feat(anki): add media timing review before card creation (#203)

src/core/services/config-hot-reload.test.ts

@@ -33,6 +33,7 @@ test('classifyConfigHotReloadDiff treats safe nested config paths as hot-reloada
   next.ankiConnect.deck = 'Mining';
   next.ankiConnect.media.normalizeAudio = !prev.ankiConnect.media.normalizeAudio;
   next.ankiConnect.media.mirrorMpvVolume = !prev.ankiConnect.media.mirrorMpvVolume;
+  next.ankiConnect.media.reviewTiming = !prev.ankiConnect.media.reviewTiming;
   next.ankiConnect.behavior.autoUpdateNewCards = !prev.ankiConnect.behavior.autoUpdateNewCards;
   next.ankiConnect.knownWords.highlightEnabled = !prev.ankiConnect.knownWords.highlightEnabled;
   next.ankiConnect.knownWords.refreshMinutes = prev.ankiConnect.knownWords.refreshMinutes + 5;
@@ -69,6 +70,7 @@ test('classifyConfigHotReloadDiff treats safe nested config paths as hot-reloada
       'ankiConnect.deck',
       'ankiConnect.media.normalizeAudio',
       'ankiConnect.media.mirrorMpvVolume',
+      'ankiConnect.media.reviewTiming',
       'ankiConnect.behavior.autoUpdateNewCards',
       'ankiConnect.knownWords.highlightEnabled',
       'ankiConnect.knownWords.refreshMinutes',

src/core/services/config-hot-reload.ts

@@ -70,6 +70,7 @@ const HOT_RELOAD_EXACT_OR_PREFIX_PATHS = [
   'ankiConnect.deck',
   'ankiConnect.media.normalizeAudio',
   'ankiConnect.media.mirrorMpvVolume',
+  'ankiConnect.media.reviewTiming',
   'ankiConnect.behavior.autoUpdateNewCards',
   'ankiConnect.knownWords.highlightEnabled',
   'ankiConnect.knownWords.refreshMinutes',

src/core/services/immersion-tracker/lexical-rollups.test.ts

@@ -306,9 +306,11 @@ test('vocabulary charts use complete top-word and lexical rollup data', () => {
       `INSERT INTO imm_words(headword, word, reading, first_seen, last_seen, frequency)
        VALUES (?, ?, '', 1700000000, 1700000000, ?)`,
     );
+    db.exec('BEGIN');
     for (let index = 0; index < 501; index += 1) {
       insertWord.run(`語${index}`, `語${index}`, index === 500 ? 10_000 : 1);
     }
+    db.exec('COMMIT');
 
     const charts = getVocabularyChartData(db);
 

src/core/services/ipc.test.ts

@@ -648,6 +648,83 @@ test('registerIpcHandlers exposes playback window activation request', async ()
   assert.deepEqual(calls, ['activate']);
 });
 
+test('registerIpcHandlers accepts the keep-without-media timing decision', async () => {
+  const { registrar, handlers } = createFakeIpcRegistrar();
+  const requests: unknown[] = [];
+  registerIpcHandlers(
+    createRegisterIpcDeps({
+      resolveMediaTimingReview: async (request) => {
+        requests.push(request);
+        return { ok: true };
+      },
+    }),
+    registrar,
+  );
+
+  const handler = handlers.handle.get(IPC_CHANNELS.request.mediaTimingReviewResolve);
+  assert.ok(handler);
+  assert.deepEqual(
+    await handler!({}, { reviewId: 'review-1', decision: { action: 'skip-media' } }),
+    { ok: true },
+  );
+  assert.deepEqual(requests, [{ reviewId: 'review-1', decision: { action: 'skip-media' } }]);
+});
+
+test('registerIpcHandlers validates and forwards combined timing review text', async () => {
+  const { registrar, handlers } = createFakeIpcRegistrar();
+  const requests: unknown[] = [];
+  registerIpcHandlers(
+    createRegisterIpcDeps({
+      resolveMediaTimingReview: async (request) => {
+        requests.push(request);
+        return { ok: true };
+      },
+    }),
+    registrar,
+  );
+
+  const handler = handlers.handle.get(IPC_CHANNELS.request.mediaTimingReviewResolve);
+  assert.ok(handler);
+  assert.deepEqual(
+    await handler!(
+      {},
+      {
+        reviewId: 'review-1',
+        decision: {
+          action: 'confirm',
+          startTime: 10,
+          endTime: 12,
+          text: '前の行 対象の行',
+        },
+      },
+    ),
+    { ok: true },
+  );
+  assert.deepEqual(requests, [
+    {
+      reviewId: 'review-1',
+      decision: {
+        action: 'confirm',
+        startTime: 10,
+        endTime: 12,
+        text: '前の行 対象の行',
+      },
+    },
+  ]);
+
+  assert.deepEqual(
+    await handler!(
+      {},
+      {
+        reviewId: 'review-1',
+        decision: { action: 'confirm', startTime: 10, endTime: 12, text: '   ' },
+      },
+    ),
+    { ok: false, message: 'Timing review is unavailable.' },
+  );
+  assert.equal(requests.length, 1);
+});
+
 test('registerIpcHandlers forwards yomitan lookup tracking commands to immersion tracker', () => {
   const { registrar, handlers } = createFakeIpcRegistrar();
   const calls: string[] = [];

src/core/services/ipc.ts

@@ -19,6 +19,13 @@ import type {
   YoutubePickerResolveRequest,
   YoutubePickerResolveResult,
 } from '../../types';
+import type {
+  MediaTimingReviewActionResult,
+  MediaTimingReviewPreviewRequest,
+  MediaTimingReviewResolveRequest,
+  MediaTimingReviewWaveformRequest,
+  MediaTimingReviewWaveformResult,
+} from '../../types/anki';
 import { IPC_CHANNELS, type OverlayHostedModal } from '../../shared/ipc/contracts';
 import {
   parseMpvCommand,
@@ -99,6 +106,16 @@ export interface IpcServiceDeps {
   onYoutubePickerResolve: (
     request: YoutubePickerResolveRequest,
   ) => Promise<YoutubePickerResolveResult>;
+  previewMediaTimingReview?: (
+    request: MediaTimingReviewPreviewRequest,
+  ) => Promise<MediaTimingReviewActionResult>;
+  getMediaTimingReviewWaveform?: (
+    request: MediaTimingReviewWaveformRequest,
+  ) => Promise<MediaTimingReviewWaveformResult>;
+  stopMediaTimingReviewPreview?: (reviewId: string) => Promise<MediaTimingReviewActionResult>;
+  resolveMediaTimingReview?: (
+    request: MediaTimingReviewResolveRequest,
+  ) => MediaTimingReviewActionResult | Promise<MediaTimingReviewActionResult>;
   getAnkiConnectStatus: () => boolean;
   getRuntimeOptions: () => unknown;
   setRuntimeOption: (id: RuntimeOptionId, value: RuntimeOptionValue) => unknown;
@@ -222,6 +239,72 @@ function parseOverlayNotificationActionPayload(
   return { notificationId, actionId, ...(typeof noteId === 'number' ? { noteId } : {}) };
 }
 
