Jyotisha/frontend/src/lib/rectification-agentic/v9/evidence-model.ts

/**
 * V9 evidence model contracts: event kinds, domains, date precision and the
 * append-only revision/status machine. IDs are always generated by the server.
 */
import { z } from "zod";
import { splitHoldoutEvents, type DatedEventInput } from "../core/split-holdout.ts";

export const EVIDENCE_KINDS = [
  "education_start",
  "education_completion",
  "education_interruption",
  "education_change",
  "education_milestone",
  "career_entry",
  "career_change",
  "promotion",
  "career_pressure",
  "career_exit",
  "business_start",
  "relationship_start",
  "relationship_commitment",
  "relationship_separation",
  "relationship_end",
  "relationship_change",
  "relocation",
  "foreign_move",
  "return",
  "home_change",
  "finance_gain",
  "finance_loss",
  "income_change",
  "asset_change",
  "finance_change",
  "self_health_event",
  "pressure_period",
  "family_event",
  "appearance_note",
  "birthmark_or_scar",
  "occupation_note",
  "horary_query",
  "other",
] as const;

export type EvidenceKind = (typeof EVIDENCE_KINDS)[number];

export const EVIDENCE_DOMAINS = [
  "education",
  "career",
  "relationship",
  "relocation",
  "finance",
  "health",
  "health_pressure",
  "family",
  "appearance",
  "marks",
  "occupation",
  "horary",
  "other",
] as const;

export type EvidenceDomain = (typeof EVIDENCE_DOMAINS)[number];

export const evidenceKindSchema = z.enum(
  EVIDENCE_KINDS as unknown as [EvidenceKind, ...EvidenceKind[]],
);
export const evidenceDomainSchema = z.enum(
  EVIDENCE_DOMAINS as unknown as [EvidenceDomain, ...EvidenceDomain[]],
);

export const DATE_PRECISIONS = [
  "year",
  "month",
  "quarter",
  "day",
  "range",
  "unknown",
] as const;

export type DatePrecision = (typeof DATE_PRECISIONS)[number];

export const EVIDENCE_STATUSES = [
  "draft",
  "pending_confirmation",
  "confirmed",
  "superseded",
  "rejected",
] as const;

export type EvidenceStatus = (typeof EVIDENCE_STATUSES)[number];

const KIND_SET = new Set<string>(EVIDENCE_KINDS);
const DOMAIN_SET = new Set<string>(EVIDENCE_DOMAINS);
const PRECISION_SET = new Set<string>(DATE_PRECISIONS);
const STATUS_SET = new Set<string>(EVIDENCE_STATUSES);

export function isEvidenceKind(value: unknown): value is EvidenceKind {
  return typeof value === "string" && KIND_SET.has(value);
}

export function isEvidenceDomain(value: unknown): value is EvidenceDomain {
  return typeof value === "string" && DOMAIN_SET.has(value);
}

export function isDatePrecision(value: unknown): value is DatePrecision {
  return typeof value === "string" && PRECISION_SET.has(value);
}

export function isEvidenceStatus(value: unknown): value is EvidenceStatus {
  return typeof value === "string" && STATUS_SET.has(value);
}

/**
 * Kinds that are semantically distinct and must never be folded together.
 * The scoring path keys on event_kind, so collapsing these would corrupt
 * both the ledger and the candidate contrast.
 */
export const DISTINCT_KIND_GROUPS: readonly (readonly EvidenceKind[])[] = [
  ["career_entry", "career_pressure", "career_exit"],
  ["relationship_start", "relationship_commitment", "relationship_separation"],
];

