openapi: 3.0.0
info:
  title: Streaming Chat Completion API with Multimedia Support
  version: 1.0.0
  description: API for streaming chat completions with support for text, image, and audio content

paths:
  /chat/completions:
    post:
      summary: Create a streaming chat completion
      description: Streams a chat completion response
      operationId: createChatCompletion
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/ChatCompletionRequest"
      responses:
        "200":
          description: Successful response
          content:
            application/json:
              schema:
                oneOf:
                  - $ref: "#/components/schemas/ChatCompletionResponse"
                  - $ref: "#/components/schemas/ChatCompletionChunk"
      x-stream: true

components:
  schemas:
    ChatCompletionRequest:
      type: object
      required:
        - messages
      properties:
        context:
          type: object
        model:
          type: string
          example: "gpt-4o"
        messages:
          type: array
          items:
            oneOf:
              - $ref: "#/components/schemas/SystemMessage"
              - $ref: "#/components/schemas/UserMessage"
              - $ref: "#/components/schemas/AssistantMessage"
              - $ref: "#/components/schemas/ToolMessage"
        response_format:
          $ref: "#/components/schemas/ResponseFormat"
        modalities:
          type: array
          items:
            type: string
            enum: [text, audio]
          default: [text]
        audio:
          type: object
          properties:
            voice:
              type: string
        tools:
          type: array
          items:
            $ref: "#/components/schemas/Tool"
        tool_choice:
          oneOf:
            - type: string
              enum: [auto, none, required]
            - type: object
              properties:
                type:
                  type: string
                  enum: [function]
                function:
                  type: object
        parallel_tool_calls:
          type: boolean
          default: true
        stream:
          type: boolean
          default: true
        ssml_enabled:
          type: boolean
          default: false

    SystemMessage:
      type: object
      required:
        - role
        - content
      properties:
        name:
          type: string
        role:
          type: string
          enum: [system]
        content:
          oneOf:
            - type: string
            - type: array
              items:
                type: string

    UserMessage:
      type: object
      required:
        - role
        - content
      properties:
        name:
          type: string
        role:
          type: string
          enum: [user]
        content:
          oneOf:
            - type: string
            - type: array
              items:
                oneOf:
                  - $ref: "#/components/schemas/TextContent"
                  - $ref: "#/components/schemas/ImageContent"
                  - $ref: "#/components/schemas/AudioContent"

    AssistantMessage:
      type: object
      required:
        - role
        - content
      properties:
        name:
          type: string
        role:
          type: string
          enum: [system]
        audio:
          type: object
          properties:
            id:
              type: string
        content:
          oneOf:
            - type: string
            - type: array
              items:
                $ref: "#/components/schemas/TextContent"
        tool_calls:
          type: object
          properties:
            id:
              type: string
            type:
              type: string
              enum: [function]
            function:
              type: object
              properties:
                name:
                  type: string
                arguments:
                  type: string

    ToolMessage:
      type: object
      required:
        - role
        - content
        - tool_call_id
      properties:
        role:
          type: string
          enum: [tool]
        content:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        tool_call_id:
          type: string

    TextContent:
      type: object
      required:
        - type
        - text
      properties:
        type:
          type: string
          enum: [text]
        text:
          type: string

    ImageContent:
      type: object
      required:
        - type
        - image_url
      properties:
        type:
          type: string
          enum: [image_url]
        image_url:
          type: string
          format: uri

    AudioContent:
      type: object
      required:
        - type
        - input_audio
      properties:
        type:
          type: string
          enum: [input_audio]
        input_audio:
          type: object
          properties:
            data:
              type: string
            format:
              type: string

    Tool:
      type: object
      properties:
        type:
          type: string
          enum: [function]
        function:
          type: object
          required:
            - name
          properties:
            name:
              type: string
            description:
              type: string
            parameters:
              type: object
            strict:
              type: boolean
              default: false

    ResponseFormat:
      type: object
      properties:
        type:
          type: string
          enum: [json_schema]
        json_schema:
          type: object
          properties:
            name:
              type: string
            schema:
              type: object

    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
        created:
          type: integer
        model:
          type: string
        usage:
          $ref: "#/components/schemas/Usage"
        choices:
          type: array
          items:
            $ref: "#/components/schemas/Choice"

    ChatCompletionChunk:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
        created:
          type: integer
        model:
          type: string
        usage:
          $ref: "#/components/schemas/Usage"
        choices:
          type: array
          items:
            $ref: "#/components/schemas/DeltaChoice"

    Usage:
      type: object
      properties:
        completion_tokens:
          type: integer
        prompt_tokens:
          type: integer
        total_tokens:
          type: integer
        completion_tokens_details:
          type: object
          properties:
            accepted_prediction_tokens:
              type: integer
            audio_tokens:
              type: integer
            reasoning_tokens:
              type: integer
            rejected_prediction_tokens:
              type: integer
        prompt_tokens_details:
          type: object
          properties:
            audio_tokens:
              type: integer
            cached_tokens:
              type: integer

    Choice:
      type: object
      properties:
        message:
          $ref: "#/components/schemas/ResponseMessage"
        index:
          type: integer
        finish_reason:
          type: string

    DeltaChoice:
      type: object
      properties:
        delta:
          $ref: "#/components/schemas/ResponseMessage"
        index:
          type: integer
        finish_reason:
          type: string

    Delta:
      type: object
      properties:
        content:
          type: string

    ResponseMessage:
      type: object
      properties:
        content:
          type: string
        refusal:
          type: string
        tool_calls:
          $ref: "#/components/schemas/ToolCall"
        role:
          type: string
        audio:
          $ref: "#/components/schemas/Audio"

    ToolCall:
      type: object
      properties:
        id:
          type: string
        type:
          type: string
          enum: [function]
        function:
          type: object
          properties:
            name:
              type: string
            arguments:
              type: string

    Audio:
      type: object
      properties:
        id:
          type: string
        expires_at:
          type: integer
        data:
          type: string
        transcript:
          type: string