+function parseMediaTimingReviewPreviewRequest(
+  payload: unknown,
+): MediaTimingReviewPreviewRequest | null {
+  if (!payload || typeof payload !== 'object') return null;
+  const record = payload as Record<string, unknown>;
+  if (
+    typeof record.reviewId !== 'string' ||
+    !record.reviewId ||
+    typeof record.startTime !== 'number' ||
+    !Number.isFinite(record.startTime) ||
+    typeof record.endTime !== 'number' ||
+    !Number.isFinite(record.endTime)
+  ) {
+    return null;
+  }
+  return {
+    reviewId: record.reviewId,
+    startTime: record.startTime,
+    endTime: record.endTime,
+  };
+}
+
+function parseMediaTimingReviewWaveformRequest(
+  payload: unknown,
+): MediaTimingReviewWaveformRequest | null {
+  return parseMediaTimingReviewPreviewRequest(payload);
+}
+
+function parseMediaTimingReviewResolveRequest(
+  payload: unknown,
+): MediaTimingReviewResolveRequest | null {
+  if (!payload || typeof payload !== 'object') return null;
+  const record = payload as Record<string, unknown>;
+  if (typeof record.reviewId !== 'string' || !record.reviewId) return null;
+  const decision = record.decision;
+  if (!decision || typeof decision !== 'object') return null;
+  const decisionRecord = decision as Record<string, unknown>;
+  if (
+    decisionRecord.action === 'use-original' ||
+    decisionRecord.action === 'skip-media' ||
+    decisionRecord.action === 'discard'
+  ) {
+    return { reviewId: record.reviewId, decision: { action: decisionRecord.action } };
+  }
+  if (
+    decisionRecord.action === 'confirm' &&
+    typeof decisionRecord.startTime === 'number' &&
+    Number.isFinite(decisionRecord.startTime) &&
+    typeof decisionRecord.endTime === 'number' &&
+    Number.isFinite(decisionRecord.endTime) &&
+    (decisionRecord.text === undefined ||
+      (typeof decisionRecord.text === 'string' && decisionRecord.text.trim().length > 0))
+  ) {
+    return {
+      reviewId: record.reviewId,
+      decision: {
+        action: 'confirm',
+        startTime: decisionRecord.startTime,
+        endTime: decisionRecord.endTime,
+        ...(decisionRecord.text === undefined ? {} : { text: decisionRecord.text }),
+      },
+    };
+  }
+  return null;
+}
+
 export interface IpcDepsRuntimeOptions {
   getMainWindow: () => WindowLike | null;
   getVisibleOverlayVisibility: () => boolean;
@@ -278,6 +361,10 @@ export interface IpcDepsRuntimeOptions {
   onYoutubePickerResolve: (
     request: YoutubePickerResolveRequest,
   ) => Promise<YoutubePickerResolveResult>;
+  previewMediaTimingReview?: IpcServiceDeps['previewMediaTimingReview'];
+  getMediaTimingReviewWaveform?: IpcServiceDeps['getMediaTimingReviewWaveform'];
+  stopMediaTimingReviewPreview?: IpcServiceDeps['stopMediaTimingReviewPreview'];
+  resolveMediaTimingReview?: IpcServiceDeps['resolveMediaTimingReview'];
   getAnkiConnectStatus: () => boolean;
   getRuntimeOptions: () => unknown;
   setRuntimeOption: (id: RuntimeOptionId, value: RuntimeOptionValue) => unknown;
@@ -371,6 +458,10 @@ export function createIpcDepsRuntime(options: IpcDepsRuntimeOptions): IpcService
       options.activatePlaybackWindowForOverlayInteraction ?? (() => false),
     runSubsyncManual: options.runSubsyncManual,
     onYoutubePickerResolve: options.onYoutubePickerResolve,
+    previewMediaTimingReview: options.previewMediaTimingReview,
+    getMediaTimingReviewWaveform: options.getMediaTimingReviewWaveform,
+    stopMediaTimingReviewPreview: options.stopMediaTimingReviewPreview,
+    resolveMediaTimingReview: options.resolveMediaTimingReview,
     getAnkiConnectStatus: options.getAnkiConnectStatus,
     getRuntimeOptions: options.getRuntimeOptions,
     setRuntimeOption: options.setRuntimeOption,
@@ -498,6 +589,46 @@ export function registerIpcHandlers(deps: IpcServiceDeps, ipc: IpcMainRegistrar
     },
   );
 
+  ipc.handle(
+    IPC_CHANNELS.request.mediaTimingReviewPreview,
+    async (_event: unknown, payload: unknown) => {
+      const request = parseMediaTimingReviewPreviewRequest(payload);
+      if (!request || !deps.previewMediaTimingReview) {
+        return { ok: false, message: 'Timing preview is unavailable.' };
+      }
+      return await deps.previewMediaTimingReview(request);
+    },
+  );
+  ipc.handle(
+    IPC_CHANNELS.request.mediaTimingReviewWaveform,
+    async (_event: unknown, payload: unknown) => {
+      const request = parseMediaTimingReviewWaveformRequest(payload);
+      if (!request || !deps.getMediaTimingReviewWaveform) {
+        return { ok: false, message: 'Timing waveform is unavailable.' };
+      }
+      return await deps.getMediaTimingReviewWaveform(request);
+    },
+  );
+  ipc.handle(
+    IPC_CHANNELS.request.mediaTimingReviewStopPreview,
+    async (_event: unknown, reviewId: unknown) => {
+      if (typeof reviewId !== 'string' || !reviewId || !deps.stopMediaTimingReviewPreview) {
+        return { ok: false, message: 'Timing preview is unavailable.' };
+      }
+      return await deps.stopMediaTimingReviewPreview(reviewId);
+    },
+  );
+  ipc.handle(
+    IPC_CHANNELS.request.mediaTimingReviewResolve,
+    async (_event: unknown, payload: unknown) => {
+      const request = parseMediaTimingReviewResolveRequest(payload);
+      if (!request || !deps.resolveMediaTimingReview) {
+        return { ok: false, message: 'Timing review is unavailable.' };
+      }
+      return await deps.resolveMediaTimingReview(request);
+    },
+  );
+
   ipc.on(IPC_CHANNELS.command.openYomitanSettings, () => {
     deps.openYomitanSettings();
   });

src/core/services/media-timing-preview.test.ts

@@ -0,0 +1,291 @@
+import assert from 'node:assert/strict';
+import { EventEmitter } from 'node:events';
+import net from 'node:net';
+import { describe, test } from 'node:test';
+import { buildMediaTimingPreviewArgs, MediaTimingPreviewSession } from './media-timing-preview';
+
+describe('buildMediaTimingPreviewArgs', () => {
+  test('creates a hidden audio-only reusable mpv session', () => {
+    const args = buildMediaTimingPreviewArgs('/tmp/review.sock', {
+      mediaPath: '/video/show.mkv',
+      audioTrackId: 3,
+      volume: 55,
+    });
+
+    assert.ok(args.includes('--no-video'));
+    assert.ok(args.includes('--force-window=no'));
+    assert.ok(args.includes('--idle=yes'));
+    assert.ok(args.includes('--pause=yes'));
+    assert.ok(args.includes('--input-ipc-server=/tmp/review.sock'));
+    assert.ok(args.includes('--aid=3'));
+    assert.ok(args.includes('--volume=55'));
+    assert.equal(args.at(-2), '--');
+    assert.equal(args.at(-1), '/video/show.mkv');
+  });
+
+  test('keeps source timestamps for cached remote windows', () => {
+    const args = buildMediaTimingPreviewArgs('/tmp/review.sock', {
+      mediaPath: '/tmp/window.mkv',
+      absoluteTimestamps: true,
+    });
+
+    assert.ok(args.includes('--rebase-start-time=no'));
+    assert.equal(
+      buildMediaTimingPreviewArgs('/tmp/review.sock', { mediaPath: '/video/show.mkv' }).includes(
+        '--rebase-start-time=no',
+      ),
+      false,
+    );
+  });
+
+  test('separates an option-like media path without adding optional audio arguments', () => {
+    const args = buildMediaTimingPreviewArgs('/tmp/review.sock', {
+      mediaPath: '--fullscreen',
+    });
+
+    assert.equal(args.at(-2), '--');
+    assert.equal(args.at(-1), '--fullscreen');
+    assert.equal(
+      args.some((arg) => arg.startsWith('--aid=')),
