dsh-qq-plugin
QQ channel for DeepSeek Harness: drive the agent on your computer from your phone in QQ. Runs on Tencent's official QQ bot platform, so no public IP and no reverse proxy are needed. 适合需要通过手机QQ安全、免公网IP控制本地DSH服务的用户。
インストール
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xcisxc29/dsh-qq-pluginドキュメント
README 全文を読む ↗Usage
Just send a message and it reaches the agent:
你好
What follows is grouped by capability, and each group carries a real screenshot showing what it looks like and what it proves.
Conversation management, from your phone
One QQ chat sits in front of any number of DSH conversations. /list opens this workspace's
conversations, ten per screen:

One shot, four things proved: ten rows per screen, a six-character id at the end of every row
(7cee80, 4b55e1…), the current conversation marked ← 当前, and that footer line. The list also
tells you there are 89 more conversations in the other session folders.
/list all is the level above — the session folders (across projects and workspaces), each with
its conversation count; reply with a number or a name to enter one, and what you get is that
folder's conversation list (the screenshot replies 1, so it enters 「QQ 会话」):

Entering a folder only moves where you are browsing, not which conversation you are bound to — to actually switch you still pick a conversation inside it.
A bare digit is /switch : with the list on screen there is no need to type /switch,
just reply 2 — and it tells you which one you landed on, short id included, so you can check it
against the row you meant:

★ Quoting freezes the numbering: long-press the list message and quote it before replying with a number, and the number is read as that screen printed it. Sessions running while you read cannot make you land on the wrong one — the numbering is frozen inside that message. The list footer says so itself: 「引用这条消息再回编号,可以避免编号过期。」
Plain language works too. Here the user sends 「查看所有会话」 (show all conversations) — not a command:

The agent judges intent rather than matching fixed rules: it recognised "list conversations", listed the session folders, and told you that a number switches and 「查看其余」 turns the page. A switch also reports whether it succeeded or failed.
Type these to control which DSH conversation you are talking to:
| Command | What it does |
|---|---|
/new [title] | Start a fresh conversation. Anything after it becomes the title: /new 修复登录 starts a conversation called 「修复登录」 |
/list | Go straight to this workspace's conversations (ten per screen) |
/list all | List the session folders (workspaces) on this machine, one per line with its conversation count; reply with a number or a name to enter |
/switch 3 | Move to the 3rd row of that screen |
/switch e716f0 | Move by the short id at the end of the row — unrelated to numbering, and it never expires |
| Reply 「查看其余」 | Walk down ten rows (both levels, all the way to the end). Numbering runs on across screens (1–10, then 11–20) |
Reply 3, a name, or a trailing id | No need to type /switch while the list is on screen |
Quote a list message → /switch 3 | Numbered by that screen; the numbering is frozen inside that message |
/model | Which models there are, and each one's reasoning levels, with the one in use marked |
/model 2 | Switch to the 2nd one; a model name works too |
/model 等级 high | Change the reasoning level of the current model (the level names are the ones the list prints) |
/model 2 等级 high | Change the model and the level together |
/current | Which conversation you are in |
/cancel | Stop the task that is running |
/help | This list |
Spaces are optional: /switch3, /switch 3 and /switch:3 all work — these commands get typed
on a phone keyboard, where a dropped space is normal. A word that merely starts with a command is
not one, so /news is not /new.
Numbering expires: sessions run while you are reading the list, so by the time you reply "3" the 3rd row may be someone else. Every row therefore ends with a short id of at most 6 characters — reply with that, or quote that screen's list message and the number is read as that message printed it.
The list has two levels, ten rows per screen: /list opens this workspace's conversations;
/list all lists the session folders (workspaces), which you enter by number or name. Both
levels walk down ten rows with 「查看其余」, and numbering runs on across screens. When you reach
the end it says so instead of inviting you to keep going. Entering a folder only moves where you
are browsing, not which conversation you are bound to — to actually switch you still pick a
conversation inside it.
Models and reasoning levels
/model lists which models there are (marked 「(当前)」/「(默认)」 — current / default) and each
one's reasoning levels. /model switches model; /model 等级 high changes only the
reasoning level; /model 2 等级 high changes both. A switch takes effect from the next step.
Reasoning levels come from the host adapter. The bundled DeepSeek adapter publishes
off/low/high/max(printed asOff/Low/High/Max), and those are the names/model 等级accepts, case-insensitively. There is no separate Chinese spelling — the level names are the ones the list prints, exactly as the WeChat channel does it.
Plain language works here too — "switch to the other one", "what conversations do I have", "stop". The agent judges the intent rather than matching fixed rules, and a switch tells you whether it succeeded or failed.
Media in both directions: images, video, voice, files
In: send the agent an image / video / voice message / file from your phone. Voice is transcribed server-side and you never see that step. Document attachments (Word, Excel) are readable too.
Here is a photo of a dog sent in, with a single question — "what is this":

