fix: split message type into normalized label + raw code

The scraper was writing a normalized type label ("text"/"unknown"/...) into
Message.type, but the column was Integer, so the storage layer coerced it to
NULL and the raw code was only recoverable from raw_json. Align with design
§4.3, which specifies two fields: `type` (normalized enum) and `type_raw`
(original code).

- Model (Message): type -> String(32) normalized label; add type_raw Integer
  for the raw upstream type code.
- Scraper: _normalize_message sets both `type` (label) and `type_raw`
  (coerced int from messageType/type); _is_divider now checks raw -2.
- Repos: type_raw joins _INT_FIELDS; Message.type stored as-is (string).
- Migration 96975050fa79: add type_raw + alter type Integer->String(32),
  wrapped in batch_alter_table so it runs on SQLite and MySQL.
- env.py: enable render_as_batch on SQLite (dev/test) for portable batch
  migrations; MySQL still uses direct ALTER.
- Tests updated end-to-end (scraper, repos, models).

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

yunke-server/app/db/models.py

@@ -351,7 +351,12 @@ class Message(Base):
         String(128), nullable=True
     )  # @chatroom id; NULL/empty = direct message
     is_send: Mapped[bool | None] = mapped_column(Boolean, nullable=True)  # mine/isSend
-    type: Mapped[int | None] = mapped_column(Integer, nullable=True)
+    type: Mapped[str | None] = mapped_column(
+        String(32), nullable=True
+    )  # normalized enum label (text/image/voice/.../unknown); see design §4.3
+    type_raw: Mapped[int | None] = mapped_column(
+        Integer, nullable=True
+    )  # original upstream type code (e.g. WeChat 1=text, -2=divider)
     text: Mapped[str | None] = mapped_column(Text, nullable=True)  # content/text
     file_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
     file_th_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)

yunke-server/app/scraper/wechat.py

@@ -190,6 +190,34 @@ async def scrape_wechat_friends(
 # ===========================================================================
 
 
+def _coerce_int_or_none(value: Any) -> int | None:
+    """Coerce a possibly-string numeric value to ``int``; ``None`` preserved.
+
+    Mirrors :func:`app.storage.repos._coerce_int` so the scraper can emit a
+    ready-to-store ``type_raw`` int and check raw type codes (e.g. the ``-2``
+    divider drop) without depending on the storage layer (the scraper has no
+    DB dependency by design). A non-numeric value (``"text"`` / ``None`` /
+    missing) returns ``None``.
+    """
+    if value is None:
+        return None
+    if isinstance(value, bool):
+        return int(value)
+    if isinstance(value, int):
+        return value
+    if isinstance(value, float):
+        return int(value)
+    if isinstance(value, str):
+        s = value.strip()
+        if not s:
+            return None
+        try:
+            return int(s)
+        except ValueError:
+            return None
+    return None
+
+
 async def _fetch_msg_page(
     client: YunkeClient,
     *,
@@ -245,9 +273,13 @@ def _normalize_message(record: dict[str, Any]) -> dict[str, Any]:
     """Map one upstream ``msg/chats`` record to the ``Message`` column shape.
 
     Adds ``channel="wechat"`` and preserves the original record under
-    ``raw_json``. The ``type`` field is normalized via
+    ``raw_json``. Per design §4.3 the message type is carried as TWO fields:
-    :func:`normalize_wechat_type` to a stable enum string; the raw code is
+
-    still recoverable from ``raw_json`` for the persistence layer.
+    * ``type`` — the normalized enum label (``"text"`` / ``"unknown"`` / ...)
+      via :func:`normalize_wechat_type`.
+    * ``type_raw`` — the original upstream type code (``messageType`` falling
+      back to ``type``), coerced to ``int | None`` so the raw code survives
+      end-to-end without round-tripping through ``raw_json``.
 
     ``None``-safe: missing fields become ``None`` rather than raising, so a
     partial payload does not break the whole scrape. Value coercion
@@ -281,6 +313,7 @@ def _normalize_message(record: dict[str, Any]) -> dict[str, Any]:
         "room_id": record.get("roomid"),
         "is_send": is_send,
         "type": normalize_wechat_type(raw_type),
+        "type_raw": _coerce_int_or_none(raw_type),
         "text": record.get("text"),
         "file_url": record.get("file"),
         "file_th_url": record.get("fileTh"),
@@ -305,15 +338,19 @@ def _normalize_message(record: dict[str, Any]) -> dict[str, Any]:
 
 
 def _is_divider(record: dict[str, Any]) -> bool:
-    """True iff this record is a date-divider (``type``/``messageType`` == -2).
+    """True iff this record is a date-divider (raw type code ``-2``).
 
