fix(stats): keep same-title anime and YouTube records separate

- Scope title identity, aliases, AniList matching, and sync by media kind
- Migrate legacy schemas while preserving IDs, history, and assignments

src/core/services/immersion-tracker/storage.ts

@@ -571,6 +571,8 @@ function ensureSubtitleLineEventIndex(db: DatabaseSync): void {
 }
 
 export function getOrCreateAnimeRecord(db: DatabaseSync, input: AnimeRecordInput): number {
+  const mediaKind = input.mediaKind ?? 'anime';
+  const anilistId = mediaKind === 'anime' ? input.anilistId : null;
   const seasonScope = normalizeSeasonScope(input.seasonScope);
   const identityTitle = buildSeasonScopedAnimeTitle(input.parsedTitle, seasonScope);
   const canonicalTitle =
@@ -582,17 +584,23 @@ export function getOrCreateAnimeRecord(db: DatabaseSync, input: AnimeRecordInput
   }
 
   const byAnilistId =
-    input.anilistId !== null
-      ? (db.prepare('SELECT anime_id FROM imm_anime WHERE anilist_id = ?').get(input.anilistId) as {
+    anilistId !== null
+      ? (db
+          .prepare("SELECT anime_id FROM imm_anime WHERE anilist_id = ? AND media_kind = 'anime'")
+          .get(anilistId) as {
           anime_id: number;
         } | null)
       : null;
   const byNormalizedTitle = db
-    .prepare('SELECT anime_id FROM imm_anime WHERE normalized_title_key = ?')
-    .get(normalizedTitleKey) as { anime_id: number } | null;
+    .prepare('SELECT anime_id FROM imm_anime WHERE normalized_title_key = ? AND media_kind = ?')
+    .get(normalizedTitleKey, mediaKind) as { anime_id: number } | null;
   const byTitleAlias = db
-    .prepare('SELECT anime_id FROM imm_anime_title_aliases WHERE normalized_title_key = ?')
-    .get(normalizedTitleKey) as { anime_id: number } | null;
+    .prepare(
+      `SELECT a.anime_id FROM imm_anime_title_aliases AS alias
+      JOIN imm_anime AS a ON a.anime_id = alias.anime_id
+      WHERE alias.normalized_title_key = ? AND a.media_kind = ?`,
+    )
+    .get(normalizedTitleKey, mediaKind) as { anime_id: number } | null;
   const existing = byAnilistId ?? byNormalizedTitle ?? byTitleAlias;
   if (existing?.anime_id) {
     // An alias remembers an intentionally merged-away spelling. Reusing it
@@ -604,7 +612,7 @@ export function getOrCreateAnimeRecord(db: DatabaseSync, input: AnimeRecordInput
         SET
           media_kind = COALESCE(?, media_kind),
           canonical_title = COALESCE(NULLIF(?, ''), canonical_title),
-          anilist_id = COALESCE(?, anilist_id),
+          anilist_id = CASE WHEN ? = 'youtube' THEN NULL ELSE COALESCE(?, anilist_id) END,
           title_romaji = COALESCE(?, title_romaji),
           title_english = COALESCE(?, title_english),
           title_native = COALESCE(?, title_native),
@@ -615,7 +623,8 @@ export function getOrCreateAnimeRecord(db: DatabaseSync, input: AnimeRecordInput
     ).run(
       byAnilistId || byNormalizedTitle ? (input.mediaKind ?? null) : null,
       canonicalTitleUpdate,
-      input.anilistId,
+      mediaKind,
+      anilistId,
       input.titleRomaji,
       input.titleEnglish,
       input.titleNative,
@@ -648,7 +657,7 @@ export function getOrCreateAnimeRecord(db: DatabaseSync, input: AnimeRecordInput
       input.mediaKind ?? 'anime',
       normalizedTitleKey,
       canonicalTitle,
-      input.anilistId,
+      anilistId,
       input.titleRomaji,
       input.titleEnglish,
       input.titleNative,
@@ -882,13 +891,61 @@ function migrateLegacyAnimeMetadata(db: DatabaseSync): void {
   }
 }
 
