title: WeChat Group Daily Digest description: Read WeChat group messages, extract public account articles and video content, and summarize article contents from URLs. Also covers WeChat message sending reverse engineering. name: wechat-group-digest
trigger: When user asks for WeChat group digest, wants to read/send WeChat messages, or reverse engineer WeChat internals.
WeChat Group Daily Digest & RE Skill
WeChat Message Sending Architecture (2026-06-30)
WeChat messages use Tencent's mars networking framework (native C++), NOT HTTP REST:
Java UI: ChattingUI → sk.p0(String msg, int type, String extra)
↓ writes to DB (status=2, history only)
mars Bridge: libMMProtocalJni.so → protobuf + ECDH/AES encrypt
mars Native: libmarscomm.so (queue), libmarsquic.so (QUIC transport)
↓ TCP/QUIC
WeChat Server
Attack Vector Analysis (5 paths, by ban risk)
| Rank | Path | Ban Risk | Status |
|---|---|---|---|
| 1 | A. DB Injection | 🟢 Low | ❌ mars uses in-memory queue |
| 2 | D. HTTP CGI Fallback | 🟢 Low | ❌ CGI through mars tunnel |
| 3 | B. LSPosed Hook sk.p0() | 🟡 Low-Med | ✅ Viable, skeleton ready |
| 4 | C. mars Queue Injection | 🟠 Med | Needs Frida native |
| 5 | E. Frida Native Protocol | 🔴 High | Tencent anti-Frida SDK |
Path A: DB Injection — BLOCKED
messagetable is history-only; mars has in-memory task queue- Status codes: 2=sent(37), 3=delivered(2692). No status=0/1 messages exist
massendinfois media upload queue only (not text)
Path D: HTTP CGI — BLOCKED
- CGI EXISTS:
POST /cgi-bin/micromsg-bin/newsendmsg, FuncID 522 - Request:
ez5 { d:int, e:LinkedList<ll4> }protobuf - Transported through mars::stn ECDH tunnel, NOT direct HTTP
Path B: LSPosed Hook — VIABLE
- Target:
com.tencent.mm.ui.chatting.component.sk.p0(String, int, String) - Module skeleton:
~/WeChatHook/ - ON-DEVICE compilation: Full toolchain at
~/tmp/android-sdk/build-tools/36.0.0/(d8, apksigner, zipalign),~/tmp/android.jar(27MB),~/tmp/api-82.jar. Gradle 9.6 + Java 17 in Termux. - Risk: WeChat historically tolerant of Xposed modules
Key File Paths
w11/r0.smali — NetSceneSendMsg (CGI path + protobuf)
w11/e0.smali — NetSceneNewSync (CGI: /cgi-bin/micromsg-bin/newsync)
r45/ez5.smali — SendMsgRequest protobuf
r45/fz5.smali — SendMsgResponse protobuf
r45/ll4.smali — Individual message protobuf
WeChat Viewer Web App (2026-07-08)
项目路径: ~/wechat-viewer/。架构原则:日报生成和图片生成走 Hermes CLI 子进程 + skill,不写死 Python。用户原话:"应该调用 Hermes 子任务来完成。不是写死 Python 代码,未来 skill 变化时没法迭代。"
- Page 1 (/): 会话列表 → 点击跳转
/chat/<talker>独立聊天页。每个群聊右侧有 📋 生成日报按钮 - Page 2 (/circle): 本地 SQLite 加工数据中心
- Page 3 (/reports): 日报列表 → 生成日报按钮 flush → Hermes CLI 子进程加载 wechat-group-digest skill → LLM 归纳话题 → Markdown 入库。每条日报有「生成图片」和「删除」按钮
- Page 4 (/report-images): 日报图片列表 → 每个日报点「生成图片」→ Hermes CLI 加载 gpt-image-gen skill → GPT Image 2 API → WSJ 风格图。有「发送微信」按钮(弹窗选联系人 → 直接调 send_image_via_hook)
- 聊天页: 无限滚动(最新在上),图片/语音/文章卡片/视频号卡片。右上角 📋 生成日报按钮
启动: bash ~/wechat-viewer/restart.sh
发图到微信: 不走 Hermes 子进程,直接 from wechat_hook_send import send_image_via_hook 在 daemon thread 里调。因为 MCP tool 在 hermes chat -t terminal 里不可用。
详见 skill wechat-web-viewer。
启动: bash ~/wechat-viewer/restart.sh(先 kill 旧进程再启动,避免端口冲突通知轰炸)
关键技术细节 (详见 references/wechat-message-content-format.md)
- sqlcipher 输出
ok\n前缀 →output[2:].strip()后再 json.loads - Flask 无法直接读 WeChat 数据目录 (PermissionError) →
