feat: Sprachnotizen übernehmen, melden und abschreiben (T7 L2 Tasks 8, 9, 11)

Task 8: POST /inspections nimmt voiceCaptureId; die Notiz wird zuletzt
in derselben Transaktion bestätigt (jeder offene Status, Ruling 1),
Inhalt, Audio und Claim gelöscht; fremde oder geschlossene Notiz 409
VOICE_CAPTURE_GONE, anderes Volk 409 VOICE_CAPTURE_COLONY_MISMATCH;
Wiederholung mit gleichem Schlüssel idempotent.

Task 9: Ereignisse VoiceCaptureReady/VoiceCaptureFailed (nur IDs und
Endcodes), Meldungen „Sprachnotiz für … ist fertig“ bzw. Fehlerhinweis
mit nächstem Schritt, Betreiberhinweis bei abgeschalteter Auswertung;
Handler auch im Worker registriert (sonst gingen die Ereignisse
ungehört durch); keine Weiterleitung an Webhooks.

Task 11: Job voice-transcribe mit Phasen fetch (Audio nur im Speicher
entschlüsselt in ein RAM-Arbeitsverzeichnis 0700/0600) und ingest
(Ergebnis gegen Claim geprüft, Transkript versiegelt, Audio gelöscht,
Auswertung geweckt; Stille/zu lang enden FAILED); Ereignisse genau
einmal in derselben Transaktion. Aufbewahrung: Audio 24 h, Inhalt bis
contentExpiresAt, deaktivierte Besitzer, Zeilen 90 Tage; im täglichen
Cleanup inkl. leerer Job-Läufe (Ruling 10).

Gates: Backend lint, typecheck, 4471 Unit-Tests, build; e2e 103 Suites
(einziger Fehler: Wetter-Test gegen echte API).

Refs #27

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

ApiCore-Backend/src/jobs/cleanup.job.spec.ts

@@ -1,6 +1,7 @@
 import { Logger } from '@nestjs/common';
 import { IdempotencyCleanupService } from '../common/idempotency/idempotency-cleanup.service';
 import { PrismaService } from '../prisma/prisma.service';
+import * as voiceRetention from '../voice/voice-retention';
 import { JobRunService } from '../system/job-run.service';
 import { WEATHER_RETENTION_YEARS } from '../weather/history/weather-history.config';
 import {
@@ -9,6 +10,7 @@ import {
   FAILED_RETENTION_DAYS,
   JOB_RUN_RETENTION_DAYS,
   JOB_RUN_STALE_HOURS,
+  VOICE_IDLE_RUN_RETENTION_HOURS,
   PENDING_DELIVERY_MAX_AGE_DAYS,
   WEBHOOK_DELIVERY_RETENTION_DAYS,
 } from './cleanup.job';
@@ -37,6 +39,13 @@ describe('CleanupJob', () => {
   };
 
   beforeEach(() => {
+    jest.spyOn(voiceRetention, 'expireVoiceContent').mockResolvedValue({
+      audioExpired: 1,
+      contentExpired: 2,
+      inactiveOwnersWiped: 3,
+    });
+    jest.spyOn(voiceRetention, 'deleteOldVoiceRows').mockResolvedValue(4);
+    jest.spyOn(voiceRetention, 'deleteIdleVoiceRuns').mockResolvedValue(21);
     let count = 10;
     executeRaw = jest.fn<Promise<number>, RawCall>(() =>
       Promise.resolve(count++),
@@ -62,6 +71,17 @@ describe('CleanupJob', () => {
     expect(JOB_RUN_STALE_HOURS).toBe(6);
   });
 
+  it('cleanup runs the voice retention and prunes idle voice-transcribe runs only', async () => {
+    await job.run();
+
+    expect(voiceRetention.expireVoiceContent).toHaveBeenCalledTimes(1);
+    expect(voiceRetention.deleteOldVoiceRows).toHaveBeenCalledTimes(1);
+    expect(voiceRetention.deleteIdleVoiceRuns).toHaveBeenCalledWith(
+      expect.anything(),
+      VOICE_IDLE_RUN_RETENTION_HOURS,
+    );
+  });
+
   it('cleanup deletes weather days before January 1st four years back', async () => {
     await job.run();
 