     These are not real messages — the upstream inserts them as visual date
     bars in the chat UI — and must never be yielded or persisted. Per the
-    Task 1.6 spec we drop a record when EITHER ``type`` or ``messageType`` is
+    Task 1.6 spec we drop a record when EITHER ``messageType`` or ``type`` is
     ``-2``; all other unknown codes pass through.
+
+    The check is on the RAW code (not the normalized label) so the drop
+    decision is robust against any future change to
+    :func:`normalize_wechat_type`'s label vocabulary.
     """
-    return normalize_wechat_type(record.get("messageType")) == "divider" or (
+    return _coerce_int_or_none(record.get("messageType")) == -2 or (
-        normalize_wechat_type(record.get("type")) == "divider"
+        _coerce_int_or_none(record.get("type")) == -2
     )
 
 

yunke-server/app/storage/repos.py

@@ -23,9 +23,9 @@ dict (see :func:`_coerce_bool`, :func:`_coerce_int`):
   ``1`` / ``"1"`` / ``True`` -> ``True``; ``0`` / ``"0"`` / ``False`` ->
   ``False``; ``None`` preserved.
 * ``gender``: ``"0"`` / ``"1"`` / ``"2"`` (str) -> ``int`` when not ``None``.
-* ``type`` (Message): coerced to ``int``; a non-numeric string (e.g. a
+* ``type_raw`` (Message): the raw upstream type code, coerced to
-  normalized type label like ``"text"``) collapses to ``None`` — the raw code
+  ``int | None``. ``Message.type`` is a normalized label string and is
-  is still recoverable from ``raw_json``.
+  stored as-is (no int coercion).
 * Timestamps (``last_chat_time`` / ``timestamp`` / ``last_update`` / ...):
   passed through as-is (ms-epoch ``int`` or ``None``).
 * ``raw_json``: the original record dict, preserved verbatim. When the input
@@ -72,7 +72,7 @@ _BOOL_FIELDS: frozenset[str] = frozenset(
 _INT_FIELDS: frozenset[str] = frozenset(
     {
         "gender",
-        "type",
+        "type_raw",
         "pic_type",
         "friend_state",
         "delete_flag",
@@ -118,8 +118,7 @@ def _coerce_int(value: Any) -> int | None:
 
     ``"2"`` -> ``2``; ``2`` -> ``2``; ``0``/``"0"`` -> ``0``; ``None`` ->
     ``None``. A non-numeric string (e.g. ``"text"``) returns ``None`` — the
-    caller (Message.type) treats that as "no value", and the raw code is still
+    caller (e.g. Message.type_raw) treats that as "no value".
-    recoverable from ``raw_json``.
     """
     if value is None:
         return None
@@ -287,9 +286,10 @@ async def upsert_customers(session: AsyncSession, recs: list[dict[str, Any]]) ->
 async def upsert_messages(session: AsyncSession, recs: list[dict[str, Any]]) -> int:
     """Batch idempotent upsert for :class:`Message` (PK = ``msg_id``).
 
-    Applies the documented coercions (``is_send``/``is_del`` -> bool, ``type``
+    Applies the documented coercions (``is_send``/``is_del`` -> bool,
-    -> int). Returns the number of records processed (input length); the DB
+    ``type_raw`` -> int). ``Message.type`` is the normalized label string and
-    collapses duplicate ``msg_id`` values to one row.
+    is stored as-is. Returns the number of records processed (input length);
+    the DB collapses duplicate ``msg_id`` values to one row.
 
     .. note::
        For M1 the ``Message`` model maps to a single physical ``message``

yunke-server/migrations/env.py

@@ -50,6 +50,11 @@ def _sync_url(url: str) -> str:
 def run_migrations_offline() -> None:
     """Run migrations in 'offline' mode (emit SQL without a live connection)."""
     url = _sync_url(get_settings().db_url)
+    # SQLite cannot ALTER most column properties directly; Alembic's batch mode
+    # (table-recreate) handles it. Enable it for SQLite so the SAME migration
+    # scripts run on both SQLite (dev/test) and MySQL (prod). MySQL needs no
+    # batch mode and gets direct ALTERs.
+    render_as_batch = url.startswith("sqlite")
     context.configure(
         url=url,
         target_metadata=target_metadata,
@@ -57,6 +62,7 @@ def run_migrations_offline() -> None:
         dialect_opts={"paramstyle": "named"},
         compare_type=True,
         compare_server_default=True,
+        render_as_batch=render_as_batch,
     )
 
