feat: add reasoning and reasoning_content fields to OpenAI message types

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

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: https://github.com/vllm-project/vllm/issues/12468

Signed-off-by: Charlie Doern <cdoern@redhat.com>

client-sdks/stainless/openapi.yml

@@ -4151,6 +4151,16 @@ components:
             type: array
           - type: 'null'
           nullable: true
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIAssistantMessageParam
       type: object
     OpenAIChatCompletionContentPartImageParam:
@@ -4880,6 +4890,11 @@ components:
           - type: string
           - type: 'null'
           nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIChoiceDelta
       type: object
     OpenAIChunkChoice:
@@ -11747,6 +11762,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
@@ -11776,6 +11799,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.

docs/static/deprecated-llama-stack-spec.yaml

@@ -994,6 +994,16 @@ components:
             type: array
           - type: 'null'
           nullable: true
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIAssistantMessageParam
       type: object
     OpenAIChatCompletionContentPartImageParam:
@@ -1723,6 +1733,11 @@ components:
           - type: string
           - type: 'null'
           nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIChoiceDelta
       type: object
     OpenAIChunkChoice:
@@ -8590,6 +8605,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
@@ -8619,6 +8642,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.

docs/static/experimental-llama-stack-spec.yaml

@@ -859,6 +859,16 @@ components:
             type: array
           - type: 'null'
           nullable: true
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIAssistantMessageParam
       type: object
     OpenAIChatCompletionContentPartImageParam:
@@ -1588,6 +1598,11 @@ components:
           - type: string
           - type: 'null'
           nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIChoiceDelta
       type: object
     OpenAIChunkChoice:
@@ -7582,6 +7597,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
@@ -7611,6 +7634,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.

docs/static/llama-stack-spec.yaml

@@ -3172,6 +3172,16 @@ components:
             type: array
           - type: 'null'
           nullable: true
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIAssistantMessageParam
       type: object
     OpenAIChatCompletionContentPartImageParam:
@@ -3901,6 +3911,11 @@ components:
           - type: string
           - type: 'null'
           nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIChoiceDelta
       type: object
     OpenAIChunkChoice:
@@ -10417,6 +10432,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
@@ -10446,6 +10469,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.

docs/static/stainless-llama-stack-spec.yaml

@@ -4151,6 +4151,16 @@ components:
             type: array
           - type: 'null'
           nullable: true
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIAssistantMessageParam
       type: object
     OpenAIChatCompletionContentPartImageParam:
@@ -4880,6 +4890,11 @@ components:
           - type: string
           - type: 'null'
           nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
       title: OpenAIChoiceDelta
       type: object
     OpenAIChunkChoice:
@@ -11747,6 +11762,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.
@@ -11776,6 +11799,14 @@ components:
               $ref: '#/components/schemas/OpenAIChatCompletionToolCall'
             type: array
           - type: 'null'
+        reasoning_content:
+          anyOf:
+          - type: string
+          - type: 'null'
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
       type: object
       title: OpenAIAssistantMessageParam
       description: A message containing the model's (assistant) response in an OpenAI-compatible chat completion request.

src/llama_stack_api/inference.py

@@ -448,12 +448,16 @@ class OpenAIAssistantMessageParam(BaseModel):
     :param content: The content of the model's response
     :param name: (Optional) The name of the assistant message participant.
     :param tool_calls: List of tool calls. Each tool call is an OpenAIChatCompletionToolCall object.
+    :param reasoning_content: (Optional) The reasoning content from the model (for vLLM ≤ v0.8.4)
+    :param reasoning: (Optional) The reasoning content from the model (for vLLM ≥ v0.9.x)
     """
 
     role: Literal["assistant"] = "assistant"
     content: OpenAIChatCompletionTextOnlyMessageContent | None = None
     name: str | None = None
     tool_calls: list[OpenAIChatCompletionToolCall] | None = None
+    reasoning_content: str | None = None
+    reasoning: str | None = None
 
 
 @json_schema_type
@@ -605,7 +609,8 @@ class OpenAIChoiceDelta(BaseModel):
     :param refusal: (Optional) The refusal of the delta
     :param role: (Optional) The role of the delta
     :param tool_calls: (Optional) The tool calls of the delta
-    :param reasoning_content: (Optional) The reasoning content from the model (non-standard, for o1/o3 models)
+    :param reasoning_content: (Optional) The reasoning content from the model (for vLLM ≤ v0.8.4)
+    :param reasoning: (Optional) The reasoning content from the model (for vLLM ≥ v0.9.x)
     """
 
     content: str | None = None
@@ -613,6 +618,7 @@ class OpenAIChoiceDelta(BaseModel):
     role: str | None = None
     tool_calls: list[OpenAIChatCompletionToolCall] | None = None
     reasoning_content: str | None = None
+    reasoning: str | None = None
 
 
 @json_schema_type