+// SQLite cannot drop a table-level UNIQUE constraint. Rebuild with IDs intact
+// and foreign keys disabled so dependent history and manual assignments survive.
+function migrateAnimeTitleUniqueness(db: DatabaseSync): void {
+  const schema = db.prepare("SELECT sql FROM sqlite_master WHERE name = 'imm_anime'").get() as {
+    sql: string;
+  };
+  if (/normalized_title_key TEXT NOT NULL UNIQUE/i.test(schema.sql)) {
+    const foreignKeys = db.prepare('PRAGMA foreign_keys').get() as { foreign_keys: number };
+    const sequence = db
+      .prepare("SELECT seq FROM sqlite_sequence WHERE name = 'imm_anime'")
+      .get() as { seq: number } | null;
+    db.exec('PRAGMA foreign_keys = OFF');
+    try {
+      db.exec('BEGIN IMMEDIATE');
+      db.exec(
+        schema.sql
+          .replace(
+            /CREATE TABLE (?:IF NOT EXISTS )?["`]?imm_anime["`]?/i,
+            'CREATE TABLE imm_anime_new',
+          )
+          .replace(
+            /normalized_title_key TEXT NOT NULL UNIQUE/i,
+            'normalized_title_key TEXT NOT NULL',
+          ),
+      );
+      db.exec(`INSERT INTO imm_anime_new SELECT * FROM imm_anime;
+        DROP TABLE imm_anime;
+        ALTER TABLE imm_anime_new RENAME TO imm_anime;`);
+      if (sequence) {
+        db.prepare("UPDATE sqlite_sequence SET seq = MAX(seq, ?) WHERE name = 'imm_anime'").run(
+          sequence.seq,
+        );
+      }
+      db.exec('COMMIT');
+    } catch (error) {
+      db.exec('ROLLBACK');
+      throw error;
+    } finally {
+      db.exec(`PRAGMA foreign_keys = ${foreignKeys.foreign_keys}`);
+    }
+  }
+  db.exec(`CREATE UNIQUE INDEX IF NOT EXISTS idx_anime_kind_title
+    ON imm_anime(media_kind, normalized_title_key)`);
+}
+
 // Older builds can create channel rows with the default anime kind even after
 // the schema upgrade. Repair classification on every startup without moving videos.
 function classifyYoutubeChannels(db: DatabaseSync): void {
   db.exec(`
     UPDATE imm_anime
-    SET media_kind = 'youtube'
+    SET media_kind = 'youtube', anilist_id = NULL
     WHERE media_kind = 'anime'
+      AND NOT EXISTS (SELECT 1 FROM imm_anime AS channel
+        WHERE channel.media_kind = 'youtube'
+          AND channel.normalized_title_key = imm_anime.normalized_title_key)
       AND (
         normalized_title_key LIKE 'youtube channel %'
         OR CASE WHEN json_valid(metadata_json)
@@ -932,7 +989,7 @@ export function ensureSchema(db: DatabaseSync): void {
   db.exec(`
     CREATE TABLE IF NOT EXISTS imm_anime(
       anime_id INTEGER PRIMARY KEY AUTOINCREMENT,
-      normalized_title_key TEXT NOT NULL UNIQUE,
+      normalized_title_key TEXT NOT NULL,
       canonical_title TEXT NOT NULL,
       anilist_id INTEGER UNIQUE,
       title_romaji TEXT,
@@ -951,7 +1008,6 @@ export function ensureSchema(db: DatabaseSync): void {
     'media_kind',
     "TEXT NOT NULL DEFAULT 'anime' CHECK(media_kind IN ('anime', 'youtube'))",
   );
-  classifyYoutubeChannels(db);
   db.exec(`
     CREATE TABLE IF NOT EXISTS imm_videos(
       video_id INTEGER PRIMARY KEY AUTOINCREMENT,
@@ -1495,6 +1551,8 @@ export function ensureSchema(db: DatabaseSync): void {
     );
   }
 