     with context.begin_transaction():
@@ -74,11 +80,14 @@ def run_migrations_online() -> None:
     )
 
     with connectable.connect() as connection:
+        # See offline mode for the rationale on batch mode per dialect.
+        render_as_batch = connection.dialect.name == "sqlite"
         context.configure(
             connection=connection,
             target_metadata=target_metadata,
             compare_type=True,
             compare_server_default=True,
+            render_as_batch=render_as_batch,
         )
 
         with context.begin_transaction():

yunke-server/migrations/versions/96975050fa79_message_type_split_normalized_label_and_.py

@@ -0,0 +1,59 @@
+"""message type: split normalized label and raw code
+
+Revision ID: 96975050fa79
+Revises: d7a9bc760c6b
+Create Date: 2026-08-01 12:01:31.810063
+
+Splits the ``message.type`` column to match design §4.3:
+
+* ``type`` becomes ``String(32)`` holding the NORMALIZED enum label produced
+  by :func:`app.scraper.parsers.normalize_wechat_type` (``"text"`` /
+  ``"unknown"`` / ...). Previously this column was ``Integer`` but the
+  scraper was already writing a normalized string into it, so the storage
+  layer silently coerced that string to ``NULL`` and the only way to recover
+  the raw code was via ``raw_json``.
+* ``type_raw`` (new, ``Integer``) carries the ORIGINAL upstream type code
+  end-to-end (scraper -> repos -> DB) so it no longer has to be round-tripped
+  through ``raw_json``.
+
+The operations are wrapped in ``batch_alter_table`` so the SAME migration
+runs on SQLite (dev/test, where ALTER COLUMN is unsupported and Alembic
+recreates the table) and MySQL (prod, where it emits a direct ``MODIFY
+COLUMN`` / ``ADD COLUMN``).
+"""
+from collections.abc import Sequence
+
+import sqlalchemy as sa
+from alembic import op
+
+# revision identifiers, used by Alembic.
+revision: str = '96975050fa79'
+down_revision: str | Sequence[str] | None = 'd7a9bc760c6b'
+branch_labels: str | Sequence[str] | None = None
+depends_on: str | Sequence[str] | None = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('message', schema=None) as batch_op:
+        batch_op.add_column(sa.Column('type_raw', sa.Integer(), nullable=True))
+        batch_op.alter_column('type',
+               existing_type=sa.INTEGER(),
+               type_=sa.String(length=32),
+               existing_nullable=True)
+
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('message', schema=None) as batch_op:
+        batch_op.alter_column('type',
+               existing_type=sa.String(length=32),
+               type_=sa.INTEGER(),
+               existing_nullable=True)
+        batch_op.drop_column('type_raw')
+
+    # ### end Alembic commands ###

yunke-server/tests/test_models.py

@@ -179,7 +179,8 @@ async def test_message_natural_pk():
                 owner_account_id="wxid_staff",
                 talker_id="wxid_abc",
                 is_send=False,
-                type=1,
+                type="text",
+                type_raw=1,
                 text="hello",
                 timestamp=1700000000000,
             )
@@ -195,6 +196,8 @@ async def test_message_natural_pk():
             assert fetched.text == "hello"
             assert fetched.timestamp == 1700000000000
             assert fetched.is_send is False
+            assert fetched.type == "text"
+            assert fetched.type_raw == 1
     finally:
         await engine.dispose()
 

yunke-server/tests/test_repos.py

@@ -72,10 +72,10 @@ def test_coerce_int_handles_documented_cases():
 
 
 def test_coerce_int_returns_none_for_non_numeric_string():
-    """A non-numeric string (e.g. normalized 'type' label) -> None.
+    """A non-numeric string (e.g. a label) -> None.
 
