ChatGPT-style rich answers inside DeepSeek Harness: entity panels, KPI cards, charts, tables, layers and local controls.
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add @kyoukisu/dsh-rich-ui@0.6.2
Compatibility and provenance
Rich Ui is published as @kyoukisu/dsh-rich-ui and currently resolves to version 0.6.2. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
A model can describe a comparison, but a wall of Markdown makes the reader do the layout work. This plugin gives the model a small declarative language for the cases where structure carries the answer: side-by-side options, an object you want to inspect, a number the reader will change.
The renderer is a real React tree behind a strict schema. There is no generated HTML, no eval, no shell access, and no page-level JavaScript from the model. Local controls recompute in the browser; the model is only called again when the reader explicitly asks.
rich-ui.beako.best — the real renderer in laboratory conditions, no install. Scenarios: dashboard, films, listing, calculator, configurator, technical breakdown and the rejected-block diagnostic; add &theme=dark for the dark theme. Demo data is illustrative.
Install
Requires DeepSeek Harness 0.2.x and Node 22.19+. No NixOS change, no patched Harness.
dsh plugin --profile web add @kyoukisu/dsh-rich-ui
systemctl --user restart deepseek-harness # or restart however your Harness runs
From a checkout — this is the loop the author uses:
git clone https://github.com/kyoukisu/dsh-rich-ui && cd dsh-rich-ui
npm ci && npm run build:plugin
dsh plugin --profile web add link:$PWD
Unreleased commits: dsh plugin --profile web add github:kyoukisu/dsh-rich-ui.
The plugin registers itself as a bundle; the fence language is rich-ui.
Quick start
Ask for something that benefits from structure, in a new session:
Compare three electric kettles by price, volume and features. Make it clickable.
The reply arrives as an interface: a summary strip, rows with photos, and a green highlight on the cheapest option. Opening a row shows facts, sources and related items without leaving the conversation.
Things worth trying: "build a budget calculator with three sliders", "show this quarter as a chart and a table", "make a configurator with tabs and conditional warnings".
What it can render
Group
Nodes
Layout
stack, row, grid, card, divider, meta
Text
text with inline code, bold, links and [[entityId]] chips; callout with optional title; code with syntax colour, language label, line numbers and copy
Objects
entity-ref, entity-list in compact or layout:"feature" rows, with poster, square or landscape previews; entity details dock in the native right column or fall back to an in-page drawer, with a two-up photo gallery or one captioned screenshot at a time, plus cast
Data
stat (KPI card), progress, status, table (sortable, filterable, status and progress columns, scroll hint when it overflows), chart (bar / line / area / donut / scatter, 1–6 series, units, tooltips), computed
Flow
diagram with ordered steps, connector labels and branch depth; layers for boxes-inside-boxes architecture with member chips
Media
image with caption, image-group with optional per-frame captions and an inline presentation:"gallery", video and audio with native controls, gallery lightbox, popover, tooltip
expressions (add, mul, round, comparisons…), conditional, local actions, send-message
Roughly 150 Lucide icons resolve by name, with semantic tones (success, warning, danger, muted) so colour means something. Light and dark themes follow the host palette and font.
The contract in ten lines
```rich-ui
{"version":1,"title":"Budget","initialState":{"spend":1200},
"nodes":[
{"type":"slider","stateKey":"spend","label":"Monthly spend, €","min":100,"max":5000,"step":100},
{"type":"computed","label":"Per year, €","expr":{"op":"mul","args":[{"state":"spend"},12]}},
{"type":"callout","tone":"info","content":"Recomputed locally — no model call."}
]}
```
Entities, tables, charts and actions — one complete document
flowchart LR
A["Model writes a rich-ui fence"] --> B["Adapter finds the code block"]
B --> C{Strict JSON schema}
C -- invalid --> D["Stays a normal code block"]
C -- valid --> E["React renderer mounts"]
E --> F["Local state, no model call"]
F -- explicit button --> G["rich-ui action message"]
Node half registers one always-on system-prompt section with the whole contract and the absolute path of the reference files, plus the rich_ui_validate tool. The model can validate the exact JSON before emitting it; a schema error comes back as a tool result, not a visible user message.
Browser half validates the fence and mounts into a plugin-owned root. While the model is still writing, closed nodes render in an inert preview and become interactive when the block settles.
A malformed document is never patched in place and never triggers an automatic message: it shows a diagnostic card with the exact error and the rejected JSON, plus a copy button. A browser plugin has no tool channel, so the card deliberately has no "ask the model" button. Unfinished streams stay code until the model closes them.
Safety
Risk
Mitigation
Arbitrary code execution
Declarative JSON only; no HTML, CSS, JS, eval or property paths
Prompt-injected actions
Local actions cannot call tools; send-message needs an explicit click and is delivered as ordinary user text
Secrets in the UI
Password/secret state keys are rejected; no secret input components exist
Hostile URLs
http(s) only, credentials in URLs rejected
Resource exhaustion
Bounded depth, node count, string size and expression budget
Stored data
Persistence is opt-in, per session, and never stores text or date inputs
Parity with the reference
Measured, not claimed: 19 of 27 reference scenarios reproduced, 2 partial, 6 missing — with an itemised deviation list in docs/PARITY.md. Missing today: Mermaid/ER graphs, math, maps, artifacts, persistent panels and mini-apps.
Known limitation: the fence label is not preserved by Harness, so an unlabelled block is claimed only when its payload looks like a spec document and passes the strict parser. A json-labelled block is never claimed.
Troubleshooting
The block stayed as code. The JSON did not pass the schema — usually an unknown field (title inside a node that has none, or items from another plugin's syntax). A claimed fence shows the exact error and the rejected source, and copies them on request. Nothing is executed, rewritten or sent automatically. The model should call rich_ui_validate before sending; if it did not, ask it to fix the document and validate it.
Images show a placeholder. The URL is wrong, blocked by the remote host, or not http(s). Ozon/WB CDNs reject hotlinks; use a permitted source or your own media host.
Old dsh-ui messages stopped rendering. That is a different plugin's syntax. This one claims rich-ui only.
Development
npm ci
npm run dev # lab at http://127.0.0.1:4173, HMR, no Harness needed
npm run build # typecheck + lab build
npm run build:plugin # the two real bundle artifacts
npm test # 217 unit, schema and DOM tests
npm run test:browser # 58 Playwright desktop + mobile checks (goldens never auto-update)
# Interaction timings: docs/PERFORMANCE.md
Browser tests run in a pinned container so no system libraries are required:
Scenarios in the lab: ?demo=dashboard, films, listing, apps, calculator, configurator, technical, primitives, plus &theme=dark.
Screenshots in this README are captures of that lab, not mockups. Golden images under tests/ are regression baselines and say nothing about fidelity to another product.
License
MIT — see LICENSE. Demo photography comes from Wikimedia Commons under free licences; prices and metadata are illustrative. DeepSeek Harness is a separate project by DeepSeek; this plugin is unaffiliated. ChatGPT is a trademark of OpenAI: the description points at the style of rich answers, not at any affiliation, endorsement or shared code.
