Function runQuestionsWithImmediateSave

Parameters

• options: {
      auditResponsesRepo: AuditResponsesRepo;
      auditRunId: AuditRunId;
      auditTemplateId: string | number;
      context?: QuestionRunContext;
      logger: BaseLogger;
      patient: {
          address_city: string | null;
          address_state: string | null;
          address_street1: string | null;
          address_street2: string | null;
          address_zipcode: string | null;
          created_at: string;
          created_by: string | null;
          dob: string | null;
          email: string | null;
          entity_id: number | null;
          external_patient_id: string | null;
          external_source:
              | "kipu"
              | "lightningstep"
              | "sunwave"
              | "qualifacts_insync"
              | "synthetic"
              | null;
          facility_id: string
          | null;
          first_name: string | null;
          gender: string | null;
          intake_notes: string | null;
          last_name: string | null;
          last_updated_summary: string | null;
          patient_id: number;
          phone_mobile: string | null;
          primary_provider_id: number | null;
          status: number | null;
          summary: Json;
      };
      questions: RunnableAuditQuestion[];
      reviewCriteriaInstructions?: string
      | null;
      runner: QuestionRunner;
      sessionId?: SessionId;
      summaryInstructions?: string | null;
  }

  • auditResponsesRepo: AuditResponsesRepo

  • auditRunId: AuditRunId

  • auditTemplateId: string | number

    Template the questions belong to. Stamped onto each per-question LangSmith span so a question is filterable on its own (template -> run -> question).

  • Optionalcontext?: QuestionRunContext

    Run-scoped context hoisted once by the orchestrator and forwarded to every question, so runners reuse a single chart/admission/level-of-care fetch instead of re-fetching per question. Undefined for the session-note path (whose runner uses only the injected note).

  • logger: BaseLogger

  • patient: {
        address_city: string | null;
        address_state: string | null;
        address_street1: string | null;
        address_street2: string | null;
        address_zipcode: string | null;
        created_at: string;
        created_by: string | null;
        dob: string | null;
        email: string | null;
        entity_id: number | null;
        external_patient_id: string | null;
        external_source:
            | "kipu"
            | "lightningstep"
            | "sunwave"
            | "qualifacts_insync"
            | "synthetic"
            | null;
        facility_id: string
        | null;
        first_name: string | null;
        gender: string | null;
        intake_notes: string | null;
        last_name: string | null;
        last_updated_summary: string | null;
        patient_id: number;
        phone_mobile: string | null;
        primary_provider_id: number | null;
        status: number | null;
        summary: Json;
    }

  • questions: RunnableAuditQuestion[]

  • OptionalreviewCriteriaInstructions?: string | null

    Template custom_review_criteria_prompt: rubric that guides retrieval and pass/fail grading.

  • runner: QuestionRunner

  • OptionalsessionId?: SessionId

    When set, each persisted audit_response row is stamped with this sessionId so the session-note chart-review badge can surface the run via auditRunsRepo.listIdsBySessionId.

  • OptionalsummaryInstructions?: string | null

    Template custom_summary_prompt: format for the summary deliverable.