fix(anki): separate word audio mapping for animation sync (#256)

changes/fix-animated-word-audio-sync.md

@@ -0,0 +1,4 @@
+type: fixed
+area: anki
+
+- Added `ankiConnect.fields.wordAudio` to read word audio separately from the generated sentence-audio destination, fixing animated images that start moving immediately when `fields.audio` points to `SentenceAudio`.

changes/word-audio-mapping-docs.md

@@ -0,0 +1,4 @@
+type: docs
+area: anki
+
+- Documented the separate word-audio mapping for animated-image synchronization and that existing images need regeneration to pick up the corrected freeze.

config.example.jsonc

@@ -541,7 +541,7 @@
   // ==========================================
   // AnkiConnect Integration
   // Automatic Anki updates and media generation options.
-  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
+  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/wordAudio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
   // Shared AI provider transport settings are read from top-level ai and typically require restart.
   // Most other AnkiConnect settings still require restart.
   // ==========================================
@@ -562,6 +562,7 @@
     "fields": {
       "word": "Expression", // Card field for the mined word or expression text.
       "audio": "ExpressionAudio", // Card field that receives generated sentence audio.
+      "wordAudio": "ExpressionAudio", // Existing word-audio field read to time the frozen first frame of animated images. This mapping is only used for synchronization.
       "image": "Picture", // Card field that receives the captured screenshot or animated image.
       "sentence": "Sentence", // Card field that receives the source sentence text.
       "miscInfo": "MiscInfo", // Card field that receives the miscellaneous info pattern (see ankiConnect.metadata.pattern).

docs-site/anki-integration.md

@@ -125,6 +125,7 @@ SubMiner maps its data to your Anki note fields. Configure these under `ankiConn
   "fields": {
     "word": "Expression",        // mined word / expression text
     "audio": "SentenceAudio",    // sentence audio clip cut from the video
+    "wordAudio": "ExpressionAudio", // existing Yomitan word audio, read for animation sync
     "image": "Picture",          // screenshot or animated clip
     "sentence": "Sentence",      // subtitle text
     "miscInfo": "MiscInfo"       // metadata (filename, timestamp)
@@ -136,6 +137,8 @@ SubMiner maps its data to your Anki note fields. Configure these under `ankiConn
 
 Field names are matched against your Anki note type case-insensitively (an exact match wins, then a lowercase comparison). If a configured field does not exist on the note type, SubMiner skips it without error.
 
+`fields.wordAudio` selects the existing dictionary-audio field used to calculate the animated image's opening freeze. This mapping only reads audio; `fields.audio` still controls where generated sentence audio is written. See [config.example.jsonc](/config.example.jsonc) for defaults.
+
 These mappings always control normal word-card enrichment, including Yomitan proxy/polling updates and manual clipboard updates. Enabling Lapis or Kiku does not replace the configured word-card sentence and audio fields with `Sentence` and `SentenceAudio`. The dedicated sentence-card and audio-card shortcuts still use those Lapis/Kiku field names.
 
