GeeeekExplorer 4b25b0e76d feat(web): make the ask-user question card collapsible
The ask-user takeover rendered the pending question set as a bottom card
capped at min(60vh, 520px) with no way to reduce it, which buried the
conversation above while the user decided. Add a minimize toggle next to
the dismiss action: collapsed, the card becomes a header strip (title plus
the two icon buttons) and the option body and footer unmount; expanding
restores the full card. Drafts and the current question index live in
QuestionFlow local state, so collapse/expand never loses them. The
free-form textarea autofocuses only on first presentation, so re-expanding
does not steal focus from the toggle.

Agent Note: .agents/notes/implemented/feature/2026-08-11-collapsible-ask-user-question-card.{md,zh.md,i18n.yaml}
2026-08-17 01:18:44 +08:00
2026-08-13 15:32:38 +08:00
2026-08-13 15:32:17 +08:00
2026-08-13 13:07:24 +08:00
2026-08-13 15:32:13 +08:00
2026-08-13 13:07:24 +08:00
2026-08-13 18:37:45 +08:00
2026-08-13 18:37:45 +08:00
2026-08-13 18:29:09 +08:00
2026-08-13 01:35:47 +08:00

DeepSeek Harness

English | 中文

DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI.

It uses an architecture where everything is a plugin, and is powered by Cordis, whose design is described in A Programming Paradigm for Spatiotemporal Composability.

Developer preview

DeepSeek Harness is currently in developer preview and is iterating rapidly. THERE WILL BE COMPATIBILITY-BREAKING CHANGES.

Run

Run from npm

Install Node.js, then run:

npx @deepseek-ai/dsh web

The command starts the Web UI, served at http://127.0.0.1:3080 by default. See Web UI guide.

Run from source

To run from a repository checkout:

git clone https://github.com/deepseek-ai/deepseek-harness.git
cd deepseek-harness
pnpm install
pnpm run build
pnpm dsh web

Community and support

Contributing

See CONTRIBUTING.md.

Development

Start with the development guide and architecture documentation.

For agents, follow AGENTS.md.

License

MIT

Third-party dependencies and their licenses are disclosed in THIRD_PARTY_NOTICES.md.

Description
DeepSeek Harness
Readme MIT 122 MiB
Languages
TypeScript 96.9%
CSS 1.6%
Python 0.7%
JavaScript 0.6%
Shell 0.1%