+      false,
+    );
+    assert.equal(
+      args.some((arg) => arg.startsWith('--volume=')),
+      false,
+    );
+  });
+});
+
+test('preview session handles socket errors after connecting', async () => {
+  const socket = new net.Socket();
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => child as never,
+    connectSocket: () => {
+      queueMicrotask(() => socket.emit('connect'));
+      return socket;
+    },
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  await session.start({ mediaPath: '/video/show.mkv' });
+  assert.doesNotThrow(() => socket.emit('error', new Error('pipe closed')));
+  await assert.rejects(session.play(1, 2), /not ready/);
+  session.dispose();
+});
+
+test('preview session keeps failed connection errors handled through destruction', async () => {
+  const socket = new EventEmitter() as EventEmitter & {
+    destroy: () => void;
+  };
+  socket.destroy = () => {
+    socket.emit('error', new Error('socket failed again while closing'));
+  };
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  const times = [0, 0, 0, 6_000];
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => child as never,
+    connectSocket: () => {
+      queueMicrotask(() => socket.emit('error', new Error('connection failed')));
+      return socket as never;
+    },
+    now: () => times.shift() ?? 6_000,
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  await assert.rejects(session.start({ mediaPath: '/video/show.mkv' }), /Timed out starting/);
+});
+
+test('preview session rejects a connection that finishes after disposal', async () => {
+  const socket = new net.Socket();
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => child as never,
+    connectSocket: () => socket,
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  const pendingStart = session.start({ mediaPath: '-playlist' });
+  session.dispose();
+  socket.emit('connect');
+
+  await assert.rejects(pendingStart, /closed/);
+  assert.equal(socket.destroyed, true);
+});
+
+test('preview session shares one startup across concurrent start calls', async () => {
+  const socket = new net.Socket();
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  let spawnCount = 0;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => {
+      spawnCount += 1;
+      return child as never;
+    },
+    connectSocket: () => socket,
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  const firstStart = session.start({ mediaPath: '/video/show.mkv' });
+  const secondStart = session.start({ mediaPath: '/video/show.mkv' });
+  socket.emit('connect');
+
+  await Promise.all([firstStart, secondStart]);
+  assert.equal(spawnCount, 1);
+  session.dispose();
+});
+
+test('preview session can start again after a startup failure', async () => {
+  const socket = new net.Socket();
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  let spawnCount = 0;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => {
+      spawnCount += 1;
+      if (spawnCount === 1) throw new Error('spawn failed');
+      return child as never;
+    },
+    connectSocket: () => {
+      queueMicrotask(() => socket.emit('connect'));
+      return socket;
+    },
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  await assert.rejects(session.start({ mediaPath: '/video/show.mkv' }), /spawn failed/);
+  await session.start({ mediaPath: '/video/show.mkv' });
+  assert.equal(spawnCount, 2);
+  session.dispose();
+});
+
+test('preview session bounds a connection attempt that never settles', async () => {
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  let nowMs = 0;
+  let connectAttempts = 0;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => child as never,
+    connectSocket: () => {
+      connectAttempts += 1;
+      const socket = new net.Socket();
+      socket.destroy = (() => {
+        socket.emit('error', new Error('socket failed while timing out'));
+        return socket;
+      }) as typeof socket.destroy;
+      return socket;
+    },
+    now: () => {
+      const current = nowMs;
+      nowMs += 1_000;
+      return current;
+    },
+    schedule: (callback) => setTimeout(callback, 0),
+    cancelSchedule: (timeout) => clearTimeout(timeout),
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+
+  await assert.rejects(session.start({ mediaPath: '/video/show.mkv' }), /Timed out starting/);
+  assert.equal(connectAttempts, 1);
+});
+
+function createFakeSocket() {
+  const socket = new EventEmitter() as EventEmitter & {
+    destroyed: boolean;
+    write: (data: string) => boolean;
+    end: () => void;
+    destroy: () => void;
+    off: EventEmitter['off'];
+  };
+  const writes: string[] = [];
+  socket.destroyed = false;
+  socket.write = (data) => {
+    writes.push(data);
+    return true;
+  };
+  socket.end = () => undefined;
+  socket.destroy = () => {
+    socket.destroyed = true;
+  };
+  return { socket, writes };
+}
+
+test('preview session plays once to the clip end and reports when mpv has drained it', async () => {
+  const { socket, writes } = createFakeSocket();
+  const child = new EventEmitter() as EventEmitter & { kill: () => boolean };
+  child.kill = () => true;
+  const session = new MediaTimingPreviewSession({
+    platform: 'linux',
+    spawnProcess: () => child as never,
+    connectSocket: () => {
+      queueMicrotask(() => socket.emit('connect'));
+      return socket as never;
+    },
+    removeSocketFile: () => undefined,
+    createSocketPath: () => '/tmp/review.sock',
+  });
+  let endedCount = 0;
+  session.onPlaybackEnded(() => {
+    endedCount += 1;
+  });
+  const property = (name: string, data: boolean): string =>
+    `${JSON.stringify({ event: 'property-change', name, data })}\n`;
+
+  await session.start({ mediaPath: '/video/show.mkv' });
+  assert.deepEqual(
+    writes.map((line) => JSON.parse(line).command),
+    [
+      ['observe_property', 1, 'eof-reached'],
+      ['observe_property', 2, 'pause'],
+    ],
+  );
+  // The observers' initial replies describe the idle paused player, not a finished preview.
+  socket.emit('data', property('eof-reached', false) + property('pause', true));
+  assert.equal(endedCount, 0);
+
+  writes.length = 0;
+  await session.play(12.25, 14.5);
+  assert.deepEqual(
+    writes.map((line) => JSON.parse(line).command),
+    [
+      ['set_property', 'pause', true],
+      ['seek', 12.25, 'absolute+exact'],
+      ['set_property', 'end', '14.500'],
+      ['set_property', 'pause', false],
+    ],
+  );
+
+  // Events may arrive split across chunks. The decoder passing `end` flips eof-reached while
+  // audio still drains; only the keep-open pause that follows marks the preview as finished.
+  socket.emit('data', property('eof-reached', false) + property('pause', false).slice(0, 20));
+  socket.emit('data', property('pause', false).slice(20) + property('eof-reached', true));
+  assert.equal(endedCount, 0);
+  socket.emit('data', property('pause', true));
+  assert.equal(endedCount, 1);
+  socket.emit('data', property('pause', true));
+  assert.equal(endedCount, 1);
+
+  // Stopping early pauses without an end signal, and a later real EOF is not a preview end.
+  await session.play(1, 2);
+  socket.emit('data', property('eof-reached', false) + property('pause', false));
+  await session.stop();
+  socket.emit('data', property('pause', true) + property('eof-reached', true));
+  assert.equal(endedCount, 1);
+  session.dispose();
+});

