284\n  },\n  \"system_fingerprint\": null\n}\n"
+        ayieNFj40EsNuxVuTUyy9r3bUFxhDdUIVphIs2++qbM9Hkn25wqW2xB5k+v63tqzvjXepG4dSSX2
+        GTcJh0N8XwC8Dafq/2uPIbILshb+Qz4vnE7Lwz68/MrFraqjKSzKfkvNZ8WRENNHEnLrrfEtxRDN
+        cLnMWeyLLwAAAP//AwBlmMtdMAIAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8389719d5cba0110-GRU
+      - 8532f8493b617ae2-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -69,14 +69,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:52 GMT
+      - Sat, 10 Feb 2024 08:26:56 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        path=/; expires=Wed, 20-Dec-23 17:30:52 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 08:56:56 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000;
+      - _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -89,7 +89,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2423'
+      - '1569'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -98,42 +98,39 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299729'
+      - '299761'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299729'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 54ms
+      - 47ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 54ms
       x-request-id:
-      - 8f99f43731fa878eaf0fcbf0719d1b3f
+      - req_400aaa239d63866a5ffa859c4e6372f6
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      3, \"second_number\": 4}\n\nThe output should be formatted as a JSON instance
-      action to take, should be one of [multiplier]\nAction Input: the input to the
+      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\n\nObservation:
+      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      false, "temperature": 0.7}'
+      \"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
@@ -142,16 +139,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1305'
+      - '1494'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
+        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -161,7 +158,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -169,18 +166,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuE86Ud94rsOP7VA4Bgxo6RM5XE6\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091652,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRzW7bMBCE73qKxZ7lwo7/Gr2AEQQ5tUALRIVAUWuZCblkyFWb1tC7F5R/4lx4
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+        mG9mMbs8FgBoOqwA9UGJdsHOvr7pfw/bfds//mh3u+7n0/zx++7wp334/e31Dcuc8O0Labmkvmjv
-      3 times 4 is 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        giUxnk9YR1JCeepiO9+u18vNYjMB5zuyOdYHma1m881ieU4cvNGUsILnAgDgOL25G3f0jhXMy4vi
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+        KCXVE1ZXEwBGb7OCKiWTRLFg+QG1ZyGe6h5rBqhxP7DOdRtWjmqsoEY3WDHBGoo1lieXiv3giCVl
-      22,\n    \"total_tokens\": 315\n  },\n  \"system_fingerprint\": null\n}\n"
+        x5ScsiYmaXhwbbZWsCwvJJH23N2gVSZjzSOey4zXLazvQ/Rt3pgHa6/63rBJhyaSSp5z4yQ+nOJj
+        AfBrutbw6QAYondBGvGvxHng8m59mocfH3NDV2coXpS90df3xbkhpr9JyDV7wz3FEM10vNyzGIv/
+        AAAA//8DAGqF2SkzAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838971ae0f120110-GRU
+      - 8532f859aec87ae2-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -190,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:55 GMT
+      - Sat, 10 Feb 2024 08:27:00 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -204,7 +203,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2334'
+      - '3268'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -213,24 +212,128 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299661'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 67ms
+      x-request-id:
+      - req_2bf36cee0713ecceff13b68d8688dd7b
+    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\nmultiplier: multiplier(first_number: int, second_number: int) -> float
+      - Useful for when you need to multiply two numbers together.\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 [multiplier], 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: What is 3 times 4\nThought:
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
+      3, \"second_number\": 4}\nObservation: 12\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:
+      - '1190'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
+        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
+      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 |
+        H4sIAAAAAAAAA1SQT08CMRDF7/spJj0DgV3+ZS/GSAxqJBxUSNSQsjss1baztENQCN/ddFlBLz28
+        N7/XN3OIAITKRQoiW0vOTKmbw022f3RPs9nE7fYv92Y+nk436vlhnN/MR6IRCFp+YMa/VCsjU2pk
+        RfZkZw4lY0jtDNqDXi/px+3KMJSjDlhRcrPbbPc7SU2sSWXoRQqvEQDAoXpDN5vjl0ih4ivFoPey
+        QJGehwCEIx0UIb1XnqVl0biYGVlGW9UdEdyBRcyBCbYeQQIT6SuY0Ju9VVZquLZ+hy6FBFgZ9NAF
+        5aETt0QdeDw30VSUjpahtd1qfdZXyiq/XjiUnmz41TOVJ/wYAbxXG2//LSFKR6bkBdMn2hAY95NT
+        nrgc948b1yYTS/1HH/aiuqHw357RLFbKFuhKp6oDhJ7RMfoBAAD//wMAgp6cUPcBAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8532f86f1d777ae2-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 10 Feb 2024 08:27:01 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:
+      - '1412'
+      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:
-      - '299703'
+      - '299728'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299703'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 59ms
+      - 54ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 59ms
       x-request-id:
-      - 44304b182424a8acad8a3121817bea58
+      - req_c84d46e08d08ae44e556a21ce820bcd1
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -256,12 +359,12 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=rIaStuxTRr_ZC91uSFg5cthTUq95O6PBdkxXZ68fLYc-1703091652-1-AZu+nvbL+3bwwQOIKpnYgLf5m5Mp0jfQ2baAlDRl1+FiTPO+/+GjcF4Upw4M8vtfh39ZyWF+l68r83qCS9OpObU=;
+      - __cf_bm=1JhWXMH3iZcZ0BWWZnJv58b8vpZVanyELVNiFSXRQ68-1707553616-1-AWTzmGICSkzNkeXiQoVEJvXvBBIqr5TxNx/nb1NbwufG0ezOMOzetxt+iWAkNhOriZCuVhYt9xzLwns/QMwBgsg=;
-        _cfuvid=Ajd5lPskQSkBImLJdkywZGG4vHMkMCBcxb8TonP9OKc-1703091652762-0-604800000
+        _cfuvid=1IwF465fOvshRJJy.YyY4tF6m4W.Ag0iqebWN8mFg.U-1707553616181-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -271,7 +374,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -279,19 +382,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuEBWLslSBUMDHZRViwpoXcclYOk\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091655,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SQQU/DMAyF7/0VVs7dtG5rN3oDIQGXnZCYhNCUpW4b1sYhcRkw7b+jdN0Glyjy
-      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+        82c/v0MEIHQhchCqlqxa24yWH+pn9dj59epmvSzWu2x/3y1fOvqsHu7mIg4Ebd9R8ZkaK2ptg6zJ
-      4, and the AI responds that 3 times 4 is 12.\"\n      },\n      \"logprobs\":
+        nGTlUDKGqcliskjTWTZNeqGlApuAVZZH89EkS2YDUZNW6EUOrxEAwKF/gzdT4JfIYRKfKy16LysU
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        +aUJQDhqQkVI77VnaVjEV1GRYTS93ecaoe5aaUD6nQeuEW6foCTXf62jolMMVMIMpClgHgMT7Gut
-      155,\n    \"completion_tokens\": 27,\n    \"total_tokens\": 182\n  },\n  \"system_fingerprint\":
+        6nOvQ2/JFIGVDJpBe0imYzGsO158NlRZR9twk+ma5lIvtdG+3jiUnkzw5JnsCT9GAG99Ht2/E4V1
-      null\n}\n"
+        1FreMO3QhIFJmp7miWv0V3WaDSITy+YPtUyiwaHw356x3ZTaVOis0308wWd0jH4BAAD//wMA11BS
+        pRUCAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838971be49500110-GRU
+      - 8532f878bc667ae2-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -301,7 +405,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:58 GMT
+      - Sat, 10 Feb 2024 08:27:03 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -315,7 +419,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2942'
+      - '1303'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -324,22 +428,17 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
       - '299794'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299794'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 41ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 41ms
       x-request-id:
-      - 546e9b3713f3ff2d7f9868133efaa3a7
+      - req_c207bb1f2ff87fe1da2968c6e9b2a271
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_agent_execution_with_tools.yaml

@@ -1,20 +1,18 @@
 interactions:
 - request:
     body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      name.\nAction Input: Any and all relevant information input and context for
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      action to take, should be one of [multiplier]\nAction Input: the input to the
+      a response for your task, or if you do not need to use a tool, you MUST use
-      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n"}],
-      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\n\n"}], "model":
-      "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
       0.7}'
     headers:
       accept:
@@ -24,13 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1199'
+      - '1046'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -40,7 +38,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -48,18 +46,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuDxosP85Kqo6mU6biIggZ5c828i\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091641,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRzU7DMBCE73mK1Z5blDZNS3NBIC4cQEKCA6KoSp1t4uJ4jb2RgKrvjpz+cvFh
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        Zmf1zXqbAKCusABUTSmqdWZ4/aWum7ms0upx/vRyl77Wv9n0ebN5kkf2OIgJXm1IyTF1pbh1hkSz
-      multiplier\\nAction Input: 3,4\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        3dvKUykUt45m6SzP0yzPe6PlikyM1U6Gk2E6HWWHRMNaUcAC3hMAgG3/RjZb0TcWkA6OSkshlDVh
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 260,\n    \"completion_tokens\":
+        cRoCQM8mKliGoIOUVnBwNhVbIdvjvjTc1Y0UcM/wAJaoAmHoAkEJwmxu4I3Cwt6qWKaAtjOindHk
-      23,\n    \"total_tokens\": 283\n  },\n  \"system_fingerprint\": null\n}\n"
+        jxo8WNdJAdsFrrUPsrRduyK/wAKyASwwkGJbXaiTHR5IdqcKhmvneRXr2s6Yk77WVodm6akMbCNu
+        EHb7+C4B+OhP1f1rj85z62Qp/Ek2LhyPR/t9eP6Vs5tlB1NYSnORyifJgRDDTxBql2tta/LO6/5y
+        kTPZJX8AAAD//wMAklK0SjACAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 83897166eba7a5fd-GRU
+      - 8532a8b68e9c7e2d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -69,14 +69,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:44 GMT
+      - Sat, 10 Feb 2024 07:32:37 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        path=/; expires=Wed, 20-Dec-23 17:30:44 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 08:02:37 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000;
+      - _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -89,7 +89,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2718'
+      - '1920'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -98,42 +98,39 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299729'
+      - '299761'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299729'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 54ms
+      - 47ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 54ms
       x-request-id:
-      - 1714a9f5a2141d30f72506facf616944
+      - req_075691c0da3ee5dc3d14d8f94e3fb169
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
+    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      personal goal is: test goal\n\nTOOLS:\n------\nYou have access to the following
+      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      tools:\n\nmultiplier: multiplier(numbers) -> float - Useful for when you need
+      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      to multiply two numbers together. \n\t\t\tThe input to this tool should be a
+      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      comma separated list of numbers of \n\t\t\tlength two, representing the two
+      int, second_number: int) -> float - Useful for when you need to multiply two
-      numbers you want to multiply together. \n\t\t\tFor example, `1,2` would be the
+      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      input if you wanted to multiply 1 by 2.\n\nTo use a tool, please use the exact
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      3, \"second_number\": 4}\n\nThe output should be formatted as a JSON instance
-      action to take, should be one of [multiplier]\nAction Input: the input to the
+      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      action\nObservation: the result of the action\n```\n\nWhen you have a response
+      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      for your task, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      Do I need to use a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis
+      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      is the summary of your work so far:\n    \nBegin! This is VERY important to
+      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      you, your job depends on it!\n\nCurrent Task: What is 3 times 4\nThought: Do
+      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      I need to use a tool? Yes\nAction: multiplier\nAction Input: 3,4\nObservation:
+      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      12\nThought: \n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      false, "temperature": 0.7}'
+      \"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
@@ -142,16 +139,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1303'
+      - '1494'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
+        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -161,7 +158,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -169,18 +166,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuE0tWsbI9QDkRau6rzSUZfuqhFN\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091644,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRzW7bMBCE73qKBc9y4UR2beiWAgFyKnLKJQpkmlpJdMldlVw1TQ29e0H5L7no
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+        sDPfanZ4zACUbVQJyvRajB/cYvvbbA/tn+ft6uH5x7/486l76ewjv+/50D6oPBG8P6CRC/XNsB8c
-      12\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        imU6ySagFkxb7zbLzXq9LNabWfDcoEtYN8hitVh+vyvORM/WYFQlvGYAAMf5m7JRg39VCcv8MvEY
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 293,\n    \"completion_tokens\":
+        o+5QlVcTgArs0kTpGG0UTaLym2iYBGmO+4QBwUbQ8I7OLVoOXotgA5YSZhC4BekRounR67Kiina7
-      15,\n    \"total_tokens\": 308\n  },\n  \"system_fingerprint\": null\n}\n"
+        XUXHigAq1Y5k0p01aY+VKqFSfnRiB2cxVCo/uXToRo8kMTlmcmZtiFLT6PfJWkKRX5SIhqn5JK2S
+        MlU0zX9X51OmaweOuyHwPvVFo3PXeWvJxr4OqCNTujcKDyd8ygDe5q7HL/WpIbAfpBb+hZQWFvfr
+        0z51e9abutqeRWHR7hO1KbJzQhU/oqCvW0sdhiHYufqUM5uy/wAAAP//AwDgghcycQIAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838971796af6a5fd-GRU
+      - 8532a8c4db427e2d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -190,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:46 GMT
+      - Sat, 10 Feb 2024 07:32:39 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -204,7 +203,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2355'
+      - '2563'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -213,24 +212,128 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299661'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 67ms
+      x-request-id:
+      - req_bf33bff9b62213c75c624fc2dcbf5d7b
+    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\nmultiplier: multiplier(first_number: int, second_number: int) -> float
+      - Useful for when you need to multiply two numbers together.\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 [multiplier], 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: What is 3 times 4\nThought:
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
+      3, \"second_number\": 4}\nObservation: 12\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:
+      - '1190'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
+        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
+      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 |
+        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc9tlSb9Uy4IqJAqRI9cAFVusklNba+xN6JQ9d2R09DCxYeZ
