Supervised fine-tuning adds separate thinking traces and multi-turn GPT OSS support

We now support supervised fine tuning with separate thinking traces for reasoning models (e.g. DeepSeek R1, GPT OSS, Qwen3 Thinking etc) that ensures training-inference consistency. An example including thinking traces would look like:

  {
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}, 
      {"role": "assistant", "content": "Paris.", "reasoning_content": "The user is asking about the capital city of France, it should be Paris."}
    ]
  }
  {
    "messages": [
      {"role": "user", "content": "What is 1+1?"},
      {"role": "assistant", "content": "2", "weight": 0, "reasoning_content": "The user is asking about the result of 1+1, the answer is 2."},
      {"role": "user", "content": "Now what is 2+2?"},
      {"role": "assistant", "content": "4", "reasoning_content": "The user is asking about the result of 2+2, the answer should be 4."}
    ]
  }

We are also properly supporting multi-turn fine tuning (with or without thinking traces) for GPT OSS model family that ensures training-inference consistency.