Merge b99eb2a1d2 into 4237eb4aaa

2025-12-03 01:48:05 +00:00 · 2025-12-03 01:04:16 +00:00 · 2025-12-03 01:04:16 +00:00 · f2e5b8d7b4
commit f2e5b8d7b4
parent 4237eb4aaa b99eb2a1d2
6 changed files with 188 additions and 1 deletions
--- a/client-sdks/stainless/openapi.yml
+++ b/client-sdks/stainless/openapi.yml
@ -4157,6 +4157,16 @@ 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:
@ -4224,6 +4234,11 @@ components:
            title: OpenAIChatCompletionToolCallFunction
          - type: 'null'
          title: OpenAIChatCompletionToolCallFunction
+        extra_content:
+          anyOf:
+          - additionalProperties: true
+            type: object
+          - type: 'null'
      type: object
      title: OpenAIChatCompletionToolCall
      description: Tool call specification for OpenAI-compatible chat completion responses.
@ -4886,6 +4901,11 @@ components:
          - type: string
          - type: 'null'
          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
      title: OpenAIChoiceDelta
      type: object
    OpenAIChunkChoice:
@ -11753,6 +11773,14 @@ 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.
@ -11782,6 +11810,14 @@ 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.
--- a/docs/static/deprecated-llama-stack-spec.yaml
+++ b/docs/static/deprecated-llama-stack-spec.yaml
@ -1151,6 +1151,16 @@ 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:
@ -1218,6 +1228,11 @@ components:
            title: OpenAIChatCompletionToolCallFunction
          - type: 'null'
          title: OpenAIChatCompletionToolCallFunction
+        extra_content:
+          anyOf:
+          - additionalProperties: true
+            type: object
+          - type: 'null'
      type: object
      title: OpenAIChatCompletionToolCall
      description: Tool call specification for OpenAI-compatible chat completion responses.
@ -1880,6 +1895,11 @@ components:
          - type: string
          - type: 'null'
          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
      title: OpenAIChoiceDelta
      type: object
    OpenAIChunkChoice:
@ -8747,6 +8767,14 @@ 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.
@ -8776,6 +8804,14 @@ 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.
--- a/docs/static/experimental-llama-stack-spec.yaml
+++ b/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:
@ -926,6 +936,11 @@ components:
            title: OpenAIChatCompletionToolCallFunction
          - type: 'null'
          title: OpenAIChatCompletionToolCallFunction
+        extra_content:
+          anyOf:
+          - additionalProperties: true
+            type: object
+          - type: 'null'
      type: object
      title: OpenAIChatCompletionToolCall
      description: Tool call specification for OpenAI-compatible chat completion responses.
@ -1588,6 +1603,11 @@ components:
          - type: string
          - type: 'null'
          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
      title: OpenAIChoiceDelta
      type: object
    OpenAIChunkChoice:
@ -7582,6 +7602,14 @@ 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 +7639,14 @@ 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.
--- a/docs/static/llama-stack-spec.yaml
+++ b/docs/static/llama-stack-spec.yaml
@ -2962,6 +2962,16 @@ 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:
@ -3029,6 +3039,11 @@ components:
            title: OpenAIChatCompletionToolCallFunction
          - type: 'null'
          title: OpenAIChatCompletionToolCallFunction
+        extra_content:
+          anyOf:
+          - additionalProperties: true
+            type: object
+          - type: 'null'
      type: object
      title: OpenAIChatCompletionToolCall
      description: Tool call specification for OpenAI-compatible chat completion responses.
@ -3691,6 +3706,11 @@ components:
          - type: string
          - type: 'null'
          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
      title: OpenAIChoiceDelta
      type: object
    OpenAIChunkChoice:
@ -10189,6 +10209,14 @@ 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.
@ -10218,6 +10246,14 @@ 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.
--- a/docs/static/stainless-llama-stack-spec.yaml
+++ b/docs/static/stainless-llama-stack-spec.yaml
@ -4157,6 +4157,16 @@ 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:
@ -4224,6 +4234,11 @@ components:
            title: OpenAIChatCompletionToolCallFunction
          - type: 'null'
          title: OpenAIChatCompletionToolCallFunction
+        extra_content:
+          anyOf:
+          - additionalProperties: true
+            type: object
+          - type: 'null'
      type: object
      title: OpenAIChatCompletionToolCall
      description: Tool call specification for OpenAI-compatible chat completion responses.
@ -4886,6 +4901,11 @@ components:
          - type: string
          - type: 'null'
          nullable: true
+        reasoning:
+          anyOf:
+          - type: string
+          - type: 'null'
+          nullable: true
      title: OpenAIChoiceDelta
      type: object
    OpenAIChunkChoice:
@ -11753,6 +11773,14 @@ 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.
@ -11782,6 +11810,14 @@ 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.
--- a/src/llama_stack_api/inference.py
+++ b/src/llama_stack_api/inference.py
@ -438,6 +438,7 @@ class OpenAIChatCompletionToolCall(BaseModel):
    id: str | None = None
    type: Literal["function"] = "function"
    function: OpenAIChatCompletionToolCallFunction | None = None
+    extra_content: dict[str, Any] | None = None


@json_schema_type
@ -448,12 +449,16 @@ 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 +610,8 @@ 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 +619,7 @@ 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