interactions:
- request:
    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier\nTool Arguments: {''first_number'': {''description'': None, ''type'': ''int''}, ''second_number'': {''description'': None, ''type'': ''int''}}\nTool Description: Useful for when you need to multiply two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final
      answer to the original input question\n```"},{"role":"user","content":"\nCurrent Task: What is 3 times 4?\n\nThis is the expected criteria for your final answer: The result of the multiplication.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"}],"model":"gpt-4.1-mini"}'
    headers:
      User-Agent:
      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
      - ACCEPT-ENCODING-XXX
      authorization:
      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
      - '1411'
      content-type:
      - application/json
      host:
      - api.openai.com
      x-stainless-arch:
      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - X-STAINLESS-OS-XXX
      x-stainless-package-version:
      - 1.83.0
      x-stainless-read-timeout:
      - X-STAINLESS-READ-TIMEOUT-XXX
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.10
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    body:
      string: "{\n  \"id\": \"chatcmpl-CjDrkaLpE7gzrxWaoNgDXoHiVYlox\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894096,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"```\\nThought: I need to multiply 3 and 4 to find the answer.\\nAction: multiplier\\nAction Input: {\\\"first_number\\\": 3, \\\"second_number\\\": 4}\\n```\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 294,\n    \"completion_tokens\": 40,\n    \"total_tokens\": 334,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n\
        \  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_24710c7f06\"\n}\n"
    headers:
      CF-RAY:
      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
      - Fri, 05 Dec 2025 00:21:37 GMT
      Server:
      - cloudflare
      Set-Cookie:
      - SET-COOKIE-XXX
      Strict-Transport-Security:
      - STS-XXX
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - X-CONTENT-TYPE-XXX
      access-control-expose-headers:
      - ACCESS-CONTROL-XXX
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - OPENAI-ORG-XXX
      openai-processing-ms:
      - '814'
      openai-project:
      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
      x-envoy-upstream-service-time:
      - '826'
      x-openai-proxy-wasm:
      - v0.1
      x-ratelimit-limit-requests:
      - X-RATELIMIT-LIMIT-REQUESTS-XXX
      x-ratelimit-limit-tokens:
      - X-RATELIMIT-LIMIT-TOKENS-XXX
      x-ratelimit-remaining-requests:
      - X-RATELIMIT-REMAINING-REQUESTS-XXX
      x-ratelimit-remaining-tokens:
      - X-RATELIMIT-REMAINING-TOKENS-XXX
      x-ratelimit-reset-requests:
      - X-RATELIMIT-RESET-REQUESTS-XXX
      x-ratelimit-reset-tokens:
      - X-RATELIMIT-RESET-TOKENS-XXX
      x-request-id:
      - X-REQUEST-ID-XXX
    status:
      code: 200
      message: OK
- request:
    body: '{"messages":[{"role":"system","content":"You are test role. test backstory\nYour personal goal is: test goal\nYou ONLY have access to the following tools, and should NEVER make up tools that are not listed here:\n\nTool Name: multiplier\nTool Arguments: {''first_number'': {''description'': None, ''type'': ''int''}, ''second_number'': {''description'': None, ''type'': ''int''}}\nTool Description: Useful for when you need to multiply two numbers together.\n\nIMPORTANT: Use the following format in your response:\n\n```\nThought: you should always think about what to do\nAction: the action to take, only one name of [multiplier], just the name, exactly as it''s written.\nAction Input: the input to the action, just a simple JSON object, enclosed in curly braces, using \" to wrap keys and values.\nObservation: the result of the action\n```\n\nOnce all necessary information is gathered, return the following format:\n\n```\nThought: I now know the final answer\nFinal Answer: the final
      answer to the original input question\n```"},{"role":"user","content":"\nCurrent Task: What is 3 times 4?\n\nThis is the expected criteria for your final answer: The result of the multiplication.\nyou MUST return the actual complete content as the final answer, not a summary.\n\nBegin! This is VERY important to you, use the tools available and give your best Final Answer, your job depends on it!\n\nThought:"},{"role":"assistant","content":"```\nThought: I need to multiply 3 and 4 to find the answer.\nAction: multiplier\nAction Input: {\"first_number\": 3, \"second_number\": 4}\n```\nObservation: 12"}],"model":"gpt-4.1-mini"}'
    headers:
      User-Agent:
      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
      - ACCEPT-ENCODING-XXX
      authorization:
      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
      - '1606'
      content-type:
      - application/json
      cookie:
      - COOKIE-XXX
      host:
      - api.openai.com
      x-stainless-arch:
      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-lang:
      - python
      x-stainless-os:
      - X-STAINLESS-OS-XXX
      x-stainless-package-version:
      - 1.83.0
      x-stainless-read-timeout:
      - X-STAINLESS-READ-TIMEOUT-XXX
      x-stainless-retry-count:
      - '0'
      x-stainless-runtime:
      - CPython
      x-stainless-runtime-version:
      - 3.12.10
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    body:
      string: "{\n  \"id\": \"chatcmpl-CjDrlef5BRgjys4egJ1gNp0jIS5RR\",\n  \"object\": \"chat.completion\",\n  \"created\": 1764894097,\n  \"model\": \"gpt-4.1-mini-2025-04-14\",\n  \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\": \"assistant\",\n        \"content\": \"```\\nThought: I now know the final answer\\nFinal Answer: 12\\n```\",\n        \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 343,\n    \"completion_tokens\": 18,\n    \"total_tokens\": 361,\n    \"prompt_tokens_details\": {\n      \"cached_tokens\": 0,\n      \"audio_tokens\": 0\n    },\n    \"completion_tokens_details\": {\n      \"reasoning_tokens\": 0,\n      \"audio_tokens\": 0,\n      \"accepted_prediction_tokens\": 0,\n      \"rejected_prediction_tokens\": 0\n    }\n  },\n  \"service_tier\": \"default\",\n  \"system_fingerprint\": \"fp_24710c7f06\"\n}\n"
    headers:
      CF-RAY:
      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
      - Fri, 05 Dec 2025 00:21:38 GMT
      Server:
      - cloudflare
      Strict-Transport-Security:
      - STS-XXX
      Transfer-Encoding:
      - chunked
      X-Content-Type-Options:
      - X-CONTENT-TYPE-XXX
      access-control-expose-headers:
      - ACCESS-CONTROL-XXX
      alt-svc:
      - h3=":443"; ma=86400
      cf-cache-status:
      - DYNAMIC
      openai-organization:
      - OPENAI-ORG-XXX
      openai-processing-ms:
      - '750'
      openai-project:
      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
      x-envoy-upstream-service-time:
      - '765'
      x-openai-proxy-wasm:
      - v0.1
      x-ratelimit-limit-requests:
      - X-RATELIMIT-LIMIT-REQUESTS-XXX
      x-ratelimit-limit-tokens:
      - X-RATELIMIT-LIMIT-TOKENS-XXX
      x-ratelimit-remaining-requests:
      - X-RATELIMIT-REMAINING-REQUESTS-XXX
      x-ratelimit-remaining-tokens:
      - X-RATELIMIT-REMAINING-TOKENS-XXX
      x-ratelimit-reset-requests:
      - X-RATELIMIT-RESET-REQUESTS-XXX
      x-ratelimit-reset-tokens:
      - X-RATELIMIT-RESET-TOKENS-XXX
      x-request-id:
      - X-REQUEST-ID-XXX
    status:
      code: 200
      message: OK
version: 1