# Annotated review companion for justinchuby/onnx-genai-stable-diffusion-bk-sdm-small.
# Model form: Stable Diffusion image generation.
# Canonical authority: inference_metadata.yaml at revision 2d30ae2ebfacf5c071693836d70ebd14d8fd84d3.
# Comments explain authored semantics, derived structure, and fail-closed omissions.
# After YAML parsing this file is mechanically equal to the canonical metadata; comments do not create a second contract.
# Backend implementation, recorded execution, and performance evidence remain separate from this portable metadata.
# Schema spelling `v1` normalizes under the current reader; versioning gates unknown fields before typed parsing. No component authors batch_capacity, so independent requests must execute per item at every component.
schema_version: v1
# The pipeline contains executable package semantics. Deployment/QoS policy and backend-derived execution plans live outside this portable contract.
pipeline:
  # This typed SSA workflow is the authoritative execution contract for the package.
  workflow:
    # Manifest vocabulary declares interpreter/adapter ABI requirements. It is not ORT/native readiness or performance evidence.
    manifest:
      # Current v1 capability strings mirror typed workflow structure; the structure remains the semantic source of truth.
      capabilities:
      - workflow_ssa
      - linear_effects
      - nested_control_flow
      - loop_induction_values
      - typed_emit
    # Workflow inputs are the complete typed boundary. Roles and sources are authored; absent required values must fail before execution.
    inputs:
      # Input `request.max_iterations` is optional; omission uses semantic default 10, provided by the request through a typed runtime role, and carries runtime role max_iterations@1.0. Unsupported required roles must fail closed.
      request.max_iterations:
        # Authored tensor ABI: dtype int64, rank 1, shape [1]. No grouping permission is implied by this shape.
        contract:
          dtype: int64
          rank: 1
          shape:
          - 1
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: runtime
          version: '1.0'
          role: max_iterations
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: request
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: 10
      # Input `package.false` is optional; omission uses semantic default False, a package-authored literal/default, and carries opaque. Unsupported required roles must fail closed.
      package.false:
        # Authored tensor ABI: dtype bool, rank 1, shape [component.unet.batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: bool
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: opaque
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: literal
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: false
      # Input `request.seed` is optional; omission uses semantic default 0, provided by the request through a typed runtime role, and carries runtime role seed@1.0. Unsupported required roles must fail closed.
      request.seed:
        # Authored tensor ABI: dtype int64, rank 1, shape [component.unet.batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: int64
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: runtime
          version: '1.0'
          role: seed
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: request
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: 0
        # The caller may supply this exact tensor instead of asking the workflow to derive it.
        externally_suppliable: true
      # Input `package.rng_offset` is optional; omission uses semantic default 0, a package-authored literal/default, and carries opaque. Unsupported required roles must fail closed.
      package.rng_offset:
        # Authored tensor ABI: dtype int64, rank 1, shape [component.unet.batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: int64
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: opaque
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: literal
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: 0
      # Input `request.input_ids` is required, provided by the request through a typed runtime role, and carries runtime role prompt_tokens@1.0. Unsupported required roles must fail closed.
      request.input_ids:
        # Authored tensor ABI: dtype int64, rank 2, shape [component.text_encoder.batch, component.text_encoder.sequence_len]. No grouping permission is implied by this shape.
        contract:
          dtype: int64
          rank: 2
          shape:
          - component.text_encoder.batch
          - component.text_encoder.sequence_len
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: runtime
          version: '1.0'
          role: prompt_tokens
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: request
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: true
        # The caller may supply this exact tensor instead of asking the workflow to derive it.
        externally_suppliable: true
      # Input `request.negative_input_ids` is required, provided by the request through a typed runtime role, and carries runtime role negative_prompt_tokens@1.0. Unsupported required roles must fail closed.
      request.negative_input_ids:
        # Authored tensor ABI: dtype int64, rank 2, shape [component.text_encoder.batch, component.text_encoder.sequence_len]. No grouping permission is implied by this shape.