src/core/services/media-timing-preview.ts

@@ -0,0 +1,394 @@
+import { spawn, type ChildProcess } from 'child_process';
+import fs from 'fs';
+import net, { type Socket } from 'net';
+import os from 'os';
+import path from 'path';
+import { randomUUID } from 'crypto';
+
+const CONNECT_TIMEOUT_MS = 5_000;
+const CONNECT_ATTEMPT_TIMEOUT_MS = 500;
+const CONNECT_RETRY_MS = 40;
+/**
+ * mpv flips eof-reached as soon as the decoder passes `end`, while its audio buffer is still
+ * draining; keep-open then pauses once the buffer has played out. A preview has ended when
+ * both have happened.
+ */
+const EOF_OBSERVER_ID = 1;
+const PAUSE_OBSERVER_ID = 2;
+
+export interface MediaTimingPreviewStartOptions {
+  mediaPath: string;
+  executablePath?: string;
+  audioTrackId?: number;
+  volume?: number;
+  /** The file keeps source timestamps (a cached remote window); seek with the original times. */
+  absoluteTimestamps?: boolean;
+}
+
+type PreviewProcess = Pick<ChildProcess, 'kill' | 'once'>;
+
+interface MediaTimingPreviewDeps {
+  platform: NodeJS.Platform;
+  spawnProcess: (command: string, args: string[]) => PreviewProcess;
+  connectSocket: (socketPath: string) => Socket;
+  now: () => number;
+  schedule: (callback: () => void, delayMs: number) => ReturnType<typeof setTimeout>;
+  cancelSchedule: (timeout: ReturnType<typeof setTimeout>) => void;
+  removeSocketFile: (socketPath: string) => void;
+  createSocketPath: () => string;
+}
+
+export function buildMediaTimingPreviewArgs(
+  socketPath: string,
+  options: MediaTimingPreviewStartOptions,
+): string[] {
+  const args = [
+    '--no-config',
+    '--no-video',
+    '--audio-display=no',
+    '--force-window=no',
+    '--idle=yes',
+    '--keep-open=yes',
+    '--pause=yes',
+    '--terminal=no',
+    '--msg-level=all=warn',
+    `--input-ipc-server=${socketPath}`,
+  ];
+  if (typeof options.audioTrackId === 'number' && Number.isInteger(options.audioTrackId)) {
+    args.push(`--aid=${options.audioTrackId}`);
+  }
+  if (typeof options.volume === 'number' && Number.isFinite(options.volume)) {
+    args.push(`--volume=${Math.max(0, options.volume)}`);
+  }
+  if (options.absoluteTimestamps) {
+    args.push('--rebase-start-time=no');
+  }
+  args.push('--', options.mediaPath);
+  return args;
+}
+
+function createDefaultSocketPath(): string {
+  const suffix = `${process.pid}-${randomUUID()}`;
+  return process.platform === 'win32'
+    ? `\\\\.\\pipe\\subminer-timing-preview-${suffix}`
+    : path.join(
+        // macOS limits Unix socket paths to 104 bytes, while its temp directory can be long.
+        process.platform === 'darwin' ? '/tmp' : os.tmpdir(),
+        `subminer-timing-preview-${suffix}.sock`,
+      );
+}
+
+function removePosixSocketFile(socketPath: string): void {
+  if (process.platform === 'win32') return;
+  try {
+    fs.unlinkSync(socketPath);
+  } catch (error) {
+    if ((error as NodeJS.ErrnoException).code !== 'ENOENT') {
+      throw error;
+    }
+  }
+}
+
+export class MediaTimingPreviewSession {
+  private readonly deps: MediaTimingPreviewDeps;
+  private socketPath: string | null = null;
+  private socket: Socket | null = null;
+  private process: PreviewProcess | null = null;
+  private startupError: Error | null = null;
+  private startPromise: Promise<void> | null = null;
+  private retryWait: {
+    timeout: ReturnType<typeof setTimeout>;
+    resolve: () => void;
+  } | null = null;
+  private disposed = false;
+  private readBuffer = '';
+  private playing = false;
+  private eofReached = false;
+  private paused = true;
+  private readonly endedListeners = new Set<() => void>();
+
+  constructor(deps: Partial<MediaTimingPreviewDeps> = {}) {
+    this.deps = {
+      platform: process.platform,
+      spawnProcess: (command, args) => spawn(command, args, { stdio: 'ignore' }),
+      connectSocket: (socketPath) => net.createConnection(socketPath),
+      now: Date.now,
+      schedule: (callback, delayMs) => setTimeout(callback, delayMs),
+      cancelSchedule: (timeout) => clearTimeout(timeout),
+      removeSocketFile: removePosixSocketFile,
+      createSocketPath: createDefaultSocketPath,
+      ...deps,
+    };
+  }
+
+  async start(options: MediaTimingPreviewStartOptions): Promise<void> {
+    if (this.disposed) throw new Error('Preview session is closed');
+    if (this.socket) return;
+    if (this.startPromise) return await this.startPromise;
+
+    const startPromise = this.startOnce(options);
+    this.startPromise = startPromise;
+    try {
+      await startPromise;
+    } catch (error) {
+      this.releaseResources();
+      throw error;
+    } finally {
+      if (this.startPromise === startPromise) this.startPromise = null;
+    }
+  }
+
+  private async startOnce(options: MediaTimingPreviewStartOptions): Promise<void> {
+    const mediaPath = options.mediaPath.trim();
+    if (!mediaPath) throw new Error('No media source is available for preview');
+
+    const socketPath = this.deps.createSocketPath();
+    this.socketPath = socketPath;
+    if (this.deps.platform !== 'win32') {
+      this.deps.removeSocketFile(socketPath);
+    }
+
+    const command = options.executablePath?.trim() || 'mpv';
+    this.startupError = null;
+    const child = this.deps.spawnProcess(
+      command,
+      buildMediaTimingPreviewArgs(socketPath, { ...options, mediaPath }),
+    );
+    this.process = child;
+    child.once('error', (error) => {
+      if (this.process !== child) return;
+      this.startupError = error;
+    });
+    child.once('exit', () => {
+      if (this.process !== child) return;
+      if (!this.socket && !this.disposed && !this.startupError) {
+        this.startupError = new Error('The hidden mpv preview player exited during startup');
+      }
+      this.socket?.destroy();
+      this.socket = null;
+      this.process = null;
+    });
+
+    await this.connectWithRetry(socketPath);
+  }
+
+  /**
+   * Plays [startTime, endTime) once. mpv stops itself at `end` and, thanks to keep-open,
+   * pauses after draining the audio device, so the listener hears the whole clip even on
+   * high-latency outputs. onPlaybackEnded fires when mpv reports the end was reached.
+   */
+  async play(startTime: number, endTime: number): Promise<void> {
+    if (!this.socket || this.socket.destroyed) {
+      throw new Error('Preview player is not ready');
+    }
+    if (!Number.isFinite(startTime) || !Number.isFinite(endTime) || endTime <= startTime) {
+      throw new Error('Preview timing is invalid');
+    }
+
+    this.playing = false;
+    this.send(['set_property', 'pause', true]);
+    this.send(['seek', startTime, 'absolute+exact']);
