ApiCore/ApiCore-Backend/src/voice/voice-retention.ts

import { Prisma } from '../../generated/prisma';
import { PrismaService } from '../prisma/prisma.service';
import { recordVoiceCaptureFailed } from './voice-failure-hook';

/** Audio is kept until it is transcribed, 24 hours at most. */
export const VOICE_AUDIO_MAX_AGE_HOURS = 24;
/** The row itself (no content) stays 90 days for the error and cost overview. */
export const VOICE_ROW_RETENTION_DAYS = 90;

export interface VoiceRetentionCounts {
  audioExpired: number;
  contentExpired: number;
  inactiveOwnersWiped: number;
}

export interface VoiceRetentionOptions {
  /**
   * Extra condition on "VoiceCapture" columns, ANDed to every statement
   * (e.g. an owner filter in tests). Trusted SQL only.
   */
  filter?: Prisma.Sql;
}

const OPEN_CONTENT = Prisma.sql`"status" NOT IN ('CONFIRMED', 'DISCARDED', 'EXPIRED')`;

/**
 * Audio older than 24 hours goes, and a note that still waited for its
 * transcript (QUEUED, TRANSCRIBING) ends FAILED/AUDIO_EXPIRED; its claim is
 * cleared, so a job that still holds it loses the compare-and-set. A note in
 * another state keeps its status (FAILED keeps its own code).
 */
async function expireAudio(
  tx: Prisma.TransactionClient,
  filter: Prisma.Sql,
): Promise<number> {
  const moved = await tx.$queryRaw<{ id: string }[]>(Prisma.sql`
    WITH old AS (
      SELECT c."id"
      FROM "VoiceCaptureAudio" a
      JOIN "VoiceCapture" c ON c."id" = a."captureId"
      WHERE a."createdAt" < now() - interval '24 hours' ${filter}
      ORDER BY c."id"
      FOR UPDATE OF c
    ), gone AS (
      DELETE FROM "VoiceCaptureAudio"
      WHERE "captureId" IN (SELECT "id" FROM old)
    )
    UPDATE "VoiceCapture"
    SET "status" = 'FAILED',
        "lastErrorCode" = 'AUDIO_EXPIRED',
        "claimedAt" = NULL,
        "claimToken" = NULL,
        "updatedAt" = now()
    WHERE "id" IN (SELECT "id" FROM old)
      AND "status" IN ('QUEUED', 'TRANSCRIBING')
    RETURNING "id"`);
  for (const { id } of moved) {
    await recordVoiceCaptureFailed(tx, id, 'AUDIO_EXPIRED');
  }
  return moved.length;
}

/**
 * Deletes audio, transcript and suggestions of the notes the `due`
 * condition selects and marks them EXPIRED. Locks the rows first, so a
 * confirm or discard in flight finishes before the wipe looks at the state.
 */
function wipeContent(
  tx: Prisma.TransactionClient,
  due: Prisma.Sql,
  filter: Prisma.Sql,
): Promise<number> {
  return tx.$executeRaw(Prisma.sql`
    WITH due AS (
      SELECT "id" FROM "VoiceCapture"
      WHERE "contentDeletedAt" IS NULL AND ${OPEN_CONTENT} AND ${due} ${filter}
      ORDER BY "id"
      FOR UPDATE
    ), gone AS (
      DELETE FROM "VoiceCaptureAudio"
      WHERE "captureId" IN (SELECT "id" FROM due)
    )
    UPDATE "VoiceCapture"
    SET "status" = 'EXPIRED',
        "transcriptEnc" = NULL,
        "suggestionEnc" = NULL,
        "contentDeletedAt" = now(),
        "claimedAt" = NULL,
        "claimToken" = NULL,
        "updatedAt" = now()
    WHERE "id" IN (SELECT "id" FROM due)`);
}

/**
 * The retention rules that must not wait for the daily cleanup: audio over
 * 24 hours, content past its 7 days (contentExpiresAt), content of
 * deactivated users. Pure SQL against the database clock, no key needed, so
 * every CronJob run (every 2 minutes) can do it - the cleanup job calls the
 * same function. Hooks and writes share one transaction.
 */
export function expireVoiceContent(
  db: PrismaService,
  options: VoiceRetentionOptions = {},
): Promise<VoiceRetentionCounts> {
  const filter = options.filter
    ? Prisma.sql`AND ${options.filter}`
    : Prisma.empty;
  return db.$transaction(async (tx) => {
    const audioExpired = await expireAudio(tx, filter);
    const contentExpired = await wipeContent(
      tx,
      Prisma.sql`"contentExpiresAt" < now()`,
      filter,
    );
    const inactiveOwnersWiped = await wipeContent(
      tx,
      Prisma.sql`"ownerUserId" IN (SELECT "id" FROM "User" WHERE "isActive" = false)`,
      filter,
    );
    return { audioExpired, contentExpired, inactiveOwnersWiped };
  });
}

/**
 * Removes successful voice-transcribe runs older than `hours` in which every
 * counter is 0 (no work): the CronJob runs every 2 minutes and would add
 * 1440 rows a day. Runs with work, and failed runs, stay with the normal
 * 90 days. `filter` narrows on "JobRun" columns (tests).
 */
export function deleteIdleVoiceRuns(
  db: PrismaService,
  hours: number,
  filter?: Prisma.Sql,
): Promise<number> {
  return db.$executeRaw(Prisma.sql`
    DELETE FROM "JobRun"
    WHERE "job" = 'voice-transcribe' AND "status" = 'SUCCEEDED'
      AND "startedAt" < now() - (${hours} * interval '1 hour')
      AND "result" IS NOT NULL
      AND NOT EXISTS (
        SELECT 1 FROM jsonb_each_text("result"::jsonb) AS counter
        WHERE counter.value <> '0')
      ${filter ? Prisma.sql`AND ${filter}` : Prisma.empty}`);
}

/** Deletes rows (and, by cascade, any audio) older than 90 days. */
export function deleteOldVoiceRows(db: PrismaService): Promise<number> {
  return db.$executeRaw`
    DELETE FROM "VoiceCapture"
    WHERE "createdAt" < now() - (${VOICE_ROW_RETENTION_DAYS} * interval '1 day')`;
}