feat: phone-call + sms scrapers

M4 (/pc/ CRM module): mirror phone-call + SMS endpoints.

Scraper (app/scraper/call.py):
- scrape_phone_calls: POST /pc/callLog/list -> PhoneCall (channel='phone_call')
  Envelope data.data / data.totalCount / data.pageCount; page-number pagination.
  incomingCall (1=incoming/0=outgoing) stored DIRECTLY (no inversion, unlike
  voice-call isSend); callSeconds preferred over legacy callDuration string;
  startCallTime (YYYY-MM-DD HH:MM:SS) -> ms epoch.
- scrape_sms: POST /pc/customer/smsLogsList -> Sms (channel='sms')
  Envelope data.data / data.dataCount (NOT totalCount), no pageCount;
  relies on empty-page stop signal. createTime (YYYY-MM-DD HH:MM) -> ms epoch;
  empty smsSub normalized to None content_preview.

Shared helper: extracted parse_datetime_to_ms(value, formats) to
app/scraper/parsers.py and refactored _parse_voice_start_time to delegate
(DRY across all three call/SMS datetime sources).

Repos: upsert_phone_call + upsert_sms (idempotent Core upsert by call_id /
sms_id). Added create_time to _INT_FIELDS for defensive numeric-str coercion,
matching start_call_time's existing treatment.

Orchestrator: sync_phone_calls + sync_sms (full re-scrape + idempotent upsert
+ SyncRun log + watermark), mirroring sync_wechat_voice_calls. Entity types
'phone_call' and 'sms'.

Tests (+15, suite 211 -> 226): respx-mocked scraper tests (2-page fixtures
exercising pagination + full field mapping), repo idempotency + coercion
tests, orchestrator SyncRun/watermark tests with monkeypatched scrapers.
ruff clean.

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

yunke-server/app/sync/orchestrator.py

@@ -46,6 +46,7 @@ from typing import Any
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from app.db.models import SyncRun
+from app.scraper.call import scrape_phone_calls, scrape_sms
 from app.scraper.media import download_message_media
 from app.scraper.wechat import (
     scrape_departments,
@@ -62,6 +63,8 @@ from app.storage.repos import (
     upsert_customer,
     upsert_department,
     upsert_messages,
+    upsert_phone_call,
+    upsert_sms,
     upsert_voice_call,
     upsert_wechat_account,
 )
@@ -73,6 +76,8 @@ __all__ = [
     "SyncResult",
     "sync_all_wechat",
     "sync_departments",
+    "sync_phone_calls",
+    "sync_sms",
     "sync_wechat_accounts",
     "sync_wechat_friends",
     "sync_wechat_groups",
@@ -93,6 +98,10 @@ ENTITY_WECHAT_FRIEND = "wechat_friend"
 ENTITY_WECHAT_GROUP = "wechat_group"
 ENTITY_WECHAT_VOICE_CALL = "wechat_voice_call"
 ENTITY_MESSAGE = "message"
+# M4 (/pc/ CRM module) — phone calls + SMS share no channel column with the
+# wechat-family entities; they track their own SyncRun / SyncState rows.
+ENTITY_PHONE_CALL = "phone_call"
+ENTITY_SMS = "sms"
 
 CHANNEL_WECHAT = "wechat"
 
@@ -432,6 +441,54 @@ async def sync_wechat_voice_calls(
     )
 
 
+async def sync_phone_calls(
+    session: AsyncSession, client: YunkeClient
+) -> SyncResult:
+    """Full re-scrape of all phone-call records (``/pc/callLog/list``) and
+    idempotent upsert into :class:`PhoneCall` (``channel="phone_call"``).
+
+    Mirrors :func:`sync_wechat_voice_calls`: the callLog endpoint has no
+    ``since`` param, so "incremental" = re-scrape everything and rely on the
+    repo's idempotent Core upsert (same ``call_id`` twice -> one refreshed
+    row). Records a SyncRun row (``entity_type='phone_call'``) and stamps the
+    watermark's ``last_synced_at`` (no cursor advance — there is no upstream
+    window to close). A scraper failure is recorded as a failed SyncRun and a
+    failed SyncResult is returned (no re-raise), so a phone-call scrape that
+    500s does NOT abort a larger batch.
+    """
+    return await _sync_full_rescrape(
+        session,
+        entity_type=ENTITY_PHONE_CALL,
+        channel=None,
+        scope_id=None,
+        scrape=lambda: scrape_phone_calls(client),
+        upsert=upsert_phone_call,
+    )
+
+
+async def sync_sms(
+    session: AsyncSession, client: YunkeClient
+) -> SyncResult:
+    """Full re-scrape of all SMS records (``/pc/customer/smsLogsList``) and
+    idempotent upsert into :class:`Sms`.
+
+    Mirrors :func:`sync_phone_calls`: the smsLogsList endpoint has no
+    ``since`` param, so "incremental" = re-scrape everything and rely on the
+    repo's idempotent Core upsert (same ``sms_id`` twice -> one refreshed
+    row). Records a SyncRun row (``entity_type='sms'``) and stamps the
+    watermark's ``last_synced_at``. A scraper failure is recorded as a failed
+    SyncRun + SyncResult without re-raising.
+    """
+    return await _sync_full_rescrape(
+        session,
+        entity_type=ENTITY_SMS,
+        channel=None,
+        scope_id=None,
+        scrape=lambda: scrape_sms(client),
+        upsert=upsert_sms,
+    )
+
+
 # ---------------------------------------------------------------------------
 # Coordinator
 # ---------------------------------------------------------------------------