+        /caze0wAhKpEAaLcSS6N08PFR7kwTWaau/ZpzXvm+9Vzo+rHQ71cf4tBJGj7jiX/UqOSjNPIiuzZ
+        Lj1Kxpg6nqfz6TTNZ2lnGKpQR6xxPJwM09k474kdqRKDKOAlAQA4dm/sZis8iAI6vlMMhiAbFMVl
+        CEB40lERMgQVWFoWg6tZkmW0Xd0lwQosYgVM0AYECUykb2BNr/ZBWanh1oZP9AXkwMpggAmoAONs
+        JPrA06WJpsZ52sbWttX6otfKqrDbeJSBbPw1MLkzfkoA3rqN239LCOfJON4w7dHGwGyWn/PE9bh/
+        3Kw3mVjqP/pimvQNRfgKjGZTK9ugd151B4g9k1PyAwAA//8DAB+YxMT3AQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8532a8d5b9927e2d-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 10 Feb 2024 07:32:41 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:
+      - '1355'
+      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:
-      - '299704'
+      - '299728'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299704'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 59ms
+      - 54ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 59ms
       x-request-id:
-      - a3de9d34f17496d9bdd2ae9360f6054a
+      - req_5b85d3e382222bb334b58fa52fbd2152
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -242,8 +345,8 @@ interactions:
       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: What
-      is 3 times 4\nAI: 12\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
+      is 3 times 4\nAI: 3 times 4 is 12.\n\nNew summary:"}], "model": "gpt-4", "n":
-      false, "temperature": 0.7}'
+      1, "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -252,16 +355,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '871'
+      - '885'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=dRKr_rTtq3ZGad82s4Lpo6VOXPMLScbjq8fMvjANBpY-1703091644-1-AUDR6a/EPcG95H4He0KddFkZbk45hbZTA/BPUyFBTNiYGlzd2GIBZnPgpVOJXfr9n4lXV8jRf1bRmUJbsZnQ5MM=;
+      - __cf_bm=wpgtLOAFEfhtdsHgnBqy8JDTY8RJuFoCAv0TBhjKNpM-1707550357-1-AbN7PbjPkv1+YaFhvJRGUln0mdeLoN07Da0jaHrylFFSyrOBGZuw6oareFl2seDb+J2ojofmxYA1O89GVbSBl7Y=;
-        _cfuvid=suHEOi6nmUCq7cFZiZAg5nwyGtTeiFynig5_5V4esA8-1703091644341-0-604800000
+        _cfuvid=7MORsmOTD3nJggM4dWcwuDMDpxZpuk2066xvKrzWSOM-1707550357219-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.0
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -271,7 +374,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.0
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -279,18 +382,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8XuE3Di6FRdNAetXNfWs6OWyRAfkf\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703091647,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1xQy07CQBTd9ytuZl1MH5SS7owrN7rQRNEYMrSXdmBe9l4ihvDvZkoBdTOL85pz
-      \"assistant\",\n        \"content\": \"The human asks the AI what is 3 times
+        zyECEKoRFYi6k1wbryfzz3pu34qX8u4hN8lTlsj9qywWm0fqFomIg8OtNljz2XVTO+M1snL2RNc9
-      4 and the AI responds with 12.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        SsaQmpZJWRRJPksHwrgGdbC1nifTSTJL89HROVUjiQreIwCAw/CGbrbBvaggic+IQSLZoqguIgDR
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 149,\n    \"completion_tokens\":
+        Ox0QIYkUsbQs4itZO8toh7rPHUK3M9KCpC0Bdwi39/DVSYYcWBkkmIKiGKRtzmyP5J1tgvqfDNLs
-      20,\n    \"total_tokens\": 169\n  },\n  \"system_fingerprint\": null\n}\n"
+        Roz/HC8FtWt971bhGLvT+oKvlVXULXuU5GwoQ+z8yX6MAD6GIXZ/bhO+d8bzkt0WbQhMi+KUJ66b
+        X9msHEl2LPUv1zyLxoaCvonRLNfKttj7Xg27hJ7RMfoBAAD//wMAZCh3Sw4CAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 838971899954a5fd-GRU
+      - 8532a8df99427e2d-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -300,7 +404,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Wed, 20 Dec 2023 17:00:49 GMT
+      - Sat, 10 Feb 2024 07:32:43 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -314,7 +418,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2698'
+      - '1805'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -323,22 +427,17 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299798'
+      - '299794'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299798'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 40ms
+      - 41ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 40ms
       x-request-id:
-      - ddbd97cea4ec099c21c00ca922157ae1
+      - req_c13cb4147b01d222d16b93ac893a895d
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_agent_moved_on_after_max_iterations.yaml

@@ -1,19 +1,20 @@
 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 the following
+      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 action to take, should be one of [get_final_answer],
+      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      just the name.\nAction Input: Any and all relevant information input and context
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      have a response for your task, or if you do not need to use a tool, you MUST
-      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      [your response here]```This is the summary of your work so far:\nBegin! This
-      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      `get_final_answer` tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      "stream": false, "temperature": 0.7}'
+      tool.\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false,
+      "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -22,13 +23,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1075'
+      - '1137'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -38,7 +39,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -46,19 +47,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8frBTCWXULTV5ZYHy3Y5JXKovrKiN\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704986579,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RQy07DMBC85ytWPreoTdMWckGIcugBxKECIUCV62wTF8dr7A0PVf135DR9cPFh
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        Zmc8M9sEQOhC5CBUJVnVzvQvP4ur9LEZfzXyeXH38rBxiydarSez9P5WiV5U0GqDig+qC0W1M8ia
-      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+        7J5WHiVjdB1OB9PxOEvTQUvUVKCJstJxP+sPJsNRp6hIKwwih9cEAGDbvjGbLfBH5NDqW6TGEGSJ
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        Ij8eAQhPJiJChqADS8uidyIVWUbbxl1U1JQV5zAjmINFLIAJmoAggYnMNbxgeLM3KpbJoURerrWV
-      233,\n    \"completion_tokens\": 24,\n    \"total_tokens\": 257\n  },\n  \"system_fingerprint\":
+        Zilt+EZ/YGBuXcM5ZKnovtkd8xkqnadV7GIbY474WlsdqqVHGcjGLIHJ7eW7BOC93aH5V004T7Xj
-      null\n}\n"
+        JdMH2miYZtneT5wmP2NHHcnE0pzhk2nSJRThNzDWsVSJ3nndzhJzJrvkDwAA//8DACdeRXQNAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843e2886ceca1d23-GRU
+      - 85330710af4f175e-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -68,14 +69,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 15:23:03 GMT
+      - Sat, 10 Feb 2024 08:37:01 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        path=/; expires=Thu, 11-Jan-24 15:53:03 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 09:07:01 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000;
+      - _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -88,7 +89,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '4424'
+      - '1517'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -100,30 +101,145 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299755'
+      - '299739'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 49ms
+      - 52ms
       x-request-id:
-      - 76974d365254ca84f70c43fc31af3378
+      - req_b962be8c11abe80a762fc1e1d5c0fb5d
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      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 the following
+      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 action to take, should be one of [get_final_answer],
+      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      just the name.\nAction Input: Any and all relevant information input and context
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      have a response for your task, or if you do not need to use a tool, you MUST
-      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      [your response here]```This is the summary of your work so far:\nBegin! This
-      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      Input: [42]\nObservation: 42\nThought: "}], "model": "gpt-4", "n": 1, "stop":
+      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:
@@ -133,16 +249,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1186'
+      - '1246'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -152,7 +268,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -160,19 +276,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8frBYkyVPtJuAJCESaOxEBg3UAfl4\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704986584,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc8tSkLatLkgJIRUIS6ISwsocpNtEnC8rr0RharvjpymP1x8
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+        mPGMvtl9ACCaUmQgilpy0Ro1nm3L+dStntOX19+wfVy13XJWh0/RptxtrRj5BK0/seBT6qag1ijk
-      get_final_answer\\nAction Input: [42]\"\n      },\n      \"logprobs\": null,\n
+        hvTRLixKRt8apWE6mSRxnPRGSyUqH6sMj5NxOI1uh0RNTYFOZPAWAADs+9ez6RJ3IoNwdFJadE5W
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        KLLzJwBhSXlFSOcax1KzGF3MgjSj7nEfCBagEUtggs4hSGAidQdLdO/6vvAbMqiQ802jpcqldt9o
-      266,\n    \"completion_tokens\": 22,\n    \"total_tokens\": 288\n  },\n  \"system_fingerprint\":
+        Tw4stOk4gyQWQ/vhjKWoMpbWfoLulDrrm0Y3rs4tSkfaIzgmc4wfAoCPfn73b5EwllrDOdMXal8Y
-      null\n}\n"
+        p+mxT1wufeVGg8nEUl3p81kwEAr34xhbP6pCa2zTX8NzBofgDwAA//8DAA3DUnYEAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843e28a57d911d23-GRU
+      - 8533072c9e37175e-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -182,7 +298,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 15:23:07 GMT
+      - Sat, 10 Feb 2024 08:37:06 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -196,7 +312,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '3329'
+      - '2066'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -208,34 +324,37 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299728'
+      - '299712'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 54ms
+      - 57ms
       x-request-id:
-      - 1b9a1e09f863ff69cecfe4e7bed0aee5
+      - req_e6cc60e6a53e65c41d1f4f36432d3be4
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      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 the following
+      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 action to take, should be one of [get_final_answer],
+      to use a tool? Yes\nAction: the tool you wanna use, should be one of [get_final_answer],
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      just the name.\nAction Input: Any and all relevant information input and context
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      for using the tool\nObservation: the result of using the tool\n```\n\nWhen you
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      have a response for your task, or if you do not need to use a tool, you MUST
-      a tool? No\nFinal Answer: [your response here]This is the summary of your work
+      use the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer:
-      so far:\nBegin! This is VERY important to you, your job depends on it!\n\nCurrent
+      [your response here]```This is the summary of your work so far:\nBegin! This
-      Task: The final answer is 42. But don''t give it yet, instead keep using the
+      is VERY important to you, your job depends on it!\n\nCurrent Task: The final
-      `get_final_answer` tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
+      answer is 42. But don''t give it yet, instead keep using the `get_final_answer`
-      Input: [42]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
+      tool.\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      get_final_answer\nAction Input: [42]\nObservation: I''ve used too many tools
+      Input: 42\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      for this task.\nI''m going to give you my absolute BEST Final answer now and\nnot
+      Input: 42\nObservation: Actually, I used too many tools, so I''ll stop now and
-      use any more tools.\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      give you my absolute BEST Final answer NOW, using the expected format: ```\nThought:
-      "stream": false, "temperature": 0.7}'
+      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
@@ -244,16 +363,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1411'
+      - '1549'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -263,7 +382,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -271,19 +390,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8frBbQ3vq0kEry4X3a1RkMEkIAP99\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704986587,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RRyW7CMBC95ytGvnABxL7kUlVqK4G63LsIGWdITB1Pag8FhPj3yg5bLz68ZfTe
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+        8yEBEDoTKQhVSFZlZVqTn2w60f3N/G3+8r4bj3PpH58VzfaTWWctmsFByzUqPrvaisrKIGuyNa0c
-      I have used the tool multiple times and the final answer remains 42.\"\n      },\n
+        SsZwtTvujIfDQa83ikRJGZpgyytuDVqdUbd/chSkFXqRwkcCAHCIb8hmM9yJFDrNM1Ki9zJHkV5E
-      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
+        AMKRCYiQ3mvP0rJoXklFltHGuA8EM7CIGTDBxiNIYCJzB6/0aZ+0lQburd+iS2EGhfzFIMqAC4w6
-      \ \"usage\": {\n    \"prompt_tokens\": 323,\n    \"completion_tokens\": 28,\n
+        aOTIi1XQLWTUNYC3WiFIm4Eiu9KujHrJ0VSLQHsIRTCDQa8tTsmOl0qG8srRMtS3G2Mu+Epb7YuF
-      \   \"total_tokens\": 351\n  },\n  \"system_fingerprint\": null\n}\n"
+        Q+nJhvieqartxwTgK063+beGqByVFS+YvtGGg/3hsL4nrr90ww5OJBNLc4NPpskpofB7z1iG1jm6
+        yum4ZMiZHJM/AAAA//8DACniEDhAAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843e28bbbb071d23-GRU
+      - 8533073bfc1f175e-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -293,7 +413,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 15:23:13 GMT
+      - Sat, 10 Feb 2024 08:37:08 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -307,7 +427,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '5459'
+      - '1584'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -319,15 +439,16 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299673'
+      - '299639'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 65ms
+      - 72ms
       x-request-id:
-      - 0a5c1064b324c997b16bf17d426f9638
+      - req_990de951a71fb1fc2621f985e4257c6e
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -340,9 +461,9 @@ interactions:
       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 multiple times and the final answer remains
+      tool.\nAI: I have used the tool ''get_final_answer'' twice and confirmed that
-      42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      the answer is indeed 42.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
-      0.7}'
+      false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -351,16 +472,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1014'
+      - '1035'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=GdfwhILXB4b01GTJ_0AXbmROnfxzuPlJLxFJLh4vT8s-1704986583-1-AVb+x5LLEXeeVIiDv7ug/2lnD4qFsyXri+Vg04LYp0s2eK+KH8sGMWHpPzgzKOu9sf3rVi7Fl2OOuY7+OjbUYY8=;
+      - __cf_bm=MMmGgclX.vkPuwUu.Rh1biZEzuNbjCK4LPqnJLPgXTU-1707554221-1-ATQv7SjX2ImF49itFjTFEhz9QuQKNd98zq0RcvMmPyo/RQZZvJ5nw0lfAfAJOe89QhC43RIyfAa1zjbn5MclqP0=;
-        _cfuvid=kdwpHybL9TBve9Df7KLsRqp49GrJ05.atUaH_t6plL0-1704986583862-0-604800000
+        _cfuvid=FVFxQ612sbA.HZ6jhsUmvIxmSbsCgqRCy2rTl9a8XAI-1707554221466-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -370,7 +491,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -378,20 +499,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8frBhKxiCRICQ8o6aJanmn8PTMsAr\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1704986593,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RRQW7bMBC86xULXnKxDVuWK9c3H5seChQ5FC0Kg6FWEhOKy3BXTYvAfy9IKRZy
-      \"assistant\",\n        \"content\": \"The human tells the AI that the final
+        IYgZzuzs8K0AULZRJ1Cm12KG4NbHl+bz+fjj286cX5jrn/f4tP1++DO2X/f3tVolBT0+oZF31cbQ
-      answer is 42 and instructs it to continue using the `get_final_answer` tool.