        contract:
          dtype: int64
          rank: 2
          shape:
          - component.text_encoder.batch
          - component.text_encoder.sequence_len
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: runtime
          version: '1.0'
          role: negative_prompt_tokens
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: request
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: true
        # The caller may supply this exact tensor instead of asking the workflow to derive it.
        externally_suppliable: true
      # Input `request.guidance_scale` is optional; omission uses semantic default 7.5, provided by the request through a typed runtime role, and carries runtime role guidance_scale@1.0. Unsupported required roles must fail closed.
      request.guidance_scale:
        # Authored tensor ABI: dtype float32, rank 1, shape [component.unet.batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: runtime
          version: '1.0'
          role: guidance_scale
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: request
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: 7.5
      # Input `package.loop_0_active` is optional; omission uses semantic default True, a package-authored literal/default, and carries opaque. Unsupported required roles must fail closed.
      package.loop_0_active:
        # Authored tensor ABI: dtype bool, rank 1, shape [1]. No grouping permission is implied by this shape.
        contract:
          dtype: bool
          rank: 1
          shape:
          - 1
        # Role identifies runtime semantics without relying on a model-family name.
        role:
          kind: opaque
        # Source states who must provide this value; the runtime must not invent application data.
        source:
          kind: literal
        # Required values fail closed when absent; optional values may use only their authored default/presence rule.
        required: false
        # This is a semantic tensor default used only when the optional input is omitted.
        default: true
    # Workflow outputs are the complete public result boundary and retain explicit tensor contracts.
    outputs:
      # Output `image` publishes the authored image result at the pre_adapter stage; it is not backend-readiness evidence.
      image:
        # Authored tensor ABI: dtype float32, rank 4, shape [component.vae_decoder.batch, 3, component.vae_decoder.image_height, component.vae_decoder.image_width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 4
          shape:
          - component.vae_decoder.batch
          - 3
          - component.vae_decoder.image_height
          - component.vae_decoder.image_width
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        role: image
        # The numeric range is part of the output interpretation contract.
        value_range: negative_one_to_one
        # Stage records whether adapters/postprocessing have run before this value is exposed.
        stage: pre_adapter
      # Output `latent` publishes the authored tensor result at the pre_adapter stage; it is not backend-readiness evidence.
      latent:
        # Authored tensor ABI: dtype float32, rank 4, shape [component.unet.batch, 4, component.unet.height, component.unet.width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 4
          shape:
          - component.unet.batch
          - 4
          - component.unet.height
          - component.unet.width
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        role: tensor
        # Stage records whether adapters/postprocessing have run before this value is exposed.
        stage: pre_adapter
      # Output `noise_estimate` publishes the authored tensor result at the pre_adapter stage; it is not backend-readiness evidence.
      noise_estimate:
        # Authored tensor ABI: dtype float32, rank 4, shape [component.unet.batch, 4, component.unet.height, noise_estimate_width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 4
          shape:
          - component.unet.batch
          - 4
          - component.unet.height
          - noise_estimate_width
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        role: tensor
        # Stage records whether adapters/postprocessing have run before this value is exposed.
        stage: pre_adapter
      # Output `latent_trajectory` publishes the authored tensor result at the pre_adapter stage; it is not backend-readiness evidence.
      latent_trajectory:
        # Authored tensor ABI: dtype float32, rank 4, shape [component.unet.batch, 4, component.unet.height, trajectory_width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 4
          shape:
          - component.unet.batch
          - 4
          - component.unet.height
          - trajectory_width
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        role: tensor
        # Stage records whether adapters/postprocessing have run before this value is exposed.
        stage: pre_adapter
      # Output `rng_offset` publishes the authored tensor result at the pre_adapter stage; it is not backend-readiness evidence.
      rng_offset:
        # Authored tensor ABI: dtype int64, rank 1, shape [component.unet.batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: int64
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        role: tensor
        # Stage records whether adapters/postprocessing have run before this value is exposed.
        stage: pre_adapter
    # Components are the executable artifacts and semantic policy programs. Their presence does not prove ORT/native readiness or performance.
