Strata/serve/chat_golden.json

[
 {
  "name": "single user",
  "messages": [
   {
    "role": "user",
    "content": "Hello"
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "system + user",
  "messages": [
   {
    "role": "system",
    "content": "You are a helpful assistant."
   },
   {
    "role": "user",
    "content": "What is 2+2?"
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nWhat is 2+2?<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\nYou are a helpful assistant.<|im_end|>\n<|im_start|>user\nWhat is 2+2?<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "multi-turn",
  "messages": [
   {
    "role": "system",
    "content": "Be brief."
   },
   {
    "role": "user",
    "content": "Hi"
   },
   {
    "role": "assistant",
    "content": "Hello! How can I help?"
   },
   {
    "role": "user",
    "content": "Explain BPE in one sentence."
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\nBe brief.<|im_end|>\n<|im_start|>user\nHi<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nHello! How can I help?<|im_end|>\n<|im_start|>user\nExplain BPE in one sentence.<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\nBe brief.<|im_end|>\n<|im_start|>user\nHi<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nHello! How can I help?<|im_end|>\n<|im_start|>user\nExplain BPE in one sentence.<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "assistant with thinking",
  "messages": [
   {
    "role": "user",
    "content": "What is 17*23?"
   },
   {
    "role": "assistant",
    "content": "Let me compute.",
    "reasoning_content": "17*23 = 17*20 + 17*3 = 340+51 = 391"
   },
   {
    "role": "user",
    "content": "Thanks"
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nWhat is 17*23?<|im_end|>\n<|im_start|>assistant\n<think>\n17*23 = 17*20 + 17*3 = 340+51 = 391\n</think>\n\nLet me compute.<|im_end|>\n<|im_start|>user\nThanks<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nWhat is 17*23?<|im_end|>\n<|im_start|>assistant\n<think>\n17*23 = 17*20 + 17*3 = 340+51 = 391\n</think>\n\nLet me compute.<|im_end|>\n<|im_start|>user\nThanks<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "no generation prompt",
  "messages": [
   {
    "role": "user",
    "content": "Hello"
   },
   {
    "role": "assistant",
    "content": "Hi there"
   }
  ],
  "add_generation_prompt": false,
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nHi there<|im_end|>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\nHi there<|im_end|>\n"
 },
 {
  "name": "thinking disabled",
  "messages": [
   {
    "role": "user",
    "content": "Hello"
   }
  ],
  "enable_thinking": false,
  "rendered": "<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n",
  "error": null,
  "hf": "<|im_start|>user\nHello<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
 },
 {
  "name": "unicode content",
  "messages": [
   {
    "role": "user",
    "content": "你好，世界 😀"
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\n你好，世界 😀<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\n你好，世界 😀<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "tool call and response",
  "messages": [
   {
    "role": "user",
    "content": "Weather in Oslo?"
   },
   {
    "role": "assistant",
    "content": "",
    "tool_calls": [
     {
      "type": "function",
      "function": {
       "name": "get_weather",
       "arguments": {
        "city": "Oslo"
       }
      }
     }
    ]
   },
   {
    "role": "tool",
    "content": "{\"temp\": 3}",
    "name": "get_weather"
   },
   {
    "role": "user",
    "content": "And in Bergen?"
   }
  ],
  "tools": [
   {
    "type": "function",
    "function": {
     "name": "get_weather",
     "description": "Get the weather",
     "parameters": {
      "type": "object",
      "properties": {
       "city": {
        "type": "string"
       }
      },
      "required": [
       "city"
      ]
     }
    }
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\n# Tools\n\nYou have access to the following functions:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_weather\", \"description\": \"Get the weather\", \"parameters\": {\"type\": \"object\", \"properties\": {\"city\": {\"type\": \"string\"}}, \"required\": [\"city\"]}}}\n</tools>\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT><|im_end|>\n<|im_start|>user\nWeather in Oslo?<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n<tool_call>\n<function=get_weather>\n<parameter=city>\nOslo\n</parameter>\n</function>\n</tool_call><|im_end|>\n<|im_start|>user\n<tool_response>\n{\"temp\": 3}\n</tool_response><|im_end|>\n<|im_start|>user\nAnd in Bergen?<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.\n\n# Tools\n\nYou have access to the following functions:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"get_weather\", \"description\": \"Get the weather\", \"parameters\": {\"type\": \"object\", \"properties\": {\"city\": {\"type\": \"string\"}}, \"required\": [\"city\"]}}}\n</tools>\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT><|im_end|>\n<|im_start|>user\nWeather in Oslo?<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n<tool_call>\n<function=get_weather>\n<parameter=city>\nOslo\n</parameter>\n</function>\n</tool_call><|im_end|>\n<|im_start|>user\n<tool_response>\n{\"temp\": 3}\n</tool_response><|im_end|>\n<|im_start|>user\nAnd in Bergen?<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "empty user",
  "messages": [
   {
    "role": "user",
    "content": ""
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\n<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\n<|im_end|>\n<|im_start|>assistant\n<think>\n"
 },
 {
  "name": "whitespace and newlines",
  "messages": [
   {
    "role": "user",
    "content": "  line1\n  line2\n\n\nend  "
   }
  ],
  "rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nline1\n  line2\n\n\nend<|im_end|>\n<|im_start|>assistant\n<think>\n",
  "error": null,
  "hf": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nline1\n  line2\n\n\nend<|im_end|>\n<|im_start|>assistant\n<think>\n"
 }
]