Enum EvidenceAttribution 

pub enum EvidenceAttribution {
    Named,
    Anonymous,
}

How an Observation is attributed in the evidence bundle handed to the LLM (docs/loop.md). Named renders <observer> (a person) said of <subject>: <text>; Anonymous renders the bare text, which is what the engine did before 2026-09-04.

It is host policy for two independent reasons. An operator may not want observer identities rendered into a model prompt at all — an observer id can be a person’s name or account — and that is a privacy decision only the host can make. And it is the one variable in the receipts ablation (crates/areev-bench/RECEIPTS.md), where naming the speaker is what stopped one model reading a correction as a request.

Variants

Named

Name the observer on an Observation that records one.

Anonymous

Render the bare text, attributing nothing.

Trait Implementations

impl Clone for EvidenceAttribution

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for EvidenceAttribution

impl Debug for EvidenceAttribution

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

Formats the value using the given formatter.

impl Default for EvidenceAttribution

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for EvidenceAttribution

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for EvidenceAttribution

impl PartialEq for EvidenceAttribution

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for EvidenceAttribution

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 EvidenceAttribution