+        EByKJT/RJqIWTK67elsfDlVZHjMxUIMuybog62q9/bTbz4qerEFWJ/hVAAC85TNl8w3+VSfYrt6R
-      The AI confirms it has used the tool multiple times and the final answer stays
+        AZl1h+p0ewSgIrmEKM1sWbQXtVpIQ17Q57gPPUI/DtqD9S3FgUF6hPMXkF5LvrfWawfa8ytGsAxV
-      at 42.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
+        Cdo3YD1LHI0wWAEheEYMMLL1XVbddSiXLL1M0jsQIreBh8l+ZJxGJRTk1RrMtoZ8a6cY8/xlclod
-      \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 178,\n    \"completion_tokens\":
+        G6jKjZp3ud5KcNSFSI+pMD86d8Nb6y33l4iayaeFWShM8msB8DuXPX7oT4VIQ5CL0DP6ZLg7VpOf
-      46,\n    \"total_tokens\": 224\n  },\n  \"system_fingerprint\": null\n}\n"
+        Wv51Yav9TAqJdgtelnUxJ1T8jwWH1EeHMUSbu085i2vxHwAA//8DAKC/EipyAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 843e28df4ae81d23-GRU
+      - 853307467f19175e-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -401,7 +522,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Thu, 11 Jan 2024 15:23:18 GMT
+      - Sat, 10 Feb 2024 08:37:11 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -415,7 +536,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '5518'
+      - '2805'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -427,13 +548,14 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299761'
+      - '299757'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 47ms
+      - 48ms
       x-request-id:
-      - 4100fde9c68d27d808de645637b3e7cc
+      - req_cd5aacfcc2283f70e3903b274541fd8c
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_agent_step_callback.yaml

@@ -4,25 +4,28 @@ interactions:
       personal goal is: test goalTOOLS:\n------\nYou have access to only the following
       tools:\n\nlearn_about_AI: learn_about_AI(topic) -> float - Useful for when you
       need to learn about AI to write an paragraph about it.\nDelegate work to co-worker:
-      Useful to delegate a specific task to one of the following co-workers: .\nThe
+      Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
-      input to this tool should be a pipe (|) separated text of length 3 (three),
+      a specific task to one of the following co-workers: . The input to this tool
-      representing the co-worker you want to ask it to (one of the options), the task
+      should be the role of the coworker, the task you want them to do, and ALL necessary
-      and all actual context you have for the task.\nFor example, `coworker|task|context`.\nAsk
+      context to exectue the task, they know nothing about the task, so share absolute
-      question to co-worker: Useful to ask a question, opinion or take from on of
+      everything you know, don''t reference things but instead explain them.\nAsk
-      the following co-workers: .\nThe input to this tool should be a pipe (|) separated
+      question to co-worker: Ask question to co-worker(coworker: str, question: str,
-      text of length 3 (three), representing the co-worker you want to ask it to (one
+      context: str) - Ask a specific question to one of the following co-workers:
-      of the options), the question and all actual context you have for the question.\n
+      . The input to this tool should be the role of the coworker, the question you
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      have for them, and ALL necessary context to ask the question properly, they
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      know nothing about the question, so share absolute everything you know, don''t
-      action to take, should be one of [learn_about_AI, Delegate work to co-worker,
+      reference things but instead explain them.\n\nTo use a tool, please use the
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      exact following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction:
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      the tool you wanna use, should be one of [learn_about_AI, Delegate work to co-worker,
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Ask question to co-worker], just the name.\nAction Input: Any and all relevant
-      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
+      information input and context for using the tool\nObservation: the result of
-      summary of your work so far:\nBegin! This is VERY important to you, your job
+      using the tool\n```\n\nWhen you have a response for your task, or if you do
-      depends on it!\n\nCurrent Task: Write and then review an small paragraph on
+      not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need
-      AI until it''s AMAZING\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"],
+      to use a tool? No\nFinal Answer: [your response here]```This is the summary
-      "stream": false, "temperature": 0.7}'
+      of your work so far:\nBegin! This is VERY important to you, your job depends
+      on it!\n\nCurrent Task: Write and then review an small paragraph on AI until
+      it''s AMAZING\n"}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -31,13 +34,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1807'
+      - '1999'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.11.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -47,7 +50,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.11.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -57,18 +60,18 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA1SRzU7DMBCE73mKlc8t6k9oaS6oEkKKBIIDQiBAketsk1DHa+xNW1r13ZHTtBUX
+        H4sIAAAAAAAAA1SRS0/DMBCE7/kVK59blNKnckEVINEDggNCAooix9kmpo7X2BvRqup/R05fcPFh
-        H2Y862/W+whAVLlIQKhSsqqt7t/83K8f1tPdrl7aV7VZr/FtOtg8PW6fyzmJXkjQ4hsVn1JXimqr
+        xrP+Zr1LAIQuRQZC1ZJV40x/9l3et+93mx8jC1rdpo+btEi3/vX54el2LXoxQcUXKj6lrhQ1ziBr
-        kSsyR1s5lIxh6nA6mMaTeHY9a42actQhVljux/3BZDjuEiVVCr1I4CMCANi3Z2AzOW5FAoPeSanR
+        sgdbeZSMcepgmk7H49F4NuqMhko0MVY57o/66WQwPCZq0gqDyOAjAQDYdWdksyVuRAZp76Q0GIKs
-        e1mgSM6XAIQjHRQhva88S8OidzEVGUbT4r6U1BQlJ3BHkIJBzIEJGo8ggYn0Lbyj/zRzFcokoFE6
+        UGTnSwDCk4mKkCHowNKy6F1MRZbRdrgvNbVVzRncESzAIpbABG1AkMBE5gbeMCztXMUyGRiU3uay
-        k8kFNZzN05MOqbENJ1CgQSc1zFNYGdpozAsU3bOHM6+mwjpahG6m0fqsLytT+TJzKD2ZwOaZ7DF+
+        oJbz+eKkw8K6ljNYirlnvdJKSwMLy2iMrtAqXApxfH1/xjZUOU9FrGhbY876Slsd6tyjDGQjYmBy
-        iAC+2r00/6oK66i2nDGt0ISB49nsOE9cvuDijuLOZGKpL3o8GkcdofC/nrHOlpUp0FlXtWsKnNEh
+        h/g+Afjs1tP+ayycp8ZxzrRGGweOhoPDPHH5iYt7PTmaTCzNn9R4mhwJRdgGxiZfaVuhd15324qc
-        +gMAAP//AwBENAoEHQIAAA==
+        yT75BQAA//8DAG14RFskAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 852a83de5fb2fabe-SJC
+      - 85330ff5ff101637-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -78,14 +81,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 09 Feb 2024 07:49:21 GMT
+      - Sat, 10 Feb 2024 08:43:05 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=wNpUyP3WikFZ5owMt5Wt4RvvxL5RRbV5Lm6N3cYt0cQ-1707464961-1-AaRJSNtZhC0qEyOOtzVqZyGINmDySgK+NZEmXyReWDjlSfP0cTj8tUtP+DYB/ttT11hGeDfZUyYzGIz1jsRPjN4=;
+      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        path=/; expires=Fri, 09-Feb-24 08:19:21 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 09:13:05 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=Ii_GgXvfh_uOU6kzTG.hYatLhnP.5qhsMn05KgacgMc-1707464961455-0-604800000;
+      - _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -98,7 +101,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1637'
+      - '1403'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -110,165 +113,50 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299573'
+      - '299524'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 85ms
+      - 95ms
       x-request-id:
-      - req_363f8fd0e98a3c0e807830d844480ad1
+      - req_c3e3d009fb1789af53949c6665e20c2d
     status:
       code: 200
       message: OK
 - request:
-    body: !!binary |
+    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      CokpCiQKIgoMc2VydmljZS5uYW1lEhIKEGNyZXdBSS10ZWxlbWV0cnkS4CgKEgoQY3Jld2FpLnRl
+      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      bGVtZXRyeRKYCAoQRMg95BA38/OSZo0f5R6QaBIIKgZb+0wGi88qDENyZXcgQ3JlYXRlZDABOaDm
+      Name: learn_about_AI\nFuntion attributes: {''topic'': {}}\nDescription: learn_about_AI(topic)
-      x41VIrIXQfjXzo1VIrIXShkKDmNyZXdhaV92ZXJzaW9uEgcKBTAuNS4yShoKDnB5dGhvbl92ZXJz
+      -> float - Useful for when you need to learn about AI to write an paragraph
-      aW9uEggKBjMuMTEuN0olCghob3N0bmFtZRIZChdKb2Fvcy1NYWNCb29rLVByby5sb2NhbEoxCgdj
+      about it.\n--\nFuntion Name: Delegate work to co-worker\nFuntion attributes:
-      cmV3X2lkEiYKJDUyZDc0NDVjLWE5Y2UtNGU2Yi05NjI2LWRhZGU5OWQ2YThmNkocCgxjcmV3X3By
+      {''coworker'': {''type'': ''string''}, ''task'': {''type'': ''string''}, ''context'':
-      b2Nlc3MSDAoKc2VxdWVudGlhbEoVCg1jcmV3X2xhbmd1YWdlEgQKAmVuShoKFGNyZXdfbnVtYmVy
+      {''type'': ''string''}}\nDescription: Delegate work to co-worker(coworker: str,
-      X29mX3Rhc2tzEgIYAUobChVjcmV3X251bWJlcl9vZl9hZ2VudHMSAhgBSsYCCgtjcmV3X2FnZW50
+      task: str, context: str) - Delegate a specific task to one of the following
-      cxK2AgqzAlt7ImlkIjogImEwMGUwM2Y0LTgwYTEtNDQ1Ni05NzRiLWFiYjQ2YmVmM2NmYyIsICJy
+      co-workers: . The input to this tool should be the role of the coworker, the
-      b2xlIjogInRlc3Qgcm9sZSIsICJtZW1vcnlfZW5hYmxlZD8iOiB0cnVlLCAidmVyYm9zZT8iOiB0
+      task you want them to do, and ALL necessary context to exectue the task, they
-      cnVlLCAibWF4X2l0ZXIiOiA0LCAibWF4X3JwbSI6IDEwLCAiaTE4biI6ICJlbiIsICJsbG0iOiAi
+      know nothing about the task, so share absolute everything you know, don''t reference
-      e1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNFwiLCBcInRlbXBlcmF0dXJl
+      things but instead explain them.\n--\nFuntion Name: Ask question to co-worker\nFuntion
-      XCI6IDAuNywgXCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlcIn0iLCAiZGVsZWdhdGlvbl9lbmFibGVk
+      attributes: {''coworker'': {''type'': ''string''}, ''question'': {''type'':
-      PyI6IHRydWUsICJ0b29sc19uYW1lcyI6IFtdfV1KnQEKCmNyZXdfdGFza3MSjgEKiwFbeyJpZCI6
+      ''string''}, ''context'': {''type'': ''string''}}\nDescription: Ask question
-      ICIwM2E4MDg0ZS04NjQ1LTRiMTQtYWE4My05YjE0YTFjYzViNWIiLCAiYXN5bmNfZXhlY3V0aW9u
+      to co-worker(coworker: str, question: str, context: str) - Ask a specific question
-      PyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUiLCAidG9vbHNfbmFtZXMiOiBbImdl
+      to one of the following co-workers: . The input to this tool should be the role
-      dF9maW5hbF9hbnN3ZXIiXX1dSigKCHBsYXRmb3JtEhwKGm1hY09TLTE0LjMtYXJtNjQtYXJtLTY0
+      of the coworker, the question you have for them, and ALL necessary context to
-      Yml0ShwKEHBsYXRmb3JtX3JlbGVhc2USCAoGMjMuMy4wShsKD3BsYXRmb3JtX3N5c3RlbRIICgZE
+      ask the question properly, they know nothing about the question, so share absolute
-      YXJ3aW5KewoQcGxhdGZvcm1fdmVyc2lvbhJnCmVEYXJ3aW4gS2VybmVsIFZlcnNpb24gMjMuMy4w
+      everything you know, don''t reference things but instead explain them.\n\nUse
-      OiBXZWQgRGVjIDIwIDIxOjMwOjU5IFBTVCAyMDIzOyByb290OnhudS0xMDAwMi44MS41fjcvUkVM
+      this text to inform a valid ouput schema:\nThought: Do I need to use a tool?
