feat(sync): 长语音音频本地化(voice_clip media_hash+download+local-first playback)

Mirror download_call_recordings pattern for voice_clips:
- VoiceClip.media_hash column + Alembic migration (c4d5e6f7a8b9)
- VoiceClipOut.media_hash + frontend VoiceClip.media_hash type
- download_voice_clip_audio in app/scraper/media.py (resilient, sha256-dedup,
  same download_url/upsert_media helpers as call recordings)
- sync_voice_clip_audio orchestrator wrapper (commits own SyncRun, mirrors
  sync_call_recordings semantics)
- scheduler: _run_voice_clip_audio + ENTITY_FUNCS['voice_clip_audio'] +
  appended to daily _run_all job (after voice_clips)
- VoiceClipModal playClip local-first: /api/media/{media_hash} with OSS
  oss_file_name fallback (mirrors CallList.playRecord)

Tested: 376 pytest pass; vue-tsc clean; migration applied; 1523/1533 clips
localized (10 pending are genuine upstream HTTP 404s — resilient skip).

Co-Authored-By: Claude <noreply@anthropic.com>

yunkes/src/api/types.ts

@@ -169,6 +169,8 @@ export interface VoiceClip {
   end_time?: number | null
   /** OSS recording URL (aliyun OSS 直链). */
   oss_file_name?: string | null
+  /** sha256 media_hash of the localized audio (NULL until downloaded). */
+  media_hash?: string | null
   /** seconds */
   mp3_duration?: number | null
   /** `HH:MM:SS` formatted duration from upstream. */