yunke/docs/superpowers/plans/2026-08-07-yunke-plan4a-wa-voice-scrape.md

# Plan 4a: WA 语音通话抓取 Implementation Plan

> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.

**Goal:** 新增 WhatsApp 语音通话抓取（`scrape_wa_voice_calls`），复用云客统一语音接口 `queryWeChatVoiceList` + `callSource:"4"`，存入 `PhoneCall` 表（`channel='wa_voice_call'`），并挂进 scheduler + smoke 实跑验证，为 Plan 4b（CallList UI 对齐 WA tab）提供数据。

**Architecture:** 复用现有 `scrape_wechat_voice_calls`（`app/scraper/wechat.py:1222`）的翻页/解析/upsert 模式，在 `app/scraper/whatsapp.py` 新增 `scrape_wa_voice_calls`——唯一差异：请求 body 加 `callSource:"4"`（=WA；微信=`"0"`）、归一化 `channel="wa_voice_call"`。**不加 PhoneCall 列、不做 Alembic 迁移**（yunke 用 `Base.metadata.create_all`，无 alembic 目录）：WA 特有字段（`weChatId`=ownerWA/`callFileId`/`nextId`/`isRoom`）落 `raw_json`，员工用现有 `user_id` 列筛。

**Tech Stack:** Python 3.12 + httpx + respx（scraper 测试）+ FastAPI/SQLAlchemy（复用）。

**Spec/事实依据:**
- `docs/superpowers/specs/2026-08-06-yunke-comm-operations-audit.md`（核对表 §6 WA 语音 5 列 + 操作）
- **Phase 0 浏览器采集（2026-08-06/07）**：WA `wavoicecalllist` 页数据请求 = `POST /wechatweb/callRecord/queryWeChatVoiceList`，body `{"pageNum":1,"pageSize":10,"startTime":"...","endTime":"...","departmentId":"...","isRoom":"0","callSource":"4","ids":[],"userId":""}`，response `data.total=143` + 每行字段（见下）。**微信页同接口 `callSource:"0"`**。
- **代码分析（Explore）**：`scrape_wechat_voice_calls`（wechat.py:1222）已实现且 URL 正确；smoke.db `phone_call` 0 行是因 `scripts/smoke_wechat.py` 没调语音 scraper（非代码错）；whatsapp.py 无 voice scraper；`upsert_voice_call`（repos.py:515）复用 `_upsert_one(PhoneCall)`；PhoneCall 无 `owner_account_id` 列（weChatId 落 raw_json）。

---

## 范围

**本 plan 覆盖（4a 抓取）**：
- 新增 `scrape_wa_voice_calls`（whatsapp.py）+ TDD 测试
- 新增 `sync_wa_voice_calls`（sync 编排）+ scheduler `ENTITY_FUNCS["wa_voice_calls"]` + 接进 `_run_all_wechat`/`_run_all`
- smoke 脚本挂载 WA + 微信语音 scraper 实跑，验证填 smoke.db

**不在本 plan 范围**：
- CallList UI 对齐（WA tab/列结构/长语音 modal/统计卡片/录音异常检查/工具栏）—— **Plan 4b**（依赖本 plan 产出的真实数据字段）。
- 长语音片段抓取（`/wechatweb/call/list`）—— 随 Plan 4b 长语音 modal。
- 微信语音 scraper 改造（现状能用；若 smoke 实测返回含 WA 数据，本 plan Task 4 补 `callSource:"0"` 加固）。
- PhoneCall 加列 / Alembic 迁移（刻意避免：无 alembic 目录；channel 区分 + raw_json 足够）。

### WA 语音字段映射（Phase 0 实测 response → PhoneCall 列）

| 云客字段 | PhoneCall 列 | 说明 |
|---|---|---|
| `id` | `call_id` (PK) | |
| — | `channel` = `"wa_voice_call"` | 区分微信(`voice_call`)/电话(`phone_call`) |
| `startTime` `"2026-08-06 11:28:22"` | `start_call_time` | `%Y-%m-%d %H:%M:%S` → ms epoch（naive UTC，同微信语音） |
| `duration` `"82"` | `call_duration` | 字符串秒 → int |
| `callStatus` (1=接通有录音/2=未接通) | `call_status` | int |
| `isSend` (0=呼入/1=呼出) | `incoming_call` | **翻转** `1 - isSend`（同微信语音，对齐 PhoneCall 极性 1=呼入）|
| `userId` | `user_id` | 员工 |
| `userName` | `user_id_name` | 员工姓名 |
| `talker` (`584142462772@s.whatsapp.net`) | `call_number` | 客户 WA id |
| `talkerNickName` | `plan_customer_name` | 脱敏昵称 |
| `ossFileName` (mp3 URL 或 null) | `record_file` | 录音直链 |
| `version` | `version` | |
| `weChatId`/`callFileId`/`nextId`/`isRoom`/`from` 等 | `raw_json` | WA 特有，无对应列 |