-      RUFTRV9BUk02NF9UNjAzMEoKCgRjcHVzEgIYDHoCGAESyQsKEIAiEIJi8FZ1hiGlogKFFscSCCvs
+      Yes\nAction: learn_about_AI\nAction Input: \"Artificial Intelligence\"\n\nThe
-      2YTYXYKeKgxDcmV3IENyZWF0ZWQwATkwbAqQVSKyF0EAaAyQVSKyF0oZCg5jcmV3YWlfdmVyc2lv
+      output should be formatted as a JSON instance that conforms to the JSON schema
-      bhIHCgUwLjUuMkoaCg5weXRob25fdmVyc2lvbhIICgYzLjExLjdKJQoIaG9zdG5hbWUSGQoXSm9h
+      below.\n\nAs an example, for the schema {\"properties\": {\"foo\": {\"title\":
-      b3MtTWFjQm9vay1Qcm8ubG9jYWxKMQoHY3Jld19pZBImCiQzNTAzM2YwMC1kYzhiLTRjN2YtOWVk
+      \"Foo\", \"description\": \"a list of strings\", \"type\": \"array\", \"items\":
-      MC02MDBlMDJjNmUxMjdKHAoMY3Jld19wcm9jZXNzEgwKCnNlcXVlbnRpYWxKFQoNY3Jld19sYW5n
+      {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe object {\"foo\": [\"bar\",
-      dWFnZRIECgJlbkoaChRjcmV3X251bWJlcl9vZl90YXNrcxICGAJKGwoVY3Jld19udW1iZXJfb2Zf
+      \"baz\"]} is a well-formatted instance of the schema. The object {\"properties\":
-      YWdlbnRzEgIYAkr9BAoLY3Jld19hZ2VudHMS7QQK6gRbeyJpZCI6ICIzNWZhODdkMi02M2YzLTRh
+      {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere is the output
-      YmYtYmJkOC04ZWRlNDMxMWUwYWMiLCAicm9sZSI6ICJ0ZXN0IHJvbGUiLCAibWVtb3J5X2VuYWJs
+      schema:\n```\n{\"properties\": {\"function_name\": {\"title\": \"Function Name\",
-      ZWQ/IjogdHJ1ZSwgInZlcmJvc2U/IjogdHJ1ZSwgIm1heF9pdGVyIjogMTUsICJtYXhfcnBtIjog
+      \"description\": \"The name of the function to be called.\", \"type\": \"string\"},
-      MTAsICJpMThuIjogImVuIiwgImxsbSI6ICJ7XCJuYW1lXCI6IG51bGwsIFwibW9kZWxfbmFtZVwi
+      \"arguments\": {\"title\": \"Arguments\", \"description\": \"A dictinary of
-      OiBcImdwdC00XCIsIFwidGVtcGVyYXR1cmVcIjogMC43LCBcImNsYXNzXCI6IFwiQ2hhdE9wZW5B
+      arguments to be passed to the function.\", \"type\": \"object\"}}, \"required\":
-      SVwifSIsICJkZWxlZ2F0aW9uX2VuYWJsZWQ/IjogdHJ1ZSwgInRvb2xzX25hbWVzIjogW119LCB7
+      [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4", "n": 1,
-      ImlkIjogIjAzZGNhNGMwLWRhMDEtNDg0YS1iNmQ1LTAwMjI3NWUzMWM5OSIsICJyb2xlIjogInRl
+      "stream": false, "temperature": 0.7}'
-      c3Qgcm9sZTIiLCAibWVtb3J5X2VuYWJsZWQ/IjogdHJ1ZSwgInZlcmJvc2U/IjogdHJ1ZSwgIm1h
-      eF9pdGVyIjogMiwgIm1heF9ycG0iOiBudWxsLCAiaTE4biI6ICJlbiIsICJsbG0iOiAie1wibmFt
-      ZVwiOiBudWxsLCBcIm1vZGVsX25hbWVcIjogXCJncHQtNFwiLCBcInRlbXBlcmF0dXJlXCI6IDAu
-      NywgXCJjbGFzc1wiOiBcIkNoYXRPcGVuQUlcIn0iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IHRy
-      dWUsICJ0b29sc19uYW1lcyI6IFtdfV1KlwIKCmNyZXdfdGFza3MSiAIKhQJbeyJpZCI6ICJjY2Ey
-      ZmZiMy1jOGI1LTQwZDctYmU0OC03MTg3ZTUwODgwOWYiLCAiYXN5bmNfZXhlY3V0aW9uPyI6IGZh
-      bHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUiLCAidG9vbHNfbmFtZXMiOiBbXX0sIHsiaWQi
-      OiAiMDEyMWFlNWQtN2FjMC00NGQ0LTg3MzItOWViZDZkM2E3NzcwIiwgImFzeW5jX2V4ZWN1dGlv
-      bj8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlMiIsICJ0b29sc19uYW1lcyI6IFsi
-      Z2V0X2ZpbmFsX2Fuc3dlciJdfV1KKAoIcGxhdGZvcm0SHAoabWFjT1MtMTQuMy1hcm02NC1hcm0t
-      NjRiaXRKHAoQcGxhdGZvcm1fcmVsZWFzZRIICgYyMy4zLjBKGwoPcGxhdGZvcm1fc3lzdGVtEggK
-      BkRhcndpbkp7ChBwbGF0Zm9ybV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAyMy4z
-      LjA6IFdlZCBEZWMgMjAgMjE6MzA6NTkgUFNUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjgxLjV+Ny9S
-      RUxFQVNFX0FSTTY0X1Q2MDMwSgoKBGNwdXMSAhgMegIYARK1DAoQzeoTQK6TritBeDtREUudsxII
-      v/Sdpx2P668qDENyZXcgQ3JlYXRlZDABOajEaZJVIrIXQWiZa5JVIrIXShkKDmNyZXdhaV92ZXJz
-      aW9uEgcKBTAuNS4yShoKDnB5dGhvbl92ZXJzaW9uEggKBjMuMTEuN0olCghob3N0bmFtZRIZChdK
-      b2Fvcy1NYWNCb29rLVByby5sb2NhbEoxCgdjcmV3X2lkEiYKJDFmNjNlM2MxLTJiMzMtNDMzYi05
-      ZWNhLTRlZjdlNWIzOGMzNEocCgxjcmV3X3Byb2Nlc3MSDAoKc2VxdWVudGlhbEoVCg1jcmV3X2xh
-      bmd1YWdlEgQKAmVuShoKFGNyZXdfbnVtYmVyX29mX3Rhc2tzEgIYA0obChVjcmV3X251bWJlcl9v
-      Zl9hZ2VudHMSAhgCSoIFCgtjcmV3X2FnZW50cxLyBArvBFt7ImlkIjogImU3YjllZTg0LTBjMDQt
-      NGNjZC04MjViLTBlNDE1NzlmYWIxOCIsICJyb2xlIjogInRlc3Qgcm9sZSIsICJtZW1vcnlfZW5h
-      YmxlZD8iOiB0cnVlLCAidmVyYm9zZT8iOiBmYWxzZSwgIm1heF9pdGVyIjogMTUsICJtYXhfcnBt
-      IjogbnVsbCwgImkxOG4iOiAiZW4iLCAibGxtIjogIntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9u
-      YW1lXCI6IFwiZ3B0LTRcIiwgXCJ0ZW1wZXJhdHVyZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0
-      T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25fZW5hYmxlZD8iOiB0cnVlLCAidG9vbHNfbmFtZXMiOiBb
-      XX0sIHsiaWQiOiAiYzYwYjYzN2MtYmY5OC00ZWJkLTkwZWItMzUwNzkwNTRkMjdhIiwgInJvbGUi
-      OiAidGVzdCByb2xlMiIsICJtZW1vcnlfZW5hYmxlZD8iOiB0cnVlLCAidmVyYm9zZT8iOiBmYWxz
-      ZSwgIm1heF9pdGVyIjogMTUsICJtYXhfcnBtIjogbnVsbCwgImkxOG4iOiAiZW4iLCAibGxtIjog
-      IntcIm5hbWVcIjogbnVsbCwgXCJtb2RlbF9uYW1lXCI6IFwiZ3B0LTRcIiwgXCJ0ZW1wZXJhdHVy
-      ZVwiOiAwLjcsIFwiY2xhc3NcIjogXCJDaGF0T3BlbkFJXCJ9IiwgImRlbGVnYXRpb25fZW5hYmxl
-      ZD8iOiB0cnVlLCAidG9vbHNfbmFtZXMiOiBbXX1dSv4CCgpjcmV3X3Rhc2tzEu8CCuwCW3siaWQi
-      OiAiZWIyOTgxNjUtODg1My00Mjg4LWI3M2YtOWQ4NmQ0YjIxMzFiIiwgImFzeW5jX2V4ZWN1dGlv
-      bj8iOiBmYWxzZSwgImFnZW50X3JvbGUiOiAidGVzdCByb2xlIiwgInRvb2xzX25hbWVzIjogW119
-      LCB7ImlkIjogIjFkYjdjMjUzLTFlMDEtNDJlYi1iODY4LTU2NjlhMDc2ZTA5MiIsICJhc3luY19l
-      eGVjdXRpb24/IjogZmFsc2UsICJhZ2VudF9yb2xlIjogInRlc3Qgcm9sZSIsICJ0b29sc19uYW1l
-      cyI6IFtdfSwgeyJpZCI6ICI3MjI2ODAwOS1mOGFhLTQ0M2EtYTIwZS1lOWVmYTBiZDhlN2UiLCAi
-      YXN5bmNfZXhlY3V0aW9uPyI6IGZhbHNlLCAiYWdlbnRfcm9sZSI6ICJ0ZXN0IHJvbGUyIiwgInRv
-      b2xzX25hbWVzIjogW119XUooCghwbGF0Zm9ybRIcChptYWNPUy0xNC4zLWFybTY0LWFybS02NGJp
-      dEocChBwbGF0Zm9ybV9yZWxlYXNlEggKBjIzLjMuMEobCg9wbGF0Zm9ybV9zeXN0ZW0SCAoGRGFy
-      d2luSnsKEHBsYXRmb3JtX3ZlcnNpb24SZwplRGFyd2luIEtlcm5lbCBWZXJzaW9uIDIzLjMuMDog
-      V2VkIERlYyAyMCAyMTozMDo1OSBQU1QgMjAyMzsgcm9vdDp4bnUtMTAwMDIuODEuNX43L1JFTEVB
-      U0VfQVJNNjRfVDYwMzBKCgoEY3B1cxICGAx6AhgBEqoIChAfSWWtcWdxaoyWECh3vhkCEgiTLpDL
-      PjEHmioMQ3JldyBDcmVhdGVkMAE5gO5llFUishdBGKBnlFUishdKGQoOY3Jld2FpX3ZlcnNpb24S
-      BwoFMC41LjJKGgoOcHl0aG9uX3ZlcnNpb24SCAoGMy4xMS43SiUKCGhvc3RuYW1lEhkKF0pvYW9z
-      LU1hY0Jvb2stUHJvLmxvY2FsSjEKB2NyZXdfaWQSJgokZjg1ZDQ3MTEtYzMwNC00NDMyLTk1N2Yt
-      MzE4NDUzNWFkOWJmShwKDGNyZXdfcHJvY2VzcxIMCgpzZXF1ZW50aWFsShUKDWNyZXdfbGFuZ3Vh
-      Z2USBAoCZW5KGgoUY3Jld19udW1iZXJfb2ZfdGFza3MSAhgBShsKFWNyZXdfbnVtYmVyX29mX2Fn
-      ZW50cxICGAFK2gIKC2NyZXdfYWdlbnRzEsoCCscCW3siaWQiOiAiNWJkOWYxODEtM2Y0ZC00MTk0
-      LThlOWEtODM1NDdhNTM1YjY4IiwgInJvbGUiOiAidGVzdCByb2xlIiwgIm1lbW9yeV9lbmFibGVk
-      PyI6IHRydWUsICJ2ZXJib3NlPyI6IGZhbHNlLCAibWF4X2l0ZXIiOiAxNSwgIm1heF9ycG0iOiBu
-      dWxsLCAiaTE4biI6ICJlbiIsICJsbG0iOiAie1wibmFtZVwiOiBudWxsLCBcIm1vZGVsX25hbWVc
-      IjogXCJncHQtNFwiLCBcInRlbXBlcmF0dXJlXCI6IDAuNywgXCJjbGFzc1wiOiBcIkNoYXRPcGVu
-      QUlcIn0iLCAiZGVsZWdhdGlvbl9lbmFibGVkPyI6IHRydWUsICJ0b29sc19uYW1lcyI6IFsibGVh
-      cm5fYWJvdXRfQUkiXX1dSpsBCgpjcmV3X3Rhc2tzEowBCokBW3siaWQiOiAiMzQ1ZGY0ZGItNGE2
-      ZC00ZGU4LWE3N2UtOTFiYTMwYzExZWVhIiwgImFzeW5jX2V4ZWN1dGlvbj8iOiBmYWxzZSwgImFn
-      ZW50X3JvbGUiOiAidGVzdCByb2xlIiwgInRvb2xzX25hbWVzIjogWyJsZWFybl9hYm91dF9BSSJd
-      fV1KKAoIcGxhdGZvcm0SHAoabWFjT1MtMTQuMy1hcm02NC1hcm0tNjRiaXRKHAoQcGxhdGZvcm1f
-      cmVsZWFzZRIICgYyMy4zLjBKGwoPcGxhdGZvcm1fc3lzdGVtEggKBkRhcndpbkp7ChBwbGF0Zm9y
-      bV92ZXJzaW9uEmcKZURhcndpbiBLZXJuZWwgVmVyc2lvbiAyMy4zLjA6IFdlZCBEZWMgMjAgMjE6
-      MzA6NTkgUFNUIDIwMjM7IHJvb3Q6eG51LTEwMDAyLjgxLjV+Ny9SRUxFQVNFX0FSTTY0X1Q2MDMw
-      SgoKBGNwdXMSAhgMegIYAQ==
-    headers:
-      Accept:
-      - '*/*'
-      Accept-Encoding:
-      - gzip, deflate
-      Connection:
-      - keep-alive
-      Content-Length:
-      - '5260'
-      Content-Type:
-      - application/x-protobuf
-      User-Agent:
-      - OTel-OTLP-Exporter-Python/1.22.0
-    method: POST
-    uri: http://telemetry.crewai.com:4318/v1/traces
-  response:
-    body:
-      string: "\n\0"
-    headers:
-      Content-Length:
-      - '2'
-      Content-Type:
-      - application/x-protobuf
-      Date:
-      - Fri, 09 Feb 2024 07:49:24 GMT
-    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\nlearn_about_AI: learn_about_AI(topic) -> float - Useful for when you
-      need to learn about AI to write an paragraph about it.\nDelegate work to co-worker:
-      Useful to delegate a specific task to one of the following co-workers: .\nThe
-      input to this tool should be a pipe (|) separated text of length 3 (three),
-      representing the co-worker you want to ask it to (one of the options), the task
-      and all actual context you have for the task.\nFor example, `coworker|task|context`.\nAsk
-      question to co-worker: Useful to ask a question, opinion or take from on of
-      the following co-workers: .\nThe input to this tool should be a pipe (|) separated
-      text of length 3 (three), representing the co-worker you want to ask it to (one
-      of the options), the question and all actual context you have for the question.\n
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
-      action to take, should be one of [learn_about_AI, Delegate work to co-worker,
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
-      the result of the action\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: Write and then review an small paragraph on
-      AI until it''s AMAZING\nThought: Do I need to use a tool? Yes\nAction: learn_about_AI\nAction
-      Input: general AI knowledge\nObservation: AI is a very broad field.\nThought:
-      "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      0.7}'
     headers:
       accept:
       - application/json
@@ -277,16 +165,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1955'
+      - '2558'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=wNpUyP3WikFZ5owMt5Wt4RvvxL5RRbV5Lm6N3cYt0cQ-1707464961-1-AaRJSNtZhC0qEyOOtzVqZyGINmDySgK+NZEmXyReWDjlSfP0cTj8tUtP+DYB/ttT11hGeDfZUyYzGIz1jsRPjN4=;
+      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        _cfuvid=Ii_GgXvfh_uOU6kzTG.hYatLhnP.5qhsMn05KgacgMc-1707464961455-0-604800000
+        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.11.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -296,7 +184,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.11.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -306,23 +194,19 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA1RTwW4bRwy96yse9rwSrEaxU10KA0EAXVIXCBAgbWFQs9xdVjPD7ZArRQj878HI
+        H4sIAAAAAAAAA1SRwW7bMBBE7/qKBc92YTeWbehmIC4a9JJrURYyTa0kJuSSIVdtWkP/XlBybPSi
-        so1c5sDH9/jIIX8sgEa6ZosmjOQhTXH54f9Px8/v+UTyMD+Y/vUw+cPX+O3mePjzw6FpK0P3/3Hw
+        w8y+1ezwUgAI04gKhO4Vaxfscv/WHH/x8fl7n/rHxy+H4zf8u7HP7/i23SexyIQ/v6DmD+qT9i5Y
-        F9YqaJoiu2h+hkNhcq6q67ubu83t5vfb9QVI2nGstGHy5WZ5c7t+d2WMKoGt2eLvBQD8uLzVW+74
+        ZONptnVExZi3rnerXVluyn05Gc43aDPWBV5ulqvt+uFK9N5oTKKCHwUAwGX65mzU4LuoYLX4UBym
-        e7PFTfsSSWxGAzfb1ySgKRprpCEzMafsTfsGBs3O+WL3o2KHzNzBFbMxCK4a/8Bn/Sd/kkwR99lO
+        pDoU1W0IQERvsyJUSiaxIhaLu6k9MdIU9ytGBJNAwW+0dtn66BQzNmAoYxrBt8A9gh84DAxJ9+hU
-        XLa4Ly69BKGIXXaOUQbOgVto75xB+33ho9Q+QYb7XQsxEI5kDsod0hxdegpcM3rh2K2wc3Cu0yIz
+        JUnS6XSSdJEEIEU7kM7n1qQcSlGBFBZVpFqd/cD14UmKxTypYjc4JE55aqKzyj4YPXOHyKY12igL
-        rtmF8sDQHjbvl51YkClKrlBVYB+106iDsLVgCiNIUi3ouMxY8oBEYbxQtMC09xMVxkl8BCFwcZKM
+        T8RoremQNEqRZ0dJ4/Rncb1mvNVgfReiP+fKaLD2preGTOrriCp5yicn9mHGxwLg51T38F+DIkTv
-        yEeOtQzNrlnTuUXHQUw0LxMdqkygifYSxc9tLd5C8is9kFUDQbMF0dkym63wZWRjFKaYDDZRRl80
+        AtfsX5HywnK3n/eJ+8ve3c3D1WTPyt717ed1cU0o0p/E6OrWUIcxRDO1n3MWY/EPAAD//wMA8S8H
-        vfhBZCq5Krui6F5dgrXI5HOhiEh5mGlgTEUDm10Tgw5ZXI6MOqW5NnixA1OkOYxIWniFj2yTOMNH
+        Q3QCAAA=
-        RidHLiZ+rv2JG2iaogSq62htHVUNBi3c4n4H8yJHtlrMJM2RnOvk+HuoWzHOiTLkl//u59xR4uwU
-        4xkUnUt1O+oJJ0aUI7c4aTk8G524BK4NVG8nLbEDFZ1zh9lWzXUpn163OeowFd3Xzc9zjK/xXrLY
-        +FiYTHPdXHOdnulPC+Dfy9XMvxxCMxVNkz+6HjhXwc27u2e95u1A39D1b5sr6uoU34D3t+vF1WJj
-        Z3NOj73kgctU5HJF1ejiafETAAD//wMAKXcLNTwEAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 852a83e94821fabe-SJC
+      - 853310010fcd1637-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -332,7 +216,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 09 Feb 2024 07:49:32 GMT
+      - Sat, 10 Feb 2024 08:43:08 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -346,7 +230,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '11068'
+      - '2273'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -358,13 +242,141 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299537'
+      - '299398'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 92ms
+      - 120ms
       x-request-id:
-      - req_b10e3d7ad93697db2a1d46243d59a41c
+      - req_9af33ac92b825be43da4372550c8c502
+    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\nlearn_about_AI: learn_about_AI(topic) -> float - Useful for when you
+      need to learn about AI to write an paragraph about it.\nDelegate work to co-worker:
+      Delegate work to co-worker(coworker: str, task: str, context: str) - Delegate
+      a specific task to one of the following co-workers: . The input to this tool
+      should be the role of the coworker, the task you want them to do, and ALL necessary
+      context to exectue the task, they know nothing about the task, so share absolute
+      everything you know, don''t reference things but instead explain them.\nAsk
+      question to co-worker: Ask question to co-worker(coworker: str, question: str,
+      context: str) - Ask a specific question to one of the following co-workers:
+      . The input to this tool should be the role of the coworker, the question you
+      have for them, and ALL necessary context to ask the question properly, they
+      know nothing about the question, so share absolute everything you know, don''t
+      reference things but instead explain them.\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 [learn_about_AI, Delegate work to co-worker,
+      Ask question to co-worker], 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: Write and then review an small paragraph on AI until
+      it''s AMAZING\nThought: Do I need to use a tool? Yes\nAction: learn_about_AI\nAction
+      Input: \"Artificial Intelligence\"\nObservation: AI is a very broad field.\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:
+      - '2154'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
+        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
+      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 |
+        H4sIAAAAAAAAA2RTwWobSxC86yuaPa+ERazY1iUYXh4IHoGEBAJJMK3Z3t22Z7s30z1ylOB/D7Na
