Circle V2 API Docs
    Preparing search index...

    A lightweight question runner that answers metadata-focused questions (signatures, sign status, completion, dates) using a single structured-output LLM call against compact per-type summary tables.

    No agent loop, no vector retrieval, no full document fetching. Designed as a cheap shortcut: when the LLM answers confidently (pass/fail) we use the result; otherwise it throws NotEnoughInformationError and the composite runner falls through to the full agent pipeline.

    Hierarchy (View Summary)

    Index

    Constructors

    Properties

    enableCalendarAwareness: boolean
    enableEpisodePatientBlock: boolean
    enableExpandedStatuses: boolean
    enableIntentAwarePlanning: boolean
    enableMetadataAwareGate: boolean
    enableQueryHydration: boolean
    enableReviewCriteriaInDocumentSelection: boolean
    enableStatusReconciliation: boolean
    enableThinRetrievalBailout: boolean
    enableTimeFilteringInChartReview: boolean
    enableUnlockedRetrieval: boolean
    logger: BaseLogger
    model: ChatOpenAI
    patientChartIds?: number[]
    referenceInstant: Date
    sessionId?: SessionId
    sessionNoteContext?: string
    supabase: SupabaseClient<Database>
    treatmentEpisodeId?: string
    useEvalNamespaces: boolean

    Methods

    • Whether this runner reads the hoisted context for any of questions, so the orchestrator can skip an expensive hoist a runner resolves for itself. Defaults to true, which is always safe.

      Parameters

      Returns boolean