    components:
      # Component `text_encoder` is an encoder compute graph using onnx from `text_encoder/model.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      text_encoder:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: text_encoder/model.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Semantic port roles identify tokens, logits, positions, masks, caches, or media without architecture-name conditionals.
          roles:
            input_ids: token_ids
            last_hidden_state: hidden_states
      # Component `unet` is a denoising compute graph using onnx from `unet/model.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      unet:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: unet/model.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Semantic port roles identify tokens, logits, positions, masks, caches, or media without architecture-name conditionals.
          roles:
            encoder_hidden_states: encoder_hidden_states
      # Component `vae_decoder` is a primary model compute graph using onnx from `vae_decoder/model.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      vae_decoder:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: vae_decoder/model.onnx
      # Component `solver_step` is an executable semantic policy component implementing `onnx-genai.solver-step` using onnx from `policies/solver_step.onnx`. Policy graphs compute tensors and semantics; they are not deployment/QoS knobs or backend readiness claims. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      solver_step:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/solver_step.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `sample`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            sample:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `derivative`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            derivative:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `step`: Authored tensor ABI: dtype int64, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            step:
              dtype: int64
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `schedule`: Authored tensor ABI: dtype float32, rank 1, shape [schedule_length]. No grouping permission is implied by this shape.
            schedule:
              dtype: float32
              rank: 1
              shape:
              - schedule_length
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `next_state`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            next_state:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
        # Semantic component ABI `onnx-genai.solver-step`; its bindings/parameters affect output correctness.
        contract:
          id: onnx-genai.solver-step
          version: '1'
          bindings:
            state: sample
            estimate: derivative
            step: step
            schedule: schedule
            next_state: next_state
      # Component `continue_predicate` is an authored workflow compute component using onnx from `policies/continue_predicate.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      continue_predicate:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/continue_predicate.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `done`: Authored tensor ABI: dtype bool, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            done:
              dtype: bool
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `continue`: Authored tensor ABI: dtype bool, rank 1, shape [1]. No grouping permission is implied by this shape.
            continue:
              dtype: bool
              rank: 1
              shape:
              - 1
      # Component `diffusion_schedule` is a diffusion/flow solver policy graph using onnx from `policies/diffusion_schedule.onnx`. Policy graphs compute tensors and semantics; they are not deployment/QoS knobs or backend readiness claims. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      diffusion_schedule:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/diffusion_schedule.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs: {}
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `schedule`: Authored tensor ABI: dtype float32, rank 1, shape [11]. No grouping permission is implied by this shape.
            schedule:
              dtype: float32
              rank: 1
              shape:
              - 11
      # Component `diffusion_timesteps` is an authored workflow compute component using onnx from `policies/diffusion_timesteps.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      diffusion_timesteps:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/diffusion_timesteps.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs: {}
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `schedule`: Authored tensor ABI: dtype float32, rank 1, shape [10]. No grouping permission is implied by this shape.
            schedule:
              dtype: float32
              rank: 1
              shape:
              - 10
      # Component `schedule_lookup` is a diffusion/flow solver policy graph using onnx from `policies/schedule_lookup.onnx`. Policy graphs compute tensors and semantics; they are not deployment/QoS knobs or backend readiness claims. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      schedule_lookup:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/schedule_lookup.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `schedule`: Authored tensor ABI: dtype float32, rank 1, shape [schedule_length]. No grouping permission is implied by this shape.
            schedule:
              dtype: float32
              rank: 1
              shape:
              - schedule_length
            # Port `step`: Authored tensor ABI: dtype int64, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            step:
              dtype: int64
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `timestep`: Authored tensor ABI: dtype float32, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            timestep:
              dtype: float32
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
      # Component `tensor_scale` is an authored workflow compute component using onnx from `policies/tensor_scale.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      tensor_scale:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/tensor_scale.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `tensor`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            tensor:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `scale`: Authored tensor ABI: dtype float32, rank 1, shape [1]. No grouping permission is implied by this shape.