+    // The option parser wants a time string; a raw JSON number is not accepted for `end`.
+    this.send(['set_property', 'end', endTime.toFixed(3)]);
+    this.send(['set_property', 'pause', false]);
+    // Only the seek's eof-reached=false and the later keep-open pause count for this play.
+    this.eofReached = false;
+    this.paused = false;
+    this.playing = true;
+  }
+
+  async stop(): Promise<void> {
+    this.playing = false;
+    if (!this.socket || this.socket.destroyed) return;
+    this.send(['set_property', 'pause', true]);
+  }
+
+  onPlaybackEnded(listener: () => void): void {
+    this.endedListeners.add(listener);
+  }
+
+  private finishPlayback(): void {
+    if (!this.playing) return;
+    this.playing = false;
+    for (const listener of this.endedListeners) listener();
+  }
+
+  private handleSocketData(chunk: Buffer | string): void {
+    this.readBuffer += chunk.toString();
+    let newline = this.readBuffer.indexOf('\n');
+    while (newline !== -1) {
+      const line = this.readBuffer.slice(0, newline).trim();
+      this.readBuffer = this.readBuffer.slice(newline + 1);
+      newline = this.readBuffer.indexOf('\n');
+      if (!line) continue;
+      let message: unknown;
+      try {
+        message = JSON.parse(line);
+      } catch {
+        continue;
+      }
+      if (
+        typeof message === 'object' &&
+        message !== null &&
+        'event' in message &&
+        message.event === 'property-change' &&
+        'name' in message &&
+        'data' in message
+      ) {
+        this.handlePropertyChange(message.name, message.data);
+      }
+    }
+  }
+
+  private handlePropertyChange(name: unknown, data: unknown): void {
+    if (name === 'eof-reached') this.eofReached = data === true;
+    else if (name === 'pause') this.paused = data === true;
+    else return;
+    if (this.playing && this.eofReached && this.paused) this.finishPlayback();
+  }
+
+  dispose(): void {
+    if (this.disposed) return;
+    this.disposed = true;
+    this.releaseResources();
+  }
+
+  private releaseResources(): void {
+    this.cancelRetryWait();
+    try {
+      this.send(['quit']);
+    } catch {
+      // The process may already have exited.
+    }
+    this.socket?.end();
+    this.socket?.destroy();
+    this.socket = null;
+    const child = this.process;
+    this.process = null;
+    child?.kill();
+    if (this.socketPath && this.deps.platform !== 'win32') {
+      try {
+        this.deps.removeSocketFile(this.socketPath);
+      } catch {
+        // mpv may still be releasing the socket. The OS temp directory owns cleanup.
+      }
+    }
+    this.socketPath = null;
+  }
+
+  private send(command: Array<string | number | boolean>): void {
+    if (!this.socket || this.socket.destroyed) {
+      throw new Error('Preview player is not connected');
+    }
+    this.socket.write(`${JSON.stringify({ command })}\n`);
+  }
+
+  private async connectWithRetry(socketPath: string): Promise<void> {
+    const deadline = this.deps.now() + CONNECT_TIMEOUT_MS;
+    while (!this.disposed && this.deps.now() < deadline) {
+      if (this.startupError) {
+        throw this.startupError;
+      }
+      try {
+        const remainingMs = deadline - this.deps.now();
+        if (remainingMs <= 0) break;
+        const socket = await this.connectOnce(
+          socketPath,
+          Math.min(CONNECT_ATTEMPT_TIMEOUT_MS, remainingMs),
+        );
+        if (this.disposed) {
+          socket.destroy();
+          throw new Error('Preview session is closed');
+        }
+        this.socket = socket;
+        this.readBuffer = '';
+        socket.on('data', (chunk: Buffer | string) => {
+          if (this.socket === socket) this.handleSocketData(chunk);
+        });
+        socket.once('close', () => this.finishPlayback());
+        this.send(['observe_property', EOF_OBSERVER_ID, 'eof-reached']);
+        this.send(['observe_property', PAUSE_OBSERVER_ID, 'pause']);
+        return;
+      } catch {
+        if (this.disposed) {
+          throw new Error('Preview session is closed');
+        }
+        const remainingMs = deadline - this.deps.now();
+        if (remainingMs <= 0) break;
+        await this.waitForRetry(Math.min(CONNECT_RETRY_MS, remainingMs));
+      }
+    }
+    if (this.startupError) {
+      throw this.startupError;
+    }
+    if (this.disposed) {
+      throw new Error('Preview session is closed');
+    }
+    throw new Error('Timed out starting the hidden mpv preview player');
+  }
+
+  private waitForRetry(delayMs: number): Promise<void> {
+    return new Promise<void>((resolve) => {
+      const timeout = this.deps.schedule(() => {
+        if (this.retryWait?.timeout === timeout) this.retryWait = null;
+        resolve();
+      }, delayMs);
+      this.retryWait = { timeout, resolve };
+    });
+  }
+
+  private cancelRetryWait(): void {
+    const pending = this.retryWait;
+    this.retryWait = null;
+    if (!pending) return;
+    this.deps.cancelSchedule(pending.timeout);
+    pending.resolve();
+  }
+
+  private connectOnce(socketPath: string, timeoutMs: number): Promise<Socket> {
+    return new Promise<Socket>((resolve, reject) => {
+      let timeout: ReturnType<typeof setTimeout> | null = null;
+      let settled = false;
+      const clearAttemptTimeout = (): void => {
+        if (timeout !== null) this.deps.cancelSchedule(timeout);
+        timeout = null;
+      };
+      const socket = this.deps.connectSocket(socketPath);
+      const onConnect = (): void => {
+        if (settled) return;
+        settled = true;
+        clearAttemptTimeout();
+        socket.off('error', onError);
+        socket.on('error', () => {
+          socket.destroy();
+          if (this.socket === socket) this.socket = null;
+        });
+        socket.once('close', () => {
+          if (this.socket === socket) this.socket = null;
+        });
+        resolve(socket);
+      };
+      const onError = (error: Error): void => {
+        if (settled) return;
+        settled = true;
+        clearAttemptTimeout();
+        socket.off('connect', onConnect);
+        socket.on('error', () => {});
+        socket.destroy();
+        reject(error);
+      };
+      socket.once('connect', onConnect);
+      socket.once('error', onError);
+      timeout = this.deps.schedule(() => {
+        if (settled) return;
+        settled = true;
+        timeout = null;
+        socket.off('connect', onConnect);
+        socket.off('error', onError);
+        socket.on('error', () => {});
+        socket.destroy();
+        reject(new Error('Timed out connecting to the hidden mpv preview player'));
+      }, timeoutMs);
+    });
+  }
+}

