Struct AssistantMessageData 

pub struct AssistantMessageData {

    pub api_call_id: Option<String>,
    pub content: String,
    pub encrypted_content: Option<String>,
    pub interaction_id: Option<String>,
    pub message_id: String,
    pub model: Option<String>,
    pub output_tokens: Option<i64>,
    pub phase: Option<String>,
    pub reasoning_opaque: Option<String>,
    pub reasoning_text: Option<String>,
    pub request_id: Option<RequestId>,
    pub server_tools: Option<AssistantMessageServerTools>,
    pub service_request_id: Option<String>,
    pub tool_requests: Option<Vec<AssistantMessageToolRequest>>,
    pub turn_id: Option<String>,
    /* private fields */
}

Session event “assistant.message”. Assistant response containing text content, optional tool requests, and interaction metadata

Fields

api_call_id: Option<String>

Provider’s completion / response identifier; shared across all chunks of a single API call. Used to group multi-chunk assistant utterances.

content: String

The assistant’s text response content

encrypted_content: Option<String>

Encrypted reasoning content from OpenAI models. Session-bound and stripped on resume.

interaction_id: Option<String>

CAPI interaction ID for correlating this message with upstream telemetry

message_id: String

Unique identifier for this assistant message

model: Option<String>

Model that produced this assistant message, if known

output_tokens: Option<i64>

Actual output token count from the API response (completion_tokens), used for accurate token accounting

phase: Option<String>

Generation phase for phased-output models (e.g., thinking vs. response phases)

reasoning_opaque: Option<String>

Opaque/encrypted extended thinking data from Anthropic models. Session-bound and stripped on resume.

reasoning_text: Option<String>

Readable reasoning text from the model’s extended thinking

request_id: Option<RequestId>

GitHub request tracing ID (x-github-request-id header) for correlating with server-side logs

server_tools: Option<AssistantMessageServerTools>

Neutral provider-tagged server-side tool-use payload (tool search, advisor) for verbatim round-tripping

service_request_id: Option<String>

Copilot service request ID (x-copilot-service-request-id header) for CAPI log correlation

tool_requests: Option<Vec<AssistantMessageToolRequest>>

Tool invocations requested by the assistant in this message

turn_id: Option<String>

Identifier for the agent loop turn that produced this message, matching the corresponding assistant.turn_start event

Trait Implementations

impl Clone for AssistantMessageData

fn clone(&self) -> AssistantMessageData

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AssistantMessageData

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

Formats the value using the given formatter.

impl Default for AssistantMessageData

fn default() -> AssistantMessageData

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AssistantMessageData

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for AssistantMessageData

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

where __S: Serializer,

Serialize this value into the given Serde serializer.