_safe_exists()+su -c "cp ... /tmp && chmod 644" - 图片:
THUMBNAIL_DIRPATH://th_<hash>→image2/{hash[:2]}/{hash[2:4]}/<hash>.jpg(原图优先, 56-123KB) 或th_<hash>(缩略图回退, 2-12KB)。同 hash 的.jpg文件是微信在本地缓存的原始分辨率版本——不是在微信内打开过就不会有。 - 语音: 用
su -c find查voice2/下的msg_<hash>.amr, 文件路径含非 hash 前缀子目录 - 视频号 CDATA:
re.sub(r"<!\\[CDATA\\[(.*?)\\]\\]>", r"\\1", content)后才能提取 nickname/desc/coverUrl
Digest Pipeline (Core Workflow)
- Query WeChat group messages via MCP:
mcp_android_phone_query_wechat(sql) - Extract articles (type=49), discussions (type=1)
- Article summary reuse (2026-07-08):
a. Collect all article URLs + titles into a list
b. Call
POST http://127.0.0.1:5000/api/articles/check-summarieswith JSON{"urls": [{"url": "...", "title": "..."}, ...], "type": "summary"}c. The API returns{results: {dedup_key: {id, content, ...}}, missing: [{url, title, dedup_key}]}d. Already-summarized articles: directly include theircontentin the report, marked[已缓存]e. Missing articles: curl the article URL + generate a summary, then callPOST http://127.0.0.1:5000/api/articles/summarizewith{"url": "...", "title": "..."}to persist the new summary into daily_reports for next time - Generate complete Markdown report (titles + summaries + sources + keywords)
- Generate infographic (newspaper style, Chinese-only, no fictional content)
- Send via ADBKeyboard workflow (search-and-tap + broadcast)
Article Summary Reuse API (批量查询去重)
Endpoint: POST http://127.0.0.1:5000/api/articles/check-summaries
Request:
{
"urls": [
{"url": "https://mp.weixin.qq.com/s/...", "title": "文章标题"},
...
],
"type": "summary" // "summary" | "learn" | "" (any)
}
Response:
{
"ok": true,
"data": {
"results": {
"biz|mid|idx|sn": {
"id": 42,
"content": "# 标题 摘要\n\n核心观点...",
"report_date": "summary",
"created_at": "2026-07-08 10:30:00"
}
},
"missing": [
{"url": "https://...", "title": "未缓存文章", "dedup_key": "abc|123|1|def"}
]
}
}
To persist a freshly-generated summary so it's reusable:
curl -s -X POST http://127.0.0.1:5000/api/articles/summarize \
-H 'Content-Type: application/json' \
-d '{"url": "ARTICLE_URL", "title": "ARTICLE_TITLE"}'
This endpoint auto-returns cached results if already exists; only spawns a Hermes subprocess for new summaries.
Critical Rules
- Report-first: Always generate complete Markdown report before infographic
- Content-only: Never invent fictional sections in infographics
- Chinese-only: All infographic text in Chinese
- Complete extraction: Every article title + summary + source
- Discussion summarization: Topics + participants + viewpoints
Group Identification
- Use
rcontact.nicknamefor group name (reliable) chatroom.displaynamefor member verification only
Message Types
| Type | Meaning |
|---|---|
| 1 | Text |
| 3 | Image |
| 34 | Voice |
| 43 | Video |
| 47 | Emoji |
| 49 | Article/link |
| 10000 | System |
| 754974769 | Unsupported / Finder (解析 <finderFeed> 里的 nickname/desc/coverUrl/videoPlayDuration 做视频号卡片) |
| 822083633 | Referenced reply (appmsg with refermsg) |
FinderFeed (视频号) 解析要点: 内容包裹在 <finderFeed> XML 内,关键字段被 CDATA 包裹(如 <nickname><![CDATA[知安物语]]></nickname>)。解析前必须先 re.sub(r"<!\\[CDATA\\[(.*?)\\]\\]>", r"\\1", content) 去掉 CDATA,否则 regex 匹配不到具体值。可用字段:<nickname>, <desc>, <avatar>, <coverUrl>, <media><url> (视频下载链接), <videoPlayDuration> (秒)。
See references/wechat-message-content-format.md for complete content format reference.
