interactions:
- request:
    body: '{"messages":[{"role":"system","content":"Ensure your final answer strictly
      adheres to the following OpenAPI schema: {\n  \"type\": \"json_schema\",\n  \"json_schema\":
      {\n    \"name\": \"LLMGuardrailResult\",\n    \"strict\": true,\n    \"schema\":
      {\n      \"properties\": {\n        \"valid\": {\n          \"description\":
      \"Whether the task output complies with the guardrail\",\n          \"title\":
      \"Valid\",\n          \"type\": \"boolean\"\n        },\n        \"feedback\":
      {\n          \"anyOf\": [\n            {\n              \"type\": \"string\"\n            },\n            {\n              \"type\":
      \"null\"\n            }\n          ],\n          \"default\": null,\n          \"description\":
      \"A feedback about the task output if it is not valid\",\n          \"title\":
      \"Feedback\"\n        }\n      },\n      \"required\": [\n        \"valid\",\n        \"feedback\"\n      ],\n      \"title\":
      \"LLMGuardrailResult\",\n      \"type\": \"object\",\n      \"additionalProperties\":
      false\n    }\n  }\n}\n\nDo not include the OpenAPI schema in the final output.
      Ensure the final output does not include any code block markers like ```json
      or ```python."},{"role":"user","content":"{\"valid\":false,\"feedback\":\"The
      task result has more than 10 words. It violates the guardrail requirement of
      having less than 10 words.\"}"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
      the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
      feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
    headers:
      User-Agent:
      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
      - ACCEPT-ENCODING-XXX
      authorization:
      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
      - '1867'
      content-type:
      - application/json
      cookie:
      - COOKIE-XXX
      host:
      - api.openai.com
      x-stainless-arch:
      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-helper-method:
      - beta.chat.completions.parse
      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:
      - 3.13.3
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    body:
      string: "{\n  \"id\": \"chatcmpl-Cy5PPD1uYxgIbXU5hMI4xS5PK4Swt\",\n  \"object\":
        \"chat.completion\",\n  \"created\": 1768436507,\n  \"model\": \"gpt-4o-2024-08-06\",\n
        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
        \"assistant\",\n        \"content\": \"{\\\"valid\\\":false,\\\"feedback\\\":\\\"The
        task result has more than 10 words. It violates the guardrail requirement
        of having less than 10 words.\\\"}\",\n        \"refusal\": null,\n        \"annotations\":
        []\n      },\n      \"logprobs\": null,\n      \"finish_reason\": \"stop\"\n
        \   }\n  ],\n  \"usage\": {\n    \"prompt_tokens\": 369,\n    \"completion_tokens\":
        32,\n    \"total_tokens\": 401,\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_a0e9480a2f\"\n}\n"
    headers:
      CF-RAY:
      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
      - Thu, 15 Jan 2026 00:21:47 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
      content-length:
      - '946'
      openai-organization:
      - OPENAI-ORG-XXX
      openai-processing-ms:
      - '463'
      openai-project:
      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
      x-envoy-upstream-service-time:
      - '671'
      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":"Ensure your final answer strictly
      adheres to the following OpenAPI schema: {\n  \"type\": \"json_schema\",\n  \"json_schema\":
      {\n    \"name\": \"LLMGuardrailResult\",\n    \"strict\": true,\n    \"schema\":
      {\n      \"properties\": {\n        \"valid\": {\n          \"description\":
      \"Whether the task output complies with the guardrail\",\n          \"title\":
      \"Valid\",\n          \"type\": \"boolean\"\n        },\n        \"feedback\":
      {\n          \"anyOf\": [\n            {\n              \"type\": \"string\"\n            },\n            {\n              \"type\":
      \"null\"\n            }\n          ],\n          \"default\": null,\n          \"description\":
      \"A feedback about the task output if it is not valid\",\n          \"title\":
      \"Feedback\"\n        }\n      },\n      \"required\": [\n        \"valid\",\n        \"feedback\"\n      ],\n      \"title\":
      \"LLMGuardrailResult\",\n      \"type\": \"object\",\n      \"additionalProperties\":
      false\n    }\n  }\n}\n\nDo not include the OpenAPI schema in the final output.
      Ensure the final output does not include any code block markers like ```json
      or ```python."},{"role":"user","content":"{\"valid\":true,\"feedback\":null}"}],"model":"gpt-4o","response_format":{"type":"json_schema","json_schema":{"schema":{"properties":{"valid":{"description":"Whether
      the task output complies with the guardrail","title":"Valid","type":"boolean"},"feedback":{"anyOf":[{"type":"string"},{"type":"null"}],"description":"A
      feedback about the task output if it is not valid","title":"Feedback"}},"required":["valid","feedback"],"title":"LLMGuardrailResult","type":"object","additionalProperties":false},"name":"LLMGuardrailResult","strict":true}},"stream":false}'
    headers:
      User-Agent:
      - X-USER-AGENT-XXX
      accept:
      - application/json
      accept-encoding:
      - ACCEPT-ENCODING-XXX
      authorization:
      - AUTHORIZATION-XXX
      connection:
      - keep-alive
      content-length:
      - '1759'
      content-type:
      - application/json
      cookie:
      - COOKIE-XXX
      host:
      - api.openai.com
      x-stainless-arch:
      - X-STAINLESS-ARCH-XXX
      x-stainless-async:
      - 'false'
      x-stainless-helper-method:
      - beta.chat.completions.parse
      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:
      - 3.13.3
    method: POST
    uri: https://api.openai.com/v1/chat/completions
  response:
    body:
      string: "{\n  \"id\": \"chatcmpl-Cy5PQkMg7YJYa44FYy6Wb04G3qmx4\",\n  \"object\":
        \"chat.completion\",\n  \"created\": 1768436508,\n  \"model\": \"gpt-4o-2024-08-06\",\n
        \ \"choices\": [\n    {\n      \"index\": 0,\n      \"message\": {\n        \"role\":
        \"assistant\",\n        \"content\": \"{\\\"valid\\\":true,\\\"feedback\\\":null}\",\n
        \       \"refusal\": null,\n        \"annotations\": []\n      },\n      \"logprobs\":
        null,\n      \"finish_reason\": \"stop\"\n    }\n  ],\n  \"usage\": {\n    \"prompt_tokens\":
        346,\n    \"completion_tokens\": 9,\n    \"total_tokens\": 355,\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_a0e9480a2f\"\n}\n"
    headers:
      CF-RAY:
      - CF-RAY-XXX
      Connection:
      - keep-alive
      Content-Type:
      - application/json
      Date:
      - Thu, 15 Jan 2026 00:21:48 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
      content-length:
      - '837'
      openai-organization:
      - OPENAI-ORG-XXX
      openai-processing-ms:
      - '316'
      openai-project:
      - OPENAI-PROJECT-XXX
      openai-version:
      - '2020-10-01'
      x-envoy-upstream-service-time:
      - '349'
      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