@@ -94,6 +114,11 @@ describe('CleanupJob', () => {
       'jobRuns.aborted': 1,
       'jobRuns.deleted': 19,
       weatherDays: 20,
+      'voice.audioExpired': 1,
+      'voice.contentExpired': 2,
+      'voice.inactiveOwnersWiped': 3,
+      'voice.rowsDeleted': 4,
+      'jobRuns.voiceIdle': 21,
     });
   });
 

ApiCore-Backend/src/jobs/cleanup.job.ts

@@ -2,6 +2,11 @@ import { Injectable, Logger } from '@nestjs/common';
 import { IdempotencyCleanupService } from '../common/idempotency/idempotency-cleanup.service';
 import { PrismaService } from '../prisma/prisma.service';
 import { JobRunService } from '../system/job-run.service';
+import {
+  deleteIdleVoiceRuns,
+  deleteOldVoiceRows,
+  expireVoiceContent,
+} from '../voice/voice-retention';
 import { WEATHER_RETENTION_YEARS } from '../weather/history/weather-history.config';
 import { Job, JobResult } from './job';
 import { JobName } from './job-names';
@@ -18,6 +23,8 @@ export const JOB_RUN_RETENTION_DAYS = 90;
 export const PENDING_DELIVERY_MAX_AGE_DAYS = 7;
 /** Far beyond activeDeadlineSeconds (at most 1 h) of every job CronJob. */
 export const JOB_RUN_STALE_HOURS = 6;
+/** A voice-transcribe run (every 2 min) that did nothing is noise after a day. */
+export const VOICE_IDLE_RUN_RETENTION_HOURS = 24;
 
 /**
  * Daily housekeeping (CronJob 04:00). Every age is compared against now(),
@@ -100,6 +107,17 @@ export class CleanupJob implements Job {
       DELETE FROM "ApiaryWeatherDay"
       WHERE "day" < make_date(
         extract(year FROM now() AT TIME ZONE 'Europe/Berlin')::int - ${WEATHER_RETENTION_YEARS}, 1, 1)`;
+    // The same retention rules the voice CronJob runs every 2 minutes (audio
+    // over 24 h, content over 7 days, deactivated users), plus the rows
+    // after 90 days.
+    const voiceRetention = await expireVoiceContent(this.prisma);
+    const voiceRowsDeleted = await deleteOldVoiceRows(this.prisma);
+    // 1440 runs a day, nearly all without work: keep only runs that did
+    // something (a counter above 0) or failed, for the usual 90 days.
+    const voiceIdleRuns = await deleteIdleVoiceRuns(
+      this.prisma,
+      VOICE_IDLE_RUN_RETENTION_HOURS,
+    );
     return {
       idempotencyRecords,
       consumedTokens,
@@ -115,6 +133,11 @@ export class CleanupJob implements Job {
       'jobRuns.aborted': jobRunsAborted,
       'jobRuns.deleted': jobRunsDeleted,
       weatherDays,
+      'voice.audioExpired': voiceRetention.audioExpired,
+      'voice.contentExpired': voiceRetention.contentExpired,
+      'voice.inactiveOwnersWiped': voiceRetention.inactiveOwnersWiped,
+      'voice.rowsDeleted': voiceRowsDeleted,
+      'jobRuns.voiceIdle': voiceIdleRuns,
     };
   }
 }

ApiCore-Backend/src/jobs/job-names.spec.ts

@@ -28,12 +28,14 @@ describe('job names', () => {
     ).toEqual([]);
   });
 
-  it('only rekey accepts an argument, and only --dry-run', () => {
+  it('only rekey and voice-transcribe accept arguments, and only their own', () => {
     expect(Object.keys(JOB_ALLOWED_ARGS)).toEqual([...JOB_NAMES]);
     for (const name of JOB_NAMES) {
-      expect(JOB_ALLOWED_ARGS[name]).toEqual(
-        name === 'rekey' ? ['--dry-run'] : [],
-      );
+      const expected: Record<string, string[]> = {
+        rekey: ['--dry-run'],
+        'voice-transcribe': ['--phase=fetch', '--phase=ingest'],
+      };
+      expect(JOB_ALLOWED_ARGS[name]).toEqual(expected[name] ?? []);
     }
   });
 });