+        WwnvMoepqaaqpvrXAqDiptpCFXr0MIxxef29eXu8eRzS/dX43+fmU2P69lV4v+4+HHhT1YWh+3sK
+        /sxaBR3GSM4qJzgkQqcydX11cbXZXG6urydg0IZioXWjLy+XF6/Xr2ZGrxzIqi18WQAA/JrOok0a
+        +lFt4aJ+vhnIDDuqti+PAKqksdxUaMbmKF7VZzCoOMkk9x+FHQhRA66QjQDBVeMbeKdf5V8WjHAr
+        9khpC7fJueXAGGEnTjFyRxKoBm2dBHC/T3Tg4hPQ4HZXAxsgHNAcWqbYrGDnQFLCQTMyOGBizQaW
+        98uGLfAYWcgApQGn0ItG7ZgMvEcH5KGIPGUJA4b+5bEdzWkwCDjiPhJoCyOlVtPA0oGjPcwzHjXH
+        BrJljPEIib5nTgR9HlCA/zC1go89Gc1UlhBzQxAJk5SJbdIB6MdIictrqyFLQ6kE3RRc0HPCCBGl
+        y9hRDYmCdsI/CzqiOyWxGsak+0jD0jQeWLp6MtNQYGMVGPCBpZukQKcYi63bXUlV1OE+m5c8Eo2R
+        Q4nk/zZgnx0wmv4R3HNWUx4B5Tmp2eugiYDa8tEkHo+TJAwhJ3SKx1VR0GOhE4xaalQKMek4aMyl
+        8/yTzl9LwTVZPWdY7PeE0fuAiWpoWXDqkCcUGzU5lgmnIIqUVTXX9uml71G7klvZDckxvty3LGz9
+        XSI0ldJtcx1P9KcFwLdpr/Jfq1KNSYfR71wfSMrAy6t5r6rzCp/R9fpmRl0d4xnYXN8sZonVKd+7
+        lqWjNCae9qwIXTwtfgMAAP//AwDp3F89XgQAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 853310125de31637-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 10 Feb 2024 08:43:14 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:
+      - '6017'
+      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:
+      - '299486'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 102ms
+      x-request-id:
+      - req_c153504e2e53f18e15a640221b664aba
     status:
       code: 200
       message: OK
@@ -380,15 +392,15 @@ interactions:
       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: Write
       and then review an small paragraph on AI until it''s AMAZING\nAI: Artificial
-      Intelligence, often abbreviated as AI, is a vast and multifaceted field. It
+      Intelligence, often abbreviated as AI, is a vast field. It encompasses various
-      encompasses a range of sub-disciplines and methodologies, each aimed at creating
+      sub-disciplines and technologies that aim to create machines and systems capable
-      machines or software with a certain level of autonomy, decision-making capability,
+      of performing tasks that would usually require human intelligence. These tasks
-      and, in certain cases, consciousness. These realms span from machine learning
+      include learning from experiences, understanding natural language, recognizing
-      to robotics, natural language processing to cognitive computing, and so much
+      patterns, problem-solving, and decision making. The goal of AI is not just to
-      more. Despite the diversity of its applications, at its core, AI strives to
+      replicate human intelligence but also to create systems that can perform tasks
-      simulate or exceed human intelligence, fundamentally altering how we live, work,
+      more efficiently and accurately. AI has the potential to revolutionize various
-      and perceive the world around us.\n\nNew summary:"}], "model": "gpt-4", "n":
+      sectors, including healthcare, finance, transportation, and more.\n\nNew summary:"}],
-      1, "stream": false, "temperature": 0.7}'
+      "model": "gpt-4", "n": 1, "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -397,16 +409,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1513'
+      - '1547'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=wNpUyP3WikFZ5owMt5Wt4RvvxL5RRbV5Lm6N3cYt0cQ-1707464961-1-AaRJSNtZhC0qEyOOtzVqZyGINmDySgK+NZEmXyReWDjlSfP0cTj8tUtP+DYB/ttT11hGeDfZUyYzGIz1jsRPjN4=;
+      - __cf_bm=FHcpgH1eZBeZ3Rbcza28Oc6NWTXs_wBg2dFweW8n7iE-1707554585-1-AeO0TVKmSDiPyhIhqVNGXLU1AqKVAJroEV7Mq1JaqrBTJlB6hP4FrF9q/F66TJ4PAMcnMJ6YKH9wW4gQAx2jhis=;
-        _cfuvid=Ii_GgXvfh_uOU6kzTG.hYatLhnP.5qhsMn05KgacgMc-1707464961455-0-604800000
+        _cfuvid=CyquHMSR3lyGv7DVvBmUUvZ_N5p0T0sRkvGYdcRgwUo-1707554585722-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.11.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -416,7 +428,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.11.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -426,22 +438,21 @@ interactions:
   response:
     body:
       string: !!binary |
-        H4sIAAAAAAAAA1STQW/bMAyF7/kVhC+7OEHTBk2XW3YYFmyHAeuGFcNQMDJjs5FFTaTtZkX/+yAn
+        H4sIAAAAAAAAA1RSTW/bMAy951cQuuySBM0aL21uxYBhxW5FdhqGgpFpm60sqiKd9AP974PstMEu
-        bdaLD6Te0yfy+WkCUHBVrKBwDZpro5/e/PnY3314+Hbz+fv+i3XzcLjqftzpp59f46YryqyQ7QM5
+        OpB6j4+P720G4Lh2W3C+Q/N9Courp/pH9TPZ8+53vNu8rL5Xq4fjjW52d9/CLzcvCNk/kLcP1NJL
-        e1HNnLTRk7GEY9slQqPsOl9eLBfXi/fLy7HRSkU+y+po08X04np+dVI0wo60WMGvCQDA0/jNbKGi
+        nwIZS5zaPhMaFdbV5mJTVevquhobvdQUCqxNtlgvLr6tLk+ITtiTui38mQEAvI1v0RZrenZbuJh/
-        x2IFF+VLpSVVrKlYvR4CKJL4XClQldUwWFGem06CURhxbxuCpmsxAOpewRqC9QZMYEhsBBgqSNQz
+        VHpSxZbc9vMTgMsSSsWhKqthNDc/N71EozjK3XUE3dBjBNRHBesIbm7BBI6ZjQBjXWoRMh2YjoCg
-        DYCgLXoPERPWCWMDEvLZLhh7YHungC3+5VDP4PZoM3ooIOR5JGooKPf0nwM9Ro8cONRgDRqsNyVI
+        PYYACTO2GVMHEgtgiMYB2L4oYI+vHNsl7CauTJok1gpHtg4Q9pmpATlQHhmlgZvbOdSkPvOeYwts
-        gnUy3rFj9LAJRt5zTcFRCZzNelQbwdrOG+/QkVEFOyZfzWBjwMH5riKFHhNLp6DddlqxOo6eQ+bJ
+        gAoIB1SDhinUE/SAmWVQ0GG/qFk9p8CRdNJIvosSpGXSJdwa9BSL/WUjtHGtVjBM04C1bDgdBfRF
-        WrJGKvFSM2kJ+WHILVWABuO2MlOLrhkVkkBlZwMmgoGtyU+iZMgBPPXkQXaAnUmQ9lBCRY6VJUxb
+        jXoFjwn3gcqXRLmR3BcxdrIFDQYdMIQXyPQ0cP6wjaNRCNxS9DQ/+YVWpnQ4+ZmkmM0YytBMBwlD
-        3GcbhxG37NkO5Xh3lDx9Ru8PJTgJ6jJmINUZrDd5jjF6dpjzo5DvrLinpFTCtrNMyKbgJOWJWObW
+        kcavdF6JvElW4OjDUJe5HWGwzmOmOTQc8cyeMWqSbFhIlu501ffPOARpU5Z9iU4cQvisNxxZu/tM
-        vDHltvNolGnp0RFVp83ymxmiN0oZq5EBBgLPPZUwSNqf6Cg5ymvKWRgk+WpWnKLz/Jo5L3VMss35
+        qBLL6dUkTfD3GcDfMXbDf0lyKUuf7N7kkWIh/FpdT3zunPBz96o6NU0Mw7l+uV7PTgrd5PZ9w7Gl
-        DJ33r/UdB9bmPhGqhJwvNYlH+fME4PeY7e5NXIuYpI12b7KnkA0vrxdHv+L8G52784vlqWti6M+N
+        nDKPKSw6Z++zfwAAAP//AwBANdK6fAMAAA==
-        q+V8ckIs9KBG7f2OQ00pJh6znkEnz5N/AAAA//8DAG6VJ3HiAwAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 852a842f29cffabe-SJC
+      - 8533103aae201637-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -451,7 +462,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 09 Feb 2024 07:49:38 GMT
+      - Sat, 10 Feb 2024 08:43:18 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -465,7 +476,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '6156'
+      - '2948'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -477,13 +488,13 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299636'
+      - '299629'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 72ms
+      - 74ms
       x-request-id:
-      - req_c4d71f28b3724c8591d7a1c79a9773a8
+      - req_bf6f7315d0ac178598b80627d7b1af72
     status:
       code: 200
       message: OK

tests/cassettes/test_agent_without_max_rpm_respet_crew_rpm.yaml

@@ -2,25 +2,27 @@ 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\nDelegate work to co-worker: Useful to delegate a specific task to
+      tools:\n\nDelegate work to co-worker: Delegate work to co-worker(coworker: str,
-      one of the following co-workers: test role, test role2.\nThe input to this tool
+      task: str, context: str) - Delegate a specific task to one of the following
-      should be a pipe (|) separated text of length 3 (three), representing the co-worker
+      co-workers: test role2. The input to this tool should be the role of the coworker,
-      you want to ask it to (one of the options), the task and all actual context
+      the task you want them to do, and ALL necessary context to exectue the task,
-      you have for the task.\nFor example, `coworker|task|context`.\nAsk question
+      they know nothing about the task, so share absolute everything you know, don''t
-      to co-worker: Useful to ask a question, opinion or take from on of the following
+      reference things but instead explain them.\nAsk question to co-worker: Ask question
-      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      to co-worker(coworker: str, question: str, context: str) - Ask a specific question
-      (|) separated text of length 3 (three), representing the co-worker you want
+      to one of the following co-workers: test role2. The input to this tool should
-      to ask it to (one of the options), the question and all actual context you have
+      be the role of the coworker, the question you have for them, and ALL necessary
-      for the question.\n For example, `coworker|question|context`.\n\nTo use a tool,
+      context to ask the question properly, they know nothing about the question,
-      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
+      so share absolute everything you know, don''t reference things but instead explain
-      Yes\nAction: the action to take, should be one of [Delegate work to co-worker,
+      them.\n\nTo use a tool, please use the exact following format:\n\n```\nThought:
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      Do I need to use a tool? Yes\nAction: the tool you wanna use, should be one
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      of [Delegate work to co-worker, Ask question to co-worker], just the name.\nAction
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Input: Any and all relevant information input and context for using the tool\nObservation:
-      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      the result of using the tool\n```\n\nWhen you have a response for your task,
-      of your work so far:\nBegin! This is VERY important to you, your job depends
+      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1, "stop":
+      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      ["\nObservation"], "stream": false, "temperature": 0.7}'
+      summary of your work so far:\nBegin! This is VERY important to you, your job
+      depends on it!\n\nCurrent Task: Just say hi.\n"}], "model": "gpt-4", "n": 1,
+      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -29,13 +31,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1652'
+      - '1825'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -45,7 +47,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -53,18 +55,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPA1vnW1g25Qr3SJLWB5zeOsUe4\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1705198848,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SQzU7DMBCE73mKlc8tStSmLbmgih8BEiAECFRAlZtsE4PjNfZGQKu+O3KatuKy
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? No\\nFinal
+        hxnP7LdeRwBCFSIDkVeS89rq/uSruFk9u+kjPfF92sx4tjq/G3h8Ob2ePoheSNDiA3PepY5yqq1G
-      Answer: Hi!\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        VmS2du5QMobWZByP0zSNJ2lr1FSgDrHScn/Yj0fJoEtUpHL0IoPXCABg3c7AZgr8ERnEvZ1So/ey
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 367,\n    \"completion_tokens\":
+        RJHtHwEIRzooQnqvPEvDoncwczKMpsV9rKgpK87gjOAKDGIBTNB4BAlMpE/glt7MhTJSw9T4b3QZ
-      17,\n    \"total_tokens\": 384\n  },\n  \"system_fingerprint\": null\n}\n"
+        XCrRdW32EJpK62gRgE2j9V5fKqN8NXcoPZmw0DPZbXwTAby3xzb/+IV1VFueM32iCYWD4+G2Txz+
+        9eAmo85kYqkP+jCJo45Q+F/PWM+XypTorFPt7YEz2kR/AAAA//8DABJPZgfyAQAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 845266dd5f1f1a96-GRU
+      - 85331c3028ba7aac-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -74,14 +77,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sun, 14 Jan 2024 02:20:50 GMT
+      - Sat, 10 Feb 2024 08:51:26 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+      - __cf_bm=PApKfMOxYmqCPfv1QzKEuqGGYEUQhozoSuKopWRTbzg-1707555086-1-AeIZ1ozsIHX7RW0ZxnKJ17u8m5eIvUTNkNMhFDdTwc71TeSLRieXLv/0waJkA48Sz1+FjLHulvMGaPnUEf7K19k=;
-        path=/; expires=Sun, 14-Jan-24 02:50:50 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 09:21:26 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000;
+      - _cfuvid=ivN7v5z_DwT9MCx4fk0bd86wOUph.ZASgr.z0qq5y2k-1707555086057-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -94,7 +97,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1832'
+      - '899'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -106,15 +109,16 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299611'
+      - '299566'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 77ms
+      - 86ms
       x-request-id:
-      - 12d633fe239a29022ea7206037da096a
+      - req_561f62ebd7103f1fd1e54ced4754dcce
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -126,7 +130,7 @@ interactions:
       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: Just
-      say hi.\nAI: Hi!\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
+      say hi.\nAI: Hi\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false,
       "temperature": 0.7}'
     headers:
       accept:
@@ -136,16 +140,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '867'
+      - '866'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=TbP3njfV8Qa2w4gTk3GfLx8EOChqceUdui85lv8w_0s-1705198850-1-AVv9rXKeGNOAPhhVrRvcK49dv9odkct+so0djAQM52Bfzf/nc8ZTJ3zhk2LlfNTWSQ9dcT4UwZHjEHyP8LH39Xg=;
+      - __cf_bm=PApKfMOxYmqCPfv1QzKEuqGGYEUQhozoSuKopWRTbzg-1707555086-1-AeIZ1ozsIHX7RW0ZxnKJ17u8m5eIvUTNkNMhFDdTwc71TeSLRieXLv/0waJkA48Sz1+FjLHulvMGaPnUEf7K19k=;
-        _cfuvid=y6p2l8rtoLMo6gBiQsUGfETrVWxPY83uCFZsS7Jozok-1705198850215-0-604800000
+        _cfuvid=ivN7v5z_DwT9MCx4fk0bd86wOUph.ZASgr.z0qq5y2k-1707555086057-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -155,7 +159,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -163,19 +167,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPCF34yiaqHuTbro7PMBexYagyU\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1705198850,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SQT0sDMRDF7/sphpxb2dW2lt48qQgFUbyolDQ73aRmM2lmFq3S7y7Z/tNLIPPy
-      \"assistant\",\n        \"content\": \"The human asks the AI to simply say hi,
+        Xn7zfgoA5Wo1A2WsFtNGP5xu6nl5a76f6ul9s35plo9JwsO6ruaXk40aZAct12jk6Low1EaP4ijs
-      and the AI responds with \\\"Hi!\\\"\"\n      },\n      \"logprobs\": null,\n
+        ZZNQC+bU6rq8Ho/H5XTSCy3V6LOtiTIcDctJdXVwWHIGWc3gtQAA+OnPzBZq/FIzKAfHSYvMukE1
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        Oz0CUIl8nijN7Fh0EDU4i4aCYOhxny2C7VodwAWW1BlhEItwcw9CsO5YgPUWrBvk+6d1xh71hBwp
-      144,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 162\n  },\n  \"system_fingerprint\":
+        1Aw6xkQxOS3ot/DpxMKbunNv6kId/tydYD01MdEyLxY670/zlQuO7SKhZgoZjIXi3r4rAN77Urp/
-      null\n}\n"
+        e6qYqI2yEPrAkAOr0Wifp879n9XL6iAKifZ/XJNxcSBUvGXBdrFyocEUk+s7ypzFrvgFAAD//wMA
+        D9d32RoCAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 845266ee78dc1a96-GRU
