DecisionRun

An evaluation run of a decision corpus (1.58.0): the Provider and model version, the corpus version, and precision and recall per label over a threshold sweep with a proposed threshold. Numbers only.

An object with 19 fields.

Fields

Field	Type	Required	Description
`agent_id`	AgentId	yes
`agent_version`	integer	yes	The active version whose chain ran.
`cases`	integer	yes	The cases sent.
`completed_at`	Timestamp or null	yes
`corpus_id`	DecisionCorpusId	yes
`corpus_version`	integer	yes
`created_at`	Timestamp	yes
`created_by`	ActorRef	yes
`error_code`	string or null	yes	Why a `failed` run failed, such as `provider_unavailable`; null otherwise.
`id`	DecisionRunId	yes
`job_id`	JobId	yes
`model_version`	string	yes
`object`	`"decision_run"`	yes
`precision_target`	number	yes	The precision a proposed threshold must meet, 0.9 when omitted (a target).
`provider`	ProviderId	yes
`question_set`	QuestionSetKey	yes
`results`	array of DecisionQuestionResult	yes	Per question, once `completed`; empty before.
`status`	DecisionRunStatus	yes
`usage`	DecisionRunUsage or null	no	What the run used (1.59.0), once its result landed, completed or failed; null while it is `queued` or `running`. Absent from an api before 1.59.0, which a reader treats as null.

Used by

The operations whose parameters, request body or responses name this shape directly.