ApiCore-Backend/src/jobs/job-names.ts

@@ -7,6 +7,7 @@ export const JOB_NAMES = [
   'cleanup',
   'app-backup',
   'rekey',
+  'voice-transcribe',
 ] as const;
 
 export type JobName = (typeof JOB_NAMES)[number];
@@ -18,6 +19,7 @@ export const JOB_LABELS_DE: Record<JobName, string> = {
   cleanup: 'Aufräumen',
   'app-backup': 'App-Backup',
   rekey: 'Schlüssel umstellen',
+  'voice-transcribe': 'Sprachnotizen abschreiben',
 };
 
 /**
@@ -32,6 +34,7 @@ export const JOB_FAILURE_PERMISSION: Record<JobName, PermissionKey> = {
   cleanup: 'system:manage',
   'app-backup': 'backup:configure',
   rekey: 'system:manage',
+  'voice-transcribe': 'system:manage',
 };
 
 /**
@@ -45,6 +48,7 @@ export const JOB_ALLOWED_ARGS: Record<JobName, readonly string[]> = {
   cleanup: [],
   'app-backup': [],
   rekey: ['--dry-run'],
+  'voice-transcribe': ['--phase=fetch', '--phase=ingest'],
 };
 
 export function isJobName(value: string): value is JobName {

ApiCore-Backend/src/jobs/jobs.module.ts

@@ -21,6 +21,7 @@ import { JobRegistry, JOBS } from './job-registry';
 import { RekeyJob } from './rekey.job';
 import { TimeEventsStep } from './steps/time-events.step';
 import { TaskTemplatesJob } from './task-templates.job';
+import { VoiceTranscribeJob } from './voice-transcribe.job';
 
 const JOB_CLASSES = [
   DailyEvaluationJob,
@@ -28,6 +29,7 @@ const JOB_CLASSES = [
   CleanupJob,
   AppBackupJob,
   RekeyJob,
+  VoiceTranscribeJob,
 ];
 
 /**

ApiCore-Backend/src/jobs/voice-transcribe.job.spec.ts

@@ -0,0 +1,79 @@
+import { mkdtemp, readdir, rm } from 'node:fs/promises';
+import { tmpdir } from 'node:os';
+import path from 'node:path';
+import { PrismaService } from '../prisma/prisma.service';
+import * as claims from '../voice/claims/voice-claims';
+import * as retention from '../voice/voice-retention';
+import { VoiceTranscribeJob } from './voice-transcribe.job';
+
+describe('VoiceTranscribeJob', () => {
+  let dir: string;
+  let job: VoiceTranscribeJob;
+  let retentionSpy: jest.SpyInstance;
+  let staleSpy: jest.SpyInstance;
+  let claimSpy: jest.SpyInstance;
+  const tx = {};
+  const prisma = {
+    $transaction: (fn: (t: typeof tx) => Promise<unknown>) => fn(tx),
+  } as unknown as PrismaService;
+
+  beforeEach(async () => {
+    dir = await mkdtemp(path.join(tmpdir(), 'voice-job-'));
+    process.env.VOICE_WORK_DIR = dir;
+    retentionSpy = jest
+      .spyOn(retention, 'expireVoiceContent')
+      .mockResolvedValue({
+        audioExpired: 2,
+        contentExpired: 1,
+        inactiveOwnersWiped: 0,
+      });
+    staleSpy = jest
+      .spyOn(claims, 'releaseStaleVoiceClaims')
+      .mockResolvedValue([]);
+    claimSpy = jest.spyOn(claims, 'claimVoiceCaptures').mockResolvedValue([]);
+    job = new VoiceTranscribeJob(prisma);
+  });
+  afterEach(async () => {
+    delete process.env.VOICE_WORK_DIR;
+    jest.restoreAllMocks();
+    await rm(dir, { recursive: true, force: true });
+  });
+
+  it('is named voice-transcribe', () => {
+    expect(job.name).toBe('voice-transcribe');
+  });
+
+  it('refuses a missing or unknown phase', async () => {
+    await expect(job.run([])).rejects.toThrow(/exactly one phase argument/);
+    await expect(job.run(['--phase=whisper'])).rejects.toThrow(
+      /exactly one phase argument/,
+    );
+    await expect(job.run(['--phase=fetch', '--phase=ingest'])).rejects.toThrow(
+      /exactly one phase argument/,
+    );
+  });
+
+  it('fetch ends quickly without work and writes no manifest', async () => {
+    const result = await job.run(['--phase=fetch']);
+
+    expect(result).toMatchObject({
+      claimed: 0,
+      audioExpired: 2,
+      contentExpired: 1,
+    });
+    expect(retentionSpy).toHaveBeenCalledTimes(1);
+    expect(staleSpy).toHaveBeenCalledWith(tx, 'transcribe', {});
+    expect(claimSpy).toHaveBeenCalledWith(prisma, 'transcribe', {
+      limit: 5,
+      maxTotalSec: 600,
+    });
+    expect(await readdir(dir)).not.toContain('manifest.json');
+    await expect(readdir(path.join(dir, 'in'))).resolves.toEqual([]);
+  });
+
+  it('ingest without a manifest does nothing', async () => {
+    const result = await job.run(['--phase=ingest']);
+
+    expect(result).toEqual({ ingested: 0, failed: 0, retried: 0, lost: 0 });
+  });
+});