 Two related options live alongside `fields`: `ankiConnect.deck` (target deck; empty falls back as described above) and `ankiConnect.tags` (tags added to mined cards, default `["SubMiner"]`; set `[]` to disable tagging). The `miscInfo` content is controlled by `ankiConnect.metadata.pattern` (default `[SubMiner] %f (%t)`; tokens: `%f` filename, `%F` filename with extension, `%t` timestamp, `%T` timestamp with milliseconds, `<br>` newline).
@@ -241,7 +244,7 @@ SubMiner can produce an animated AVIF spanning the subtitle duration instead of
 }
 ```
 
-Animated AVIF requires an AV1 encoder (`libaom-av1`, `libsvtav1`, or `librav1e`) in your FFmpeg build. Generation timeout is 60 seconds. `media.syncAnimatedImageToWordAudio` (default `true`) prepends a frozen first frame matching the existing word-audio duration, so the motion starts together with the sentence audio.
+Animated AVIF requires an AV1 encoder (`libaom-av1`, `libsvtav1`, or `librav1e`) in your FFmpeg build. Generation timeout is 60 seconds. `media.syncAnimatedImageToWordAudio` (default `true`) prepends a frozen first frame matching the existing audio duration in `fields.wordAudio`, so the motion starts together with the sentence audio. The freeze is baked into the image when mined; changing the mapping does not repair previously generated images.
 
 ### Behavior options
 

docs-site/configuration.md

@@ -976,6 +976,7 @@ This example is intentionally compact. The option table below documents availabl
 | `ankiConnect.deck`                                | string                                      | Restrict duplicate detection and card enrichment to this Anki deck. Leave empty to use the Yomitan mining deck when available. In Settings, this dropdown auto-fills and persists Yomitan's current mining deck when available. |
 | `fields.word`                                     | string                                      | Card field for mined word / expression text (default: `Expression`)                                                                                                                                                             |
 | `fields.audio`                                    | string                                      | Card field for the generated sentence audio clip (default: `ExpressionAudio`). Set this to a dedicated field such as `SentenceAudio` so it does not collide with the word audio Yomitan writes.                                  |
+| `fields.wordAudio`                                | string                                      | Existing word-audio field read for the animated image's opening freeze. Independent of the sentence-audio destination in `fields.audio`; this mapping does not write audio. See [config.example.jsonc](/config.example.jsonc) for defaults. |
 | `fields.image`                                    | string                                      | Card field for images (default: `Picture`)                                                                                                                                                                                      |
 | `fields.sentence`                                 | string                                      | Card field for sentences (default: `Sentence`)                                                                                                                                                                                  |
 | `fields.miscInfo`                                 | string                                      | Card field for metadata (default: `"MiscInfo"`, set to `null` to disable)                                                                                                                                                       |

docs-site/public/config.example.jsonc

@@ -541,7 +541,7 @@
   // ==========================================
   // AnkiConnect Integration
   // Automatic Anki updates and media generation options.
-  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
+  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/wordAudio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
   // Shared AI provider transport settings are read from top-level ai and typically require restart.
   // Most other AnkiConnect settings still require restart.
   // ==========================================
@@ -562,6 +562,7 @@
     "fields": {
       "word": "Expression", // Card field for the mined word or expression text.
       "audio": "ExpressionAudio", // Card field that receives generated sentence audio.
+      "wordAudio": "ExpressionAudio", // Existing word-audio field read to time the frozen first frame of animated images. This mapping is only used for synchronization.
       "image": "Picture", // Card field that receives the captured screenshot or animated image.
       "sentence": "Sentence", // Card field that receives the source sentence text.
       "miscInfo": "MiscInfo", // Card field that receives the miscellaneous info pattern (see ankiConnect.metadata.pattern).

src/anki-integration/animated-image-sync.test.ts

@@ -14,7 +14,8 @@ test('resolveAnimatedImageLeadInSeconds sums configured word audio durations for
   const leadInSeconds = await resolveAnimatedImageLeadInSeconds({
     config: {
       fields: {
-        audio: 'ExpressionAudio',
+        audio: 'SentenceAudio',
+        wordAudio: 'Pronunciation',
       },
       media: {
         imageType: 'avif',
@@ -25,7 +26,8 @@ test('resolveAnimatedImageLeadInSeconds sums configured word audio durations for
     noteInfo: {
       noteId: 42,
       fields: {
-        ExpressionAudio: {
+        SentenceAudio: { value: '[sound:sentence.mp3]' },
+        Pronunciation: {
           value: '[sound:word.mp3][sound:alt.ogg]',
         },
       },
@@ -121,3 +123,32 @@ test('resolveAnimatedImageLeadInSeconds falls back to zero when sync is disabled
 
   assert.equal(leadInSeconds, 0);
 });
