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

changes/media-timing-review.md

@@ -0,0 +1,5 @@
+type: added
+area: mining
+
+- Added optional pre-generation timing review for word, sentence, and audio cards with a compact speech-weighted waveform, clearly labeled mined-line boundaries, drag and keyboard adjustments, audio preview with a sweeping playhead, exact screenshot and AVIF timing, cancellation choices that include keeping a card without media, and a session-only runtime toggle.
+- The timing review can pull any number of previous and next subtitle lines onto the card: `P`/`N` (or the Prev/Next steppers) add lines one at a time, Shift removes them, the sentence preview highlights exactly what the card will contain, and the clip range follows the added lines automatically.

config.example.jsonc

@@ -523,7 +523,7 @@
   // ==========================================
   // AnkiConnect Integration
   // Automatic Anki updates and media generation options.
-  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
+  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.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.
   // ==========================================
@@ -569,6 +569,7 @@
       "syncAnimatedImageToWordAudio": true, // For animated AVIF images, prepend a frozen first frame matching the existing word-audio duration so motion starts with sentence audio. Values: true | false
       "normalizeAudio": true, // Normalize generated sentence audio loudness during media extraction. Changes apply live. Values: true | false
       "mirrorMpvVolume": true, // Apply mpv's current software volume curve to generated sentence audio. Changes apply live. Values: true | false
+      "reviewTiming": false, // Review and preview subtitle media timing before SubMiner creates or enriches a mined card. Values: true | false
       "audioPadding": 0, // Seconds of padding appended to both ends of generated sentence audio and animated AVIF clips.
       "fallbackDuration": 3, // Fallback clip duration in seconds when subtitle timing data is unavailable.
       "maxMediaDuration": 30 // Maximum allowed media clip duration in seconds.

docs-site/anki-integration.md

@@ -168,6 +168,7 @@ Audio is extracted from the video file using the subtitle's start and end timest
     "generateAudio": true,
     "normalizeAudio": true,      // normalize generated clip loudness
     "mirrorMpvVolume": true,     // apply the current mpv volume level
+    "reviewTiming": false,       // review and adjust timing before media generation
     "audioPadding": 0,           // optional seconds before and after subtitle timing
     "maxMediaDuration": 30       // cap total duration in seconds
   }
@@ -180,6 +181,12 @@ Output format: MP3 at 44100 Hz. If the video has multiple audio streams, SubMine
 
 The audio is uploaded to Anki's media folder and inserted as `[sound:audio_<timestamp>.mp3]`.
 
+Set `media.reviewTiming` to `true` to pause playback and review each word, sentence, or audio card before its media is generated. The review opens with the subtitle range plus configured audio padding. Drag either edge of the clip to trim it, drag the middle to slide it without changing its length, or press anywhere else on the waveform to snap the nearer edge there. A focused edge also moves with the arrow keys, by 100 ms alone or 500 ms with Shift, and the 100 ms buttons do the same. Space previews the selection with a playhead that sweeps the clip, Enter confirms, and Escape cancels. The Earlier and Later buttons reveal another two seconds of available timeline without moving the selected clip. A speech-weighted waveform shows the mined subtitle as a tinted band with labeled line-start and line-end rails, making adjacent dialogue easier to distinguish. SubMiner uses a center channel when one carries dialogue, then falls back to a speech-band mono mix. Waveform analysis failure leaves the timing controls available. The confirmed range is exact: SubMiner does not apply audio padding a second time. Static screenshots use its midpoint, and animated AVIF clips use the full confirmed range.
+
+The review can also pull adjacent subtitle lines onto the card. Press `P` or `N` (or use the Prev and Next steppers above the sentence preview) to add the previous or next line, as many times as lines are available; Shift+`P` and Shift+`N` remove them again. The sentence preview lists every included line with the mined line highlighted, so the card's sentence field is always visible before you confirm, and the clip start or end follows the outermost added line, keeping the review's audio padding. Confirming writes the combined lines to the sentence field; the Reset button drops the added lines along with any timing changes. Adjacent lines come from the parsed subtitle track when one is loaded; otherwise only lines that already played are offered, and a clip capped by `media.maxMediaDuration` keeps the full combined sentence even when the audio cannot cover every added line.
+
+Canceling the review lets you keep editing, finish with the original timing, keep or create the card without audio or an image, or discard the card. Discard deletes an existing Yomitan or audio card and skips creation for a direct sentence card. Clipboard updates and stats-dashboard mining do not open timing review. Audio preview failure does not block confirmation or card creation. The option is disabled by default and hot-reloads. You can also toggle **Review Media Timing** for the current session from the runtime options palette (`Ctrl/Cmd+Shift+O`).
+
 ### Screenshots (Static)
 
 A single frame is captured at the current playback position.

docs-site/configuration.md

@@ -873,9 +873,10 @@ When config hot-reload updates shortcut/keybinding/style values, close and reope
 
 Use the runtime options palette to toggle settings live while SubMiner is running. These changes are session-only and reset on restart.
 
