QuantCDN API — AI Inference

naftiko: 1.0.0-alpha2
info:
  label: QuantCDN API — AI Inference
  description: 'QuantCDN API — AI Inference. 6 operations. Lead operation: Chat inference via API Gateway (buffered responses)
    with multimodal support. Self-contained Naftiko capability covering one Quantcdn business surface.'
  tags:
  - Quantcdn
  - AI Inference
  created: '2026-05-19'
  modified: '2026-05-19'
binds:
- namespace: env
  keys:
    QUANTCDN_API_KEY: QUANTCDN_API_KEY
capability:
  consumes:
  - type: http
    namespace: quantcdn-ai-inference
    baseUri: https://dashboard.quantcdn.io
    description: QuantCDN API — AI Inference business capability. Self-contained, no shared references.
    resources:
    - name: api-v3-organizations-organisation-ai-chat
      path: /api/v3/organizations/{organisation}/ai/chat
      operations:
      - name: chatinference
        method: POST
        description: Chat inference via API Gateway (buffered responses) with multimodal support
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: api-v3-organizations-organisation-ai-chat-callback
      path: /api/v3/organizations/{organisation}/ai/chat/callback
      operations:
      - name: submittoolcallback
        method: POST
        description: Submit Client Tool Results (Callback)
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: api-v3-organizations-organisation-ai-chat-executions-identifier
      path: /api/v3/organizations/{organisation}/ai/chat/executions/{identifier}
      operations:
      - name: getdurableexecutionstatus
        method: GET
        description: Get Durable Execution Status
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: identifier
          in: path
          type: string
          description: Either the requestId from async response, or full executionArn (URL-encoded)
          required: true
    - name: api-v3-organizations-organisation-ai-chat-stream
      path: /api/v3/organizations/{organisation}/ai/chat/stream
      operations:
      - name: chatinferencestream
        method: POST
        description: Chat inference via streaming endpoint (true HTTP streaming) with multimodal support
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: api-v3-organizations-organisation-ai-embeddings
      path: /api/v3/organizations/{organisation}/ai/embeddings
      operations:
      - name: embeddings
        method: POST
        description: Generate text embeddings for semantic search and RAG applications
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    - name: api-v3-organizations-organisation-ai-image-generation
      path: /api/v3/organizations/{organisation}/ai/image-generation
      operations:
      - name: imagegeneration
        method: POST
        description: Generate images with Amazon Nova Canvas
        outputRawFormat: json
        outputParameters:
        - name: result
          type: object
          value: $.
        inputParameters:
        - name: organisation
          in: path
          type: string
          description: The organisation ID
          required: true
        - name: body
          in: body
          type: object
          description: Request body (JSON).
          required: true
    authentication:
      type: bearer
      token: '{{env.QUANTCDN_API_KEY}}'
  exposes:
  - type: rest
    namespace: quantcdn-ai-inference-rest
    port: 8080
    description: REST adapter for QuantCDN API — AI Inference. One Spectral-compliant resource per consumed operation, prefixed
      with /v1.
    resources:
    - path: /v1/api/v3/organizations/{organisation}/ai/chat
      name: api-v3-organizations-organisation-ai-chat
      description: REST surface for api-v3-organizations-organisation-ai-chat.
      operations:
      - method: POST
        name: chatinference
        description: Chat inference via API Gateway (buffered responses) with multimodal support
        call: quantcdn-ai-inference.chatinference
        with:
          organisation: rest.organisation
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/api/v3/organizations/{organisation}/ai/chat/callback
      name: api-v3-organizations-organisation-ai-chat-callback
      description: REST surface for api-v3-organizations-organisation-ai-chat-callback.
      operations:
      - method: POST
        name: submittoolcallback
        description: Submit Client Tool Results (Callback)
        call: quantcdn-ai-inference.submittoolcallback
        with:
          organisation: rest.organisation
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/api/v3/organizations/{organisation}/ai/chat/executions/{identifier}
      name: api-v3-organizations-organisation-ai-chat-executions-identifier
      description: REST surface for api-v3-organizations-organisation-ai-chat-executions-identifier.
      operations:
      - method: GET
        name: getdurableexecutionstatus
        description: Get Durable Execution Status
        call: quantcdn-ai-inference.getdurableexecutionstatus
        with:
          organisation: rest.organisation
          identifier: rest.identifier
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/api/v3/organizations/{organisation}/ai/chat/stream
      name: api-v3-organizations-organisation-ai-chat-stream
      description: REST surface for api-v3-organizations-organisation-ai-chat-stream.
      operations:
      - method: POST
        name: chatinferencestream
        description: Chat inference via streaming endpoint (true HTTP streaming) with multimodal support
        call: quantcdn-ai-inference.chatinferencestream
        with:
          organisation: rest.organisation
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/api/v3/organizations/{organisation}/ai/embeddings
      name: api-v3-organizations-organisation-ai-embeddings
      description: REST surface for api-v3-organizations-organisation-ai-embeddings.
      operations:
      - method: POST
        name: embeddings
        description: Generate text embeddings for semantic search and RAG applications
        call: quantcdn-ai-inference.embeddings
        with:
          organisation: rest.organisation
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
    - path: /v1/api/v3/organizations/{organisation}/ai/image-generation
      name: api-v3-organizations-organisation-ai-image-generation
      description: REST surface for api-v3-organizations-organisation-ai-image-generation.
      operations:
      - method: POST
        name: imagegeneration
        description: Generate images with Amazon Nova Canvas
        call: quantcdn-ai-inference.imagegeneration
        with:
          organisation: rest.organisation
          body: rest.body
        outputParameters:
        - type: object
          mapping: $.
  - type: mcp
    namespace: quantcdn-ai-inference-mcp
    port: 9090
    transport: http
    description: MCP adapter for QuantCDN API — AI Inference. One tool per consumed operation, routed inline through this
      capability's consumes block.
    tools:
    - name: chat-inference-api-gateway-buffered
      description: Chat inference via API Gateway (buffered responses) with multimodal support
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: quantcdn-ai-inference.chatinference
      with:
        organisation: tools.organisation
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: submit-client-tool-results-callback
      description: Submit Client Tool Results (Callback)
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: quantcdn-ai-inference.submittoolcallback
      with:
        organisation: tools.organisation
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: get-durable-execution-status
      description: Get Durable Execution Status
      hints:
        readOnly: true
        destructive: false
        idempotent: true
      call: quantcdn-ai-inference.getdurableexecutionstatus
      with:
        organisation: tools.organisation
        identifier: tools.identifier
      outputParameters:
      - type: object
        mapping: $.
    - name: chat-inference-streaming-endpoint-true
      description: Chat inference via streaming endpoint (true HTTP streaming) with multimodal support
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: quantcdn-ai-inference.chatinferencestream
      with:
        organisation: tools.organisation
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: generate-text-embeddings-semantic-search
      description: Generate text embeddings for semantic search and RAG applications
      hints:
        readOnly: true
        destructive: false
        idempotent: false
      call: quantcdn-ai-inference.embeddings
      with:
        organisation: tools.organisation
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.
    - name: generate-images-amazon-nova-canvas
      description: Generate images with Amazon Nova Canvas
      hints:
        readOnly: false
        destructive: false
        idempotent: false
      call: quantcdn-ai-inference.imagegeneration
      with:
        organisation: tools.organisation
        body: tools.body
      outputParameters:
      - type: object
        mapping: $.