-    The column is INTEGER; a non-numeric value cannot be stored. The raw value
+    Integer columns (``type_raw``, ``gender``, ...) cannot store a
-    remains recoverable from ``raw_json``.
+    non-numeric value; the coercion collapses it to ``None``.
     """
     assert _coerce_int("text") is None
     assert _coerce_int("unknown") is None
@@ -229,7 +229,8 @@ async def test_upsert_customers_batch_returns_count():
 
 
 async def test_upsert_messages_coerces_types():
-    """is_send '1' -> True; is_del 0 -> False; same msg_id twice -> 1 row."""
+    """is_send '1' -> True; is_del 0 -> False; type label stored as string;
+    type_raw coerced to int; same msg_id twice -> 1 row."""
     engine = await _make_engine()
     try:
         SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
@@ -239,7 +240,8 @@ async def test_upsert_messages_coerces_types():
                 "channel": "wechat",
                 "is_send": "1",
                 "is_del": 0,
-                "type": "1",
+                "type": "text",  # normalized label — stored as-is (no coercion)
+                "type_raw": "1",  # raw code arrives as str -> coerced to int
                 "timestamp": 1_700_000_000_000,
             }
             await upsert_messages(session, [rec])
@@ -252,17 +254,18 @@ async def test_upsert_messages_coerces_types():
             ).scalar_one()
             assert fetched.is_send is True
             assert fetched.is_del is False
-            assert fetched.type == 1
+            assert fetched.type == "text"  # string label preserved
+            assert fetched.type_raw == 1  # raw code coerced to int
             assert fetched.timestamp == 1_700_000_000_000
 
-            # Upsert same msg_id again with different text -> row updated, not
+            # Upsert same msg_id again with different text + new raw code ->
-            # duplicated.
+            # row updated, not duplicated.
-            rec2 = dict(rec, text="updated")
+            rec2 = dict(rec, text="updated", type="unknown", type_raw=3)
             await upsert_messages(session, [rec2])
             await session.commit()
 
             # ``populate_existing=True`` bypasses the identity-map cache so we
-            # observe the second upsert's text value.
+            # observe the second upsert's values.
             rows = (
                 await session.execute(
                     sa.select(Message)
@@ -272,6 +275,34 @@ async def test_upsert_messages_coerces_types():
             ).scalars().all()
             assert len(rows) == 1
             assert rows[0].text == "updated"
+            assert rows[0].type == "unknown"
+            assert rows[0].type_raw == 3
+    finally:
+        await engine.dispose()
+
+
+async def test_upsert_messages_preserves_none_type_and_type_raw():
+    """Missing / None type & type_raw stay None (no spurious coercion)."""
+    engine = await _make_engine()
+    try:
+        SessionLocal = async_sessionmaker(engine, expire_on_commit=False)
+        async with SessionLocal() as session:
+            rec = {
+                "msg_id": "m_none",
+                "channel": "wechat",
+                "type": None,
+                "type_raw": None,
+            }
+            await upsert_messages(session, [rec])
+            await session.commit()
+
+            fetched = (
+                await session.execute(
+                    sa.select(Message).where(Message.msg_id == "m_none")
+                )
+            ).scalar_one()
+            assert fetched.type is None
+            assert fetched.type_raw is None
     finally:
         await engine.dispose()
 

yunke-server/tests/test_scrape_wechat_messages.py

@@ -106,7 +106,8 @@ async def test_scrape_wechat_messages_drops_divider_and_paginates_backward():
     assert r1["ori_talker"] == "wxid_friend_0001"
     assert r1["room_id"] == ""              # raw value carried through
     assert r1["is_send"] == 0               # pulled from `mine`
-    assert r1["type"] == "text"
+    assert r1["type"] == "text"             # normalized label (design §4.3)
+    assert r1["type_raw"] == 1              # original raw code preserved
     assert r1["text"] == "hi alice"
     assert r1["timestamp"] == E1 + 600000
     assert r1["sender_name"] == "Alice Wang"
@@ -119,6 +120,7 @@ async def test_scrape_wechat_messages_drops_divider_and_paginates_backward():
     assert r2["ori_talker"] == "room12345@chatroom"
     assert r2["is_send"] == 1
     assert r2["type"] == "unknown"          # unmapped code passes through
+    assert r2["type_raw"] == 3              # raw image-type code preserved
     assert r2["file_url"] == "https://cdn.example.com/img2.jpg"
     assert r2["file_th_url"] == "https://cdn.example.com/img2_th.jpg"
     assert r2["file_hd_url"] == "https://cdn.example.com/img2_hd.jpg"
@@ -133,6 +135,7 @@ async def test_scrape_wechat_messages_drops_divider_and_paginates_backward():
     # m3 — voice / transcription.
     assert r3["msg_id"] == "999999"
     assert r3["type"] == "unknown"
+    assert r3["type_raw"] == 34             # raw voice-type code preserved
     assert r3["duration"] == 5
     assert r3["transcription_text"] == "hello from yesterday"
     assert r3["pay_msg_id"] == "pay-abc-123"