            scale:
              dtype: float32
              rank: 1
              shape:
              - 1
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `scaled`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            scaled:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
      # Component `decoder_input_scale` is a primary model compute graph using onnx from `policies/decoder_input_scale.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      decoder_input_scale:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/decoder_input_scale.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs: {}
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `value`: Authored tensor ABI: dtype float32, rank 1, shape [1]. No grouping permission is implied by this shape.
            value:
              dtype: float32
              rank: 1
              shape:
              - 1
      # Component `guidance_combine` is an executable semantic policy component implementing `onnx-genai.guidance-combine` using onnx from `policies/guidance_combine.onnx`. Policy graphs compute tensors and semantics; they are not deployment/QoS knobs or backend readiness claims. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      guidance_combine:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/guidance_combine.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `unconditional`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            unconditional:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `conditional`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            conditional:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `scale`: Authored tensor ABI: dtype float32, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            scale:
              dtype: float32
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `estimate`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            estimate:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
        # Semantic component ABI `onnx-genai.guidance-combine`; its bindings/parameters affect output correctness.
        contract:
          id: onnx-genai.guidance-combine
          version: '1'
          bindings:
            unconditional: unconditional
            conditional: conditional
            scale: scale
            estimate: estimate
      # Component `image_output_clamp` is an authored workflow compute component using onnx from `policies/image_output_clamp.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      image_output_clamp:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/image_output_clamp.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `tensor`: Authored tensor ABI: dtype float32, rank 4, shape [batch, axis_1, axis_2, axis_3]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            tensor:
              dtype: float32
              rank: 4
              shape:
              - batch
              - axis_1
              - axis_2
              - axis_3
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `clamped`: Authored tensor ABI: dtype float32, rank 4, shape [batch, axis_1, axis_2, axis_3]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            clamped:
              dtype: float32
              rank: 4
              shape:
              - batch
              - axis_1
              - axis_2
              - axis_3
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
      # Component `conditioning_cast` is an authored workflow compute component using onnx from `policies/conditioning_cast.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      conditioning_cast:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/conditioning_cast.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `tensor`: Authored tensor ABI: dtype float16, rank 3, shape [batch, axis_1, axis_2]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            tensor:
              dtype: float16
              rank: 3
              shape:
              - batch
              - axis_1
              - axis_2
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `cast`: Authored tensor ABI: dtype float32, rank 3, shape [batch, axis_1, axis_2]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            # This explicit cast aligns dtype at an authored boundary; the runtime must not guess a different precision.
            cast:
              dtype: float32
              rank: 3
              shape:
              - batch
              - axis_1
              - axis_2
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
      # Component `latent_row_shape` is an authored workflow compute component using onnx from `policies/latent_row_shape.onnx`. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      latent_row_shape:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/latent_row_shape.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs: {}
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `shape`: Authored tensor ABI: dtype int64, rank 1, shape [3]. No grouping permission is implied by this shape.
            shape:
              dtype: int64
              rank: 1
              shape:
              - 3
      # Component `latent_noise` is an executable semantic policy component implementing `onnx-genai.counter-rng` using onnx from `policies/latent_noise.onnx`. Policy graphs compute tensors and semantics; they are not deployment/QoS knobs or backend readiness claims. No batch_capacity is authored, so the runtime must not group independent requests at this component.
      latent_noise:
        # Selects a packaged implementation/artifact only; provider/backend readiness requires separate recorded evidence.
        implementation:
          kind: onnx
          artifact: policies/latent_noise.onnx
        # Ports bind workflow names to the artifact's exact graph ABI; model-family inference is forbidden.
        ports:
          # Exact graph inputs; each tensor shape/dtype is authored.
          inputs:
            # Port `seed`: Authored tensor ABI: dtype int64, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            seed:
              dtype: int64
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `offset`: Authored tensor ABI: dtype int64, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            offset:
              dtype: int64
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `row_shape`: Authored tensor ABI: dtype int64, rank 1, shape [row_rank]. No grouping permission is implied by this shape.