+  migrateAnimeTitleUniqueness(db);
+  classifyYoutubeChannels(db);
   migrateSessionEventTimestampsToText(db);
 
   ensureLexicalDailyRollupTables(db);

src/core/services/immersion-tracker/types.ts

@@ -1,6 +1,6 @@
 import type { MediaKind } from '../../../shared/media-kind';
 
-export const SCHEMA_VERSION = 24;
+export const SCHEMA_VERSION = 25;
 export const DEFAULT_QUEUE_CAP = 1_000;
 export const DEFAULT_BATCH_SIZE = 25;
 export const DEFAULT_FLUSH_INTERVAL_MS = 500;

src/core/services/immersion-tracker/youtube-kind.test.ts

@@ -81,7 +81,7 @@ test('schema 23 channel migration preserves history and manual assignments and i
     const history = getAnimeLibrary(db);
     // Reproduce the previous schema, including its lack of a media kind column.
     db.exec(
-      'ALTER TABLE imm_anime DROP COLUMN media_kind; DELETE FROM imm_schema_version; INSERT INTO imm_schema_version VALUES (23, 0)',
+      'DROP INDEX idx_anime_kind_title; ALTER TABLE imm_anime DROP COLUMN media_kind; DELETE FROM imm_schema_version; INSERT INTO imm_schema_version VALUES (23, 0)',
     );
     ensureSchema(db);
     ensureSchema(db);
@@ -163,6 +163,7 @@ test('startup reclassifies channels created by an older build after the schema u
     ensureSchema(db);
     // An old build omits media_kind when creating a channel in the upgraded DB.
     const channelId = createAnime(db, 'youtube-channel:UCnew');
+    db.prepare('UPDATE imm_anime SET anilist_id = 321 WHERE anime_id = ?').run(channelId);
     const animeId = createAnime(db, 'Regular anime');
     const videoId = createVideo(db, 'older-build');
     db.prepare(
@@ -176,6 +177,14 @@ test('startup reclassifies channels created by an older build after the schema u
     const channel = getAnimeLibrary(db)[0];
     assert.equal(channel?.animeId, channelId);
     assert.equal(channel?.mediaKind, 'youtube');
+    assert.equal(
+      (
+        db.prepare('SELECT anilist_id FROM imm_anime WHERE anime_id = ?').get(channelId) as {
+          anilist_id: number | null;
+        }
+      ).anilist_id,
+      null,
+    );
     assert.equal(channel?.totalActiveMs, 120000);
     assert.equal(channel?.totalCards, 5);
     assert.equal(linkYoutubeVideoToAnimeRecord(db, videoId, metadata), channelId);
@@ -186,3 +195,116 @@ test('startup reclassifies channels created by an older build after the schema u
     db.close();
   }
 });
+
+test('title identity and aliases never cross media kinds', () => {
+  const db = new Database(':memory:');
+  try {
+    ensureSchema(db);
+    const animeId = createAnime(db, 'Shared title');
+    const input = {
+      mediaKind: 'youtube' as const,
+      parsedTitle: 'Shared title',
+      canonicalTitle: 'Shared title',
+      anilistId: null,
+      titleRomaji: null,
+      titleEnglish: null,
+      titleNative: null,
+      metadataJson: null,
+    };
+    const channelId = getOrCreateAnimeRecord(db, input);
+    assert.notEqual(channelId, animeId);
+    db.prepare('UPDATE imm_anime SET anilist_id = 123 WHERE anime_id = ?').run(channelId);
+    assert.equal(getOrCreateAnimeRecord(db, input), channelId);
+    assert.equal(
+      (
+        db.prepare('SELECT anilist_id FROM imm_anime WHERE anime_id = ?').get(channelId) as {
+          anilist_id: number | null;
+        }
+      ).anilist_id,
+      null,
+    );
+    assert.equal(createAnime(db, 'Shared title'), animeId);