---

## 运行命令（验证用）

- 单测：`cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_scrape_wa_voice_calls.py -q`
- 全后端：`cd yunke-server && .venv/Scripts/python.exe -m pytest tests/ -q`
- smoke 实跑（填 smoke.db）：`cd yunke-server && DB_URL="sqlite+aiosqlite:///./smoke.db" .venv/Scripts/python.exe -m app.sync.cli sync --entity wa_voice_calls`（.env 有 YK_USERID/COMPANY/COOKIE）
- 查 smoke.db：`cd yunke-server && .venv/Scripts/python.exe -c "import sqlite3;c=sqlite3.connect('smoke.db');print(c.execute(\"select channel,count(*) from phone_call group by channel\").fetchall())"`

---

## File Map

- Modify `app/scraper/whatsapp.py` — 新增 `scrape_wa_voice_calls` + `_build_wa_voice_body`/`_normalize_wa_voice_call`/`_parse_wa_voice_total`/`_parse_wa_voice_rows` + 常量 + `__all__`
- Create `tests/test_scrape_wa_voice_calls.py` — TDD（respx + cassette，照 `test_scrape_wechat_voice_calls.py`）
- Create `tests/cassettes/wa_voice_fixture.py` — WA 响应 fixture（照 `voiceCall_fixture.py`）
- Modify sync 编排（`app/sync/` 下含 `sync_wechat_voice_calls` 的模块）— 新增 `sync_wa_voice_calls`
- Modify `app/sync/scheduler.py` — `ENTITY_FUNCS["wa_voice_calls"]` + 接进 `_run_all_wechat`/`_run_all`
- Modify `scripts/smoke_wechat.py`（或新 `scripts/smoke_calls.py`）— 挂载 voice/wa_voice/phone/sms scraper

---

## Task 1: WA 语音 scraper + 解析（TDD）

> 事实：`scrape_wechat_voice_calls`（wechat.py:1222）用 `paginate_by_page` + `VOICE_LIST_PATH="/wechatweb/callRecord/queryWeChatVoiceList"` + `_parse_voice_total`（读 `data.total`）/`_parse_voice_rows`（读 `data.data`）+ `_build_voice_body`（`{pageNum,pageSize}`）+ `_normalize_voice_call`。WA 用**同接口同 envelope**，仅 body 加 `callSource:"4"`、channel 改 `wa_voice_call`。`paginate_by_page` 签名见 `scraper/base.py`。`coerce_int_or_none` + `parse_datetime_to_ms` 都从 `app.scraper.parsers`（whatsapp.py:36 已 import，直接用）。

**Files:**
- Create: `tests/cassettes/wa_voice_fixture.py`
- Create: `tests/test_scrape_wa_voice_calls.py`
- Modify: `app/scraper/whatsapp.py`

- [ ] **Step 1: 写 WA 响应 fixture**（`tests/cassettes/wa_voice_fixture.py`，照 `tests/cassettes/voiceCall_fixture.py` 模式）：导出 `WA_VOICE_RECORDS`（2-3 条 WA 记录，字段对齐 Phase 0 实测：`id`/`userId`/`userName`/`userWeChatNickName`/`userWeChatAlias`/`talker`/`talkerNickName`/`talkerAlias`/`callType`/`isSend`/`callStatus`/`ossFileName`/`duration`/`startTime`/`weChatId`/`callFileId`/`nextId`/`isRoom`/`version`）+ `make_wa_voice_list_response(records, total, page_num, page_size)`（返回 `{"message":"调用成功","code":"10000","data":{"pageNum":...,"pageSize":...,"total":total,"data":records}}` envelope）。先读 `voiceCall_fixture.py` 对齐 `make_voice_list_response` 的确切结构。

