feat(api): 长语音 voice_clip 后端(model+migration+scraper+sync+endpoint)

- VoiceClip model (BigInteger PK voice_clip_id, structured cols + raw_json)
- Alembic migration a1b2c3d4e5f6 (chains from 8c4f1d2a9e6b)
- scrape_voice_clips(client, user_id, *, channel, page_size) per-employee scraper
  over POST /wechatweb/call/list {pageNum, pageSize, userId}; channel stamped
  locally (wechat/whatsapp), startTime/endTime ms-epoch string -> int
- upsert_voice_clip repo + start_time/end_time/mp3_duration int coercion
- sync_voice_clips orchestrator: iterates distinct user_id across
  WechatAccount + WhatsappAccount, stamps channel per account table
- scheduler ENTITY_FUNCS['voice_clips'] + added to daily 'all' job
- GET /api/voice-clips (user_id exact beats user_real_name fuzzy; channel;
  company_code; start/end window on end_time; ordered end_time desc)
- VoiceClipOut schema + router registered in main.py
- tests: scraper (5) + API (11) = 16 new; full suite 370 green

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

yunke-server/app/api/schemas.py

@@ -249,6 +249,37 @@ class SmsOut(BaseModel):
     raw_json: dict[str, Any] | None = None
 
 
+class VoiceClipOut(BaseModel):
+    """长语音 (voice_clip) row — a long audio segment from ``/wechatweb/call/list``.
+
+    The structured columns power the VoiceClipModal table (员工姓名 /
+    企业串码 / 文件地址 / 录音开始时间 / 录音结束时间 / 录音时长); the verbatim
+    upstream record is exposed as ``raw_json`` so the frontend can render any
+    extra fields without a second endpoint. Picked up automatically via
+    ``from_attributes``.
+    """
+
+    model_config = ConfigDict(from_attributes=True)
+
+    voice_clip_id: int
+    user_id: str
+    channel: str
+    user_real_name: str | None = None
+    wx_id: str | None = None
+    talker: str | None = None
+    status: str | None = None
+    is_send: bool | None = None
+    company_code: str | None = None
+    start_time: int | None = None
+    end_time: int | None = None
+    # OSS recording URL — surfaced so the modal can render an inline
+    # ``<audio controls>`` player (see spec §6).
+    oss_file_name: str | None = None
+    mp3_duration: int | None = None
+    duration_format: str | None = None
+    raw_json: dict[str, Any] | None = None
+
+
 # ---------------------------------------------------------------------------
 # Sync monitor
 # ---------------------------------------------------------------------------