- Chatroom message
sender:\nprefix stripping - Image path resolution from
imgPath(hash subdirectories,THUMBNAIL_DIRPATH://) - Voice path resolution (complex directory structure, use
find) - SQLCipher CLI quirks ("ok\n" prefix, multi-line JSON,
supermission handling) - Group name resolution (
rcontact.nicknamevschatroom.displayname)
Sending Messages (ADBKeyboard Workflow)
WARNING: The MCP tool send_wechat_message / send_wechat_message_ui() calls
am force-stop com.tencent.mm before every send (wechat_send.py:363). This kills
tablet login. If tablet login is active, use the manual ADBKeyboard workflow below
and SKIP the force-stop step.
- Open WeChat → search-and-tap target chat
- Set ADBKeyboard:
ime set com.android.adbkeyboard/.AdbIME - Clear field:
ADB_INPUT_CODE 67× 10-15 - Type:
ADB_INPUT_TEXT --es msg "text" - OCR-find send button, tap
- Verify in DB:
SELECT ... FROM message WHERE isSend=1 ORDER BY createTime DESC LIMIT 1 - Restore keyboard
Pitfall: mcp_android_phone_send_wechat_message unreliable for ALL chat types AND kills tablet login. Use manual ADBKeyboard workflow.
File Locations
- CGI analysis:
references/wechat-sendmsg-cgi-analysis.md - LSPosed module design:
references/wechat-lsposed-send-module.md - On-Device LSPosed build:
references/on-device-xposed-build.md - LSPosed DB config:
references/lsposed-module-config.md - SQLCipher DB access:
references/sqlcipher-wechat-db-access.md - MCP parsing guide:
references/mcp-output-parsing-guide.md - ADBKeyboard workflow:
references/adbkeyboard-manual-send-workflow.md - Infographic v4:
references/newspaper_infographic_v4.py
Pitfalls
- WeChat timestamps are in ms since epoch, convert to Beijing time (UTC+8)
- Group name in
rcontact.nickname, notchatroom.chatroomnick(usually NULL) mcp_android_phone_send_wechat_messageunreliable for ALL chat types- ADBKeyboard accumulates text — always clear field with backspace before typing
- Report-first workflow: NEVER generate infographic directly from raw messages
- Chinese-only infographics: titles, section names, dates all in Chinese
- Content-only rule: no fictional sections in generated images
- Outer screen send coordinates differ from inner screen — always OCR for send button
- Dozing state blocks screenshots — use
keyevent 26(power key) to wake - Foldable screens require long display IDs for screencap
- MCP output is double-escaped JSON — use
json.loads()not string replace - WeChat CGI endpoints are mars-transported, NOT plain HTTP
- On-device Android compilation IS possible — toolchain at
~/tmp/android-sdk/ - TABLET LOGIN FATAL:
send_wechat_message_ui()callsam force-stop com.tencent.mmbefore every send (wechat_send.py:363). This KILLS the tablet login session. NEVER use this function if tablet login is active. Use manual ADBKeyboard workflow WITHOUT force-stop instead. - LSPosed DAEMON FATAL:
killall lspdpermanently kills the daemon on JingMatrix Vector A16 — it does NOT auto-restart. Only reboot restores it. Never kill lspd. - LSPosed DB FATAL: Writing to
/data/adb/lspd/config/modules_config.dbvia sqlcipher/sqlite3 can trigger LSPosed's FileObserver to delete module entries. Never toggle the enabled field via SQL — use LSPosed Manager UI only. - Check tablet login before any WeChat operation: verify lspd running (
pgrep -f lspd), WeChatHook injected (grep /proc//maps for lspd .so), and WeChat not on login screen. → Full root cause analysis:references/tablet-login-protection.md