src/core/services/media-timing-waveform.test.ts

@@ -0,0 +1,125 @@
+import assert from 'node:assert/strict';
+import test from 'node:test';
+import {
+  buildSpeechWaveformArgs,
+  computeWaveformPeaks,
+  generateSpeechWaveform,
+} from './media-timing-waveform';
+
+function pcm(samples: number[]): Buffer {
+  const result = Buffer.alloc(samples.length * 2);
+  samples.forEach((sample, index) => result.writeInt16LE(sample, index * 2));
+  return result;
+}
+
+test('speech waveform maps the selected FFmpeg stream and visible range', () => {
+  const args = buildSpeechWaveformArgs(
+    {
+      mediaPath: '/video/show.mkv',
+      startTime: 8,
+      endTime: 15,
+      audioStreamIndex: 3,
+    },
+    'center',
+  );
+
+  assert.deepEqual(args.slice(args.indexOf('-ss'), args.indexOf('-t') + 2), [
+    '-ss',
+    '8',
+    '-i',
+    '/video/show.mkv',
+    '-t',
+    '7',
+  ]);
+  assert.deepEqual(args.slice(args.indexOf('-map'), args.indexOf('-map') + 2), ['-map', '0:3']);
+  assert.match(args[args.indexOf('-af') + 1] ?? '', /c0=FC/);
+});
+
+test('speech waveform seeks cached windows by source timestamps', () => {
+  const args = buildSpeechWaveformArgs(
+    {
+      mediaPath: { path: '/tmp/window.mkv', absoluteTimestamps: true, singleResolvedStream: true },
+      startTime: 8,
+      endTime: 15,
+    },
+    'downmix',
+  );
+
+  assert.deepEqual(args.slice(args.indexOf('-ss'), args.indexOf('-t') + 2), [
+    '-ss',
+    '8',
+    '-seek_timestamp',
+    '1',
+    '-i',
+    '/tmp/window.mkv',
+    '-t',
+    '7',
+  ]);
+  assert.equal(args.includes('-map'), false);
+});
+
+test('waveform levels rise with loudness and top out at the reference level', () => {
+  const peaks = computeWaveformPeaks(pcm([0, 1_000, -2_000, 4_000, -8_000, 16_000]), 3);
+
+  assert.equal(peaks.length, 3);
+  assert.equal(peaks[0], 0);
+  assert.ok((peaks[1] ?? 0) > 0);
+  assert.ok((peaks[1] ?? 0) < (peaks[2] ?? 0));
+  assert.equal(peaks[2], 1);
+});
+
+test('waveform flattens steady background noise and keeps speech bursts tall', () => {
+  // 20 slices of steady noise at a fixed level with an 18 dB louder "speech" burst in the middle.
+  const noise = 1_000;
+  const samples: number[] = [];
+  for (let slice = 0; slice < 20; slice += 1) {
+    const level = slice >= 8 && slice < 12 ? noise * 8 : noise;
+    for (let sample = 0; sample < 50; sample += 1) {
+      samples.push(sample % 2 === 0 ? level : -level);
+    }
+  }
+
+  const peaks = computeWaveformPeaks(pcm(samples), 20);
+
+  for (const [index, peak] of peaks.entries()) {
+    if (index >= 8 && index < 12) assert.equal(peak, 1);
+    else assert.equal(peak, 0);
+  }
+});
+
+test('waveform stays flat when the whole range is a single steady level', () => {
+  const peaks = computeWaveformPeaks(
+    pcm(Array.from({ length: 400 }, (_, i) => (i % 2 ? 900 : -900))),
+    40,
+  );
+
+  assert.ok(peaks.every((peak) => peak === 0));
+});
+
+test('speech waveform uses a mono downmix when the source has no center activity', async () => {
+  const calls: string[][] = [];
+  const peaks = await generateSpeechWaveform(
+    { mediaPath: '/video/show.mkv', startTime: 0, endTime: 2 },
+    async (args) => {
+      calls.push(args);
+      return calls.length === 1 ? pcm([0, 0, 0, 0]) : pcm([0, 4_000, -8_000, 16_000]);
+    },
+  );
+
+  assert.equal(calls.length, 2);
+  assert.match(calls[1]?.[calls[1].indexOf('-af') + 1] ?? '', /channel_layouts=mono/);
+  assert.equal(Math.max(...peaks), 1);
+});
+
+test('speech waveform keeps an active center channel without doing a second decode', async () => {
+  let calls = 0;
+  await generateSpeechWaveform(
+    { mediaPath: '/video/show.mkv', startTime: 0, endTime: 2 },
+    async () => {
+      calls += 1;
+      return pcm([0, 4_000, -8_000, 16_000]);
+    },
+  );
+
+  assert.equal(calls, 1);
+});

src/core/services/media-timing-waveform.ts

@@ -0,0 +1,185 @@
+import { spawn } from 'node:child_process';
+import { normalizeMediaInput, type MediaInput } from '../../media-input';
+
+const WAVEFORM_SAMPLE_RATE = 8_000;
+const WAVEFORM_POINT_COUNT = 480;
+const WAVEFORM_TIMEOUT_MS = 15_000;
+const MAX_WAVEFORM_BYTES = 16 * 1024 * 1024;
+// Keep the band where speech intelligibility lives; bass, drums, and hum sit below it.
+const SPEECH_FILTER = 'highpass=f=250,lowpass=f=3500';
+const NOISE_FLOOR_PERCENTILE = 0.2;
+const REFERENCE_PERCENTILE = 0.95;
+const NOISE_GATE_DB = 3;
+const MIN_DISPLAY_RANGE_DB = 12;
+const SILENCE_DB = -100;
+const CENTER_CHANNEL_FILTER = `pan=mono|c0=FC,${SPEECH_FILTER}`;
+const DOWNMIX_FILTER = `aformat=channel_layouts=mono,${SPEECH_FILTER}`;
+
+export interface SpeechWaveformOptions {
+  mediaPath: MediaInput;
+  startTime: number;
+  endTime: number;
+  audioStreamIndex?: number;
+}
+
+type RunFfmpeg = (args: string[]) => Promise<Buffer>;
+
+export function buildSpeechWaveformArgs(
+  options: SpeechWaveformOptions,
+  mode: 'center' | 'downmix',
+): string[] {
+  const duration = options.endTime - options.startTime;
+  const input = normalizeMediaInput(options.mediaPath);
+  const args = [
+    '-hide_banner',
+    '-nostdin',
+    '-loglevel',
+    'error',
+    '-ss',
+    String(options.startTime),
+    ...input.inputArgs,
+    '-i',
+    input.path,
+    '-t',
+    String(duration),
+  ];
+  if (
+    options.audioStreamIndex !== undefined &&
+    Number.isInteger(options.audioStreamIndex) &&
+    options.audioStreamIndex >= 0
+  ) {
+    args.push('-map', `0:${options.audioStreamIndex}`);
+  }
+  args.push(
+    '-vn',
+    '-sn',
+    '-dn',
+    '-af',
+    mode === 'center' ? CENTER_CHANNEL_FILTER : DOWNMIX_FILTER,
+    '-ac',
+    '1',
+    '-ar',
+    String(WAVEFORM_SAMPLE_RATE),
+    '-f',
+    's16le',
+    'pipe:1',
+  );
+  return args;
+}
+
+function runFfmpeg(args: string[]): Promise<Buffer> {
+  return new Promise((resolve, reject) => {
+    const child = spawn('ffmpeg', args, { stdio: ['ignore', 'pipe', 'pipe'] });
+    const chunks: Buffer[] = [];
+    let byteLength = 0;
+    let stderr = '';
+    let settled = false;
+    const timeout = setTimeout(() => {
+      if (settled) return;
+      settled = true;
+      child.kill('SIGKILL');
+      reject(new Error(`FFmpeg waveform analysis timed out after ${WAVEFORM_TIMEOUT_MS}ms`));
+    }, WAVEFORM_TIMEOUT_MS);
+
+    const settle = (callback: () => void): void => {
+      if (settled) return;
+      settled = true;
+      clearTimeout(timeout);
+      callback();
+    };
+
+    child.stdout.on('data', (chunk: Buffer) => {
+      if (settled) return;
+      byteLength += chunk.byteLength;
+      if (byteLength > MAX_WAVEFORM_BYTES) {
+        settle(() => {
+          child.kill('SIGKILL');
+          reject(new Error('The visible waveform range is too large to analyze.'));
+        });
+        return;
+      }
+      chunks.push(chunk);
+    });
+    child.stderr.setEncoding('utf8');
+    child.stderr.on('data', (chunk) => {
+      if (stderr.length < 4_000) stderr += String(chunk);
+    });
+    child.once('error', (error) => settle(() => reject(error)));
+    child.once('close', (code) => {
+      settle(() => {
+        if (code === 0) {
+          resolve(Buffer.concat(chunks, byteLength));
+          return;
+        }
+        reject(new Error(stderr.trim() || `FFmpeg exited with status ${code ?? 'unknown'}`));
+      });
+    });
+  });
+}
+
+function percentile(sortedValues: number[], fraction: number): number {
+  const index = Math.min(sortedValues.length - 1, Math.floor(sortedValues.length * fraction));
+  return sortedValues[index] ?? SILENCE_DB;
+}
+
+/**
+ * Turns mono PCM into 0..1 display heights. Each point is the RMS level of its slice in
+ * dB, measured against the clip's own noise floor (a low percentile of the slices), so
+ * constant background noise draws flat and sustained speech stands out. Peak sampling
+ * would instead follow music transients and lift the floor to nearly speech height.
+ */
+export function computeWaveformPeaks(pcm: Buffer, pointCount = WAVEFORM_POINT_COUNT): number[] {
+  const sampleCount = Math.floor(pcm.byteLength / 2);
+  if (sampleCount === 0 || pointCount <= 0) return [];
+  const resolvedPointCount = Math.min(pointCount, sampleCount);
+  const levelsDb = Array.from({ length: resolvedPointCount }, () => SILENCE_DB);
+
+  for (let point = 0; point < resolvedPointCount; point += 1) {
+    const sampleStart = Math.floor((point * sampleCount) / resolvedPointCount);
+    const sampleEnd = Math.max(
+      sampleStart + 1,
+      Math.floor(((point + 1) * sampleCount) / resolvedPointCount),
+    );
+    let energy = 0;
+    for (let sample = sampleStart; sample < sampleEnd; sample += 1) {
+      const value = pcm.readInt16LE(sample * 2) / 32_768;
+      energy += value * value;
+    }
+    const rms = Math.sqrt(energy / (sampleEnd - sampleStart));
+    levelsDb[point] = rms > 0 ? Math.max(SILENCE_DB, 20 * Math.log10(rms)) : SILENCE_DB;
+  }
+
+  const sortedLevels = [...levelsDb].sort((left, right) => left - right);
+  const floorDb = percentile(sortedLevels, NOISE_FLOOR_PERCENTILE) + NOISE_GATE_DB;
+  const referenceDb = Math.max(
+    percentile(sortedLevels, REFERENCE_PERCENTILE),
+    floorDb + MIN_DISPLAY_RANGE_DB,
+  );
+  return levelsDb.map(
+    (levelDb) =>
+      Math.round(Math.min(1, Math.max(0, (levelDb - floorDb) / (referenceDb - floorDb))) * 1_000) /
+      1_000,
+  );
+}
+
+function hasAudibleSamples(pcm: Buffer): boolean {
+  for (let offset = 0; offset + 1 < pcm.byteLength; offset += 2) {
+    if (Math.abs(pcm.readInt16LE(offset)) >= 164) return true;
+  }
+  return false;
+}
+
+export async function generateSpeechWaveform(
+  options: SpeechWaveformOptions,
+  execute: RunFfmpeg = runFfmpeg,
+): Promise<number[]> {
+  try {
+    const centerPcm = await execute(buildSpeechWaveformArgs(options, 'center'));
+    if (hasAudibleSamples(centerPcm)) return computeWaveformPeaks(centerPcm);
+  } catch {
+    // Sources without a named center channel can reject the center-only filter.
+  }
+
+  const downmixPcm = await execute(buildSpeechWaveformArgs(options, 'downmix'));
+  return computeWaveformPeaks(downmixPcm);
+}