/**
 * Legal evidence status transitions. Only the server confirmation path may
 * produce `confirmed`; a grounded draft may use that server path in the same run.
 */
export const EVIDENCE_STATUS_TRANSITIONS: Readonly<
  Record<EvidenceStatus, readonly EvidenceStatus[]>
> = {
  draft: ["pending_confirmation", "confirmed", "rejected", "superseded"],
  pending_confirmation: ["confirmed", "rejected", "superseded"],
  confirmed: ["superseded"],
  superseded: [],
  rejected: [],
};

export function canTransitEvidenceStatus(
  from: EvidenceStatus,
  to: EvidenceStatus,
): boolean {
  return EVIDENCE_STATUS_TRANSITIONS[from].includes(to);
}

/**
 * Normalized quote grounding contract: a user_quote is accepted only when it
 * is a substring match after whitespace/punctuation normalization of the
 * source turn's user message.
 */
const QUOTE_PUNCTUATION = /[\s\u3000，。！？、；：“”‘’（）《》·—…,!.;:?]/g;

export function normalizeQuote(value: string): string {
  return value.replace(QUOTE_PUNCTUATION, "").toLowerCase();
}

const PRECISION_RANK: Readonly<Record<string, number>> = {
  day: 4,
  month: 3,
  quarter: 2,
  range: 2,
  year: 1,
  unknown: 0,
};

export function datePrecisionRank(precision: string): number {
  return PRECISION_RANK[precision] ?? -1;
}

export function datedPrecision(value: string): DatedEventInput["precision"] {
  if (value === "day" || value === "month" || value === "year" || value === "unknown") return value;
  return "year";
}

/**
 * Agent-facing date label. Day precision must never collapse to a year.
 */
export function displayDateLabel(
  precision: string,
  occurredFrom: string | null,
  occurredTo: string | null,
): string {
  const from = occurredFrom?.slice(0, 10) ?? "";
  const to = occurredTo?.slice(0, 10) ?? "";
  if (precision === "day" && from) return from;
  if (precision === "month" && from) return from.slice(0, 7);
  if (precision === "year" && from) return `${from.slice(0, 4)}年`;
  if (precision === "quarter" && from) return from.slice(0, 7);
  if (precision === "range") {
    if (from && to) return `${from}–${to}`;
    return from || to || "日期范围";
  }
  if (precision === "unknown") return "日期不明";
  return from || "日期不明";
}

export function quoteIsGroundedInMessage(
  userMessage: string,
  quote: string,
): boolean {
  const normalizedMessage = normalizeQuote(userMessage);
  const normalizedQuote = normalizeQuote(quote);
  return (
    normalizedQuote.length > 0 &&
    normalizedMessage.includes(normalizedQuote)
  );
}

/** Background kinds that never advance scoring coverage counts. */
export const BACKGROUND_ONLY_KINDS: ReadonlySet<EvidenceKind> = new Set([
  "other",
  "horary_query",
]);

/** Notes that may cover a method layer but do not count as primary scoring events. */
export const AUXILIARY_EVIDENCE_KINDS: ReadonlySet<EvidenceKind> = new Set([
  "appearance_note",
  "birthmark_or_scar",
  "occupation_note",
]);

export const NON_PRIMARY_SCORING_DOMAINS: ReadonlySet<string> = new Set([
  "appearance",
  "marks",
  "occupation",
  "horary",
  "other",
]);

/** Same floors as `scripts/rectification/decision_policy.py`. Counted on training events only. */
export const MIN_ACCEPTANCE_EVENTS = 3;
export const MIN_ACCEPTANCE_DOMAINS = 2;

export function isBackgroundEvidenceKind(kind: EvidenceKind): boolean {
  return BACKGROUND_ONLY_KINDS.has(kind);
}

export function isPrimaryScoreableEvidence(item: {
  status: string;
  domain: string;
  datePrecision: string;
  occurredFrom: string | null;
  occurredTo: string | null;
  eventKind?: string | null;
}): boolean {
  if (item.status !== "confirmed") return false;
  if (item.datePrecision === "unknown") return false;
  if (!item.occurredFrom && !item.occurredTo) return false;
  if (NON_PRIMARY_SCORING_DOMAINS.has(item.domain)) return false;
  const kind = item.eventKind;
  if (
    kind === "other"
    || kind === "horary_query"
    || kind === "appearance_note"
    || kind === "birthmark_or_scar"
    || kind === "occupation_note"
  ) {
    return false;
  }
  return true;
}