-Current runtime options cover automatic card updates, known-word highlighting,
-known-word maturity coloring, N+1 annotation, JLPT underlines, frequency
-highlighting, known-word match mode, and Kiku field grouping mode.
+Current runtime options cover automatic card updates, media timing review,
+known-word highlighting, known-word maturity coloring, N+1 annotation, JLPT
+underlines, frequency highlighting, known-word match mode, and Kiku field
+grouping mode.
 
 Annotation toggles only apply to new subtitle lines after the toggle. The currently displayed line is not re-tokenized in place.
 
@@ -967,6 +968,7 @@ Enable automatic Anki card creation and updates with media generation:
       "animatedCrf": 35,
       "normalizeAudio": true,
       "mirrorMpvVolume": true,
+      "reviewTiming": false,
       "audioPadding": 0,
       "fallbackDuration": 3,
       "maxMediaDuration": 30
@@ -1019,6 +1021,7 @@ This example is intentionally compact. The option table below documents availabl
 | `media.generateAudio`                             | `true`, `false`                             | Generate audio clips from video (default: `true`)                                                                                                                                                                               |
 | `media.normalizeAudio`                            | `true`, `false`                             | Normalize generated sentence-audio loudness during media extraction (default: `true`). Set to `false` to keep raw source loudness. Changes apply live.                                                                          |
 | `media.mirrorMpvVolume`                           | `true`, `false`                             | Apply mpv's cubic software-volume curve to each generated sentence-audio clip (default: `true`). This ignores mpv's separate mute state, falls back to unity scaling if volume cannot be read, and applies changes live.        |
+| `media.reviewTiming`                              | `true`, `false`                             | Pause playback and review word, sentence, and audio card timing before media generation (default: `false`). Clipboard updates and stats-dashboard mining do not open the review.                                                |
 | `media.generateImage`                             | `true`, `false`                             | Generate image/animation screenshots (default: `true`)                                                                                                                                                                          |
 | `media.imageType`                                 | `"static"`, `"avif"`                        | Image type: static screenshot or animated AVIF (default: `"static"`)                                                                                                                                                            |
 | `media.imageFormat`                               | `"jpg"`, `"png"`, `"webp"`                  | Image format (default: `"jpg"`)                                                                                                                                                                                                 |

docs-site/public/config.example.jsonc

@@ -523,7 +523,7 @@
   // ==========================================
   // AnkiConnect Integration
   // Automatic Anki updates and media generation options.
-  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.fieldGrouping, and lapisKiku.wordCardKind update live while SubMiner is running.
+  // Hot-reload: ankiConnect.ai.enabled, media.normalizeAudio/mirrorMpvVolume/reviewTiming, knownWords, nPlusOne, fields.word/audio/image/sentence/miscInfo, behavior.autoUpdateNewCards, isLapis.sentenceCardModel, isKiku.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.
   // ==========================================
@@ -569,6 +569,7 @@
       "syncAnimatedImageToWordAudio": true, // For animated AVIF images, prepend a frozen first frame matching the existing word-audio duration so motion starts with sentence audio. Values: true | false
       "normalizeAudio": true, // Normalize generated sentence audio loudness during media extraction. Changes apply live. Values: true | false
       "mirrorMpvVolume": true, // Apply mpv's current software volume curve to generated sentence audio. Changes apply live. Values: true | false
+      "reviewTiming": false, // Review and preview subtitle media timing before SubMiner creates or enriches a mined card. Values: true | false
       "audioPadding": 0, // Seconds of padding appended to both ends of generated sentence audio and animated AVIF clips.
       "fallbackDuration": 3, // Fallback clip duration in seconds when subtitle timing data is unavailable.
       "maxMediaDuration": 30 // Maximum allowed media clip duration in seconds.

src/anki-integration.ts

@@ -28,6 +28,8 @@ import {
   KikuMergePreviewResponse,
   NotificationOptions,
   type WordCardKind,
+  type MediaTimingReviewDecision,
+  type MediaTimingReviewRequest,
 } from './types/anki';
 import { AiConfig } from './types/integrations';
 import type { KnownWordMaturityTier } from './types/subtitle';
@@ -240,6 +242,9 @@ export class AnkiIntegration {
   private recordCardsMinedCallback: ((count: number, noteIds?: number[]) => void) | null = null;
   private knownWordCacheUpdatedCallback: (() => void) | null = null;
   private consumeSubtitleMiningContextCallback: (() => SubtitleMiningContext | null) | null = null;
+  private mediaTimingReviewCallback:
+    | ((request: MediaTimingReviewRequest) => Promise<MediaTimingReviewDecision>)
+    | null = null;
   private noteIdRedirects = new Map<number, number>();
   private trackedDuplicateNoteIds = new Map<number, number[]>();
   private getCachedMediaPath: MediaGenerationInputResolverOptions['getCachedMediaPath'] | null =
@@ -511,6 +516,7 @@ export class AnkiIntegration {
         findNotes: async (query, options) =>
           (await this.client.findNotes(query, options)) as number[],
         retrieveMediaFile: (filename) => this.client.retrieveMediaFile(filename),
+        deleteNotes: (noteIds) => this.client.deleteNotes(noteIds),
       },
       mediaGenerator: {
         generateAudio: (
@@ -568,6 +574,7 @@ export class AnkiIntegration {
       getEffectiveSentenceCardConfig: () => this.getEffectiveSentenceCardConfig(),
       getFallbackDurationSeconds: () => this.getFallbackDurationSeconds(),
       appendKnownWordsFromNoteInfo: (noteInfo) => this.appendKnownWordsFromNoteInfo(noteInfo),
+      removeKnownWordNote: (noteId) => this.removeKnownWordNote(noteId),
       isUpdateInProgress: () => this.updateInProgress,
       setUpdateInProgress: (value) => {
         this.updateInProgress = value;
@@ -583,6 +590,7 @@ export class AnkiIntegration {
       recordCardsMinedCallback: (count, noteIds) => {
         this.recordCardsMinedSafely(count, noteIds, 'card creation');
       },
+      reviewMediaTiming: (request) => this.reviewMediaTiming(request),
     });
   }
 
