MDAA TS Docs
    Preparing search index...

    Input and output token thresholds. Each threshold set creates one alarm that fires when the token count summed over one alarm period exceeds it.

    Use cases: token-spend spike detection, runaway-agent detection

    AWS: CloudWatch alarms on AWS/Bedrock InputTokenCount and OutputTokenCount (Sum)

    Validation: at least one of inputTokenThreshold or outputTokenThreshold

    interface TokenThresholdsProps {
        inputTokenThreshold?: number;
        outputTokenThreshold?: number;
    }

    Hierarchy (View Summary)

    Index

    Properties

    inputTokenThreshold?: number

    Alarm when input tokens in one alarm period exceed this value. Omit to skip the input-token alarm.

    Use cases: detecting oversized prompts or a surge in requests

    AWS: CloudWatch alarm on InputTokenCount (Sum)

    Validation: Optional; Number; >= 0

    0

    outputTokenThreshold?: number

    Alarm when output tokens in one alarm period exceed this value. Omit to skip the output-token alarm.

    Use cases: detecting runaway generation, output-token spend spikes

    AWS: CloudWatch alarm on OutputTokenCount (Sum)

    Validation: Optional; Number; >= 0

    0