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/db/models.py

@@ -477,6 +477,52 @@ class PhoneCall(Base):
     )
 
 
+class VoiceClip(Base):
+    """长语音片段 — source: ``POST /wechatweb/call/list`` (WeChat + WhatsApp
+    share the same endpoint, distinguished by the employee's channel).
+
+    Distinct from :class:`PhoneCall` (which holds ``callLog/list`` phone calls
+    and ``queryWeChatVoiceList`` voice-call records): a voice_clip is one of the
+    long audio segments listed in the 云客 微信长语音 / WA wavoicecalllist modals.
+    PK is the source ``id`` (a cross-employee-globally-unique bigint).
+
+    ``channel`` here is the **messaging channel** in {``wechat``, ``whatsapp``}
+    — stamped LOCALLY by the sync orchestrator based on which staff-account
+    table owns the scraped ``user_id`` (WechatAccount -> ``wechat``,
+    WhatsappAccount -> ``whatsapp``). The upstream endpoint is shared and does
+    NOT distinguish the channel in its response, so the channel must come from
+    the employee mapping, not the record.
+
+    ``start_time`` / ``end_time`` arrive as ms-epoch **strings** (e.g.
+    ``"1786072733378"``); the scraper normalizes them to ``int``.
+    """
+
+    __tablename__ = "voice_clip"
+
+    voice_clip_id: Mapped[int] = mapped_column(
+        BigInteger, primary_key=True, autoincrement=False
+    )
+    user_id: Mapped[str] = mapped_column(String(64), nullable=False)
+    user_real_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
+    wx_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
+    talker: Mapped[str | None] = mapped_column(String(128), nullable=True)
+    status: Mapped[str | None] = mapped_column(String(32), nullable=True)
+    is_send: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
+    company_code: Mapped[str | None] = mapped_column(String(64), nullable=True)
+    start_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    end_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
+    oss_file_name: Mapped[str | None] = mapped_column(String(1024), nullable=True)
+    mp3_duration: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    duration_format: Mapped[str | None] = mapped_column(String(32), nullable=True)
+    channel: Mapped[str] = mapped_column(String(16), nullable=False)
+
+    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
+    fetched_at: Mapped[dt.datetime] = _fetched_at()
+    updated_at: Mapped[dt.datetime] = _updated_at()
+
+    __table_args__ = (Index("ix_voice_clip_user_time", "user_id", "start_time"),)
+
+
 class Sms(Base):
     """短信记录 — source: ``POST /pc/customer/smsLogsList``."""
 
@@ -617,6 +663,7 @@ __all__ = [
     "Staff",
     "SyncRun",
     "SyncState",
+    "VoiceClip",
     "WechatAccount",
     "WhatsappAccount",
     "YkAccount",