feat(db): moments_post 表+upsert(朋友圈实体,PK=云客data.id,create_time统一ms)

- MomentsPost 模型:moments_post 表,PK=id(云客 getFriendsterInfo data.id),
  wechat_id/create_time 建索引,praise/comment/image 存 JSON 列
- 迁移 524da8d2d597(手写 create_table,已应用到 smoke.db 并在临时 SQLite
  全链路 upgrade/downgrade 验证)
- repos.upsert_moments_posts:批量幂等 upsert;附带修 _build_column_values
  对 JSON 列表的误 join(标量列 join 保持不变,dept_route 旧测试仍过)
- 修复 3 个 chat_group 旧测试缺 owner_account_id(2026-08-24 复合主键遗留)
- 全套 430 测试通过

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

yunke-server/app/storage/repos.py

@@ -36,6 +36,10 @@ dict (see :func:`_coerce_bool`, :func:`_coerce_int`):
 * ``raw_json``: the original record dict, preserved verbatim. When the input
   already carries a ``raw_json`` key (scraper output does), that value wins;
   otherwise the input dict itself is stored.
+* JSON-typed list columns (``MomentsPost.praise_json`` / ``comment_json`` /
+  ``image_urls``): list values are kept verbatim (stored as JSON arrays). The
+  list -> ``";"``-join coercion only applies to lists headed for SCALAR
+  String columns (e.g. ``Customer.dept_route``).
 
 Sharding note
 -------------
@@ -60,6 +64,7 @@ from app.db.models import (
     GroupMember,
     Media,
     Message,
+    MomentsPost,
     PhoneCall,
     Sms,
     Staff,
@@ -75,6 +80,7 @@ __all__ = [
     "upsert_department",
     "upsert_media",
     "upsert_messages",
+    "upsert_moments_posts",
     "upsert_phone_call",
     "upsert_sms",
     "upsert_staff",
@@ -220,12 +226,16 @@ def _build_column_values(
       on unknown columns).
     * Boolean / int-as-str fields are coerced via :func:`_coerce_bool` /
       :func:`_coerce_int`.
+    * List values headed for SCALAR columns (e.g. ``Customer.dept_route``) are
+      joined into a ``";"``-separated string so the bind succeeds; list values
+      headed for JSON columns (e.g. ``MomentsPost.praise_json`` /
+      ``image_urls``) are kept verbatim as JSON arrays.
     * ``raw_json`` defaults to the entire input dict when not explicitly
       provided, so the verbatim upstream record is always recoverable.
     """
-    col_names = {c.name for c in model.__table__.columns}
+    cols = {c.name: c for c in model.__table__.columns}
     values: dict[str, Any] = {}
-    for col_name in col_names:
+    for col_name, col in cols.items():
         if col_name in rec:
             v = rec[col_name]
             if col_name in _BOOL_FIELDS:
@@ -235,14 +245,15 @@ def _build_column_values(
             # Some upstream fields are lists (e.g. Customer.deptRoute is a
             # list of dept ids) but map to scalar String columns — join so the
             # bind succeeds and the data is still recoverable (raw_json keeps
-            # the original list).
-            if isinstance(v, list):
+            # the original list). JSON-typed columns keep the list verbatim
+            # (MomentsPost.praise_json / comment_json / image_urls).
+            if isinstance(v, list) and not isinstance(col.type, sa.JSON):
                 v = ";".join(str(x) for x in v)
             values[col_name] = v
     # Preserve the verbatim source record. If the scraper already set raw_json
     # (it does), that wins; otherwise the input dict itself is the source of
     # truth.
-    if "raw_json" in col_names and "raw_json" not in values:
+    if "raw_json" in cols and "raw_json" not in values:
         values["raw_json"] = rec
     # Sanitize lone surrogate chars (e.g. \udf1e from emoji fragments in the
     # upstream API) that break SQLite/MySQL UTF-8 encoding. Replaces them with
@@ -602,6 +613,28 @@ async def upsert_sms(session: AsyncSession, rec: dict[str, Any]) -> None:
     await _upsert_one(session, Sms, rec)
 
 
+# ---------------------------------------------------------------------------
+# MomentsPost (员工朋友圈) upsert — 员工聊天窗口 Phase 1
+# ---------------------------------------------------------------------------
+
+
+async def upsert_moments_posts(session: AsyncSession, recs: list[dict[str, Any]]) -> int:
+    """Batch idempotent upsert for :class:`MomentsPost` (PK = ``id``).
+
+    Same ``id`` twice -> one row, with non-PK fields refreshed from the later
+    record. ``create_time`` goes through the ``_INT_FIELDS`` int coercion (it
+    must land as a ms-epoch int; 云客 returns seconds, the scraper ×1000).
+    JSON list columns (``praise_json`` / ``comment_json`` / ``image_urls``)
+    are stored verbatim as JSON arrays — the generic list->";".join coercion
+    in :func:`_build_column_values` only applies to scalar columns. Returns
+    the number of records processed (input length); the DB collapses
+    duplicate ``id`` values to one row.
+    """
+    for rec in recs:
+        await _upsert_one(session, MomentsPost, rec)
+    return len(recs)
+
+
 # ---------------------------------------------------------------------------
 # VoiceClip (长语音) upsert
 # ---------------------------------------------------------------------------