            row_shape:
              dtype: int64
              rank: 1
              shape:
              - row_rank
          # Exact graph outputs; each tensor shape/dtype is authored.
          outputs:
            # Port `noise`: Authored tensor ABI: dtype float32, rank 4, shape [batch, channels, height, width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            noise:
              dtype: float32
              rank: 4
              shape:
              - batch
              - channels
              - height
              - width
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
            # Port `next_offset`: Authored tensor ABI: dtype int64, rank 1, shape [batch]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
            next_offset:
              dtype: int64
              rank: 1
              shape:
              - batch
              # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
              batch_layout:
                kind: request_aligned
                axis: 0
        # Semantic component ABI `onnx-genai.counter-rng`; its bindings/parameters affect output correctness.
        contract:
          id: onnx-genai.counter-rng
          version: '1'
          bindings:
            seed: seed
            offset: offset
            row_shape: row_shape
            noise: noise
            next_offset: next_offset
    # State cells make recurrence, cache mutation, lifetime, and ownership explicit. Physical paging/tiering/placement are not encoded by tensor names.
    state:
      # State `latent_state` is semantic tensor carry between workflow steps. Scope=invocation, recurrence=invariant. The authored recurrence determines how it evolves.
      latent_state:
        # Authored tensor ABI: dtype float32, rank 4, shape [component.unet.batch, 4, component.unet.height, component.unet.width]. Request rows stay aligned on axis 0; this preserves identity but does not by itself authorize grouping independent requests.
        contract:
          dtype: float32
          rank: 4
          shape:
          - component.unet.batch
          - 4
          - component.unet.height
          - component.unet.width
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
        # `invocation` defines the semantic lifetime boundary; it is not a worker-placement policy.
        scope: invocation
        # Initializer names the exact first SSA value for this state cell.
        initializer: diffusion.noise
        # Recurrence defines the next-value rule: {kind=invariant}.
        recurrence:
          kind: invariant
      # State `loop_0_active` is loop/scheduler control state. Scope=invocation, recurrence=invariant. The values affect correctness, not merely performance.
      loop_0_active:
        # Authored tensor ABI: dtype bool, rank 1, shape [1]. No grouping permission is implied by this shape.
        contract:
          dtype: bool
          rank: 1
          shape:
          - 1
        # `invocation` defines the semantic lifetime boundary; it is not a worker-placement policy.
        scope: invocation
        # Initializer names the exact first SSA value for this state cell.
        initializer: package.loop_0_active
        # Recurrence defines the next-value rule: {kind=invariant}.
        recurrence:
          kind: invariant
    # The ordered SSA program defines actual execution and dataflow; capability strings are not a substitute for these steps.
    steps:
      # Run a bounded semantic loop (request.max_iterations); carried state and termination values make progress explicit and fail closed if unsupported.
    - kind: loop
      setup:
        # Invoke component `diffusion_schedule` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: diffusion_schedule
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs: {}
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          schedule: diffusion.schedule
        # Invoke component `diffusion_timesteps` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: diffusion_timesteps
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs: {}
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          schedule: diffusion.timesteps
        # Invoke component `decoder_input_scale` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: decoder_input_scale
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs: {}
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          value: diffusion.decoder_scale
        # Invoke component `latent_row_shape` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: latent_row_shape
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs: {}
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          shape: diffusion.latent_row_shape
        # Invoke component `latent_noise` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: latent_noise
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          seed: request.seed
          offset: package.rng_offset
          row_shape: diffusion.latent_row_shape
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          noise: diffusion.noise
          next_offset: diffusion.rng_offset
        # Invoke component `text_encoder` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: text_encoder
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          input_ids: request.input_ids
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          last_hidden_state: conditioning.hidden_states_raw
        # Invoke component `conditioning_cast` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: conditioning_cast
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          tensor: conditioning.hidden_states_raw
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          # This explicit cast aligns dtype at an authored boundary; the runtime must not guess a different precision.
          cast: conditioning.hidden_states
        # Invoke component `text_encoder` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: text_encoder
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          input_ids: request.negative_input_ids
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          last_hidden_state: conditioning.unconditional_raw
        # Invoke component `conditioning_cast` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: conditioning_cast
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          tensor: conditioning.unconditional_raw
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          # This explicit cast aligns dtype at an authored boundary; the runtime must not guess a different precision.