+    db.prepare(
+      'INSERT INTO imm_anime_title_aliases(normalized_title_key, anime_id) VALUES (?, ?)',
+    ).run('alias title', animeId);
+    assert.notEqual(getOrCreateAnimeRecord(db, { ...input, parsedTitle: 'Alias title' }), animeId);
+    assert.throws(() =>
+      db
+        .prepare(
+          "INSERT INTO imm_anime(normalized_title_key, canonical_title, media_kind) VALUES ('shared title', 'duplicate', 'youtube')",
+        )
+        .run(),
+    );
+  } finally {
+    db.close();
+  }
+});
+
+test('schema 24 title constraint migration preserves referenced data', () => {
+  const db = new Database(':memory:');
+  try {
+    // Reproduce the original table-level uniqueness constraint.
+    db.exec(`CREATE TABLE imm_anime(
+      anime_id INTEGER PRIMARY KEY AUTOINCREMENT,
+      normalized_title_key TEXT NOT NULL UNIQUE,
+      canonical_title TEXT NOT NULL,
+      anilist_id INTEGER UNIQUE,
+      title_romaji TEXT, title_english TEXT, title_native TEXT,
+      episodes_total INTEGER, description TEXT, metadata_json TEXT,
+      CREATED_DATE TEXT, LAST_UPDATE_DATE TEXT,
+      media_kind TEXT NOT NULL DEFAULT 'anime' CHECK(media_kind IN ('anime', 'youtube'))
+    )`);
+    ensureSchema(db);
+    const animeId = createAnime(db, 'Shared title');
+    const videoId = createVideo(db, 'migration-video');
+    db.prepare(
+      'UPDATE imm_videos SET anime_id = ?, anime_assignment_locked = 1 WHERE video_id = ?',
+    ).run(animeId, videoId);
+    db.prepare(
+      'INSERT INTO imm_lifetime_anime(anime_id, total_active_ms, total_cards) VALUES (?, 123, 4)',
+    ).run(animeId);
+    // Restore the old constraint while leaving child rows populated.
+    db.exec(`PRAGMA foreign_keys = OFF;
+      CREATE TABLE old_anime AS SELECT * FROM imm_anime;
+      DROP TABLE imm_anime;
+      CREATE TABLE imm_anime(
+        anime_id INTEGER PRIMARY KEY AUTOINCREMENT, normalized_title_key TEXT NOT NULL UNIQUE,
+        canonical_title TEXT NOT NULL, anilist_id INTEGER UNIQUE,
+        title_romaji TEXT, title_english TEXT, title_native TEXT, episodes_total INTEGER,
+        description TEXT, metadata_json TEXT, CREATED_DATE TEXT, LAST_UPDATE_DATE TEXT,
+        media_kind TEXT NOT NULL DEFAULT 'anime' CHECK(media_kind IN ('anime', 'youtube')));
+      INSERT INTO imm_anime SELECT * FROM old_anime;
+      DROP TABLE old_anime;
+      DELETE FROM imm_schema_version;
+      INSERT INTO imm_schema_version VALUES (24, 0);
+      PRAGMA foreign_keys = ON;`);
+    ensureSchema(db);
+    ensureSchema(db);
+    assert.deepEqual(db.prepare('PRAGMA foreign_key_check').all(), []);
+    assert.equal(
+      (db.prepare('PRAGMA foreign_keys').get() as { foreign_keys: number }).foreign_keys,
+      1,
+    );
+    assert.equal(
+      (
+        db.prepare('SELECT anime_id FROM imm_videos WHERE video_id = ?').get(videoId) as {
+          anime_id: number;
+        }
+      ).anime_id,
+      animeId,
+    );
+    assert.equal(
+      (
+        db
+          .prepare('SELECT total_active_ms FROM imm_lifetime_anime WHERE anime_id = ?')
+          .get(animeId) as { total_active_ms: number }
+      ).total_active_ms,
+      123,
+    );
+    db.prepare(
+      "INSERT INTO imm_anime(normalized_title_key, canonical_title, media_kind) VALUES ('shared title', 'Channel', 'youtube')",
+    ).run();
+  } finally {
+    db.close();
+  }
+});

