simple.yaml

 1---
 2version: 2
 3interactions:
 4- id: 0
 5  request:
 6    proto: HTTP/1.1
 7    proto_major: 1
 8    proto_minor: 1
 9    content_length: 161
10    host: ""
11    body: '{"messages":[{"content":"You are a helpful assistant","role":"system"},{"content":"Say hi in Portuguese","role":"user"}],"model":"grok-3-mini","max_tokens":4000}'
12    headers:
13      Accept:
14      - application/json
15      Content-Type:
16      - application/json
17      User-Agent:
18      - Charm-Fantasy/0.12.2 (https://charm.land/fantasy)
19    url: https://fantasy-playground-resource.openai.azure.com/openai/v1/chat/completions
20    method: POST
21  response:
22    proto: HTTP/2.0
23    proto_major: 2
24    proto_minor: 0
25    content_length: -1
26    uncompressed: true
27    body: "{\"choices\":[{\"content_filter_results\":{\"hate\":{\"filtered\":false,\"severity\":\"safe\"},\"protected_material_code\":{\"filtered\":false,\"detected\":false},\"protected_material_text\":{\"filtered\":false,\"detected\":false},\"self_harm\":{\"filtered\":false,\"severity\":\"safe\"},\"sexual\":{\"filtered\":false,\"severity\":\"safe\"},\"violence\":{\"filtered\":false,\"severity\":\"safe\"}},\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"Oi! That's \\\"hi\\\" in Portuguese. \U0001F60A\",\"reasoning_content\":\"First, the user asked me to \\\"Say hi in Portuguese.\\\" So, I need to respond in a helpful and friendly manner, as per my system prompt.\\n\\nThe translation of \\\"hi\\\" in Portuguese is \\\"oi\\\" or \\\"olá\\\". \\\"Oi\\\" is more informal, like \\\"hi\\\", and \\\"olá\\\" is more formal, like \\\"hello\\\". Since the user said \\\"hi\\\", which is casual, I should use \\\"oi\\\" to match the tone.\\n\\nTo be more engaging, I could say something like \\\"Hi in Portuguese is 'oi'!\\\" or just directly say \\\"Oi!\\\" But since the user said \\\"Say hi in Portuguese\\\", they might want me to greet them in Portuguese.\\n\\nRe-reading the query: \\\"Say hi in Portuguese.\\\" This could mean two things:\\n\\n1. Translate \\\"hi\\\" to Portuguese and tell them what it is.\\n\\n2. Greet them by saying \\\"hi\\\" in Portuguese.\\n\\nGiven that it's a direct command, I think the best response is to greet them in Portuguese. So, I could start with \\\"Oi!\\\" or \\\"Olá!\\\".\\n\\nTo be more helpful, I could combine both: greet them and then explain if needed. But I should keep it simple.\\n\\nMy response should be in English unless specified, but since they're asking to say something in Portuguese, I can include that.\\n\\nPossible responses:\\n\\n- \\\"Oi!\\\" (simple and direct)\\n\\n- \\\"Hi in Portuguese is 'oi'.\\\"\\n\\n- \\\"Olá! That's how you say hi in Portuguese.\\\"\\n\\nTo make it more conversational: \\\"Sure, in Portuguese, 'hi' is 'oi'! Oi!\\\"\\n\\nRemember, I'm an AI assistant, so I should be polite and engaging.\\n\\nFinalizing my response: I'll greet them in Portuguese and then confirm in English to ensure clarity.\\n\\nSo, something like: \\\"Oi! That means 'hi' in Portuguese.\\\"\\n\\nOr, to keep it concise: \\\"Oi!\\\"\\n\\nBut adding a bit more might be better for helpfulness.\",\"refusal\":null,\"role\":\"assistant\",\"tool_calls\":null},\"stop_reason\":null}],\"created\":1773338566,\"id\":\"98198c66-3ec6-46f9-92d3-bbc2dd8cfdca_sidecar\",\"model\":\"grok-3-mini-high\",\"object\":\"chat.completion\",\"prompt_filter_results\":[{\"prompt_index\":0,\"content_filter_results\":{\"hate\":{\"filtered\":false,\"severity\":\"safe\"},\"jailbreak\":{\"filtered\":false,\"detected\":false},\"self_harm\":{\"filtered\":false,\"severity\":\"safe\"},\"sexual\":{\"filtered\":false,\"severity\":\"safe\"},\"violence\":{\"filtered\":false,\"severity\":\"safe\"}}}],\"usage\":{\"audio_prompt_tokens\":0,\"completion_tokens\":11,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":396,\"rejected_prediction_tokens\":0},\"num_sources_used\":0,\"prompt_tokens\":20,\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":0,\"image_tokens\":0,\"text_tokens\":20},\"total_tokens\":427}}\n"
28    headers:
29      Content-Type:
30      - application/json
31    status: 200 OK
32    code: 200
33    duration: 2.597864042s