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: 462
10 host: ""
11 body: '{"messages":[{"content":"You are a helpful assistant","role":"system"},{"content":"What''s the weather in Florence, Italy?","role":"user"}],"model":"grok-3-mini","reasoning_effort":"high","tool_choice":"auto","tools":[{"function":{"name":"weather","strict":false,"description":"Get weather information for a location","parameters":{"properties":{"location":{"description":"the city","type":"string"}},"required":["location"],"type":"object"}},"type":"function"}]}'
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: |
28 {"choices":[{"content_filter_results":{},"finish_reason":"tool_calls","index":0,"logprobs":null,"message":{"content":"","reasoning_content":"First, the user is asking for the weather in Florence, Italy. I have an available function called \"weather\" that can get weather information for a location.\n\nThe function description is: \"Get weather information for a location\". The parameters require a \"location\" which is a string describing the city.\n\nIn this query, the user has provided \"Florence, Italy\", which clearly specifies the city and country. This matches the required parameter for the \"weather\" function.\n\nAll required parameters are provided and inferable. The location is given as \"Florence, Italy\", so I can use that directly.\n\nAccording to the instructions, if the user's query can be addressed using an available function and all required parameters are provided, I should trigger a function call in the specified JSON format within \u003cfunction_call\u003e tags.\n\nThe format should be: \u003cfunction_call\u003e{\"action\": \"function_name\", \"action_input\": {\"parameter\": \"argument\"}}\u003c/function_call\u003e\n\nFor this case, the action is \"weather\", and the action_input should have the \"location\" parameter with the value \"Florence, Italy\".\n\nI should not make my response verbose. Keep it clear and concise. Since I'm calling a function, my response should only contain the function call if that's the next step.\n\nThe instructions say: \"You are only permitted to use the \u003cfunction_call\u003e tag in your response only if you have made the decision to call a function.\" And in this case, I have decided to call the function.\n\nAfter calling the function, in a multi-turn conversation, I might need to handle the response, but for now, the logical next step is to call the weather function.\n\nNo need to ask for clarification because the location is clear.\n\nSo, my response should be:\n\n\u003cfunction_call\u003e{\"action\": \"weather\", \"action_input\": {\"location\": \"Florence, Italy\"}}\u003c/function_call\u003e\n\nThat seems straightforward.","refusal":null,"role":"assistant","tool_calls":[{"function":{"arguments":"{\"location\":\"Florence, Italy\"}","call_id":null,"name":"weather"},"id":"call_39096519","type":"function"}]},"stop_reason":null}],"created":1773338606,"id":"4a702f64-f693-4d27-8806-c9a9907959ae_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":27,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":379,"rejected_prediction_tokens":0},"num_sources_used":0,"prompt_tokens":288,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0,"image_tokens":0,"text_tokens":288},"total_tokens":694}}
29 headers:
30 Content-Type:
31 - application/json
32 status: 200 OK
33 code: 200
34 duration: 3.557213292s
35- id: 1
36 request:
37 proto: HTTP/1.1
38 proto_major: 1
39 proto_minor: 1
40 content_length: 682
41 host: ""
42 body: '{"messages":[{"content":"You are a helpful assistant","role":"system"},{"content":"What''s the weather in Florence, Italy?","role":"user"},{"tool_calls":[{"id":"call_39096519","function":{"arguments":"{\"location\":\"Florence, Italy\"}","name":"weather"},"type":"function"}],"role":"assistant"},{"content":"40 C","tool_call_id":"call_39096519","role":"tool"}],"model":"grok-3-mini","reasoning_effort":"high","tool_choice":"auto","tools":[{"function":{"name":"weather","strict":false,"description":"Get weather information for a location","parameters":{"properties":{"location":{"description":"the city","type":"string"}},"required":["location"],"type":"object"}},"type":"function"}]}'
43 headers:
44 Accept:
45 - application/json
46 Content-Type:
47 - application/json
48 User-Agent:
49 - Charm-Fantasy/0.12.2 (https://charm.land/fantasy)
50 url: https://fantasy-playground-resource.openai.azure.com/openai/v1/chat/completions
51 method: POST
52 response:
53 proto: HTTP/2.0
54 proto_major: 2
55 proto_minor: 0
56 content_length: -1
57 uncompressed: true
58 body: |
59 {"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":"The weather in Florence, Italy, is currently 40°C.","reasoning_content":"First, the user asked: \"What's the weather in Florence, Italy?\" This directly matches the available function \"weather\", which requires a \"location\" parameter.\n\nThe function call I made was: \u003cfunction_call\u003e{\"action\": \"weather\", \"action_input\": {\"location\": \"Florence, Italy\"}}\u003c/function_call\u003e\n\nNow, the system has responded with the function output: \"Function: 40 C\". I assume this means the weather function returned that the temperature is 40 degrees Celsius.\n\nMy role is to be a helpful assistant. After calling a function, I should provide a clear, non-verbose response to the user based on the function's output.\n\nThe user's request is now fulfilled because I called the weather function, and I have the result. I don't need to call any more functions unless there's more to the query.\n\nResponse guidelines:\n- Keep the response clear and not verbose.\n- If I've called a function and have the result, I should present it to the user.\n- Only use \u003cfunction_call\u003e tags when deciding to call a function. In this case, I've already called it, and now I'm responding with the result.\n\nSo, I should now give a straightforward answer to the user based on the function's output.\n\nFunction output is \"40 C\", which I interpret as 40 degrees Celsius. I should make this user-friendly.\n\nFinal response: Inform the user about the weather in Florence, Italy, based on the function call result.","refusal":null,"role":"assistant","tool_calls":null},"stop_reason":null}],"created":1773338610,"id":"69b00015-5cfe-4d69-b451-da44ba17c1f9_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":13,"completion_tokens_details":{"accepted_prediction_tokens":0,"audio_tokens":0,"reasoning_tokens":293,"rejected_prediction_tokens":0},"num_sources_used":0,"prompt_tokens":332,"prompt_tokens_details":{"audio_tokens":0,"cached_tokens":0,"image_tokens":0,"text_tokens":332},"total_tokens":638}}
60 headers:
61 Content-Type:
62 - application/json
63 status: 200 OK
64 code: 200
65 duration: 2.248014792s