src/core/services/stats-sync/merge-catalog.ts

@@ -99,11 +99,28 @@ export function mergeAnime(
   summary: SyncMergeSummary,
 ): Map<number, number> {
   const map = new Map<number, number>();
-  const byAnilist = local.query('SELECT anime_id FROM imm_anime WHERE anilist_id = ?');
-  const byTitleKey = local.query('SELECT anime_id FROM imm_anime WHERE normalized_title_key = ?');
+  const byAnilist = local.query(
+    "SELECT anime_id FROM imm_anime WHERE anilist_id = ? AND media_kind = 'anime'",
+  );
+  const byTitleKey = local.query(
+    'SELECT anime_id FROM imm_anime WHERE normalized_title_key = ? AND media_kind = ?',
+  );
+  // A pre-classification channel can be repaired, but a genuine anime sharing
+  // its title must remain a separate entry.
+  const legacyChannel = local.query(`SELECT anime_id FROM imm_anime
+    WHERE normalized_title_key = ? AND media_kind = 'anime' AND (
+      normalized_title_key LIKE 'youtube channel %'
+      OR CASE WHEN json_valid(metadata_json)
+        THEN json_extract(metadata_json, '$.source') = 'youtube-channel' ELSE 0 END
+    )`);
+  const releaseChannelAnilistId = local.query(
+    "UPDATE imm_anime SET anilist_id = NULL WHERE media_kind = 'youtube' AND anilist_id = ?",
+  );
   const fillMissing = local.query(
     `UPDATE imm_anime
      SET
+       media_kind = ?,
+       anilist_id = CASE WHEN ? = 'youtube' THEN NULL ELSE anilist_id END,
        title_romaji = COALESCE(title_romaji, ?),
        title_english = COALESCE(title_english, ?),
        title_native = COALESCE(title_native, ?),
@@ -117,12 +134,24 @@ export function mergeAnime(
     `SELECT anime_id, ${ANIME_COPY_COLUMNS.join(', ')} FROM imm_anime`,
   )) {
     const remoteId = Number(row.anime_id);
-    const existing = ((row.anilist_id !== null ? byAnilist.get(row.anilist_id) : undefined) ??
-      byTitleKey.get(row.normalized_title_key)) as SqlRow | undefined;
+    if (row.media_kind === 'anime' && row.anilist_id !== null) {
+      // AniList identifiers belong to anime, including when an older peer
+      // incorrectly attached one to a channel.
+      releaseChannelAnilistId.run(row.anilist_id);
+    }
+    const existing = ((row.media_kind === 'anime' && row.anilist_id !== null
+      ? byAnilist.get(row.anilist_id)
+      : undefined) ??
+      byTitleKey.get(row.normalized_title_key, row.media_kind) ??
+      (row.media_kind === 'youtube' ? legacyChannel.get(row.normalized_title_key) : undefined)) as
+      | SqlRow
+      | undefined;
     if (existing) {
       const localId = Number(existing.anime_id);
       map.set(remoteId, localId);
       fillMissing.run(
+        row.media_kind,
+        row.media_kind,
         row.title_romaji,
         row.title_english,
         row.title_native,
@@ -134,7 +163,9 @@ export function mergeAnime(
     }
     // No local row matched by anilist_id (checked first in `existing` above)
     // or title key, so the remote anilist_id — if any — is free to insert as-is.
-    const values = ANIME_COPY_COLUMNS.map((column) => row[column]);
+    const values = ANIME_COPY_COLUMNS.map((column) =>
+      column === 'anilist_id' && row.media_kind !== 'anime' ? null : row[column],
+    );
     map.set(remoteId, insertRow(local, 'imm_anime', ANIME_COPY_COLUMNS, values));
     summary.animeAdded += 1;
   }