- [ ] **Step 2: 写失败测试**（`tests/test_scrape_wa_voice_calls.py`，照 `test_scrape_wechat_voice_calls.py` 的 respx 模式）：
```python
from __future__ import annotations
import httpx, respx
from app.scraper.whatsapp import scrape_wa_voice_calls
from app.session.yunke_client import YunkeClient
from tests.cassettes.wa_voice_fixture import WA_VOICE_RECORDS, TOTAL, make_wa_voice_list_response

BASE = "https://crm2.yunkecn.com"
VOICE_URL = f"{BASE}/wechatweb/callRecord/queryWeChatVoiceList"

def _primed_client() -> YunkeClient:
    return YunkeClient(base_url=BASE, userid="a"*32, company="8m0atd")

@respx.mock
async def test_scrape_wa_voice_calls_yields_records_and_paginates():
    """两页 + 空页终止 -> 全部记录；body 含 callSource=4；channel=wa_voice_call。"""
    page1 = make_wa_voice_list_response(WA_VOICE_RECORDS[:2], total=TOTAL, page_num=1, page_size=2)
    page2 = make_wa_voice_list_response(WA_VOICE_RECORDS[2:], total=TOTAL, page_num=2, page_size=2)
    page3 = make_wa_voice_list_response([], total=TOTAL, page_num=3, page_size=2)
    route = respx.post(VOICE_URL).mock(side_effect=[
        httpx.Response(200, json=page1), httpx.Response(200, json=page2), httpx.Response(200, json=page3)])
    client = _primed_client()
    try:
        results = [r async for r in scrape_wa_voice_calls(client, page_size=2)]
    finally:
        await client.aclose()
    assert route.call_count == 3
    assert len(results) == len(WA_VOICE_RECORDS)
    import json as _json
    body1 = _json.loads(route.calls[0].request.content.decode())
    assert body1["callSource"] == "4"   # 关键：WA 区分
    assert body1["pageNum"] == 1 and body1["pageSize"] == 2
    for result, record in zip(results, WA_VOICE_RECORDS, strict=True):
        assert result["channel"] == "wa_voice_call"
        assert result["call_id"] == record["id"]
        assert result["call_number"] == record["talker"]              # friendWA
        assert result["record_file"] == record["ossFileName"]
        assert result["call_status"] == record["callStatus"]
        assert result["raw_json"] == record                            # weChatId/callFileId 保 raw_json
        # incoming_call 翻转
        assert result["incoming_call"] == 1 - record["isSend"]

@respx.mock
async def test_scrape_wa_voice_calls_stops_on_empty_first_page():
    empty = make_wa_voice_list_response([], total=0, page_num=1)
    route = respx.post(VOICE_URL).mock(return_value=httpx.Response(200, json=empty))
    client = _primed_client()
    try:
        results = [r async for r in scrape_wa_voice_calls(client)]
    finally:
        await client.aclose()
    assert results == [] and route.call_count == 1
```
> implementer：参照 `test_scrape_wechat_voice_calls.py` 的 `_ms`/断言风格补全（start_call_time 的 ms 断言等）。先确认 `voiceCall_fixture.py` 的 `TOTAL`/`DEFAULT_PAGE_SIZE` 命名，WA fixture 对齐。

- [ ] **Step 3: 跑测试确认 FAIL**
```bash
cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_scrape_wa_voice_calls.py -x -q
```
预期：FAIL（`scrape_wa_voice_calls` 不存在，ImportError）。

