Circle V2 API Docs
    Preparing search index...

    Composite runner: metadata-focused questions are first attempted with the cheap one-shot SummaryTableQuestionRunner; when that throws NotEnoughInformationError (or the question is not metadata-focused) the full AgentQuestionRunner pipeline runs instead.

    For metadata questions the shared, expensive steps — question expansion and the find_documents selection — are resolved ONCE here and passed into both child runners, so they run once per question instead of once per runner. If that resolution fails, we skip the shortcut and run the agent directly.

    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