SpanAttributes

Contextual attributes capturing operation details, LLM configuration, usage metrics, and conversation data

Types

Link copied to clipboard
class Builder
Link copied to clipboard
object Companion

Properties

Link copied to clipboard

Amazon Connect agent ID

Link copied to clipboard

AI agent ARN

Link copied to clipboard

AI agent identifier

Link copied to clipboard

Entity that invoked the AI agent

Link copied to clipboard

AI agent name

Link copied to clipboard

AI agent orchestrator use case

Link copied to clipboard

AI agent type

Link copied to clipboard

AI agent version number

Link copied to clipboard

Number of input tokens that were retrieved from cache

Link copied to clipboard

Number of input tokens that were written to cache in this request

Link copied to clipboard

Amazon Connect contact identifier

Link copied to clipboard

Error classification if span failed (e.g., throttle, timeout)

Link copied to clipboard

Amazon Connect contact identifier

Link copied to clipboard

Input message collection sent to LLM

Link copied to clipboard

Amazon Connect instance ARN

Link copied to clipboard

Action being performed

Link copied to clipboard

Output message collection received from LLM

Link copied to clipboard

AI prompt ARN

Link copied to clipboard

AI prompt identifier

Link copied to clipboard

AI prompt name

Link copied to clipboard

AI prompt type

Link copied to clipboard

AI prompt version number

Link copied to clipboard

Model provider identifier (e.g., aws.bedrock)

Link copied to clipboard

Maximum tokens configured for generation

Link copied to clipboard

LLM model ID for request (e.g., anthropic.claude-3-sonnet)

Link copied to clipboard

Generation termination reasons (e.g., stop, max_tokens)

Link copied to clipboard

Actual model used for response (usually matches requestModel)

Link copied to clipboard

Session name

Link copied to clipboard

System prompt instructions

Link copied to clipboard

Sampling temperature for generation

Link copied to clipboard
val topP: Float?

Top-p sampling parameter for generation

Link copied to clipboard

Number of input tokens in prompt

Link copied to clipboard

Number of output tokens in response

Link copied to clipboard

Total tokens consumed (input + output)

Functions

Link copied to clipboard
inline fun copy(block: SpanAttributes.Builder.() -> Unit = {}): SpanAttributes
Link copied to clipboard
open operator override fun equals(other: Any?): Boolean
Link copied to clipboard
open override fun hashCode(): Int
Link copied to clipboard
open override fun toString(): String