Struct AgentMessage 

pub struct AgentMessage {

    pub message_id: MessageId,
    pub role: AgentMessageRole,
    pub parts: Vec<AgentMessagePart>,
    pub producer_ref: EntityRef,
    pub source_ref: SourceRef,
    pub destination_ref: Option<DestinationRef>,
    pub policy_refs: Vec<PolicyRef>,
    pub privacy_class: PrivacyClass,
    pub retention_class: RetentionClass,
    pub trust_class: TrustClass,
    pub lineage_refs: Vec<LineageRef>,
    pub redacted_summary: String,
    pub provider_projected: bool,
}

Carries the agent message record payload for journal, event, or fixture surfaces. Creating or cloning it only preserves serialized SDK state; append, publish, replay, or export effects are documented on the runtime and port methods that store it.

Fields

message_id: MessageId

Message identifier for transcript, projection, or provider-response lineage.

role: AgentMessageRole

Role used by this record or request.

parts: Vec<AgentMessagePart>

Collection of parts values. Ordering and membership should be treated as part of the serialized contract when relevant.

producer_ref: EntityRef

Typed producer ref reference. Resolving or executing it is a separate policy-gated step.

source_ref: SourceRef

Typed source reference that records where this item originated.

destination_ref: Option<DestinationRef>

Typed destination reference that records where this item is being sent or projected.

policy_refs: Vec<PolicyRef>

Policy references that govern admission, projection, execution, or delivery.

privacy_class: PrivacyClass

Privacy class used for projection, telemetry, and raw-content access decisions.

retention_class: RetentionClass

Retention class used by hosts and sinks when storing or exporting this item.

trust_class: TrustClass

Trust class used when deciding whether context or capabilities may be admitted.

lineage_refs: Vec<LineageRef>

Typed lineage refs references. Resolving them is separate from constructing this record.

redacted_summary: String

Redacted human-readable summary safe for events, telemetry, and logs.

provider_projected: bool

Whether provider projected is enabled. Policy, validation, or routing code uses this flag to choose the explicit behavior.

Implementations

impl AgentMessage

pub fn user_text( message_id: MessageId, text: impl Into<String>, source_ref: SourceRef, policy_ref: PolicyRef, ) -> Self

Builds the user text value with the documented defaults. This is data-only and does not perform I/O, call host ports, append journals, publish events, or start processes.

Trait Implementations

impl Clone for AgentMessage

fn clone(&self) -> AgentMessage

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AgentMessage

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AgentMessage

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for AgentMessage

impl PartialEq for AgentMessage

fn eq(&self, other: &AgentMessage) -> 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 AgentMessage

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 AgentMessage