feat: wechat message scraper

Adds Task 1.6: a backward-cursor paginator in base.py, a message-type
normalizer in parsers.py, and the WeChat chat-message scraper in wechat.py.

- app/scraper/parsers.py: normalize_wechat_type() maps 1 -> "text",
  -2 -> "divider", everything else -> "unknown". Total (never raises);
  unknown codes pass through so no real message is silently dropped.
- app/scraper/base.py: paginate_by_cursor() generic async generator. Takes
  a fetch(cursor) -> (rows, next_cursor, has_more) coroutine; advances the
  cursor and stops on has_more=False OR an empty page (defensive). Same
  RateLimiter integration as paginate_by_page.
- app/scraper/wechat.py: scrape_wechat_messages() wraps
  POST /wechatweb/msg/chats. Body is form-encoded (NOT JSON) — content-type
  is overridden per request to application/x-www-form-urlencoded via the
  YunkeClient.post(headers=...) override hook. Pages backward by setting
  end = data.end - 1 each batch, repeats until hasLast=false. Drops any
  record whose type/messageType is -2 (date divider UI chrome). Yields
  normalized dicts (snake_case Message columns + channel="wechat" +
  raw_json); the raw type code is preserved on raw_json for the
  persistence layer (Task 1.7).

Tests: 13 new (10 parser parametrized + 3 scraper). respx-mocked
msg/chats with two backward pages — asserts [m1, m2, m3] yielded (the -2
divider dropped), full field mapping vs the live-capture names, the
content-type is form-encoded (not JSON), and the 2nd request body's
end == E1 - 1 (proving the backward cursor advance).

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

yunke-server/tests/cassettes/msg_chats_fixture.py

@@ -0,0 +1,147 @@
+"""Fixture payloads for ``POST /wechatweb/msg/chats`` (Task 1.6).
+
+These records mirror the real field names captured from the live CRM (see the
+Task 1.6 spec). The cassette is shaped to drive the backward-cursor paginator
+across two pages:
+
+* page 1 -> ``messages=[m1, m_datebar(-2), m2]``, ``end=E1``, ``hasLast=true``
+* page 2 -> ``messages=[m3]``, ``end=E2``, ``hasLast=false``
+
+The ``-2`` record is a date divider that the scraper must DROP. ``E1`` is the
+oldest timestamp in page 1's batch, so the backward-cursor advance must set
+the next request's ``end`` to ``E1 - 1``. Page 2 reports ``hasLast=false`` so
+the scraper stops without a third fetch.
+"""
+
+from __future__ import annotations
+
+from typing import Any
+
+# Oldest-timestamp-in-batch returned by each page; the scraper uses these to
+# advance the backward cursor (next_request_end = page_end - 1).
+E1 = 1784517338999
+E2 = 1784517000000
+
+# Page 1 records, EXACT live-capture field names. m1 is text/direct/incoming,
+# m_datebar is a -2 divider (must be filtered), m2 is image/chatroom/outgoing.
+MESSAGE_RECORDS_PAGE1: list[dict[str, Any]] = [
+    {  # m1 — text message, incoming, direct (empty roomid).
+        "msgSvrId": "1000001",
+        "type": 1,
+        "messageType": 1,
+        "text": "hi alice",
+        "wechatId": "wxid_staff_alice",
+        "talker": "wxid_friend_0001",
+        "oriTalker": "wxid_friend_0001",
+        "roomid": "",
+        "mine": 0,
+        "isSend": 0,
+        "timestamp": E1 + 600000,
+        "createTime": E1 + 600000,
+        "name": "Alice Wang",
+        "headUrl": "https://cdn.example.com/alice.png",
+        "isDel": 0,
+        "version": "v1.0",
+    },
+    {  # date divider — type == -2; scraper MUST drop this, never yield it.
+        "msgSvrId": "1000000",
+        "type": -2,
+        "messageType": -2,
+        "text": "2026-01-01",
+        "wechatId": "wxid_staff_alice",
+        "talker": "wxid_friend_0001",
+        "oriTalker": "wxid_friend_0001",
+        "roomid": "",
+        "mine": 0,
+        "isSend": 0,
+        "timestamp": E1 + 300000,
+        "createTime": E1 + 300000,
+        "name": "",
+        "headUrl": "",
+        "isDel": 0,
+        "version": "v1.0",
+    },
+    {  # m2 — image message, outgoing, in a chatroom.
+        "msgSvrId": "1000002",
+        "type": 3,
+        "messageType": 3,
+        "text": "[image]",
+        "file": "https://cdn.example.com/img2.jpg",
+        "fileTh": "https://cdn.example.com/img2_th.jpg",
+        "fileHd": "https://cdn.example.com/img2_hd.jpg",
+        "md5": "md5img2",
+        "md5Th": "md5img2th",
+        "md5Hd": "md5img2hd",
+        "imgPath": "/tmp/img2.jpg",
+        "originalImage": "/tmp/img2_orig.jpg",
+        "picType": 1,
+        "wechatId": "wxid_staff_alice",
+        "talker": "wxid_friend_0001",
+        "oriTalker": "room12345@chatroom",
+        "roomid": "room12345@chatroom",
+        "mine": 1,
+        "isSend": 1,
+        "timestamp": E1 + 100,
+        "createTime": E1 + 100,
+        "name": "Bob Chen",
+        "headUrl": "https://cdn.example.com/bob.png",
+        "isDel": 0,
+        "version": "v1.0",
+    },
+]
+
+# Page 2 record — voice message, oldest in the history window.
+MESSAGE_RECORDS_PAGE2: list[dict[str, Any]] = [
+    {
+        "msgSvrId": "999999",
+        "type": 34,
+        "messageType": 34,
+        "text": "[voice]",
+        "file": "https://cdn.example.com/voice3.amr",
+        "md5": "md5voice3",
+        "duration": 5,
+        "transcriptionText": "hello from yesterday",
+        "wechatId": "wxid_staff_alice",
+        "talker": "wxid_friend_0001",
+        "oriTalker": "wxid_friend_0001",
+        "roomid": "",
+        "mine": 1,
+        "isSend": 1,
+        "timestamp": E2,
+        "createTime": E2,
+        "name": "Alice Wang",
+        "headUrl": "https://cdn.example.com/alice.png",
+        "isDel": 0,
+        "version": "v1.0",
+        "paymsgid": "pay-abc-123",
+        "referMsg": {"text": "earlier msg", "msgSvrId": "888888"},
+    },
+]
+
+
+def make_msg_chats_response(
+    messages: list[dict[str, Any]],
+    *,
+    end: int,
+    has_last: bool,
+    trace_id: str = "trace-msg-1",
+) -> dict[str, Any]:
+    """Build a capture-shaped ``msg/chats`` response envelope.
+
+    Shape (EXACT, per Task 1.6 spec)::
+
+        {"message":"调用成功","code":"10000","success":true,"traceId":"...",
+         "data":{"messages":[...], "end":<oldest ts in batch>,
+                 "hasLast":<bool — are there older messages?>}}
+    """
+    return {
+        "message": "调用成功",
+        "code": "10000",
+        "success": True,
+        "traceId": trace_id,
+        "data": {
+            "messages": list(messages),
+            "end": end,
+            "hasLast": has_last,
+        },
+    }