src/core/services/remote-media-window-cache.test.ts

@@ -0,0 +1,253 @@
+import assert from 'node:assert/strict';
+import * as fs from 'node:fs';
+import * as os from 'node:os';
+import * as path from 'node:path';
+import test from 'node:test';
+import {
+  buildRemoteMediaWindowArgs,
+  RemoteMediaWindowCache,
+  REMOTE_MEDIA_WINDOW_MAX_SECONDS,
+  type RemoteMediaWindowCacheOptions,
+} from './remote-media-window-cache';
+
+const SOURCE = {
+  path: 'https://jellyfin.example/Videos/abc/stream?static=true',
+  audioStreamIndex: 2,
+};
+
+type ExecFileStub = NonNullable<RemoteMediaWindowCacheOptions['execFile']>;
+
+function createStub(options: { fail?: boolean; empty?: boolean; defer?: boolean } = {}) {
+  const calls: string[][] = [];
+  const pendingCallbacks: Array<() => void> = [];
+  const execFile: ExecFileStub = (_file, args, _options, callback) => {
+    calls.push([...args]);
+    const finish = (): void => {
+      const outputPath = args.at(-1);
+      assert.ok(outputPath);
+      if (options.fail) {
+        callback(Object.assign(new Error('boom'), { code: 1 }));
+        return;
+      }
+      if (!options.empty) {
+        fs.writeFileSync(outputPath, 'mkv', 'utf8');
+      }
+      callback(null);
+    };
+    if (options.defer) {
+      pendingCallbacks.push(finish);
+    } else {
+      queueMicrotask(finish);
+    }
+  };
+  return {
+    calls,
+    execFile,
+    flush: () => {
+      for (const finish of pendingCallbacks.splice(0)) finish();
+    },
+  };
+}
+
+async function withCache(
+  stubOptions: Parameters<typeof createStub>[0],
+  cacheOptions: Omit<RemoteMediaWindowCacheOptions, 'execFile' | 'tempDir'>,
+  run: (cache: RemoteMediaWindowCache, stub: ReturnType<typeof createStub>) => Promise<void>,
+): Promise<void> {
+  const tempDir = fs.mkdtempSync(path.join(os.tmpdir(), 'subminer-media-window-test-'));
+  const stub = createStub(stubOptions);
+  const cache = new RemoteMediaWindowCache({
+    tempDir,
+    execFile: stub.execFile,
+    idleTtlMs: 0,
+    logDebug: () => undefined,
+    ...cacheOptions,
+  });
+  try {
+    await run(cache, stub);
+  } finally {
+    cache.cleanup();
+    fs.rmSync(tempDir, { recursive: true, force: true });
+  }
+}
+
+function argValue(args: string[], flag: string): string | undefined {
+  const index = args.indexOf(flag);
+  return index === -1 ? undefined : args[index + 1];
+}
+
+test('buildRemoteMediaWindowArgs stream-copies the window with source timestamps intact', () => {
+  const args = buildRemoteMediaWindowArgs(
+    { ...SOURCE, inputOptions: { reconnect: true, headers: { Referer: 'https://a.example/' } } },
+    { startTime: 22.75, endTime: 33 },
+    '/tmp/window.mkv',
+  );
+
+  const inputIndex = args.indexOf('-i');
+  assert.equal(args[inputIndex + 1], SOURCE.path);
+  assert.ok(args.indexOf('-reconnect') < inputIndex);
+  assert.ok(args.indexOf('-headers') < inputIndex);
+  assert.equal(argValue(args, '-ss'), '22.75');
+  assert.equal(argValue(args, '-t'), '10.25');
+  assert.ok(args.indexOf('-t') < inputIndex);
+  assert.deepEqual(args.slice(args.indexOf('-map'), args.indexOf('-map') + 4), [
+    '-map',
+    '0:v:0?',
+    '-map',
+    '0:2',
+  ]);
+  assert.equal(argValue(args, '-c'), 'copy');
+  assert.ok(args.includes('-copyts'));
+  assert.ok(args.includes('-start_at_zero'));
+  assert.equal(argValue(args, '-f'), 'matroska');
+  assert.equal(args.at(-1), '/tmp/window.mkv');
+});
+
+test('buildRemoteMediaWindowArgs keeps every audio stream when none is selected', () => {
+  const args = buildRemoteMediaWindowArgs(
+    { path: SOURCE.path, audioStreamIndex: null },
+    { startTime: 0, endTime: 5 },
+    '/tmp/window.mkv',
+  );
+
+  assert.equal(args[args.lastIndexOf('-map') + 1], '0:a');
+});
+
+test('acquire downloads once and reuses the window for covered ranges', async () => {
+  await withCache({}, {}, async (cache, stub) => {
+    const window = await cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+
+    assert.equal(stub.calls.length, 1);
+    assert.equal(argValue(stub.calls[0]!, '-ss'), '9.75');
+    assert.equal(argValue(stub.calls[0]!, '-t'), '5.25');
+    assert.equal(window.startTime, 9.75);
+    assert.equal(window.endTime, 15);
+    assert.equal(window.audioStreamIndex, 2);
+    assert.ok(fs.existsSync(window.path));
+    assert.deepEqual(window.media, {
+      path: window.path,
+      source: 'remote-window',
+      singleResolvedStream: true,
+      absoluteTimestamps: true,
+    });
+
+    assert.equal(await cache.acquire(SOURCE, { startTime: 11, endTime: 15 }), window);
+    assert.equal(await cache.lookup(SOURCE, { startTime: 12, endTime: 12 }), window);
+    assert.equal(
+      await cache.lookup(
+        { path: SOURCE.path, audioStreamIndex: null },
+        { startTime: 12, endTime: 13 },
+      ),
+      window,
+    );
+    assert.equal(stub.calls.length, 1);
+  });
+});
+
+test('lookup never downloads and misses on other ranges, sources, or audio streams', async () => {
+  await withCache({}, {}, async (cache, stub) => {
+    assert.equal(await cache.lookup(SOURCE, { startTime: 10, endTime: 14 }), null);
+    assert.equal(stub.calls.length, 0);
+
+    await cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+    assert.equal(await cache.lookup(SOURCE, { startTime: 14, endTime: 16 }), null);
+    assert.equal(
+      await cache.lookup(
+        { path: 'https://other.example/stream', audioStreamIndex: 2 },
+        {
+          startTime: 11,
+          endTime: 12,
+        },
+      ),
+      null,
+    );
+    assert.equal(
+      await cache.lookup(
+        { path: SOURCE.path, audioStreamIndex: 3 },
+        { startTime: 11, endTime: 12 },
+      ),
+      null,
+    );
+    assert.equal(stub.calls.length, 1);
+  });
+});
+
+test('acquire widens to the union of the old window and replaces the old file', async () => {
+  await withCache({}, {}, async (cache, stub) => {
+    const first = await cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+    const second = await cache.acquire(SOURCE, { startTime: 8, endTime: 12 });
+
+    assert.equal(stub.calls.length, 2);
+    assert.equal(argValue(stub.calls[1]!, '-ss'), '7.75');
+    assert.equal(second.startTime, 7.75);
+    assert.equal(second.endTime, 15);
+    assert.notEqual(second.path, first.path);
+    assert.equal(fs.existsSync(first.path), false);
+    assert.ok(fs.existsSync(second.path));
+    assert.equal(cache.currentWindow, second);
+  });
+});
+
+test('acquire shares an in-flight download between concurrent callers', async () => {
+  await withCache({ defer: true }, {}, async (cache, stub) => {
+    const first = cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+    await Promise.resolve();
+    const second = cache.acquire(SOURCE, { startTime: 11, endTime: 13 });
+    const lookup = cache.lookup(SOURCE, { startTime: 12, endTime: 12 });
+    await Promise.resolve();
+    assert.equal(stub.calls.length, 1);
+
+    stub.flush();
+    const [a, b, c] = await Promise.all([first, second, lookup]);
+    assert.equal(a, b);
+    assert.equal(a, c);
+    assert.equal(stub.calls.length, 1);
+  });
+});
+
+test('acquire rejects on ffmpeg failure, leaves no file, and can retry', async () => {
+  await withCache({ fail: true }, {}, async (cache, stub) => {
+    await assert.rejects(
+      cache.acquire(SOURCE, { startTime: 10, endTime: 14 }),
+      /FFmpeg media window failed: boom/,
+    );
+    assert.equal(cache.currentWindow, null);
+    assert.equal(await cache.lookup(SOURCE, { startTime: 10, endTime: 14 }), null);
+
+    await assert.rejects(cache.acquire(SOURCE, { startTime: 10, endTime: 14 }));
+    assert.equal(stub.calls.length, 2);
+  });
+  await withCache({ empty: true }, {}, async (cache) => {
+    await assert.rejects(
+      cache.acquire(SOURCE, { startTime: 10, endTime: 14 }),
+      /exited without creating a media window/,
+    );
+  });
+});
+
+test('acquire refuses invalid and oversized ranges without spawning ffmpeg', async () => {
+  await withCache({}, {}, async (cache, stub) => {
+    await assert.rejects(cache.acquire(SOURCE, { startTime: 10, endTime: 10 }), /invalid/);
+    await assert.rejects(cache.acquire(SOURCE, { startTime: -1, endTime: 10 }), /invalid/);
+    await assert.rejects(
+      cache.acquire(SOURCE, { startTime: 0, endTime: REMOTE_MEDIA_WINDOW_MAX_SECONDS + 1 }),
+      /too long/,
+    );
+    assert.equal(stub.calls.length, 0);
+  });
+});
+
+test('the window is deleted after the idle timeout and on cleanup', async () => {
+  await withCache({}, { idleTtlMs: 20 }, async (cache) => {
+    const window = await cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+    await new Promise((resolve) => setTimeout(resolve, 60));
+
+    assert.equal(cache.currentWindow, null);
+    assert.equal(fs.existsSync(window.path), false);
+
+    const again = await cache.acquire(SOURCE, { startTime: 10, endTime: 14 });
+    cache.cleanup();
+    assert.equal(fs.existsSync(again.path), false);
+    assert.equal(fs.existsSync(path.dirname(again.path)), false);
+  });
+});

