A native dsh plugin bridging DeepSeek Harness coding agents to Feishu/Lark group chats, giving each group its own isolated project folder and a persistent dsh agent reachable by chat.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-05
License
NOASSERTION
01What can it help you accomplish?
Drive a live dsh coding agent straight from a Feishu/Lark group chat
A real dsh agent — with its own tools, project directory, and persistent conversation — answers in the chat via a live-updating message
Teams that run DeepSeek Harness (dsh) and collaborate over Feishu/Lark
Keep multiple projects isolated, one per group
Each chat id maps to a stable `<workspaceRoot>/<chatId>` directory; groups never share files; sessions survive restarts
Teams running several parallel projects in one workspace
Share files and images with the agent
Attachments stored in an isolated `.attachments/<messageId>/` folder and passed as paths; limits 5/message, images ≤10 MB, others ≤20 MB
Users who send context files or screenshots to the agent
02How to install into DeepSeek Harness
Not specified by the author
03DSH integration and capability boundaries
Native plugin bridging dsh coding agents to Feishu/Lark group chats — one group, one project folder — driving a live dsh agent through the host's `agents` service.
Feishu ⇄ dsh agent bridge
Inbound Feishu/Lark chat messages→A live dsh agent reply streamed onto a live-updating Feishu message
Per-chat isolated workspace
A Feishu/Lark group chat id→A stable `<workspaceRoot>/<chatId>` project directory; a persistent session that survives restarts
Attachment handling
Files and images sent to the bot→Per-message attachments stored in `.attachments/<messageId>/` and passed to the agent as paths
Writes attachment files to disk; sweeps stale files after 7 daysSlash commands
Chat-scoped commands like /help, /new, /where, /models, /whoami→Local per-chat management; owner-only /model, /preset, /allow, /disallow change shared chat state
Owner-only commands mutate shared chat state
04Who is it for? When not to use it?
Good for
- Teams that run DeepSeek Harness (dsh) and collaborate over Feishu/Lark
- Teams running several parallel projects in one workspace
- Users who send context files or screenshots to the agent
05Compatibility, maintenance and safety notes
- Requires a Feishu/Lark account. On first launch, if no credentials exist, the plugin auto-runs a QR registration wizard that registers the bot and connects automatically.
- Attachment limits: 5 attachments per message, images ≤10 MB, other files ≤20 MB; names are sanitized and stale files are swept after 7 days. Whether an image is interpreted depends on the selected model's vision support.
NOASSERTION license · latest release v0.0.1 (2026-08-20) · curated plugin
06Frequently asked questions
How do I connect dsh-lark-bridge to Feishu/Lark?
On first launch, if no credentials exist, the plugin auto-runs a QR registration wizard — open it in the Feishu app and it registers the bot and connects automatically. No portal configuration needed.
Does each group chat share files with other groups?
No. Every chat id maps to a stable directory (`<workspaceRoot>/<chatId>`) created on first use, and different groups never touch each other's files.
Can I send files or images to the agent?
Yes. The bridge stores each message's attachments in an isolated `.attachments/<messageId>/` folder and passes the paths to the agent. Limits: 5 attachments per message, images ≤10 MB, other files ≤20 MB; stale files are swept after 7 days.
How do I reset or manage a chat's session?
Use slash commands: `/new` clears the conversation, `/where` shows the project directory, `/models` lists models, `/whoami` shows identity; owner-only `/model`, `/preset`, `/allow`, and `/disallow` change shared chat state.
Do conversations survive a restart?
Yes. A chat's conversation is persistent and survives restarts via policy-fingerprint-gated resume-or-create; `/new` really clears it.
07Related DSH workflows
archify
by tt-a1i
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
openviking
by volcengine
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
nocobase
by nocobase
NocoBase is an open-source AI + no-code platform for building business systems fast. Instead of generating everything from scratch, AI works on top of production-proven infrastructure and a WYSIWYG no-code interface, so you get both speed and reliability.
learn-harness-engineering
by walkinglabs
Harness engineering beginner tutorial, from 0 to 1
08Data and sources
A native [DeepSeek Harness](https://github.com/deepseek-ai/DeepSeek-V3) (dsh) plugin that bridges dsh coding agents to *…
**Feishu ⇄ dsh agent.** Inbound Feishu messages drive a live dsh agent through the host's `agents` service; the reply st…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-05. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.