@camunda8/orchestration-cluster-api
    Preparing search index...

    Type Alias AgentInstanceHistoryItemMetricsRequest

    Per-call token and latency metrics for an ASSISTANT history item, as submitted on a create/update request. All fields are optional: omit a field the caller has no value for rather than sending it as an explicit null.

    type AgentInstanceHistoryItemMetricsRequest = {
        cacheCreationTokenCount?: number | null;
        cacheReadTokenCount?: number | null;
        durationMs?: number | null;
        inputTokens?: number | null;
        outputTokens?: number | null;
        reasoningTokenCount?: number | null;
    }
    Index
    cacheCreationTokenCount? cacheReadTokenCount? durationMs? inputTokens? outputTokens? reasoningTokenCount?
    cacheCreationTokenCount?: number | null

    Cache-creation tokens consumed by this LLM call. Null when not provided.

    cacheReadTokenCount?: number | null

    Cache-read tokens consumed by this LLM call. Null when not provided.

    durationMs?: number | null

    Wall-clock duration of the LLM call in milliseconds. Null when not provided.

    inputTokens?: number | null

    Input tokens consumed by this LLM call. Null when not provided.

    outputTokens?: number | null

    Output tokens produced by this LLM call. Null when not provided.

    reasoningTokenCount?: number | null

    Reasoning tokens consumed by this LLM call. Null when not provided.

    Settings
    Member Visibility

    On This Page
    Properties