Circle V2 API Docs
    Preparing search index...

    Type Alias AuditQuestionPassFailInput

    type AuditQuestionPassFailInput = {
        additionalInstructions?: string | null;
        auditQuestionId?: AuditQuestionId | null;
        config?: AuditQuestionConfigOverrides;
        context?: ChartReviewRunContext;
        modelOverride?: PromptModelConfig;
        patientChartIds?: PatientChartId[];
        patientContext?: ResolvedPatientContext;
        patientId: PatientId;
        question: string;
        referenceInstant?: Date;
        reviewCriteria?: string | null;
        treatmentEpisodeId?: TreatmentEpisodeId;
        useEvalNamespaces?: boolean;
    }
    Index

    Properties

    additionalInstructions?: string | null

    This question's own note, stacked on reviewCriteria. Pass it raw — the runner gates it.

    auditQuestionId?: AuditQuestionId | null

    Tunable levers (models, sampling, loop bounds, toolset, prompts) as a deep-partial override. Missing keys fall back to the accuracy-first package defaults. Production callers resolve this from feature flags at the call site and pass it here.

    Pre-hoisted run context (charts + vector stores). When omitted the runner hoists it once for this run. Injecting it avoids a double-fetch on router escalation.

    modelOverride?: PromptModelConfig

    Per-run model + temperature override. Lets an eval experiment swap the model without editing the committed snapshot or the LangSmith hub. Production leaves it unset -> hub/snapshot model.

    patientChartIds?: PatientChartId[]

    Reviewer-selected charts; when set they are the entire candidate set.

    patientContext?: ResolvedPatientContext

    Pre-resolved patient context. When omitted the runner resolves it via @repo/db. Pass it (with context) to reuse a run-scoped resolution across tiers/questions.

    patientId: PatientId
    question: string
    referenceInstant?: Date

    Frozen "now" for all date reasoning. Production leaves this unset (wall-clock). Eval passes the instant the gold answer was graded against so date-relative questions are reproducible against a frozen data clone instead of drifting to wall-clock.

    reviewCriteria?: string | null

    Rubric that guides grading (from a template's custom_review_criteria_prompt).

    treatmentEpisodeId?: TreatmentEpisodeId
    useEvalNamespaces?: boolean

    Use isolated eval Pinecone namespaces instead of production ones.