Class LLMObsPromptVersionDataAttributes

Attributes of a specific version of an Agent Observability prompt. For a composed version, authoring_template contains its pinned include-bearing source; ordinary versions omit that attribute. Empty config is omitted when configuration authoring is disabled for the organization. Non-empty saved configuration is always returned.

Hierarchy

  • LLMObsPromptVersionDataAttributes

Constructors

Properties

additionalProperties?: {
    [key: string]: any;
}

A container for additional, undeclared properties. This is a holder for any undeclared properties as specified with the 'additionalProperties' keyword in the OAS document.

Type declaration

  • [key: string]: any
author?: string

UUID of the user who authored this version.

authoringTemplate?: LLMObsPromptTemplate

A text template, a list of chat messages and named message placeholders, or an authored chat object. Text can include an exact prompt version with {{>prompt-id version=N}}; other text, including {{>...}} sequences without a version, remains literal. Use an authored chat object when including prompts as chat messages. Preview: Prompt composition is available in Preview. To request access, contact Datadog Support or your Customer Success Manager. Without access, inline references remain literal text and structured includes are unsupported. Previously compiled prompt versions remain available for execution. Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.

config?: {
    [key: string]: any;
}

Versioned prompt configuration is in Preview. To request access, contact Datadog Support or your Customer Success Manager. Customer-owned configuration delivered with a prompt version. Datadog stores and returns the object without interpolating it, validating provider-specific keys, or applying it to model calls. Do not include secrets.

Type declaration

  • [key: string]: any
createdAt?: Date

Timestamp stored on this prompt version.

datasets?: LLMObsPromptDataset[]

Datasets observed in runs associated with this prompt version.

description?: string

Description of this version.

labels?: string[]

Labels attached to this version (for example development, staging, production).

lastSeenAt?: Date

Timestamp of the most recent observed run of this prompt version.

mlApp?: string

The ML application this prompt is associated with.

mlApps?: string[]

ML applications observed running this prompt version.

promptId: string

Customer-provided identifier of the parent prompt.

promptUuid: string

Unique identifier of the parent prompt.

tags?: string[]

Tags observed on runs of this prompt version.

A text template, a list of chat messages and named message placeholders, or an authored chat object. Text can include an exact prompt version with {{>prompt-id version=N}}; other text, including {{>...}} sequences without a version, remains literal. Use an authored chat object when including prompts as chat messages. Preview: Prompt composition is available in Preview. To request access, contact Datadog Support or your Customer Success Manager. Without access, inline references remain literal text and structured includes are unsupported. Previously compiled prompt versions remain available for execution. Preview: Message placeholders are available in Preview. To request access, contact Datadog Support or your Customer Success Manager.

userVersion?: string

User-supplied identifier for this version.

version: number

Sequential version number.

versionCreatedAt?: Date

Timestamp when this version was created.

Generated using TypeDoc