- [ ] **Step 4: 实现 WA scraper**（`app/scraper/whatsapp.py`，加在文件末尾，import `paginate_by_page` 已在 L35）：
```python
# ===========================================================================
# Voice-call scraper — POST /wechatweb/callRecord/queryWeChatVoiceList (callSource=4)
# 复用云客统一语音接口（微信 callSource=0 / WA callSource=4）；envelope 同微信语音
# (data.data / data.total)。channel="wa_voice_call" 区分。
# ===========================================================================

WA_VOICE_LIST_PATH = "/wechatweb/callRecord/queryWeChatVoiceList"


def _parse_wa_voice_total(resp: Any) -> int | None:
    """data.total（同微信语音 envelope）。"""
    try:
        body = resp.json()
    except (AttributeError, ValueError):
        return None
    data = body.get("data") if isinstance(body, dict) else None
    if not isinstance(data, dict):
        return None
    total = data.get("total")
    return int(total) if isinstance(total, (int, float)) and not isinstance(total, bool) else None


def _parse_wa_voice_rows(resp: Any) -> list[dict[str, Any]]:
    """data.data（同微信语音 envelope）。"""
    try:
        body = resp.json()
    except (AttributeError, ValueError):
        return []
    data = body.get("data") if isinstance(body, dict) else None
    if not isinstance(data, dict):
        return []
    rows = data.get("data")
    return rows if isinstance(rows, list) else []


def _build_wa_voice_body(page_num: int, page_size: int) -> dict[str, Any]:
    """WA 语音请求体：分页 + callSource=4（WA）。"""
    return {"pageNum": page_num, "pageSize": page_size, "callSource": "4"}


def _normalize_wa_voice_call(record: dict[str, Any]) -> dict[str, Any]:
    """Map one WA queryWeChatVoiceList record -> PhoneCall shape (channel="wa_voice_call")。

    字段映射同微信语音（_normalize_voice_call），唯二差异：channel 标 wa_voice_call；
    WA 特有字段（weChatId=ownerWA / callFileId / nextId / isRoom / from）无对应列，落 raw_json。
    isSend 翻转极性（0=呼入 -> incoming_call=1）。None-safe。
    """
    is_send = coerce_int_or_none(record.get("isSend"))
    incoming_call = None if is_send is None else 1 - is_send
    return {
        "call_id": record.get("id"),
        "channel": "wa_voice_call",
        "start_call_time": parse_datetime_to_ms(record.get("startTime"), _WA_DATETIME_FORMATS),
        "call_duration": coerce_int_or_none(record.get("duration")),
        "call_status": coerce_int_or_none(record.get("callStatus")),
        "incoming_call": incoming_call,
        "user_id": record.get("userId"),
        "user_id_name": record.get("userName"),
        "call_number": record.get("talker"),
        "plan_customer_name": record.get("talkerNickName"),
        "record_file": record.get("ossFileName"),
        "version": record.get("version"),
        "raw_json": record,
    }


async def scrape_wa_voice_calls(
    client: YunkeClient,
    *,
    page_size: int = 50,
) -> AsyncIterator[dict[str, Any]]:
    """Yield normalized WA voice-call records (queryWeChatVoiceList + callSource=4)."""
    async for record in paginate_by_page(
        client,
        WA_VOICE_LIST_PATH,
        page_size=page_size,
        parse_total=_parse_wa_voice_total,
        parse_rows=_parse_wa_voice_rows,
        build_body=_build_wa_voice_body,
    ):
        yield _normalize_wa_voice_call(record)
```
> 注意：`coerce_int_or_none`/`parse_datetime_to_ms` 从 `app.scraper.parsers`（L36 已 import）。`_WA_DATETIME_FORMATS`（L50）含 `%Y-%m-%d %H:%M:%S`，WA startTime 是这格式——直接用（比微信的 `_parse_voice_start_time` 更简，复用 WA 既有格式列表）。把 `"scrape_wa_voice_calls"` 加入 `__all__`（L39-43）。

- [ ] **Step 5: 跑测试确认 PASS**
```bash
cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_scrape_wa_voice_calls.py -x -q
```

- [ ] **Step 6: 全后端回归**
```bash
cd yunke-server && .venv/Scripts/python.exe -m pytest tests/ -q
```
预期：全绿（原 ≥333 + 新增）。

- [ ] **Step 7: Commit**
```bash
git add yunke-server/app/scraper/whatsapp.py yunke-server/tests/test_scrape_wa_voice_calls.py yunke-server/tests/cassettes/wa_voice_fixture.py
git commit -m "$(cat <<'EOF'
feat(scraper): WA 语音通话抓取 scrape_wa_voice_calls（callSource=4）

复用云客统一语音接口 queryWeChatVoiceList + callSource=4；channel=wa_voice_call
区分；WA 特有字段落 raw_json；复用 PhoneCall 表 + upsert_voice_call。

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
```

---

## Task 2: sync 编排 + scheduler 注册

> 事实：`scheduler.py:149-152` `_run_voice_calls` → `sync_wechat_voice_calls`（在 `app/sync/` 下，grep 定位）。`ENTITY_FUNCS`（scheduler.py:212-225）含 `"voice_calls": _run_voice_calls`。`_run_all_wechat`（:182-193）顺序含 voice_calls；`_run_all`（:196-206）= _run_all_wechat + phone_calls + sms。`upsert_voice_call`（repos.py:515）。