ApiCore-Backend/src/jobs/voice-transcribe.job.ts

@@ -0,0 +1,282 @@
+import { Injectable, Logger } from '@nestjs/common';
+import { Prisma } from '../../generated/prisma';
+import { notifyWorker, WAKE_CHANNELS } from '../common/worker-wakeup';
+import { PrismaService } from '../prisma/prisma.service';
+import {
+  claimVoiceCaptures,
+  releaseStaleVoiceClaims,
+  settleVoiceFailure,
+  settleVoiceSuccess,
+  VoiceClaim,
+} from '../voice/claims/voice-claims';
+import { sealTranscript } from '../voice/core/transcript';
+import { openVoiceBytes, voiceAad } from '../voice/core/voice-crypto';
+import {
+  clearWorkDir,
+  readManifest,
+  readResults,
+  WhisperResult,
+  workDirFromEnv,
+  writeInputs,
+} from '../voice/transcribe/work-dir';
+import { recordVoiceCaptureFailed } from '../voice/voice-failure-hook';
+import { expireVoiceContent } from '../voice/voice-retention';
+import { Job, JobResult } from './job';
+import { JobName } from './job-names';
+
+/** Per run: at most 5 notes and 600 seconds of audio (spec 4.2). */
+export const VOICE_FETCH_LIMIT = 5;
+export const VOICE_FETCH_MAX_SEC = 600;
+/** Whisper text shorter than this is no speech (spec 6.3). */
+const MIN_TEXT_CHARS = 5;
+const MIN_DURATION_SEC = 1;
+const MAX_DURATION_SEC = 240;
+
+type Phase = 'claim' | 'ingest';
+type ItemOutcome = 'ingested' | 'failed' | 'retried' | 'lost';
+
+export interface VoiceFetchOptions {
+  /** Extra condition on "VoiceCapture" (tests scope their runs to own rows). */
+  filter?: Prisma.Sql;
+}
+
+function parsePhase(args: readonly string[]): Phase {
+  if (args.length === 1 && args[0] === '--phase=fetch') return 'claim';
+  if (args.length === 1 && args[0] === '--phase=ingest') return 'ingest';
+  throw new Error('voice-transcribe needs exactly one phase argument');
+}
+
+/**
+ * CronJob `apicore-job-voice-transcribe`, the two Node halves around the
+ * Whisper container. `fetch` runs the retention rules, claims notes,
+ * decrypts their audio in memory and hands it over in the RAM work dir;
+ * `ingest` takes Whisper's results, seals the text, deletes the audio and
+ * wakes the worker - each note in one transaction, guarded by its claim
+ * token. Content is never logged: only ids, counts and fixed codes.
+ */
+@Injectable()
+export class VoiceTranscribeJob implements Job {
+  private readonly logger = new Logger(VoiceTranscribeJob.name);
+  readonly name: JobName = 'voice-transcribe';
+
+  constructor(private readonly prisma: PrismaService) {}
+
+  async run(args: readonly string[]): Promise<JobResult> {
+    return parsePhase(args) === 'claim' ? this.runFetchPhase() : this.ingest();
+  }
+
+  async runFetchPhase(options: VoiceFetchOptions = {}): Promise<JobResult> {
+    const dir = workDirFromEnv();
+    await clearWorkDir(dir);
+    const filter = options.filter ? { filter: options.filter } : {};
+    const retention = await expireVoiceContent(this.prisma, filter);
+    const staleReleased = await this.releaseStale(filter);
+    const claims = await claimVoiceCaptures(this.prisma, 'transcribe', {
+      limit: VOICE_FETCH_LIMIT,
+      maxTotalSec: VOICE_FETCH_MAX_SEC,
+      ...filter,
+    });
+    const inputs: { claim: VoiceClaim; audio: Buffer }[] = [];