src/core/services/stats-sync/merge-occurrences.test.ts

@@ -132,3 +132,88 @@ test('sync preserves the YouTube media kind when adding a channel', () => {
     fs.rmSync(dir, { recursive: true, force: true });
   }
 });
+
+test('sync separates same-title kinds and repairs only identifiable legacy channels', () => {
+  const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'subminer-sync-kinds-'));
+  const localPath = buildDb(dir, 'local', {
+    word: 'local',
+    seenMs: BASE_MS,
+    legacyOccurrences: false,
+  });
+  const remotePath = buildDb(dir, 'remote', {
+    word: 'remote',
+    seenMs: BASE_MS,
+    legacyOccurrences: false,
+  });
+  try {
+    const local = new Database(localPath);
+    local.exec(`UPDATE imm_anime SET normalized_title_key = 'shared', anilist_id = 42;
+      INSERT INTO imm_anime(anime_id, normalized_title_key, canonical_title, metadata_json, title_english, LAST_UPDATE_DATE)
+        VALUES (2, 'legacy', 'Local channel', '{"source":"youtube-channel"}', 'Keep local', '9999999999999');
+      UPDATE imm_anime SET anilist_id = 99 WHERE anime_id = 2;
+      INSERT INTO imm_anime(anime_id, normalized_title_key, canonical_title, media_kind, anilist_id)
+        VALUES (3, 'other shared', 'Channel with bad ID', 'youtube', 77);`);
+    local.close();
+    const remote = new Database(remotePath);
+    remote.exec(`UPDATE imm_anime SET normalized_title_key = 'shared', media_kind = 'youtube', anilist_id = 42;
+      INSERT INTO imm_anime(anime_id, normalized_title_key, canonical_title, media_kind, title_english, description, LAST_UPDATE_DATE)
+        VALUES (2, 'legacy', 'Remote channel', 'youtube', 'Remote title', 'Fill missing', '1');
+      INSERT INTO imm_anime(anime_id, normalized_title_key, canonical_title, media_kind, anilist_id)
+        VALUES (3, 'other shared', 'Real anime', 'anime', 77);`);
+    remote.close();
+    mergeSnapshotIntoDb(localPath, remotePath);
+    mergeSnapshotIntoDb(localPath, remotePath);
+    const db = new Database(localPath);
+    try {
+      const rows = db
+        .prepare(
+          'SELECT media_kind FROM imm_anime WHERE normalized_title_key = ? ORDER BY media_kind',
+        )
+        .all('shared');
+      assert.deepEqual(rows, [{ media_kind: 'anime' }, { media_kind: 'youtube' }]);
+      assert.deepEqual(
+        db
+          .prepare(
+            "SELECT media_kind FROM imm_anime WHERE normalized_title_key = 'other shared' ORDER BY media_kind",
+          )
+          .all(),
+        [{ media_kind: 'anime' }, { media_kind: 'youtube' }],
+      );
+      assert.equal(
+        (
+          db.prepare('SELECT media_kind FROM imm_anime WHERE anilist_id = 77').get() as {
+            media_kind: string;
+          }
+        ).media_kind,
+        'anime',
+      );
+      assert.deepEqual(
+        db
+          .prepare(
+            'SELECT media_kind, anilist_id, title_english, description FROM imm_anime WHERE anime_id = 2',
+          )
+          .all()[0],
+        {
+          media_kind: 'youtube',
+          anilist_id: null,
+          title_english: 'Keep local',
+          description: 'Fill missing',
+        },
+      );
+      assert.equal(
+        (
+          db
+            .prepare(
+              "SELECT a.media_kind FROM imm_videos v JOIN imm_anime a ON a.anime_id = v.anime_id WHERE v.video_key = 'video-remote'",
+            )
+            .get() as { media_kind: string }
+        ).media_kind,
+        'youtube',
+      );
+    } finally {
+      db.close();
+    }
+  } finally {
+    fs.rmSync(dir, { recursive: true, force: true });
+  }
+});