+
+for (const sentenceAudio of ['', '[sound:sentence.mp3]']) {
+  test(`word audio defaults independently of sentence audio (${sentenceAudio ? 'existing' : 'new'} note)`, async () => {
+    const retrieved: string[] = [];
+    const leadInSeconds = await resolveAnimatedImageLeadInSeconds({
+      config: {
+        fields: { audio: 'SentenceAudio' },
+        media: { imageType: 'avif' },
+      },
+      noteInfo: {
+        noteId: 42,
+        fields: {
+          ExpressionAudio: { value: '[sound:word.mp3]' },
+          SentenceAudio: { value: sentenceAudio },
+        },
+      },
+      resolveConfiguredFieldName: (noteInfo, ...preferredNames) =>
+        preferredNames.find((name) => name !== undefined && name in noteInfo.fields) ?? null,
+      retrieveMediaFileBase64: async (filename) => {
+        retrieved.push(filename);
+        return 'd29yZA==';
+      },
+      probeAudioDurationSeconds: async (_buffer, filename) => (filename === 'word.mp3' ? 0.6 : 4),
+    });
+
+    assert.equal(leadInSeconds, 0.6);
+    assert.deepEqual(retrieved, ['word.mp3']);
+  });
+}

src/anki-integration/animated-image-sync.ts

@@ -97,8 +97,8 @@ export async function resolveAnimatedImageLeadInSeconds<TNoteInfo extends NoteIn
 
   const wordAudioFieldName = resolveConfiguredFieldName(
     noteInfo,
-    config.fields?.audio,
-    DEFAULT_ANKI_CONNECT_CONFIG.fields.audio,
+    config.fields?.wordAudio,
+    DEFAULT_ANKI_CONNECT_CONFIG.fields.wordAudio,
   );
   if (!wordAudioFieldName) {
     return 0;

src/config/definitions/defaults-integrations.ts

@@ -29,6 +29,7 @@ export const INTEGRATIONS_DEFAULT_CONFIG: Pick<
     fields: {
       word: 'Expression',
       audio: 'ExpressionAudio',
+      wordAudio: 'ExpressionAudio',
       image: 'Picture',
       sentence: 'Sentence',
       miscInfo: 'MiscInfo',

src/config/definitions/options-integrations.ts

@@ -82,6 +82,13 @@ export function buildIntegrationConfigOptionRegistry(
       defaultValue: defaultConfig.ankiConnect.fields.audio,
       description: 'Card field that receives generated sentence audio.',
     },
+    {
+      path: 'ankiConnect.fields.wordAudio',
+      kind: 'string',
+      defaultValue: defaultConfig.ankiConnect.fields.wordAudio,
+      description:
+        'Existing word-audio field read to time the frozen first frame of animated images. This mapping is only used for synchronization.',
+    },
     {
       path: 'ankiConnect.fields.image',
       kind: 'string',

src/config/definitions/template-sections.ts

@@ -144,7 +144,7 @@ const INTEGRATION_TEMPLATE_SECTIONS: ConfigTemplateSection[] = [
     title: 'AnkiConnect Integration',
     description: ['Automatic Anki updates and media generation options.'],
     notes: [
-      'Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.',
+      'Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/wordAudio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, isSenren.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.',
       'Shared AI provider transport settings are read from top-level ai and typically require restart.',
       'Most other AnkiConnect settings still require restart.',
     ],

src/config/hot-reload.ts

@@ -29,6 +29,7 @@ const HOT_RELOAD_EXACT_OR_PREFIX_PATHS = [
   'ankiConnect.nPlusOne.minSentenceWords',
   'ankiConnect.fields.word',
   'ankiConnect.fields.audio',
+  'ankiConnect.fields.wordAudio',
   'ankiConnect.fields.image',
   'ankiConnect.fields.sentence',
   'ankiConnect.fields.miscInfo',

src/config/resolve/anki-connect.test.ts

@@ -290,6 +290,28 @@ test('accepts ankiConnect.media.syncAnimatedImageToWordAudio override', () => {
   );
 });
 
+test('word audio mapping defaults and validates independently of sentence audio', () => {
+  for (const wordAudio of [undefined, 'Pronunciation', 7]) {
+    const { context, warnings } = makeContext({
+      fields: {
+        audio: 'SentenceAudio',
+        ...(wordAudio !== undefined ? { wordAudio } : {}),
+      },
+    });
+    applyAnkiConnectResolution(context);
+
+    assert.equal(context.resolved.ankiConnect.fields.audio, 'SentenceAudio');
+    assert.equal(
+      context.resolved.ankiConnect.fields.wordAudio,
+      typeof wordAudio === 'string' ? wordAudio : DEFAULT_CONFIG.ankiConnect.fields.wordAudio,
+    );
+    assert.deepEqual(
+      warnings.map((warning) => warning.path),
+      typeof wordAudio === 'number' ? ['ankiConnect.fields.wordAudio'] : [],
+    );
+  }
+});
+
 test('invalid modern Anki subtrees warn and keep resolved defaults', () => {
   const { context, warnings } = makeContext({
     fields: { word: 7 },

src/config/resolve/anki-connect/modern-fields.ts

@@ -7,7 +7,15 @@ export function applyModernFieldsResolution(
   context: ResolveContext,
   fields: Record<string, unknown>,
 ): void {
-  for (const key of ['word', 'audio', 'image', 'sentence', 'miscInfo', 'translation'] as const) {
+  for (const key of [
+    'word',
+    'audio',
+    'wordAudio',
+    'image',
+    'sentence',
+    'miscInfo',
+    'translation',
+  ] as const) {
     applyModernValue(
       context,
       fields,

src/config/settings/registry.test.ts

@@ -364,6 +364,7 @@ test('settings registry marks safe live config paths as hot-reloadable', () => {
     'ankiConnect.nPlusOne.minSentenceWords',
     'ankiConnect.fields.word',
     'ankiConnect.fields.audio',
+    'ankiConnect.fields.wordAudio',
     'ankiConnect.fields.image',
     'ankiConnect.fields.sentence',
     'ankiConnect.fields.miscInfo',

src/types/anki.ts

@@ -157,6 +157,7 @@ export interface AnkiConnectConfig {
   fields?: {
     word?: string;
     audio?: string;
+    wordAudio?: string;
     image?: string;
     sentence?: string;
     miscInfo?: string;

src/types/config.ts

@@ -228,6 +228,7 @@ export interface ResolvedConfig {
     fields: {
       word: string;
       audio: string;
+      wordAudio: string;
       image: string;
       sentence: string;
       miscInfo: string;