Struct InferenceResponse 

pub struct InferenceResponse {
    pub request_id: String,
    pub response_id: String,
    pub model_id: String,
    pub provider: Address,
    pub output: Vec<u8>,
    pub metadata: InferenceMetadata,
    pub price: u64,
    pub timestamp: Timestamp,
    pub synthetic_content: bool,
    pub provenance: Option<ProvenanceManifest>,
}

Response from model inference

EU AI Act Article 50 (effective 2026-08-02) requires generative-AI outputs to carry both (a) a machine-readable disclosure that the content is AI-generated and (b) a verifiable provenance manifest. Both fields here are always populated by tenzro-model::routing for real inferences: synthetic_content is unconditionally true (every inference response is AI-generated by definition) and provenance carries a signed ProvenanceManifest when a ProvenanceSigner is wired into the router.

Fields

request_id: String

Request ID this response is for

response_id: String

Response ID

model_id: String

Model that generated the response

provider: Address

Provider that served the request

output: Vec<u8>

Output data

metadata: InferenceMetadata

Response metadata

price: u64

Actual price charged (in smallest TNZO unit)

timestamp: Timestamp

Response timestamp

synthetic_content: bool

EU AI Act Article 50(2) — content is machine-generated. Always true for genuine inference responses; deserialized as true by default so integrations that build responses by hand cannot accidentally drop the disclosure.

provenance: Option<ProvenanceManifest>

EU AI Act Article 50(2) — content provenance. None only for in-memory transient responses that haven’t been signed yet (e.g. mid-router). All responses returned to RPC/MCP/A2A clients have this populated.

Implementations

impl InferenceResponse

pub fn new( request_id: String, model_id: String, provider: Address, output: Vec<u8>, price: u64, ) -> Self

Creates a new inference response. The result is marked as synthetic_content = true automatically per EU AI Act Article 50. Callers should attach a ProvenanceManifest via with_provenance before publishing the response off the node.

pub fn with_provenance(self, manifest: ProvenanceManifest) -> Self

Builder helper to attach a signed provenance manifest before the response leaves the inference router.

Trait Implementations

impl Clone for InferenceResponse

fn clone(&self) -> InferenceResponse

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for InferenceResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for InferenceResponse

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for InferenceResponse

impl PartialEq for InferenceResponse

fn eq(&self, other: &InferenceResponse) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for InferenceResponse

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for InferenceResponse