src/core/services/remote-media-window-cache.ts

@@ -0,0 +1,377 @@
+import { execFile as nodeExecFile, type ExecFileException } from 'child_process';
+import * as fs from 'fs';
+import * as os from 'os';
+import * as path from 'path';
+import { createLogger } from '../../logger';
+import { normalizeMediaInput, type MediaInput, type MediaInputOptions } from '../../media-input';
+
+const log = createLogger('media-window');
+
+export const REMOTE_MEDIA_WINDOW_TIMEOUT_MS = 120_000;
+export const REMOTE_MEDIA_WINDOW_MAX_SECONDS = 180;
+const HEAD_SLACK_SECONDS = 0.25;
+const TAIL_SLACK_SECONDS = 1;
+const DEFAULT_IDLE_TTL_MS = 10 * 60_000;
+const COVERAGE_EPSILON_SECONDS = 0.01;
+
+export interface RemoteMediaWindowSource {
+  path: string;
+  inputOptions?: MediaInputOptions;
+  /** FFmpeg stream index to keep; `null`/undefined keeps every audio stream. */
+  audioStreamIndex?: number | null;
+}
+
+export interface RemoteMediaWindowRange {
+  startTime: number;
+  endTime: number;
+}
+
+export interface RemoteMediaWindow {
+  path: string;
+  startTime: number;
+  endTime: number;
+  sourcePath: string;
+  audioStreamIndex: number | null;
+  /** Input descriptor for FFmpeg reads; timestamps stay absolute so callers keep source times. */
+  media: MediaInput;
+}
+
+type WindowExecFile = (
+  file: string,
+  args: readonly string[],
+  options: { timeout: number },
+  callback: (error: ExecFileException | null) => void,
+) => void;
+
+export interface RemoteMediaWindowCacheOptions {
+  tempDir?: string;
+  execFile?: WindowExecFile;
+  idleTtlMs?: number;
+  logDebug?: (message: string) => void;
+}
+
+interface PendingFetch extends RemoteMediaWindowRange {
+  sourcePath: string;
+  audioStreamIndex: number | null;
+  promise: Promise<RemoteMediaWindow>;
+}
+
+export function isRemoteMediaWindowSourcePath(value: string): boolean {
+  return /^https?:\/\//i.test(value.trim());
+}
+
+function describeSourceForDebugLog(sourcePath: string): string {
+  try {
+    return `remote:${new URL(sourcePath).hostname.toLowerCase() || 'unknown'}`;
+  } catch {
+    return 'remote:unknown';
+  }
+}
+
+function isUsableRange(range: RemoteMediaWindowRange, allowEmpty: boolean): boolean {
+  return (
+    Number.isFinite(range.startTime) &&
+    Number.isFinite(range.endTime) &&
+    range.startTime >= 0 &&
+    (allowEmpty ? range.endTime >= range.startTime : range.endTime > range.startTime)
+  );
+}
+
+function audioStreamMatches(
+  windowIndex: number | null,
+  requested: number | null | undefined,
+): boolean {
+  return requested == null || windowIndex === requested;
+}
+
+function covers(
+  candidate: RemoteMediaWindowRange & { sourcePath: string; audioStreamIndex: number | null },
+  source: RemoteMediaWindowSource,
+  range: RemoteMediaWindowRange,
+): boolean {
+  return (
+    candidate.sourcePath === source.path &&
+    audioStreamMatches(candidate.audioStreamIndex, source.audioStreamIndex) &&
+    candidate.startTime <= range.startTime + COVERAGE_EPSILON_SECONDS &&
+    candidate.endTime >= range.endTime - COVERAGE_EPSILON_SECONDS
+  );
+}
+
+/**
+ * Stream-copies `[startTime, endTime]` of a remote source into a local Matroska file.
+ * `-copyts -start_at_zero` keeps the source timestamps, so later reads seek with the
+ * original times via `-seek_timestamp 1` (see `MediaInput.absoluteTimestamps`).
+ */
+export function buildRemoteMediaWindowArgs(
+  source: RemoteMediaWindowSource,
+  range: RemoteMediaWindowRange,
+  outputPath: string,
+): string[] {
+  const input = normalizeMediaInput({ path: source.path, inputOptions: source.inputOptions });
+  const audioMap =
+    typeof source.audioStreamIndex === 'number' && Number.isInteger(source.audioStreamIndex)
+      ? `0:${source.audioStreamIndex}`
+      : '0:a';
+  return [
+    '-hide_banner',
+    '-nostdin',
+    '-loglevel',
+    'error',
+    '-ss',
+    String(range.startTime),
+    '-t',
+    String(range.endTime - range.startTime),
+    ...input.inputArgs,
+    '-i',
+    input.path,
+    '-map',
+    '0:v:0?',
+    '-map',
+    audioMap,
+    '-c',
+    'copy',
+    '-sn',
+    '-dn',
+    '-copyts',
+    '-start_at_zero',
+    '-f',
+    'matroska',
+    '-y',
+    outputPath,
+  ];
+}
+
+/**
+ * Holds one downloaded window of the current remote stream so the timing review,
+ * audio extraction, and screenshot all read the same local bytes instead of each
+ * re-fetching the clip over HTTP. A new window replaces the old one; the file is
+ * deleted after `idleTtlMs` without use, on `clear()`, or on `cleanup()`.
+ */
+export class RemoteMediaWindowCache {
+  private readonly tempDir: string;
+  private readonly execFile: WindowExecFile;
+  private readonly idleTtlMs: number;
+  private readonly logDebug: (message: string) => void;
+  private current: RemoteMediaWindow | null = null;
+  private pending: PendingFetch | null = null;
+  private idleTimer: ReturnType<typeof setTimeout> | null = null;
+  private sequence = 0;
+
+  constructor(options: RemoteMediaWindowCacheOptions = {}) {
+    this.tempDir = options.tempDir ?? path.join(os.tmpdir(), 'subminer-media-windows');
+    this.execFile = options.execFile ?? nodeExecFile;
+    this.idleTtlMs = options.idleTtlMs ?? DEFAULT_IDLE_TTL_MS;
+    this.logDebug = options.logDebug ?? ((message) => log.debug(message));
+  }
+
+  get currentWindow(): RemoteMediaWindow | null {
+    return this.current;
+  }
+
+  /** Returns a ready or in-flight window covering the range; never starts a download. */
+  async lookup(
+    source: RemoteMediaWindowSource,
+    range: RemoteMediaWindowRange,
+  ): Promise<RemoteMediaWindow | null> {
+    if (!isUsableRange(range, true)) return null;
+    if (this.current && covers(this.current, source, range)) {
+      this.touch();
+      return this.current;
+    }
+    const pending = this.pending;
+    if (pending && covers(pending, source, range)) {
+      try {
+        const window = await pending.promise;
+        this.touch();
+        return window;
+      } catch {
+        return null;
+      }
+    }
+    return null;
+  }
+
+  /** Returns a window covering the range, downloading (and widening) one when needed. */
+  async acquire(
+    source: RemoteMediaWindowSource,
+    range: RemoteMediaWindowRange,
+  ): Promise<RemoteMediaWindow> {
+    if (!isUsableRange(range, false)) {
+      throw new Error('Media window range is invalid.');
+    }
+    if (range.endTime - range.startTime > REMOTE_MEDIA_WINDOW_MAX_SECONDS) {
+      throw new Error('Media window range is too long to download.');
+    }
+
+    for (;;) {
+      const hit = await this.lookup(source, range);
+      if (hit) return hit;
+      const pending = this.pending;
+      if (!pending) break;
+      // Another caller is already downloading; wait for it, then re-check coverage.
+      await pending.promise.catch(() => null);
+    }
+
+    return this.fetch(source, this.planFetchRange(source, range));
+  }
+
+  clear(): void {
+    this.cancelIdleTimer();
+    const current = this.current;
+    this.current = null;
+    if (current) this.removeFile(current.path);
+  }
+
+  cleanup(): void {
+    this.clear();
+    try {
+      fs.rmSync(this.tempDir, { recursive: true, force: true });
+    } catch (error) {
+      log.error('Failed to cleanup media window directory:', error);
+    }
+  }
+
+  private planFetchRange(
+    source: RemoteMediaWindowSource,
+    range: RemoteMediaWindowRange,
+  ): RemoteMediaWindowRange {
+    let startTime = Math.max(0, range.startTime - HEAD_SLACK_SECONDS);
+    let endTime = range.endTime + TAIL_SLACK_SECONDS;
+    const current = this.current;
+    if (
+      current &&
+      current.sourcePath === source.path &&
+      audioStreamMatches(current.audioStreamIndex, source.audioStreamIndex)
+    ) {
+      // Keep what was already downloaded when the review timeline grows in one direction.
+      const unionStart = Math.min(startTime, current.startTime);
+      const unionEnd = Math.max(endTime, current.endTime);
+      if (unionEnd - unionStart <= REMOTE_MEDIA_WINDOW_MAX_SECONDS) {
+        startTime = unionStart;
+        endTime = unionEnd;
+      }
+    }
+    return { startTime, endTime };
+  }
+
+  private fetch(
+    source: RemoteMediaWindowSource,
+    range: RemoteMediaWindowRange,
+  ): Promise<RemoteMediaWindow> {
+    fs.mkdirSync(this.tempDir, { recursive: true });
+    this.sequence += 1;
+    const outputPath = path.join(this.tempDir, `window_${Date.now()}_${this.sequence}.mkv`);
+    const audioStreamIndex =
+      typeof source.audioStreamIndex === 'number' ? source.audioStreamIndex : null;
+    const description = describeSourceForDebugLog(source.path);
+    const startedAt = Date.now();
+    this.logDebug(
+      `[media-window] fetch start ${description} start=${range.startTime} end=${range.endTime} audioStream=${audioStreamIndex ?? 'all'}`,
+    );
+
+    const promise = new Promise<RemoteMediaWindow>((resolve, reject) => {
+      this.execFile(
+        'ffmpeg',
+        buildRemoteMediaWindowArgs(source, range, outputPath),
+        { timeout: REMOTE_MEDIA_WINDOW_TIMEOUT_MS },
+        (error) => {
+          const elapsedMs = Math.max(0, Date.now() - startedAt);
+          const size = error ? 0 : this.fileSize(outputPath);
+          if (error || size === 0) {
+            this.removeFile(outputPath);
+            const reason = error
+              ? error.code === 'ENOENT'
+                ? 'FFmpeg not found. Install FFmpeg to enable media generation.'
+                : `FFmpeg media window failed: ${error.message}`
+              : 'FFmpeg exited without creating a media window.';
+            this.logDebug(`[media-window] fetch failed ${description} elapsedMs=${elapsedMs}`);
+            reject(new Error(reason));
+            return;
+          }
+          const window: RemoteMediaWindow = {
+            path: outputPath,
+            startTime: range.startTime,
+            endTime: range.endTime,
+            sourcePath: source.path,
+            audioStreamIndex,
+            media: {
+              path: outputPath,
+              source: 'remote-window',
+              singleResolvedStream: true,
+              absoluteTimestamps: true,
+            },
+          };
+          this.logDebug(
+            `[media-window] fetch complete ${description} elapsedMs=${elapsedMs} bytes=${size}`,
+          );
+          this.replaceCurrent(window);
+          resolve(window);
+        },
+      );
+    });
+
+    const pending: PendingFetch = {
+      sourcePath: source.path,
+      audioStreamIndex,
+      startTime: range.startTime,
+      endTime: range.endTime,
+      promise,
+    };
+    this.pending = pending;
+    promise
+      .catch(() => undefined)
+      .then(() => {
+        if (this.pending === pending) this.pending = null;
+      });
+    return promise;
+  }
+
+  private replaceCurrent(window: RemoteMediaWindow): void {
+    const previous = this.current;
+    this.current = window;
+    if (previous && previous.path !== window.path) this.removeFile(previous.path);
+    this.touch();
+  }
+
+  private touch(): void {
+    this.cancelIdleTimer();
+    if (this.idleTtlMs <= 0 || !this.current) return;
+    const timer = setTimeout(() => {
+      if (this.idleTimer === timer) this.idleTimer = null;
+      this.clear();
+    }, this.idleTtlMs);
+    timer.unref?.();
+    this.idleTimer = timer;
+  }
+
+  private cancelIdleTimer(): void {
+    if (this.idleTimer) clearTimeout(this.idleTimer);
+    this.idleTimer = null;
+  }
+
+  private fileSize(filePath: string): number {
+    try {
+      return fs.statSync(filePath).size;
+    } catch {
+      return 0;
+    }
+  }
+
+  private removeFile(filePath: string): void {
+    try {
+      fs.unlinkSync(filePath);
+    } catch (error) {
+      if ((error as NodeJS.ErrnoException).code !== 'ENOENT') {
+        log.debug(`Failed to remove media window ${filePath}:`, (error as Error).message);
+      }
+    }
+  }
+}
+
+let sharedCache: RemoteMediaWindowCache | null = null;
+
+/** Process-wide cache so the review modal and card media generation share one download. */
+export function getSharedRemoteMediaWindowCache(): RemoteMediaWindowCache {
+  sharedCache ??= new RemoteMediaWindowCache();
+  return sharedCache;
+}