{ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestEdgeCases::test_tool_without_schema[txt=vllm/Qwen/Qwen3-0.6B]", "request": { "method": "POST", "url": "http://localhost:8000/v1/v1/chat/completions", "headers": {}, "body": { "model": "Qwen/Qwen3-0.6B", "messages": [ { "role": "user", "content": "Call the no args tool" } ], "max_tokens": 4096, "tools": [ { "type": "function", "function": { "name": "no_args_tool", "description": "Tool with no arguments", "parameters": { "type": "object", "properties": {} } } } ] }, "endpoint": "/v1/chat/completions", "model": "Qwen/Qwen3-0.6B" }, "response": { "body": { "__type__": "openai.types.chat.chat_completion.ChatCompletion", "__data__": { "id": "rec-452805c3c859", "choices": [ { "finish_reason": "tool_calls", "index": 0, "logprobs": null, "message": { "content": "\nOkay, the user wants me to call the no args tool. Let me check the available functions. There's only one tool provided, which is the no_args_tool with no arguments. Since the user didn't specify any parameters, I should just return the tool call as instructed. I need to make sure the JSON is correctly formatted and within the XML tags. Alright, that's all I need.\n\n\n", "refusal": null, "role": "assistant", "annotations": null, "audio": null, "function_call": null, "tool_calls": [ { "id": "chatcmpl-tool-7a67269afe214c85924c5171612bbdbd", "function": { "arguments": "{}", "name": "no_args_tool" }, "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": 101, "prompt_tokens": 136, "total_tokens": 237, "completion_tokens_details": null, "prompt_tokens_details": null }, "prompt_logprobs": null, "kv_transfer_params": null } }, "is_streaming": false }, "id_normalization_mapping": {} }