+      - 85331c380f547aac-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -185,7 +190,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sun, 14 Jan 2024 02:20:52 GMT
+      - Sat, 10 Feb 2024 08:51:27 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -199,7 +204,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1287'
+      - '1035'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -217,34 +222,38 @@ interactions:
       x-ratelimit-reset-tokens:
       - 40ms
       x-request-id:
-      - 2a891eacb4940e36bec1689b1ab92ee0
+      - req_d47c41d14baa963cd2a25770f0f33620
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
       personal goal is: test goal2TOOLS:\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.\nDelegate
-      work to co-worker: Useful to delegate a specific task to one of the following
+      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      str) - Delegate a specific task to one of the following co-workers: test role.
-      (|) separated text of length 3 (three), representing the co-worker you want
+      The input to this tool should be the role of the coworker, the task you want
-      to ask it to (one of the options), the task and all actual context you have
+      them to do, and ALL necessary context to exectue the task, they know nothing
-      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      about the task, so share absolute everything you know, don''t reference things
-      Useful to ask a question, opinion or take from on of the following co-workers:
+      but instead explain them.\nAsk question to co-worker: Ask question to co-worker(coworker:
-      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      str, question: str, context: str) - Ask a specific question to one of the following
-      text of length 3 (three), representing the co-worker you want to ask it to (one
+      co-workers: test role. The input to this tool should be the role of the coworker,
-      of the options), the question and all actual context you have for the question.\n
+      the question you have for them, and ALL necessary context to ask the question
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      properly, they know nothing about the question, so share absolute everything
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      you know, don''t reference things but instead explain them.\n\nTo use a tool,
-      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      Yes\nAction: the tool you wanna use, should be one of [get_final_answer, Delegate
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      work to co-worker, Ask question to co-worker], just the name.\nAction Input:
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Any and all relevant information input and context for using the tool\nObservation:
-      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      the result of using the tool\n```\n\nWhen you have a response for your task,
-      of your work so far:\nBegin! This is VERY important to you, your job depends
+      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      tool.\nThis is the context you''re working with:\nHi!\n"}], "model": "gpt-4",
+      summary of your work so far:\nBegin! This is VERY important to you, your job
-      "n": 1, "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
+      depends on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using
+      the `get_final_answer` tool non-stop\nThis is the context you''re working with:\nHi\n"}],
+      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      0.7}'
     headers:
       accept:
       - application/json
@@ -253,13 +262,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1923'
+      - '2101'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -269,7 +278,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -277,19 +286,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPEml4Ifldq51knwwASO3nJroK3\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1705198852,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RQy27CMBC85ytWPkMFhfDIparUQ+mhJ4pUAYqMsyRuHa+JN4UW8e+VQ4D24sPM
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        znhmjhGA0JlIQKhCsiqd6U522Wt/+rVT+UEt9s67xXQ03728LUY/RSw6QUGbD1R8Ud0pKp1B1mTP
-      get_final_answer\\nAction Input: [1,2,3]\"\n      },\n      \"logprobs\": null,\n
+        tKpQMgbX/rg3juO4Nxk3REkZmiDLHXeH3d6oP2gVBWmFXiSwjAAAjs0bstkMDyKBXueClOi9zFEk
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        1yMAUZEJiJDea8/SsujcSEWW0TZx5wXVecEJPBHMwCJmwAS1R5DAROYB3tGv7KMKZRLIkdOtttKk
-      432,\n    \"completion_tokens\": 28,\n    \"total_tokens\": 460\n  },\n  \"system_fingerprint\":
+        0vo9VhcGZtbVnMByJZ71SqxF+9npmtJQ7irahEa2NuaKb7XVvkgrlJ5sSOSZ3Fl+igDWzRr1v4LC
-      null\n}\n"
+        VVQ6Tpk+0QbDYTw9+4nb8Df2ftiSTCzNH9VkELUJhf/2jGWolmPlKt2ME3JGp+gXAAD//wMAVFuU
+        bxMCAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 845266f9fc150316-GRU
+      - 85331c3f6c38cfc4-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -299,14 +309,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sun, 14 Jan 2024 02:20:53 GMT
+      - Sat, 10 Feb 2024 08:51:28 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        path=/; expires=Sun, 14-Jan-24 02:50:53 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 09:21:28 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000;
+      - _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -319,7 +329,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1570'
+      - '1442'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -331,42 +341,48 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299545'
+      - '299499'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 91ms
+      - 100ms
       x-request-id:
-      - 133ee7e16a1491cfd7daa90ea3e42b74
+      - req_b76f1918aa33f67b05eee313ca29e621
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
       personal goal is: test goal2TOOLS:\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.\nDelegate
-      work to co-worker: Useful to delegate a specific task to one of the following
+      work to co-worker: Delegate work to co-worker(coworker: str, task: str, context:
-      co-workers: test role, test role2.\nThe input to this tool should be a pipe
+      str) - Delegate a specific task to one of the following co-workers: test role.
-      (|) separated text of length 3 (three), representing the co-worker you want
+      The input to this tool should be the role of the coworker, the task you want
-      to ask it to (one of the options), the task and all actual context you have
+      them to do, and ALL necessary context to exectue the task, they know nothing
-      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
+      about the task, so share absolute everything you know, don''t reference things
-      Useful to ask a question, opinion or take from on of the following co-workers:
+      but instead explain them.\nAsk question to co-worker: Ask question to co-worker(coworker:
-      test role, test role2.\nThe input to this tool should be a pipe (|) separated
+      str, question: str, context: str) - Ask a specific question to one of the following
-      text of length 3 (three), representing the co-worker you want to ask it to (one
+      co-workers: test role. The input to this tool should be the role of the coworker,
-      of the options), the question and all actual context you have for the question.\n
+      the question you have for them, and ALL necessary context to ask the question
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
+      properly, they know nothing about the question, so share absolute everything
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
+      you know, don''t reference things but instead explain them.\n\nTo use a tool,
-      action to take, should be one of [get_final_answer, Delegate work to co-worker,
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
+      Yes\nAction: the tool you wanna use, should be one of [get_final_answer, Delegate
-      the result of the action\n```\n\nWhen you have a response for your task, or
+      work to co-worker, Ask question to co-worker], just the name.\nAction Input:
-      if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
+      Any and all relevant information input and context for using the tool\nObservation:
-      Do I need to use a tool? No\nFinal Answer: [your response here]This is the summary
+      the result of using the tool\n```\n\nWhen you have a response for your task,
-      of your work so far:\nBegin! This is VERY important to you, your job depends
+      or if you do not need to use a tool, you MUST use the format:\n\n```\nThought:
-      on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using the `get_final_answer`
+      Do I need to use a tool? No\nFinal Answer: [your response here]```This is the
-      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
+      summary of your work so far:\nBegin! This is VERY important to you, your job
-      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
+      depends on it!\n\nCurrent Task: Don''t give a Final Answer, instead keep using
-      42\nThought: "}], "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream":
+      the `get_final_answer` tool non-stop\nThis is the context you''re working with:\nHi\nThought:
-      false, "temperature": 0.7}'
+      Do I need to use a tool? Yes\nAction: get_final_answer\nAction Input: [\"Hi\"]\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
@@ -375,16 +391,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '2037'
+      - '2419'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+        _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -394,7 +410,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -402,19 +418,22 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPGwVu7CvxvQd3ZmBPHwz0WYbVQ\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1705198854,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA3RSTY/aMBS88ytGvvQSKhDLss2lAm2rIlVspa5arQARkzySFMcva7+UTVf73yuH
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
+        L/XQiw8znvG8N37tAarMVAyVFlrSqjb9u+dsMbLPRTX6+kO4SfdPB/rybfbn3j7M9ioKCt7+olTO
-      get_final_answer\\nAction Input: [4,5,6]\"\n      },\n      \"logprobs\": null,\n
+        qvcpV7UhKdke6dSRFgquw8lgMh6PB3cfOqLijEyQ5bX0b/qD2+HopCi4TMmrGMseALx2Z8hmM3pR
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        MQbRGanIe52Tii+XAOXYBERp70sv2oqKrmTKVsh2ce8Zc1iiDMJoPEFDmM1HPJFf2WkaZoiRk2x2
-      469,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 495\n  },\n  \"system_fingerprint\":
+        pdVmo60/kDszmNu6kRjLlZqm0mhj2gjz4BP8GJW2befnI3jG/J0x8MI1LB+gbYa8/E1ouUHVQm89
-      null\n}\n"
+        m0YIs0/fH/E5PIfjc1g8/IzQ+NLmkIJALzWlQhl27CotMZIkwWPBTV5IjP+OtOCT67RzjbFsuXFw
+        5Gu2nlCQo3WSJCu1VqdlvV22bDivHW9DI7Yx5oLvSlv6YuNIe7Zho2G+o/ytB6y7Npt/ClK146qW
+        jfCebDAc35zaVNePc2UnZ1JYtLnit8NB75RQ+dYLVaGjnFztyq7ckLP31vsLAAD//wMAzsuhnNMC
+        AAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8452670589920316-GRU
+      - 85331c496beccfc4-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -424,7 +443,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sun, 14 Jan 2024 02:20:55 GMT
+      - Sat, 10 Feb 2024 08:51:32 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -438,7 +457,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '983'
+      - '2973'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -450,259 +469,16 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299517'
+      - '299421'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 96ms
+      - 115ms
       x-request-id:
-      - cb1d820e78376ed344c16e6051cab6bc
+      - req_90dad1554de8c627760a03ab5313ce5d
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
-- request:
+      message: OK
-    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
-      personal goal is: test goal2TOOLS:\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.\nDelegate
-      work to co-worker: Useful to delegate a specific task to one of the following
-      co-workers: test role, test role2.\nThe input to this tool should be a pipe
-      (|) separated text of length 3 (three), representing the co-worker you want
-      to ask it to (one of the options), the task and all actual context you have
-      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
-      Useful to ask a question, opinion or take from on of the following co-workers:
-      test role, test role2.\nThe input to this tool should be a pipe (|) separated
-      text of length 3 (three), representing the co-worker you want to ask it to (one
-      of the options), the question and all actual context you have for the question.\n
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
-      action to take, should be one of [get_final_answer, Delegate work to co-worker,
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
-      the result of the action\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: Don''t give a Final Answer, instead keep using the `get_final_answer`
-      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
-      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
-      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: [4,5,6]\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:
-      - '2142'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
-        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.7.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.7.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPHbI2gWbt2veTT8auCPCstOnZh\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1705198855,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? Yes\\nAction:
-      get_final_answer\\nAction Input: [7,8,9]\"\n      },\n      \"logprobs\": null,\n
-      \     \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      503,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 529\n  },\n  \"system_fingerprint\":
-      null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8452670dca090316-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 14 Jan 2024 02:20:57 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:
-      - '2350'
-      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:
-      - '299492'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 101ms
