DeepSeek-harness-lark DSH plugin

This plugin integrates DeepSeek Harness with Lark/Feishu using the official WebSocket transport, eliminating the need for a public callback server. It supports text, images, and file input, and delivers model replies, generated images, and workspace files back to the chat. Each chat maintains a persistent, isolated Harness session with agent preset fallback.

remote-execution

How to install the DeepSeek-harness-lark DSH plugin

dsh plugin --profile web add github:sliverp/DeepSeek-harness-lark

Copying does not run this command. Review the repository and version before installing the DeepSeek-harness-lark DSH plugin.

DeepSeek-harness-lark DSH plugin data source

DeepSeek-harness-lark DSH plugin snapshot date: Aug 16, 2026

discovered

What the DeepSeek-harness-lark DSH plugin can do

Official WebSocket connection with automatic reconnection
Supports text, rich text, images, and ordinary file input
Persistent, isolated Harness sessions per chat; `/new` switches to a blank session while retaining history
Agent preset mounting and recording for both creation and resume; default is `standard`
Registered slash commands are executed directly without sending to the model (e.g., `/bot-ping`, `/bot-help`, `/bot-image-test`, `/bot-file-test`, `/bot-status`, `/bot-cancel`)
Workspace file delivery to chat with path validation and security checks

Where the DeepSeek-harness-lark DSH plugin fits

Interact with DeepSeek models via Feishu or Lark instant messaging
Upload images or files for the model to analyze using its filesystem tools
Use slash commands to quickly test connectivity, get help, or cancel operations
Collaborate in group chats by mentioning the bot for AI-assisted tasks
Deliver generated files (e.g., CSVs) back to the chat as downloadable attachments

Who the DeepSeek-harness-lark DSH plugin is for

DeepSeek Harness users who want to access the system via Feishu or Lark without setting up a public server
Administrators deploying AI assistants in enterprise chat environments using Feishu or Lark

DeepSeek-harness-lark DSH plugin limitations

Requires creating a Feishu/Lark application, configuring permissions (im:message.p2p_msg:readonly, etc.), and subscribing to the im.message.receive_v1 event
File upload limits per message: 10 files, 50 MiB each, 100 MiB total; reply file limits: 5 files, 30 MiB each
Only supports Node.js >=22.19 and requires PNPM for installation
App Secret must be stored via Harness credential service or environment variables; never commit credentials

DeepSeek-harness-lark DSH plugin: from the repository README

Quoted from the sliverp/DeepSeek-harness-lark README, the upstream source of the DeepSeek-harness-lark DSH plugin. Copyright remains with the original authors.

A DeepSeek Harness channel powered by the official `@larksuiteoapi/node-sdk`. It uses the official WebSocket transport, so no public callback server is required, and supports both Feishu and international Lark. ## Features - Official WebSocket connection and automatic reconnection - Direct and group access policies; groups require a bot mention by default - Text, rich-text, image, and ordinary-file input - Durable Harness attachments with model-aware multimodal input - Ordinary files are downloaded into `.dsh-lark/inbox/` under the Agent workspace so filesystem tools can inspect them - Model text replies, generated-image upload, and workspace-file delivery - Persistent, isolated Harness sessions per chat; `/new` retains old history and switches to a blank session - Agent presets are mounted and recorded for both creation and resume; the default is `standard` - Registered Harness slash commands execute directly instead of being sent to the model - `/bot-ping`, `/bot-help`, `/bot-image-test`, `/bot-file-test`, `/bot-status`, `/bot-cancel` - App Secret resolution through the Harness credential service - Dormant startup when App ID or App Secret is not configured, so installation alo

Read the full READMERepository license: MIT

DeepSeek-harness-lark DSH plugin questions

How do I install this plugin?

Run `pnpm dsh plugin --profile web add github:sliverp/DeepSeek-harness-lark` to add it from GitHub. Alternatively, you can clone the repository and use `pnpm dsh plugin --profile web add /absolute/path/to/DeepSeek-harness-lark` for a local checkout.

What permissions does my Feishu/Lark app need?

You need to grant the following scopes: `im:message.p2p_msg:readonly`, `im:message.group_at_msg:readonly`, `im:message:readonly`, `im:message:send_as_bot`, and `im:resource`. Additionally, subscribe to the `im.message.receive_v1` event using long-connection delivery.

How do I configure the App Secret?

Store the App Secret under the Harness credential reference `LARK_APP_SECRET`. You can also use environment variables `LARK_APP_ID` and `LARK_APP_SECRET` for development. For durable use, put the App ID in `~/.dsh/.env` and store the secret through the Harness credential settings surface.

Does the plugin support international Lark?

Yes, it supports both Feishu and international Lark. You can set the `domain` configuration to `lark` (instead of `feishu`) to use the international Lark endpoints.

How can I verify the plugin is working?

Send `/bot-ping` and the bot should reply with `pong`. Then try `/bot-image-test` to receive a blue diagnostic image, and `/bot-file-test` to get a downloadable text file. Finally, send a normal message to test the conversation flow.