feat: add reasoning and reasoning_content fields to OpenAI message types

[cdoern]

What does this PR do?

Add support for reasoning fields in OpenAI-compatible chat completion
messages to enable compatibility with vLLM reasoning parsers.

Changes:

• Add reasoning_content and reasoning fields to OpenAIAssistantMessageParam
• Add reasoning field to OpenAIChoiceDelta (reasoning_content already existed)

Both field names are supported for maximum compatibility:

• reasoning_content: Used by vLLM ≤ v0.8.4
• reasoning: New field name in vLLM ≥ v0.9.x
  (based on release notes)

vLLM documentation recommends migrating to the shorter reasoning field
name, but maintains backward compatibility with reasoning_content.

These fields allow reasoning models to return their chain-of-thought
process alongside the final answer, which is crucial for transparency
and debugging with reasoning models.

References:

• vLLM Reasoning Outputs: https://docs.vllm.ai/en/stable/features/reasoning_outputs/
• vLLM Issue #12468: [Feature] reasoning_content in API for reasoning models like DeepSeek R1 vllm-project/vllm#12468

Test Plan

vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B \
    --reasoning-parser deepseek_r1
  

llama stack run starter

curl http://localhost:8321/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
      "model": "vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
      "messages": [
        {"role": "user", "content": "What is 25 * 4?"}
      ]
    }'

{"id":"chatcmpl-9df9d2a5f849bbe0","choices":[{"finish_reason":"stop","index":0,"logprobs":null,"message":{"content":"\n\nTo calculate \\(25 \\times 4\\), follow these easy steps:\n\n1. **Understand the Multiplication:**\n   \n   \\(25 \\times 4\\) means you are adding the number 25 four times.\n   \n   \\[\n   25 + 25 + 25 + 25 = 100\n   \\]\n\n2. **Break Down the Multiplication:**\n   \n   - Multiply 25 by 2:\n     \\[\n     25 \\times 2 = 50\n     \\]\n   - Then multiply the result by 2:\n     \\[\n     50 \\times 2 = 100\n     \\]\n\n3. **Final Answer:**\n   \n   \\[\n   \\boxed{100}\n   \\]","refusal":null,"role":"assistant","annotations":null,"audio":null,"function_call":null,"tool_calls":null,"reasoning":"To solve 25 multiplied by 4, I start by recognizing that 25 is a quarter of 100. Multiplying 25 by 4 is the same as finding a quarter of 100 multiplied by 4, which equals 100.\n\nNext, I can consider that 25 multiplied by 4 is also equal to 25 multiplied by 2, which is 50, and then multiplied by 2 again, resulting in 100.\n\nAlternatively, I can use the distributive property by breaking down 4 into 3 and 1, so 25 multiplied by 3 is 75, and 25 multiplied by 1 is 25. Adding these together gives 100.\n\nBoth methods lead to the same result, confirming that 25 multiplied by 4 equals 100.\n","reasoning_content":"To solve 25 multiplied by 4, I start by recognizing that 25 is a quarter of 100. Multiplying 25 by 4 is the same as finding a quarter of 100 multiplied by 4, which equals 100.\n\nNext, I can consider that 25 multiplied by 4 is also equal to 25 multiplied by 2, which is 50, and then multiplied by 2 again, resulting in 100.\n\nAlternatively, I can use the distributive property by breaking down 4 into 3 and 1, so 25 multiplied by 3 is 75, and 25 multiplied by 1 is 25. Adding these together gives 100.\n\nBoth methods lead to the same result, confirming that 25 multiplied by 4 equals 100.\n"},"stop_reason":null,"token_ids":null}],"created":1764187386,"model":"vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","object":"chat.completion","service_tier":null,"system_fingerprint":null,"usage":{"completion_tokens":356,"prompt_tokens":14,"total_tokens":370,"completion_tokens_details":null,"prompt_tokens_details":null},"prompt_logprobs":null,"prompt_token_ids":null,"kv_transfer_params":null,"metrics":[{"trace_id":"9ed1630440cb1e923916455d98663df3","span_id":"a27b4cb4208ed39f","timestamp":"2025-11-26T20:03:19.089063Z","attributes":{"model_id":"vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","provider_id":"vllm"},"type":"metric","metric":"prompt_tokens","value":14,"unit":"tokens"},{"trace_id":"9ed1630440cb1e923916455d98663df3","span_id":"a27b4cb4208ed39f","timestamp":"2025-11-26T20:03:19.089072Z","attributes":{"model_id":"vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","provider_id":"vllm"},"type":"metric","metric":"completion_tokens","value":356,"unit":"tokens"},{"trace_id":"9ed1630440cb1e923916455d98663df3","span_id":"a27b4cb4208ed39f","timestamp":"2025-11-26T20:03:19.089075Z","attributes":{"model_id":"vllm/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","provider_id":"vllm"},"type":"metric","metric":"total_tokens","value":370,"unit":"tokens"}]}%

[cdoern]

this one can wait until CI is back, want to make sure this doesnt break engines which don't support the field.