What is worth noticing is not that it recognised a dog but the two details only someone who really looked at the image could give: the yellow-bodied orange-beaked duck toy, the person's legs at the left edge of the frame, and its unprompted remark that the photo is sideways (the phone was held the wrong way round).
Now a PDF sent in, again with a single question — "what is this":

Document attachments are read too: it says this is a five-page recruitment task document, exported from MarkText, and summarises it as "Part 1 environment setup / Part 2 using AI plus engineering discipline / Part 3 traditional OpenCV, four tasks".
Out: the agent sends files from this computer to your phone with send_to_qq — images arrive
as photos, videos as playable clips, everything else as a file attachment:

This is the story the cover image at the top of the page tells, and it is a complete pickup: say which file you mean, the agent finds it on the computer and sends it back, and it confirms with the filename and size so you can see at a glance whether it sent the one you meant.
★ A reply that runs long is turned into a .md file and sent to your phone (4000 characters by
default, adjustable; 0 = no limit):

Something that would not fit on one phone screen is far more usable as a file — not truncated, and not split into a dozen messages that flood the chat. The threshold is the settings page's "单条回复字数上限" (per-reply character limit).
Voice: hold to talk on the phone and the agent receives text (transcribed server-side, with nothing extra for you to do):

Under that 3-second voice bubble in the screenshot is a complete weather answer — the middle step, turning speech into text, is invisible on your phone, and does not need to be visible.
Interaction
These three have no screenshots — they are a question and an answer inside the same conversation, so a picture of one would look much like the ones above; prose says it better. This is what arrives on your phone:
- Permission approvals: when the agent wants to touch your files, a pending request appears in QQ saying what it intends to do. Reply 「允许」 (allow), 「拒绝」 (deny), or a numbered option — all three answer it, and the task carries on. (For such a prompt to appear at all, the permission preset has to be one of the two that can show prompts — see Settings.)
- Either/or and multiple-choice questions: the agent's question arrives with numbered options, and a single digit answers it.
- Quoting as context: long-press and quote one of its answers before speaking — for example "expand the second point in this one" — and it knows which answer "this one" is and which point "the second" is.
Proactivity: tell me when it is done
★★ notify_qq: any session on this machine can push a message to you — that is what "tell me
when it is done" is built on. On the left is the desktop session doing the work; on the right is
what arrives on mobile QQ:


Note that the two sides are not the same session: the work was done by that desktop session, and
the message arrived in the QQ conversation you are bound to. That is exactly why
allowCrossSessionNotify is on by default — without it, the session doing the work could not report
its own result.
It works in practice: a ten-message burst was delivered in full, and the last six of those went out as proactive pushes. (Tencent's rules for unsolicited sends can change and the plugin assumes no quota; anything undelivered is queued and flushed the next time you speak.)
Scheduled tasks run through the DSH host's own schedule_create / schedule_list / schedule_delete / schedule_update — the plugin does not reimplement what DSH already has, it is only
the channel. Plain language is enough:

When the time comes it really does push one over (this is a proactive push, not you asking):

"Remind me every morning at 9 what I have to do today", "send me the current time every hour",
"show me which scheduled tasks I have" all belong here. Showing them is schedule_list, and so are
deleting and changing them.
Reliability
- A session that is archived or disappears is re-bound automatically, with a line telling you so rather than the message being swallowed: the old conversation was archived → a new one is created to carry on, and you are notified.
- State writes on Windows have retries and backoff (for the "file is in use" kind of EPERM).
- Inbound messages with empty content or an unknown frame type leave a log line instead of leaving no trace at all.
Tools the agent can use
| Tool | What it does |
|---|---|
send_to_qq | Send a file from this machine to the conversation that asked. Images arrive as photos, videos as playable clips, everything else as a file attachment |
notify_qq | Push to your current QQ conversation from any session. This is what "tell me when it is done" is built on, and it works in practice (a ten-message burst arrived in full; the last six were proactive pushes) |
qq_session_control | Look at, switch, create or interrupt conversations; list (or switch) models and their reasoning levels |
The
qq_/_qqin those names is deliberate: tool names are unique across the whole host scope, and the WeChat plugin already occupiessession_control. Two plugins claiming the same name means whichever registers second fails silently.
Those three come from the plugin. Scheduling is not among them because it does not need the
plugin to implement anything: it runs through the DSH host's own schedule_create /
schedule_list / schedule_delete / schedule_update, and the plugin's part is only to carry the
result over the QQ channel.
Settings
**Setting