+    for (const claim of claims) {
+      const audio = await this.decryptAudio(claim);
+      if (audio === null) {
+        await this.failAttempt(claim, 'TRANSCRIBE_FAILED');
+      } else {
+        inputs.push({ claim, audio });
+      }
+    }
+    if (inputs.length > 0) {
+      await writeInputs(dir, inputs);
+    }
+    return {
+      claimed: claims.length,
+      written: inputs.length,
+      staleReleased,
+      ...retention,
+    };
+  }
+
+  async ingest(): Promise<JobResult> {
+    const dir = workDirFromEnv();
+    const counts: Record<ItemOutcome, number> = {
+      ingested: 0,
+      failed: 0,
+      retried: 0,
+      lost: 0,
+    };
+    try {
+      const manifest = await readManifest(dir);
+      if (manifest === null) {
+        return counts;
+      }
+      const results = await readResults(dir, manifest);
+      let errors = 0;
+      for (const item of manifest.items) {
+        try {
+          const outcome = await this.ingestOne(
+            item.captureId,
+            item.claimToken,
+            results.get(item.captureId) ?? null,
+          );
+          counts[outcome] += 1;
+        } catch (error: unknown) {
+          errors += 1;
+          // The message of a failed seal or query holds no content, but
+          // keep to the id anyway.
+          this.logger.error(
+            `Ingest failed for voice note ${item.captureId}: ${error instanceof Error ? error.name : 'error'}`,
+          );
+        }
+      }
+      if (errors > 0) {
+        throw new Error(
+          `voice ingest failed for ${errors} of ${manifest.items.length} notes (${JSON.stringify(counts)})`,
+        );
+      }
+      return counts;
+    } finally {
+      await clearWorkDir(dir);
+    }
+  }
+
+  private releaseStale(filter: VoiceFetchOptions): Promise<number> {
+    return this.prisma.$transaction(async (tx) => {
+      const released = await releaseStaleVoiceClaims(tx, 'transcribe', filter);
+      for (const { id, code } of released) {
+        if (code !== null) {
+          await recordVoiceCaptureFailed(tx, id, 'TRANSCRIBE_FAILED');
+        }
+      }
+      return released.length;
+    });
+  }
+
+  private async decryptAudio(claim: VoiceClaim): Promise<Buffer | null> {
+    const row = await this.prisma.voiceCaptureAudio.findUnique({
+      where: { captureId: claim.id },
+    });
+    if (!row) {
+      return null;
+    }
+    try {
+      return openVoiceBytes(
+        Buffer.from(row.dataEnc),
+        voiceAad(claim.id, 'audio'),
+      );
+    } catch {
+      this.logger.warn(`Audio of voice note ${claim.id} cannot be opened`);
+      return null;
+    }
+  }
+
+  private failAttempt(
+    claim: VoiceClaim,
+    code: 'TRANSCRIBE_FAILED',
+  ): Promise<'retry' | 'failed' | 'lost'> {
+    return this.prisma.$transaction(async (tx) => {
+      const outcome = await settleVoiceFailure(tx, 'transcribe', claim, code);
+      if (outcome === 'failed') {
+        await recordVoiceCaptureFailed(tx, claim.id, code);
+      }
+      return outcome;
+    });
+  }
+
+  /** The claim as the database holds it now; null if it is gone. */
+  private async loadClaim(