-      x-request-id:
-      - b40ffecf3dc8f547453bfb166c8c52dd
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "user", "content": "You are test role2.\ntest backstory2\n\nYour
-      personal goal is: test goal2TOOLS:\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.\nDelegate
-      work to co-worker: Useful to delegate a specific task to one of the following
-      co-workers: test role, test role2.\nThe input to this tool should be a pipe
-      (|) separated text of length 3 (three), representing the co-worker you want
-      to ask it to (one of the options), the task and all actual context you have
-      for the task.\nFor example, `coworker|task|context`.\nAsk question to co-worker:
-      Useful to ask a question, opinion or take from on of the following co-workers:
-      test role, test role2.\nThe input to this tool should be a pipe (|) separated
-      text of length 3 (three), representing the co-worker you want to ask it to (one
-      of the options), the question and all actual context you have for the question.\n
-      For example, `coworker|question|context`.\n\nTo use a tool, please use the exact
-      following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the
-      action to take, should be one of [get_final_answer, Delegate work to co-worker,
-      Ask question to co-worker], just the name.\nAction Input: the input to the action\nObservation:
-      the result of the action\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: Don''t give a Final Answer, instead keep using the `get_final_answer`
-      tool.\nThis is the context you''re working with:\nHi!\nThought: Do I need to
-      use a tool? Yes\nAction: get_final_answer\nAction Input: [1,2,3]\nObservation:
-      42\nThought: Do I need to use a tool? Yes\nAction: get_final_answer\nAction
-      Input: [4,5,6]\nObservation: 42\nThought: Do I need to use a tool? Yes\nAction:
-      get_final_answer\nAction Input: [7,8,9]\nObservation: I''ve used too many tools
-      for this task. I''m going to give you my absolute BEST Final answer now and
-      not use any more tools.\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:
-      - '2368'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
-        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.7.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.7.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPKsrN7s3j8bLplwjkAD2c7E6RK\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1705198858,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
-      I've used too many tools for this task. I'm going to give you my absolute BEST
-      Final answer now and not use any more tools.\"\n      },\n      \"logprobs\":
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
-      563,\n    \"completion_tokens\": 42,\n    \"total_tokens\": 605\n  },\n  \"system_fingerprint\":
-      null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 8452671e0b500316-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Sun, 14 Jan 2024 02:21:00 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:
-      - '2080'
-      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:
-      - '299436'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 112ms
-      x-request-id:
-      - b2b7142dc669054b82773d62077e9918
-    http_version: HTTP/1.1
-    status_code: 200
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -714,11 +490,10 @@ interactions:
       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: Don''t
-      give a Final Answer, instead keep using the `get_final_answer` tool.\nThis is
+      give a Final Answer, instead keep using the `get_final_answer` tool non-stop\nThis
-      the context you''re working with:\nHi!\nAI: I''ve used too many tools for this
+      is the context you''re working with:\nHi\nAI: Agent stopped due to iteration
-      task. I''m going to give you my absolute BEST Final answer now and not use any
+      limit or time limit.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream":
-      more tools.\n\nNew summary:"}], "model": "gpt-4", "n": 1, "stream": false, "temperature":
+      false, "temperature": 0.7}'
-      0.7}'
     headers:
       accept:
       - application/json
@@ -727,16 +502,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1096'
+      - '1031'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=.BcqEMXmdqfYfcBhvXzVDw6VVpZcS222j9Ky_mjHYg8-1705198853-1-AWhcBEd9Rcv3V/4iZJoUcp4zRPfVw7kkOb9e8JZ9J3WChdb10kNHT7f78/k6uarWxT3kJDReeFJHAIhx5KG+i40=;
+      - __cf_bm=2FkgHfXDTEWwtJx9fuYC7bMgshbFiKyrz77uUDT7zZs-1707555088-1-Aepn1cZI06+lHA4fg6WnGlRYQvOzF/0+FklFgWjzvCx0c9PWNVB0SHCULztQ+AdxbloscbFE14+qlktmxccvWLA=;
-        _cfuvid=AKii9trCQGiEB.0xzvo5UXqowzTR3yys6v0hI5JiumE-1705198853906-0-604800000
+        _cfuvid=euVu9TT31y3M3IcbZHjgSQIkmaipgL6G3sfBSomB.wA-1707555088785-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.7.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -746,7 +521,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.7.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -754,21 +529,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8gkPMD1hkXKA5DP8MyMJNpAxJXhzj\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1705198860,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1RRTU8jMQy9z6+wcm6raekH7Q3tHuAC0mq10oJQCTNmJpDY2dhTFqH+d5SZfohL
-      \"assistant\",\n        \"content\": \"The human instructs the AI not to give
+        pLznZz8/fxYAxtVmA6ZqrVYh+vHlv/p2eXf9a/5nfcft6/3fm58rb2ed/qDd0oyygp9fsdKjalJx
-      a final answer but to continue using the `get_final_answer` tool. However, the
+        iB7VMQ10ldAq5q7TVblaLBbletYTgWv0WdZEHc/H5XJ6cVC07CoUs4GHAgDgs3+zN6rxv9lAOToi
-      AI responds that it has already used many tools for the task and chooses to
+        AUVsg2ZzKgIwiX1GjBVxopbUjM5kxaRIvd3fLULbBUvgSDR1lQpoi3B1A8QKytC4HYKFF0fWgyV5
-      provide its best final answer without using any more tools.\"\n      },\n      \"logprobs\":
+        xwSW6ky9IUboxFHTa54a1G1ftx3qnkCZPRDTWJTjBK75HXeYRscRtkFSyJxA3WHuiU5bTOAUk80B
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        gnfBKXACdQGH38QcdtmfQvDcxMTPOTDqvD/hL46ctNuEVpjywnnYIN8XAI992N23/ExMHKJuld+Q
-      196,\n    \"completion_tokens\": 53,\n    \"total_tokens\": 249\n  },\n  \"system_fingerprint\":
+        pL/Zeuhnznc9s/PpgVRW68/4bFYWB4dGPkQx5GwaTDG5Pvvss9gXXwAAAP//AwAJcyracgIAAA==
-      null\n}\n"
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 8452672d1bba0316-GRU
+      - 85331c5e2baccfc4-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -778,7 +552,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Sun, 14 Jan 2024 02:21:03 GMT
+      - Sat, 10 Feb 2024 08:51:35 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -792,7 +566,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2683'
+      - '2537'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -804,13 +578,14 @@ interactions:
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299742'
+      - '299758'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 51ms
+      - 48ms
       x-request-id:
-      - c00193638e659df4a60ef9425649fe2c
+      - req_c2fe098b8481dac7ed32f9d683eb36ac
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 version: 1

tests/cassettes/test_logging_tool_usage.yaml

@@ -1,21 +1,19 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+    body: '{"messages": [{"role": "user", "content": "You are test role.\ntest backstory\n\nYour
-      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      personal goal is: test goalTOOLS:\n------\nYou have access to only the following
-      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      tools:\n\nmultiplier: multiplier(first_number: int, second_number: int) -> float
-      - Useful for when you need to multiply two numbers together.\n        The input
+      - Useful for when you need to multiply two numbers together.\n\nTo use a tool,
-      to this tool should be a comma separated list of numbers of\n        length
+      please use the exact following format:\n\n```\nThought: Do I need to use a tool?
-      two, representing the two numbers you want to multiply together.\n        For
+      Yes\nAction: the tool you wanna use, should be one of [multiplier], just the
-      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      name.\nAction Input: Any and all relevant information input and context for
-      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      using the tool\nObservation: the result of using the tool\n```\n\nWhen you have
-      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      a response for your task, or if you do not need to use a tool, you MUST use
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      the format:\n\n```\nThought: Do I need to use a tool? No\nFinal Answer: [your
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      response here]```This is the summary of your work so far:\nBegin! This is VERY
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      important to you, your job depends on it!\n\nCurrent Task: What is 3 times 5?\n"}],
-      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
-      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      0.7}'
-      on it!\n\nCurrent Task: What is 3 times 5?\n\n"}], "model": "gpt-4", "n": 1,
-      "stop": ["\nObservation"], "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -24,13 +22,13 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1231'
+      - '1047'
       content-type:
       - application/json
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -40,7 +38,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -48,18 +46,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eDhOwdMJw0817wIqiD9MoXVRU8\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703858225,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRS0/DMBCE7/kVqz2nqK8AzQUhEIIbIDggiqrU2SQujtfYGwmo+t+R0ycXH2Z2
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
+        Vt+s1wkA6hJzQNUUolpnBpdfarby1ROZ2fju9fGesko/X36W05vfc41pTPByRUr2qTPFrTMkmu3W
-      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        Vp4Kobh1dDG8yLLhdDTrjZZLMjFWOxlMB8Pz0WSXaFgrCpjDewIAsO7fyGZL+sYchuleaSmEoibM
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 264,\n    \"completion_tokens\":
+        D0MA6NlEBYsQdJDCCqZHU7EVsj3uS8Nd3UgOtwwPYIlKEIYuEBQgzOYK3ijM7bWKZXJoOyPaGU1+
-      23,\n    \"total_tokens\": 287\n  },\n  \"system_fingerprint\": null\n}\n"
+        r8GDdZ3ksJ5jpX2Qhe3aJfk55jBJYY6BFNvyRM02uCPZHCoYrp3nZaxrO2MOeqWtDs3CUxHYRtwg
+        7LbxTQLw0Z+q+9cenefWyUL4k2xcOB6Ptvvw+CtHdzLZmcJSmJNUNk12hBh+glC7qLStyTuv+8tF
+        zmST/AEAAP//AwCr+Q67MAIAAA==
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 83d28cd70f9f1cd9-GRU
+      - 8532aa4bca4e679a-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -69,14 +69,14 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 29 Dec 2023 13:57:07 GMT
+      - Sat, 10 Feb 2024 07:33:41 GMT
       Server:
       - cloudflare
       Set-Cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        path=/; expires=Fri, 29-Dec-23 14:27:07 GMT; domain=.api.openai.com; HttpOnly;
+        path=/; expires=Sat, 10-Feb-24 08:03:41 GMT; domain=.api.openai.com; HttpOnly;
         Secure; SameSite=None
-      - _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000;
+      - _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000;
         path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
       Transfer-Encoding:
       - chunked
@@ -89,7 +89,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1725'
+      - '1673'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -98,43 +98,39 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
-      - '299717'
+      - '299762'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299717'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 56ms
+      - 47ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 56ms
       x-request-id:
-      - 689757a1e38baf0844ec69f20525c5d7
+      - req_e5461f12abf90cd87cea37b9c47989e0
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
-    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
+    body: '{"messages": [{"role": "user", "content": "Return a valid schema for the
-      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
+      one tool you must use with its arguments and values.\n\nTools available:\n\nFuntion
-      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
+      Name: multiplier\nFuntion attributes: {''first_number'': {''type'': ''integer''},
-      - Useful for when you need to multiply two numbers together.\n        The input
+      ''second_number'': {''type'': ''integer''}}\nDescription: multiplier(first_number:
-      to this tool should be a comma separated list of numbers of\n        length
+      int, second_number: int) -> float - Useful for when you need to multiply two
-      two, representing the two numbers you want to multiply together.\n        For
+      numbers together.\n\nUse this text to inform a valid ouput schema:\nThought:
-      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
-      a tool, please use the exact following format:\n\n```\nThought: Do I need to
+      3, \"second_number\": 5}\n\nThe output should be formatted as a JSON instance
-      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
+      that conforms to the JSON schema below.\n\nAs an example, for the schema {\"properties\":
-      just the name.\nAction Input: the input to the action\nObservation: the result
+      {\"foo\": {\"title\": \"Foo\", \"description\": \"a list of strings\", \"type\":
-      of the action\n```\n\nWhen you have a response for your task, or if you do not
+      \"array\", \"items\": {\"type\": \"string\"}}}, \"required\": [\"foo\"]}\nthe
-      need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use
+      object {\"foo\": [\"bar\", \"baz\"]} is a well-formatted instance of the schema.
-      a tool? No\nFinal Answer: [your response here]\n```\n\t\tThis is the summary
+      The object {\"properties\": {\"foo\": [\"bar\", \"baz\"]}} is not well-formatted.\n\nHere
-      of your work so far:\n    \nBegin! This is VERY important to you, your job depends
+      is the output schema:\n```\n{\"properties\": {\"function_name\": {\"title\":
-      on it!\n\nCurrent Task: What is 3 times 5?\nThought: Do I need to use a tool?