**Files:**
- Modify: `app/sync/`（含 `sync_wechat_voice_calls` 的模块，grep 定位）
- Modify: `app/sync/scheduler.py`

- [ ] **Step 1: 照写 `sync_wa_voice_calls`（orchestrator.py）**。`sync_wechat_voice_calls` 在 `app/sync/orchestrator.py:487`（签名 `(session: AsyncSession, client: YunkeClient) -> SyncResult`，调 `scrape_wechat_voice_calls` + `upsert_voice_call`）。读它，紧邻照写 `sync_wa_voice_calls(session, client)`（调 `scrape_wa_voice_calls` + `upsert_voice_call`，其余 session/日志/计数/SyncResult 照搬）。import `scrape_wa_voice_calls` from `app.scraper.whatsapp`。

- [ ] **Step 2: 接进 daily 序列 + scheduler ENTITY_FUNCS**。
  (a) **daily 序列在 orchestrator.py，不是 scheduler.py**：`sync_all_wechat`（orchestrator.py 约 :576-582）的串行序列里，在 `await sync_wechat_voice_calls(session, client)` 那行后插入 `await sync_wa_voice_calls(session, client),`。这让 `_run_all`/daily cron 覆盖 WA voice（scheduler 的 `_run_all_wechat` 只是委托给 `sync_all_wechat`，实体顺序在后者）。
  (b) **scheduler ENTITY_FUNCS**（单实体 CLI 用）：`scheduler.py` 加 helper——**照 `_run_voice_calls`（:149-152）签名 `(session, client, store) -> list[SyncResult]`，不是 `(client)->int`**：
  ```python
  async def _run_wa_voice_calls(session, client, store) -> list[SyncResult]:
      return [await sync_wa_voice_calls(session, client)]
  ```
  `ENTITY_FUNCS` 加 `"wa_voice_calls": _run_wa_voice_calls`。import `sync_wa_voice_calls`（from orchestrator）+ `SyncResult`。

- [ ] **Step 3: 回归**
```bash
cd yunke-server && .venv/Scripts/python.exe -m pytest tests/ -q
```
（若 scheduler 有测试，确认 ENTITY_FUNCS 含新键；若无 scheduler 测试则全绿即可。）

- [ ] **Step 4: CLI 单实体冒烟（可选，需 cookie）**
```bash
cd yunke-server && DB_URL="sqlite+aiosqlite:///./smoke.db" .venv/Scripts/python.exe -m app.sync.cli sync --entity wa_voice_calls
```
预期：不报错，抓取若干 WA 语音（143 total，按 page_size 翻页）。若 cookie 失效会报 401——则跳过，靠 Task 3 smoke 验证。

- [ ] **Step 5: Commit**
```bash
git add yunke-server/app/sync/ yunke-server/app/sync/scheduler.py
git commit -m "$(cat <<'EOF'
feat(sync): sync_wa_voice_calls + scheduler ENTITY_FUNCS wa_voice_calls

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
```

---

## Task 3: smoke 脚本挂载 + 实跑验证

> 事实：`scripts/smoke_wechat.py` 只调 `scrape_wechat_friends` + `scrape_wechat_messages`（smoke.db voice 0 行根因）。CLI `app.sync.cli sync --entity <name>` 走 ENTITY_FUNCS。

**Files:**
- Modify: `scripts/smoke_wechat.py`（或新建 `scripts/smoke_calls.py`）

- [ ] **Step 1: 挂载语音 scraper 到 smoke**。读 `scripts/smoke_wechat.py`，在 friends/messages 调用旁加 `voice_calls` + `wa_voice_calls`（+ 可选 phone_calls/sms）的 sync 调用。或新建 `scripts/smoke_calls.py` 调 `sync_wechat_voice_calls` + `sync_wa_voice_calls` + `sync_phone_calls` + `sync_sms`。参照现有 smoke 脚本的 client 构造（cookie from .env）+ DB_URL 写入 smoke.db 模式。

- [ ] **Step 2: 实跑填 smoke.db**（需 .env 有效 cookie）：
```bash
cd yunke-server && DB_URL="sqlite+aiosqlite:///./smoke.db" .venv/Scripts/python.exe scripts/smoke_calls.py
```
（或逐实体 CLI：`... sync --entity voice_calls` 然后 `wa_voice_calls`）

