End-of-chat visual storyboard: a storyboard tool renders a self-contained HTML card (inline SVG diagram, numbered flow, facts grid, timeline) from a JSON spec, writes it under ~/.dsh/storyboard/<session>/ and opens it in the sidebar; a system-prompt section and a /storyboard command trigger generation. Server-only, zero runtime dependencies.
Install
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:simikangtao/dsh-storyboard
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
End-of-chat Doubao-style visual storyboard for DeepSeek Harness Web.
When a substantive conversation ends (real work done, a plan produced, or a concept explained), the model calls the storyboard tool once and a compact visual card summarizing what was done and how it works appears in the sidebar. A /storyboard [focus] command forces one on demand.
Why it is light
- Server-only plugin — no client bundle, no extra JS shipped to the browser.
- Zero runtime dependencies — node built-ins only (
crypto,fs,os,path). - One self-contained HTML file per storyboard (~5–20 KB): system fonts, inline SVG, no network requests, no CDN, works offline.
- Tiny prompt footprint — the injected guidance section is ~500 characters.
- Storyboards are written under
$DSH_HOME/storyboard/<session>/(default~/.dsh/storyboard/<session>/).
Install
# from a workspace containing this folder:
dsh plugin --profile web add file:C:\path\to\dsh-storyboard
# or by package name once published:
dsh plugin --profile web add dsh-storyboard
The bundle patch inserts one row (id: storyboard) into the web profile.
Disable it by removing that row from the profile (the prompt section, tool, and command are all registered by the row's presence).
Usage
- Automatic — at the end of a substantive exchange the model generates the card and opens it in the sidebar by itself.
- On demand — type
/storyboard(optionally/storyboard the install steps) in the chat input.
Card sections
| Section | Field | Notes |
|---|---|---|
| Title / subtitle | title, subtitle |
title required, max 40 / 80 chars |
| How it connects | diagram |
≤8 nodes, ≤12 edges, rendered as inline SVG with layered DAG layout + arrowheads |
| What was done | flow |
≤8 numbered steps with optional notes, connected by a vertical rail |
| Key facts | facts |
≤8 label/value pairs in a two-column grid |
| Timeline | timeline |
≤8 dotted-rail events with optional time labels |
| How it works | howItWorks |
≤8 mechanism bullet points |
Every string is length-capped and HTML-escaped on the host side; omit a section when you have no content for it.
Development
node test/smoke.mjs # standalone renderer + registration smoke test (no DSH host needed)
Limitations
- v1 has no settings toggle: presence of the profile row enables the feature.
- Diagram layout is a simple longest-path layering (cycles are capped, not drawn as true cycles).
- The automatic trigger is instruction-based (the model decides a conversation is ending); it is deliberately not a hard hook.
Links
More in this category
tt-a1i/archify#integrations/deepseek-harness★ 92724
Generate validated, self-contained interactive architecture, workflow, sequence, data-flow, and lifecycle diagrams from repositories or system descriptions.
dream-num/dsh-univer-office★ 657
Give DeepSeek Harness a real office environment. Univer Office Plugin brings spreadsheets, docs, slides, canvases, relational tables, and more into one runtime — with connected data, validation, versioned changes, and isolated worktrees for multi-agent collaboration.
ECNU/EduWork#dsh-knowledge-studio★ 275
A workspace-based Studio for source-grounded reports, slides, tables, mind maps, quizzes, flashcards, audio and video, using DSH models and shared artifact services. Office generation requires Python 3.12+ with its dependencies and DSH_OFFICE_PYTHON configured; media rendering requires Chromium, and local ASR additionally requires whisper.cpp and a model.
PerryLink/dsh-industry-research★ 215
Deterministic industry research reports for DeepSeek Harness — company and industry research flows produce structured, verifiable reports from staged evidence.
HuanLinOTO/dsh-plugin-mineru★ 51
Expose MineRU document parsing tools to the model.
PolinniZhong/dsh-knit★ 48
Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.