llama-stack-mirror/tests/integration/inference/recordings/744052775cf90e30dac587e6b809d41a8cc37adc29c500eecee2727f428cbf5a.json

{
  "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_with_tools[txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:tool_calling]",
  "request": {
    "method": "POST",
    "url": "http://localhost:8000/v1/v1/chat/completions",
    "headers": {},
    "body": {
      "model": "Qwen/Qwen3-0.6B",
      "messages": [
        {
          "role": "system",
          "content": "Pretend you are a weather assistant."
        },
        {
          "role": "user",
          "content": "What's the weather like in San Francisco, CA?"
        }
      ],
      "max_tokens": 4096,
      "stream": false,
      "tool_choice": "auto",
      "tools": [
        {
          "type": "function",
          "function": {
            "name": "get_weather",
            "description": "Get the current weather",
            "parameters": {
              "type": "object",
              "properties": {
                "location": {
                  "type": "string",
                  "description": "The city and state (both required), e.g. San Francisco, CA."
                }
              },
              "required": [
                "location"
              ]
            }
          }
        }
      ]
    },
    "endpoint": "/v1/chat/completions",
    "model": "Qwen/Qwen3-0.6B"
  },
  "response": {
    "body": {
      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
      "__data__": {
        "id": "rec-744052775cf9",
        "choices": [
          {
            "finish_reason": "tool_calls",
            "index": 0,
            "logprobs": null,
            "message": {
              "content": "<think>\nOkay, the user is asking about the weather in San Francisco, CA. I need to use the get_weather function. The function requires the location parameter, which is provided as San Francisco, CA. I should make sure to format the arguments correctly as a JSON object. Let me check the required parameters again. The location is required, so I can't omit it. I'll structure the tool call with the name \"get_weather\" and the arguments including \"location\": \"San Francisco, CA\". That should get the current weather information for the user.\n</think>\n\n",
              "refusal": null,
              "role": "assistant",
              "annotations": null,
              "audio": null,
              "function_call": null,
              "tool_calls": [
                {
                  "id": "chatcmpl-tool-b59dc311dd914d3dbd6d455b122bc39c",
                  "function": {
                    "arguments": "{\"location\": \"San Francisco, CA\"}",
                    "name": "get_weather"
                  },
                  "type": "function"
                }
              ],
              "reasoning_content": null
            },
            "stop_reason": null
          }
        ],
        "created": 0,
        "model": "Qwen/Qwen3-0.6B",
        "object": "chat.completion",
        "service_tier": null,
        "system_fingerprint": null,
        "usage": {
          "completion_tokens": 138,
          "prompt_tokens": 185,
          "total_tokens": 323,
          "completion_tokens_details": null,
          "prompt_tokens_details": null
        },
        "prompt_logprobs": null,
        "kv_transfer_params": null
      }
    },
    "is_streaming": false
  },
  "id_normalization_mapping": {}
}