+      \"Function Name\", \"description\": \"The name of the function to be called.\",
-      Yes\nAction: multiplier\nAction Input: 3,5\nObservation: 15\nThought: \n"}],
+      \"type\": \"string\"}, \"arguments\": {\"title\": \"Arguments\", \"description\":
-      "model": "gpt-4", "n": 1, "stop": ["\nObservation"], "stream": false, "temperature":
+      \"A dictinary of arguments to be passed to the function.\", \"type\": \"object\"}},
-      0.7}'
+      \"required\": [\"function_name\", \"arguments\"]}\n```\n```"}], "model": "gpt-4",
+      "n": 1, "stream": false, "temperature": 0.7}'
     headers:
       accept:
       - application/json
@@ -143,16 +139,16 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '1335'
+      - '1494'
       content-type:
       - application/json
       cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -162,7 +158,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -170,18 +166,20 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eG2qnUr6SZcankL5AqkwIJvYFc\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703858228,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SRO2/cMBCEe/2KBWtdIN0jF6t1kRQG7MApDISBjketJNrkUiFX8AUH/feAupfd
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
+        sNiZbzE7PGYAwjSiAqF7xdoNdvHtr76zT+XDy+HXz/v3t2e6f/xelHx4ennmpcgT4fevqPlCfdHe
-      3 times 5 is 15.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
+        DRbZeDrJOqBiTFvLbbHdbIr1spwF5xu0CesGXqwXxddydSZ6bzRGUcHvDADgOL8pGzV4EBUU+WXi
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 297,\n    \"completion_tokens\":
+        MEbVoaiuJgARvE0ToWI0kRWxyG+i9sRIc9wfGBBMBAXvaO2i9cEpZmzAUMI0gm+Be4Soe3SqkiRp
-      22,\n    \"total_tokens\": 319\n  },\n  \"system_fingerprint\": null\n}\n"
+        t9u9Rk+SjpIApGhH0unWmpRDKSqQwo2WzWANBinyk0uFbnRIHJNjJmfWhMg1jW6frBWs8osSUXtq
+        PkibpEySpjmBOJ8zXXuwvhuC36fOaLT2Om8NmdjXAVX0lG6O7IcTPmUAf+a+x08ViiF4N3DN/g0p
+        LVwtN6d94va1N3V9dxbZs7IfqO06OycU8V9kdHVrqMMwBDPXn3JmU/YfAAD//wMAtRBeM3UCAAA=
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 83d28ce3ab3b1cd9-GRU
+      - 8532aa5709e5679a-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -191,7 +189,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 29 Dec 2023 13:57:09 GMT
+      - Sat, 10 Feb 2024 07:33:44 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -205,7 +203,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '1568'
+      - '2203'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -214,24 +212,128 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '299661'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 67ms
+      x-request-id:
+      - req_a428e78fc8e9d475e463316f65950fa9
+    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\nmultiplier: multiplier(first_number: int, second_number: int) -> float
+      - Useful for when you need to multiply two numbers together.\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 [multiplier], 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: What is 3 times 5?\nThought:
+      Do I need to use a tool? Yes\nAction: multiplier\nAction Input: {\"first_number\":
+      3, \"second_number\": 5}\nObservation: 15\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:
+      - '1191'
+      content-type:
+      - application/json
+      cookie:
+      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
+        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
+      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 |
+        H4sIAAAAAAAAA1SQW0sDMRCF3/dXDHluy/aybd0XEYqiiKAiFFRKmp1uY7OZmMyipfS/S7bbiy95
+        OGfOyTezSwCELkQOQq0lq8qZ7vRbXRGrVz2fPPKd3z7MeSPty2r29uy06MQELb9Q8THVU1Q5g6zJ
+        HmzlUTLG1v4knWRZOhqMGqOiAk2MlY67o2467g/bxJq0wiByeE8AAHbNG9lsgb8ih7RzVCoMQZYo
+        8tMQgPBkoiJkCDqwtCw6Z1ORZbQN7ozgHixiAUxQBwQJTGSu4Yk+7K220sCNDT/ocxgC6woDZKAD
+        9LOeaAv3JxJDpfO0jNS2Nuakr7TVYb3wKAPZ+Gtgcof4PgH4bDau/y0hnKfK8YJpgzYWDsbDQ584
+        H/fCHbQmE0tzoU+zpCUUYRsYq8VK2xK987o5QORM9skfAAAA//8DACAb4vP3AQAA
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8532aa66fd5c679a-SJC
+      Cache-Control:
+      - no-cache, must-revalidate
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Sat, 10 Feb 2024 07:33:45 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:
+      - '1275'
+      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:
-      - '299693'
+      - '299728'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299693'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
-      - 61ms
+      - 54ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 61ms
       x-request-id:
-      - 66a02e3e08e3f6b5b29fb04cd19f50a0
+      - req_dd069a32b6514615a79356287e845a29
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
+      message: OK
 - request:
     body: '{"messages": [{"role": "user", "content": "Progressively summarize the
       lines of conversation provided, adding onto the previous summary returning a
@@ -257,12 +359,12 @@ interactions:
       content-type:
       - application/json
       cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
+      - __cf_bm=iA8sDHDKVnfosmI8wG_ElV9lor.u9ivoU2KD_Uw2Ck0-1707550421-1-AakLurCxUahX1wP/EqH55USvoahi23iv5/ZX2jxvr6ltSDBhzk8J0ipuSFcgyazwnWfYsqu0n467tSBqzuyTan0=;
-        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
+        _cfuvid=CpE5jxQFzpK609ZrTNgy1kxDFHYN2x4AY1XCThUEeQk-1707550421579-0-604800000
       host:
       - api.openai.com
       user-agent:
-      - OpenAI/Python 1.6.1
+      - OpenAI/Python 1.12.0
       x-stainless-arch:
       - arm64
       x-stainless-async:
@@ -272,7 +374,7 @@ interactions:
       x-stainless-os:
       - MacOS
       x-stainless-package-version:
-      - 1.6.1
+      - 1.12.0
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
@@ -280,19 +382,19 @@ interactions:
     method: POST
     uri: https://api.openai.com/v1/chat/completions
   response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eIfmBgQoWGLW4jiQZTu3qzEBBL\",\n  \"object\":
+    body:
-      \"chat.completion\",\n  \"created\": 1703858230,\n  \"model\": \"gpt-4-0613\",\n
+      string: !!binary |
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
+        H4sIAAAAAAAAA1SQT0/CQBDF7/0Ukz0XQgsV6E0TD2qiHtSYGEOW7dCu7D92p4lC+O5mS6F62cO8
-      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
+        93v7Zg4JAJMVK4GJhpPQTo0WO7F0ezl7549q+bx/eMp3t+v8Zlrdv27eWBoJu/5CQWdqLKx2Ckla
-      times 5 and the AI responds that 3 times 5 is 15.\"\n      },\n      \"logprobs\":
+        c5KFR04YU7P5ZF4Uk1ledIK2FaqI1Y5Gs9HkKpv2RGOlwMBK+EgAAA7dG7uZCr9ZCZP0PNEYAq+R
-      null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
+        lRcTAPNWxQnjIchA3BBLB1FYQ2i6ui8NQtNqboCHbQBqEK7vgCwIrkSrOCFMgaTGAEUK3FRni8fg
-      155,\n    \"completion_tokens\": 26,\n    \"total_tokens\": 181\n  },\n  \"system_fingerprint\":
+        rKkiwmnwgAyQFWPWf3a8tFS2dt6u40amVeoy30gjQ7PyyIM1sVEg6074MQH47K7R/luQOW+1oxXZ
-      null\n}\n"
+        LZoYmBXFKY8Nhx/UfN6LZImrP9QiT/qGLPwEQr3aSFOjd152x4k9k2PyCwAA//8DAHepd0ITAgAA
     headers:
       CF-Cache-Status:
       - DYNAMIC
       CF-RAY:
-      - 83d28cf118221cd9-GRU
+      - 8532aa703b92679a-SJC
       Cache-Control:
       - no-cache, must-revalidate
       Connection:
@@ -302,7 +404,7 @@ interactions:
       Content-Type:
       - application/json
       Date:
-      - Fri, 29 Dec 2023 13:57:12 GMT
+      - Sat, 10 Feb 2024 07:33:47 GMT
       Server:
       - cloudflare
       Transfer-Encoding:
@@ -316,7 +418,7 @@ interactions:
       openai-organization:
       - user-z7g4wmlazxqvc5wjyaaaocfz
       openai-processing-ms:
-      - '2188'
+      - '1667'
       openai-version:
       - '2020-10-01'
       strict-transport-security:
@@ -325,366 +427,17 @@ interactions:
       - '10000'
       x-ratelimit-limit-tokens:
       - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
       x-ratelimit-remaining-requests:
       - '9999'
       x-ratelimit-remaining-tokens:
       - '299794'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299794'
       x-ratelimit-reset-requests:
       - 6ms
       x-ratelimit-reset-tokens:
       - 41ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 41ms
       x-request-id:
-      - a644c703d416b1e4b06586e96e6d7297
+      - req_14ec03ab8500562c8eaac94fe2cec349
-    http_version: HTTP/1.1
+    status:
-    status_code: 200
+      code: 200
-- request:
+      message: OK
-    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
-      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
-      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
-      - Useful for when you need to multiply two numbers together.\n        The input
-      to this tool should be a comma separated list of numbers of\n        length
-      two, representing the two numbers you want to multiply together.\n        For
-      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
-      a tool, please use the exact following format:\n\n```\nThought: Do I need to
-      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
-      just the name.\nAction Input: the input to the action\nObservation: the result
-      of the action\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]\n```\n\t\tThis is the summary
-      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
-      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
-      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\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:
-      - '1317'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
-        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.6.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.6.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eKehkNtTjrXJD0aFjiVUeXU7te\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1703858232,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Thought: Do I need to use a tool? Yes\\nAction:
-      multiplier\\nAction Input: 3,5\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 290,\n    \"completion_tokens\":
-      23,\n    \"total_tokens\": 313\n  },\n  \"system_fingerprint\": null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 83d28d007f461cd9-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 29 Dec 2023 13:57:14 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:
-      - '1885'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299697'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299697'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 60ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 60ms
-      x-request-id:
-      - 87959bfa6a029f7bcafb5095e66d4964
-    http_version: HTTP/1.1
-    status_code: 200
-- request:
-    body: '{"messages": [{"role": "user", "content": "You are new test role.\nnew
-      test backstory\n\nYour personal goal is: new test goal\n\nTOOLS:\n------\nYou
-      have access to the following tools:\n\nmultiplier: multiplier(numbers) -> float
-      - Useful for when you need to multiply two numbers together.\n        The input
-      to this tool should be a comma separated list of numbers of\n        length
-      two, representing the two numbers you want to multiply together.\n        For
-      example, `1,2` would be the input if you wanted to multiply 1 by 2.\n\nTo use
-      a tool, please use the exact following format:\n\n```\nThought: Do I need to
-      use a tool? Yes\nAction: the action to take, should be one of [multiplier],
-      just the name.\nAction Input: the input to the action\nObservation: the result
-      of the action\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]\n```\n\t\tThis is the summary
-      of your work so far:\n    The human asks the AI to calculate 3 times 5 and the
-      AI responds that 3 times 5 is 15.\nBegin! This is VERY important to you, your
-      job depends on it!\n\nCurrent Task: What is 3 times 5?\n\nI just used the multiplier
-      tool with input 3,5. So I already knwo the result of that.\nObservation: Invalid
-      or incomplete response\nThought: \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:
-      - '1460'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
-        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.6.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.6.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eME5fg1w8QcXUnl0FBcqxJWy7u\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1703858234,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"Do I need to use a tool? No\\nFinal Answer:
-      3 times 5 is 15.\"\n      },\n      \"logprobs\": null,\n      \"finish_reason\":
-      \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 324,\n    \"completion_tokens\":
-      22,\n    \"total_tokens\": 346\n  },\n  \"system_fingerprint\": null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 83d28d0fcfaf1cd9-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 29 Dec 2023 13:57:17 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:
-      - '2494'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299661'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299661'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 67ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 67ms
-      x-request-id:
-      - eb9704531634d4cd3c6652dff09914bc
-    http_version: HTTP/1.1
-    status_code: 200
-- 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:\nThe human asks the AI to calculate 3 times 5
-      and the AI responds that 3 times 5 is 15.\n\nNew lines of conversation:\nHuman:
-      What is 3 times 5?\nAI: 3 times 5 is 15.\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:
-      - '972'
-      content-type:
-      - application/json
-      cookie:
-      - __cf_bm=iNTKkM.TU1FqaOYqOtdlGljM5kh2eYMOQyBBsDxjV7o-1703858227-1-AUtPBBabQY5DO7jJdGlU5rhZeJigXNSYGJkA8uYAsRU5NSaEt+YcHCLzXRQWpzm+lHKeh5JKd9iq/sLM5ylFvc8=;
-        _cfuvid=FKpE5gHVpQFRYsdYjjLPKhDX2CeCXpdvvJ8tjGmsYrM-1703858227679-0-604800000
-      host:
-      - api.openai.com
-      user-agent:
-      - OpenAI/Python 1.6.1
-      x-stainless-arch:
-      - arm64
-      x-stainless-async:
-      - 'false'
-      x-stainless-lang:
-      - python
-      x-stainless-os:
-      - MacOS
-      x-stainless-package-version:
-      - 1.6.1
-      x-stainless-runtime:
-      - CPython
-      x-stainless-runtime-version:
-      - 3.11.7
-    method: POST
-    uri: https://api.openai.com/v1/chat/completions
-  response:
-    content: "{\n  \"id\": \"chatcmpl-8b7eP77MzprkbgjaMbeaEob0aDx39\",\n  \"object\":
-      \"chat.completion\",\n  \"created\": 1703858237,\n  \"model\": \"gpt-4-0613\",\n
-      \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
-      \"assistant\",\n        \"content\": \"The human asks the AI to calculate 3
-      times 5 twice, and both times the AI responds that 3 times 5 is 15.\"\n      },\n
-      \     \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n
-      \ \"usage\": {\n    \"prompt_tokens\": 181,\n    \"completion_tokens\": 30,\n
-      \   \"total_tokens\": 211\n  },\n  \"system_fingerprint\": null\n}\n"
-    headers:
-      CF-Cache-Status:
-      - DYNAMIC
-      CF-RAY:
-      - 83d28d211f591cd9-GRU
-      Cache-Control:
-      - no-cache, must-revalidate
-      Connection:
-      - keep-alive
-      Content-Encoding:
-      - gzip
-      Content-Type:
-      - application/json
-      Date:
-      - Fri, 29 Dec 2023 13:57:20 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:
-      - '2967'
-      openai-version:
-      - '2020-10-01'
-      strict-transport-security:
-      - max-age=15724800; includeSubDomains
-      x-ratelimit-limit-requests:
-      - '10000'
-      x-ratelimit-limit-tokens:
-      - '300000'
-      x-ratelimit-limit-tokens_usage_based:
-      - '300000'
-      x-ratelimit-remaining-requests:
-      - '9999'
-      x-ratelimit-remaining-tokens:
-      - '299771'
-      x-ratelimit-remaining-tokens_usage_based:
-      - '299771'
-      x-ratelimit-reset-requests:
-      - 6ms
-      x-ratelimit-reset-tokens:
-      - 45ms
-      x-ratelimit-reset-tokens_usage_based:
-      - 45ms
-      x-request-id:
-      - e3bbd11b2e9b28f76f8b43dc7a4d2b6d
-    http_version: HTTP/1.1
-    status_code: 200
 version: 1