Struct AssistantUsageData 

pub struct AssistantUsageData {

    pub api_call_id: Option<String>,
    pub cache_read_tokens: Option<f64>,
    pub cache_write_tokens: Option<f64>,
    pub copilot_usage: Option<AssistantUsageCopilotUsage>,
    pub cost: Option<f64>,
    pub duration: Option<f64>,
    pub initiator: Option<String>,
    pub input_tokens: Option<f64>,
    pub inter_token_latency_ms: Option<f64>,
    pub model: String,
    pub output_tokens: Option<f64>,
    pub parent_tool_call_id: Option<String>,
    pub provider_call_id: Option<String>,
    pub quota_snapshots: HashMap<String, AssistantUsageQuotaSnapshot>,
    pub reasoning_effort: Option<String>,
    pub reasoning_tokens: Option<f64>,
    pub ttft_ms: Option<f64>,
}

LLM API call usage metrics including tokens, costs, quotas, and billing information

Fields

api_call_id: Option<String>

Completion ID from the model provider (e.g., chatcmpl-abc123)

cache_read_tokens: Option<f64>

Number of tokens read from prompt cache

cache_write_tokens: Option<f64>

Number of tokens written to prompt cache

copilot_usage: Option<AssistantUsageCopilotUsage>

Per-request cost and usage data from the CAPI copilot_usage response field

cost: Option<f64>

Model multiplier cost for billing purposes

duration: Option<f64>

Duration of the API call in milliseconds

initiator: Option<String>

What initiated this API call (e.g., “sub-agent”, “mcp-sampling”); absent for user-initiated calls

input_tokens: Option<f64>

Number of input tokens consumed

inter_token_latency_ms: Option<f64>

Average inter-token latency in milliseconds. Only available for streaming requests

model: String

Model identifier used for this API call

output_tokens: Option<f64>

Number of output tokens produced

parent_tool_call_id: Option<String>

👎Deprecated

Parent tool call ID when this usage originates from a sub-agent

provider_call_id: Option<String>

GitHub request tracing ID (x-github-request-id header) for server-side log correlation

quota_snapshots: HashMap<String, AssistantUsageQuotaSnapshot>

Per-quota resource usage snapshots, keyed by quota identifier

reasoning_effort: Option<String>

Reasoning effort level used for model calls, if applicable (e.g. “low”, “medium”, “high”, “xhigh”)

reasoning_tokens: Option<f64>

Number of output tokens used for reasoning (e.g., chain-of-thought)

ttft_ms: Option<f64>

Time to first token in milliseconds. Only available for streaming requests

Trait Implementations

impl Clone for AssistantUsageData

fn clone(&self) -> AssistantUsageData

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AssistantUsageData

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for AssistantUsageData

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for AssistantUsageData

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

where __S: Serializer,

Serialize this value into the given Serde serializer.