type ScoreableEvidence = Readonly<{
  id?: string;
  status: string;
  domain: string;
  datePrecision: string;
  occurredFrom: string | null;
  occurredTo: string | null;
  eventKind?: string | null;
}>;

function yearFromIso(value: string | null): number | null {
  if (!value || value.length < 4 || !/^\d{4}/.test(value)) return null;
  const year = Number(value.slice(0, 4));
  return year >= 1900 && year <= 2100 ? year : null;
}

/**
 * Discrimination requires 3 training events / 2 training domains.
 * Holdout is reserved from the 2nd dated event but does not count.
 * 3 collected events with 1 holdout must keep collecting.
 */
export function trainingScoreableGate(evidence: readonly ScoreableEvidence[]): Readonly<{
  trainingCount: number;
  trainingDomainCount: number;
  holdoutCount: number;
  open: boolean;
}> {
  const scoreable = evidence.filter(isPrimaryScoreableEvidence);
  const dated: DatedEventInput[] = scoreable.map((item, index) => ({
    id: item.id && item.id.trim() ? item.id : `scoreable:${index}:${item.domain}:${item.occurredFrom ?? ""}`,
    domain: item.domain,
    year: yearFromIso(item.occurredFrom) ?? yearFromIso(item.occurredTo),
    precision: datedPrecision(item.datePrecision),
  }));
  const split = splitHoldoutEvents(dated);
  const training = split.filter((item) => item.usage === "training");
  const domains = new Set(training.map((item) => item.domain));
  return {
    trainingCount: training.length,
    trainingDomainCount: domains.size,
    holdoutCount: split.filter((item) => item.usage === "holdout").length,
    open: training.length >= MIN_ACCEPTANCE_EVENTS && domains.size >= MIN_ACCEPTANCE_DOMAINS,
  };
}

/** Reverse-inference / conflict probes wait until training coverage could accept. */
export function meetsAcceptanceEventQuality(
  evidence: readonly ScoreableEvidence[],
): boolean {
  return trainingScoreableGate(evidence).open;
}

/** Ledger/engine subject follows the domain. Family events must not stay on the tool default `self`. */
export function evidenceSubjectForDomain(
  domain: string,
  _subject?: string | null,
): "self" | "family" | "other" {
  if (domain === "family") return "family";
  if (domain === "other") return "other";
  return "self";
}

export type OccupationCollectFocus = Readonly<{
  intent?: string | null;
  targetDomain?: string | null;
  targetKind?: string | null;
  questionId?: string | null;
}>;

export function isOccupationCollectFocus(
  focus: OccupationCollectFocus | null | undefined,
): boolean {
  if (!focus) return false;
  const collectQuestion = typeof focus.questionId === "string"
    && focus.questionId.startsWith("collect:occupation:");
  if (focus.intent && focus.intent !== "collect_method_evidence") return false;
  return focus.targetDomain === "occupation"
    || focus.targetKind === "occupation_note"
    || collectQuestion;
}

/** When the answered focus is occupation collect, do not trust the model domain. */
export function applyOccupationCollectLedgerNorm<T extends {
  domain: string;
  eventKind: EvidenceKind;
  datePrecision: string;
  occurredFrom: string | null;
  occurredTo: string | null;
}>(focus: OccupationCollectFocus | null | undefined, items: readonly T[]): T[] {
  if (!isOccupationCollectFocus(focus)) return [...items];
  return items.map((item) => {
    if (item.domain !== "career" && item.domain !== "occupation") return item;
    return {
      ...item,
      domain: "occupation",
      eventKind: "occupation_note" as EvidenceKind,
      datePrecision: "unknown",
      occurredFrom: null,
      occurredTo: null,
    };
  });
}