@@ -639,12 +647,14 @@ export class AnkiIntegration {
         notesInfo: async (noteIds) => (await this.client.notesInfo(noteIds)) as unknown,
         updateNoteFields: (noteId, fields) => this.client.updateNoteFields(noteId, fields),
         storeMediaFile: (filename, data) => this.client.storeMediaFile(filename, data),
+        deleteNotes: (noteIds) => this.client.deleteNotes(noteIds),
       },
       getConfig: () => this.config,
       getCurrentSubtitleText: () => this.mpvClient.currentSubText,
       getCurrentSubtitleStart: () => this.mpvClient.currentSubStart,
       getEffectiveSentenceCardConfig: () => this.getEffectiveSentenceCardConfig(),
       appendKnownWordsFromNoteInfo: (noteInfo) => this.appendKnownWordsFromNoteInfo(noteInfo),
+      removeKnownWordNote: (noteId) => this.removeKnownWordNote(noteId),
       extractFields: (fields) => this.extractFields(fields),
       findDuplicateNote: (expression, excludeNoteId, noteInfo) =>
         this.findDuplicateNote(expression, excludeNoteId, noteInfo),
@@ -680,6 +690,7 @@ export class AnkiIntegration {
       logWarn: (...args) => log.warn(args[0] as string, ...args.slice(1)),
       logInfo: (...args) => log.info(args[0] as string, ...args.slice(1)),
       logError: (...args) => log.error(args[0] as string, ...args.slice(1)),
+      reviewMediaTiming: (request) => this.reviewMediaTiming(request),
     });
   }
 
@@ -799,6 +810,12 @@ export class AnkiIntegration {
     }
   }
 
+  private removeKnownWordNote(noteId: number): void {
+    if (this.knownWordCache.removeNote(noteId)) {
+      this.notifyKnownWordCacheUpdated();
+    }
+  }
+
   private notifyKnownWordCacheUpdated(): void {
     if (!this.knownWordCacheUpdatedCallback) {
       return;
@@ -1039,7 +1056,7 @@ export class AnkiIntegration {
       videoPath,
       startTime,
       endTime,
-      this.config.media?.audioPadding,
+      context?.mediaPaddingSeconds ?? this.config.media?.audioPadding,
       resolveAudioStreamIndexForMediaGeneration(videoPath, this.mpvClient.currentAudioStreamIndex),
       this.config.media?.normalizeAudio !== false,
       await this.getMpvVolumeScale(),
@@ -1072,7 +1089,7 @@ export class AnkiIntegration {
         videoPath,
         mediaRange.startTime,
         mediaRange.endTime,
-        this.config.media?.audioPadding,
+        context?.mediaPaddingSeconds ?? this.config.media?.audioPadding,
         {
           fps: this.config.media?.animatedFps,
           maxWidth: this.config.media?.animatedMaxWidth,
@@ -1724,6 +1741,25 @@ export class AnkiIntegration {
     this.consumeSubtitleMiningContextCallback = callback;
   }
 
+  setMediaTimingReviewCallback(
+    callback: ((request: MediaTimingReviewRequest) => Promise<MediaTimingReviewDecision>) | null,
+  ): void {
+    this.mediaTimingReviewCallback = callback;
+  }
+
+  private async reviewMediaTiming(
+    request: Omit<MediaTimingReviewRequest, 'audioPadding' | 'maxMediaDuration'>,
+  ): Promise<MediaTimingReviewDecision> {
+    if (this.config.media?.reviewTiming !== true || !this.mediaTimingReviewCallback) {
+      return { action: 'use-original' };
+    }
+    return await this.mediaTimingReviewCallback({
+      ...request,
+      audioPadding: Math.max(0, this.config.media.audioPadding ?? 0),
+      maxMediaDuration: Math.max(0, this.config.media.maxMediaDuration ?? 30),
+    });
+  }
+
   resolveCurrentNoteId(noteId: number): number {
     let resolved = noteId;
     const seen = new Set<number>();