+    captureId: string,
+    claimToken: string,
+  ): Promise<VoiceClaim | null> {
+    const rows = await this.prisma.$queryRaw<VoiceClaim[]>(Prisma.sql`
+      SELECT "id", "claimToken", "attempts", "ownerUserId", "colonyId",
+             "audioMime", "durationSec"
+      FROM "VoiceCapture"
+      WHERE "id" = ${captureId} AND "claimToken" = ${claimToken}
+        AND "status" = 'TRANSCRIBING'`);
+    return rows[0] ?? null;
+  }
+
+  private async ingestOne(
+    captureId: string,
+    claimToken: string,
+    result: WhisperResult | null,
+  ): Promise<ItemOutcome> {
+    const claim = await this.loadClaim(captureId, claimToken);
+    if (claim === null) {
+      return 'lost';
+    }
+    if (result === null || result.error === 'DECODE_FAILED') {
+      return this.outcomeOf(await this.failAttempt(claim, 'TRANSCRIBE_FAILED'));
+    }
+    const noSpeech =
+      result.error ??
+      (result.text.trim().length < MIN_TEXT_CHARS ? 'NO_SPEECH' : null);
+    if (noSpeech === 'NO_SPEECH' || noSpeech === 'TOO_LONG') {
+      return this.finishFailed(claim, noSpeech);
+    }
+    if (result.durationSec > MAX_DURATION_SEC) {
+      return this.finishFailed(claim, 'TOO_LONG');
+    }
+    return this.finishTranscribed(claim, result);
+  }
+
+  private outcomeOf(settled: 'retry' | 'failed' | 'lost'): ItemOutcome {
+    return settled === 'retry'
+      ? 'retried'
+      : settled === 'failed'
+        ? 'failed'
+        : 'lost';
+  }
+
+  /** Terminal failure of the note itself: FAILED with the code, audio gone. */
+  private finishFailed(
+    claim: VoiceClaim,
+    code: 'NO_SPEECH' | 'TOO_LONG',
+  ): Promise<ItemOutcome> {
+    return this.prisma.$transaction(async (tx) => {
+      const changed = await tx.$executeRaw`
+        UPDATE "VoiceCapture"
+        SET "status" = 'FAILED', "lastErrorCode" = ${code},
+            "attempts" = "attempts" + 1, "updatedAt" = now(),
+            "claimedAt" = NULL, "claimToken" = NULL
+        WHERE "id" = ${claim.id} AND "status" = 'TRANSCRIBING'
+          AND "claimToken" = ${claim.claimToken}`;
+      if (changed !== 1) {
+        return 'lost';
+      }
+      await tx.voiceCaptureAudio.deleteMany({ where: { captureId: claim.id } });
+      await recordVoiceCaptureFailed(tx, claim.id, code);
+      return 'failed';
+    });
+  }
+
+  private finishTranscribed(
+    claim: VoiceClaim,
+    result: WhisperResult,
+  ): Promise<ItemOutcome> {
+    const durationSec = Math.max(
+      MIN_DURATION_SEC,
+      Math.round(result.durationSec),
+    );
+    const sealed = sealTranscript(claim.id, {
+      v: 1,
+      text: result.text,
+      durationSec: result.durationSec,
+      segments: result.segments,
+    });
+    return this.prisma.$transaction(async (tx) => {
+      const settled = await settleVoiceSuccess(
+        tx,
+        'transcribe',
+        claim,
+        Prisma.sql`"transcriptEnc" = ${sealed}, "durationSec" = ${durationSec}`,
+      );
+      if (!settled) {
+        return 'lost';
+      }
+      await tx.voiceCaptureAudio.deleteMany({ where: { captureId: claim.id } });
+      await notifyWorker(tx, WAKE_CHANNELS.voiceExtraction);
+      return 'ingested';
+    });
+  }
+}