Circle V2 API Docs
    Preparing search index...

    Class SessionNoteAuditRunner

    V1-faithful session-note validation runner.

    Reproduces the legacy circlehealthai-web audit-chart edge function's prompt + response contract verbatim (compliance-auditor system prompt, pass | fail | needs_review status), instead of v2's tool-using AgentQuestionRunner agent prompt. Used only for session-note-triggered validations (selected via runnerVariant: 'session-note-v1').

    Deliberate deviations from v1 mechanics (the reviewer's concern was the PROMPT, not the retrieval mechanism):

    • The whole cleaned session note is injected directly as the context (this.sessionNoteContext); v1 embedded it and did a 3-chunk similaritySearch. Direct injection feeds the full note and is strictly better.
    • No transformQuestion / expandQuestionWithLLM — v1 ran the raw question.
    • The shared createChartReviewChatModel is reused (gpt-4.1 / temp 0.1; settings-driven maxTokens, defaulting ≥ v1's hard-coded 1000).
    • v1's reason: string[] is folded into the persisted answer; v1's question_ui is dropped; v1's fallback-status second LLM call is replaced by a schema-required status that defaults to needs_review.

    Hierarchy (View Summary)

    Index

    Constructors

    constructor

    Properties

    enableCalendarAwareness enableEpisodePatientBlock enableExpandedStatuses enableIntentAwarePlanning enableMetadataAwareGate enableQueryHydration enableReviewCriteriaInDocumentSelection enableStatusReconciliation enableThinRetrievalBailout enableTimeFilteringInChartReview enableUnlockedRetrieval logger model patientChartIds? referenceInstant sessionId? sessionNoteContext? supabase treatmentEpisodeId? useEvalNamespaces

    Methods

    run usesRunContext

    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

    Settings

    Member Visibility

    On This Page

    Constructors
    Properties
    Methods