          cast: conditioning.unconditional
        # Invoke component `continue_predicate` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: continue_predicate
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          done: package.false
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          continue: setup.continue
      # Nested steps remain part of the typed executable workflow.
      steps:
        # Invoke component `schedule_lookup` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: schedule_lookup
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          schedule: diffusion.timesteps
          step: loop.iteration
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          timestep: diffusion.timestep
        # Invoke component `unet` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: unet
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          sample: latent_state
          timestep: diffusion.timestep
          encoder_hidden_states: conditioning.unconditional
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          noise_pred: denoiser.unconditional
        # Invoke component `unet` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: unet
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          sample: latent_state
          timestep: diffusion.timestep
          encoder_hidden_states: conditioning.hidden_states
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          noise_pred: denoiser.conditional
        # Invoke component `guidance_combine` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: guidance_combine
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          unconditional: denoiser.unconditional
          conditional: denoiser.conditional
          scale: request.guidance_scale
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          estimate: denoiser.estimate
        # Invoke component `solver_step` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: solver_step
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          sample: latent_state
          step: loop.iteration
          schedule: diffusion.schedule
          derivative: denoiser.estimate
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          next_state: latent.body
        # Publish `denoiser.estimate` as output `noise_estimate` using append semantics.
      - kind: emit
        value: denoiser.estimate
        output: noise_estimate
        # Emit/update mode is semantic replacement/append behavior, not a buffering optimization.
        mode: append
        # Publish `latent.body` as output `latent_trajectory` using append semantics.
      - kind: emit
        value: latent.body
        output: latent_trajectory
        # Emit/update mode is semantic replacement/append behavior, not a buffering optimization.
        mode: append
        # Invoke component `continue_predicate` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
      - kind: invoke
        component: continue_predicate
        # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
        inputs:
          done: package.false
        # SSA output names become the only values subsequent steps may consume.
        outputs:
          continue: loop.continue
      continue_when: loop_0_active
      max_iterations: request.max_iterations
      carried:
      - cell: latent_state
        next: latent.body
      - cell: loop_0_active
        next: loop.continue
      iteration:
        value: loop.iteration
        contract:
          dtype: int64
          rank: 1
          shape:
          - component.unet.batch
          # Tensor row layout is structural. Only component batch_capacity can authorize grouping independent requests.
          batch_layout:
            kind: request_aligned
            axis: 0
      # Invoke component `tensor_scale` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
    - kind: invoke
      component: tensor_scale
      # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
      inputs:
        tensor: latent_state
        scale: diffusion.decoder_scale
      # SSA output names become the only values subsequent steps may consume.
      outputs:
        scaled: diffusion.decoder_input
      # Invoke component `vae_decoder` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
    - kind: invoke
      component: vae_decoder
      # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
      inputs:
        latent_sample: diffusion.decoder_input
      # SSA output names become the only values subsequent steps may consume.
      outputs:
        sample: vae.raw_image
      # Invoke component `image_output_clamp` with explicit SSA input/output bindings; this is executable tensor computation, not a host-side capability flag.
    - kind: invoke
      component: image_output_clamp
      # SSA bindings supply exact values to this step; no implicit tensor discovery occurs.
      inputs:
        tensor: vae.raw_image
      # SSA output names become the only values subsequent steps may consume.
      outputs:
        clamped: vae.image
      # Publish `latent_state` as output `latent` using replace semantics.
    - kind: emit
      value: latent_state
      output: latent
      # Emit/update mode is semantic replacement/append behavior, not a buffering optimization.
      mode: replace
      # Publish `vae.image` as output `image` using replace semantics.
    - kind: emit
      value: vae.image
      output: image
      # Emit/update mode is semantic replacement/append behavior, not a buffering optimization.
      mode: replace
      # Publish `diffusion.rng_offset` as output `rng_offset` using replace semantics.
    - kind: emit
      value: diffusion.rng_offset
      output: rng_offset
      # Emit/update mode is semantic replacement/append behavior, not a buffering optimization.
      mode: replace