- [ ] **Step 3: 验证 smoke.db 有数据**
```bash
cd yunke-server && .venv/Scripts/python.exe -c "import sqlite3;c=sqlite3.connect('smoke.db');print(c.execute(\"select channel,count(*) from phone_call group by channel\").fetchall())"
```
预期：含 `('voice_call', N)` + `('wa_voice_call', M)`（M≈143 若全抓）。若 voice_call 仍 0，说明微信 scraper 不带 callSource 返回空/异常 → 触发 Task 4。

- [ ] **Step 4: 后端 API 抽查**
```bash
curl -s "http://localhost:8000/api/calls?channel=wa_voice_call&page_size=3" | head -c 500
```
（需后端跑：`uvicorn app.api.main:app --port 8000`）预期：返回 WA 语音通话 items。

- [ ] **Step 5: Commit**
```bash
git add yunke-server/scripts/smoke_calls.py yunke-server/scripts/smoke_wechat.py
git commit -m "$(cat <<'EOF'
feat(scripts): smoke 挂载 voice/wa_voice/phone/sms scraper（验证抓取填 smoke.db）

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
```

---

## Task 4（条件）: 微信语音 callSource=0 加固

> **仅当 Task 3 实测发现**：微信 `scrape_wechat_voice_calls`（不带 callSource）返回的数据**含 WA 记录**（talker 是 `@s.whatsapp.net`）或返回空 → 才执行本 task。若微信语音正常返回（纯 wxid talker），跳过本 task。

**Files:** Modify `app/scraper/wechat.py` + `tests/test_scrape_wechat_voice_calls.py`

- [ ] **Step 1: 给 `_build_voice_body` 加 `call_source` 参数**（wechat.py:1143）：
```python
def _build_voice_body(page_num: int, page_size: int, *, call_source: str = "0") -> dict[str, Any]:
    return {"pageNum": page_num, "pageSize": page_size, "callSource": call_source}
```
`scrape_wechat_voice_calls` 调用处传 `call_source="0"`（或 paginate_by_page 的 build_body kwargs）。

- [ ] **Step 2: 更新现有测试**（`test_scrape_wechat_voice_calls.py` 的 body 断言，:232-238）：加 `assert body1["callSource"] == "0"`。

- [ ] **Step 3: 回归 + smoke 复跑确认微信纯数据**
```bash
cd yunke-server && .venv/Scripts/python.exe -m pytest tests/test_scrape_wechat_voice_calls.py -q
```

- [ ] **Step 4: Commit**
```bash
git add yunke-server/app/scraper/wechat.py yunke-server/tests/test_scrape_wechat_voice_calls.py
git commit -m "$(cat <<'EOF'
fix(scraper): 微信语音 body 加 callSource=0 明确区分（防混入 WA）

Co-Authored-By: Claude <noreply@anthropic.com>
EOF
)"
```

---

## 收尾验收

- [ ] `pytest tests/ -q` 全绿（≥333 + 新增 WA voice 测试）。
- [ ] smoke.db `phone_call` 表含 `channel='wa_voice_call'` 行（实跑验证抓取链路通）。
- [ ] `GET /api/calls?channel=wa_voice_call` 返回 WA 语音数据。
- [ ] scheduler `ENTITY_FUNCS` 含 `wa_voice_calls`，`_run_all` 覆盖。
- [ ] **为 Plan 4b 留好的数据基础**：WA 语音字段（talker=friendWA、user_id=员工、record_file=录音URL、call_status/isSend）已结构化进 PhoneCall，raw_json 保留 weChatId/callFileId 供 4b modal/匹配用。

---

## 不在本 plan 范围（Plan 4b）

- CallList.vue 加 WA tab + WA 列结构（状态/客户信息/员工信息/通话时间和录音/操作）。
- 长语音列表 modal（`/wechatweb/call/list` 抓取 + voice_clip 存储 + 匹配 UI）。
- 统计卡片（todayStatistics）、录音异常检查（`/call/check/{id}` 代理）、批量语音下载/全部导出/高级筛选工具栏。
- 微信好友/微信群 tab（isRoom 区分）—— 若 4b 需要，从 raw_json.isRoom 读或加列。