プラグイン

A novel-writing workspace: one folder per book, YAML/Markdown sections, an auto-wired relationship graph, consistency checks, four LLM tasks and four export formats.

Local-first DSH Web work checklist with rich-text notes, categories, folding, drag reordering, search, JSON import/export, and a restorable trash.

Wallpaper-aware readability repair for the DSH Web GUI: it lifts the three low-contrast secondary text tokens with color-mix plus an adjustable text halo, adds content rules (bold, permanently underlined or recoloured links, tinted headings and body text) scoped to conversation Markdown only, offers adjustable rainbow-edge and gradient-fill heading effects, loads custom fonts from the plugin folder or the DSH home, and ships a draggable WYSIWYG preview with a WCAG contrast badge.

Drag folders into the DeepSeek Harness web composer instead of hitting 'only the desktop app supports folders'. Adds a host folder dialog, /folder, and drag/paste into @path mentions. Plain browser, no desktop app.

Renders inline code in DSH chat as pills with syntax colours and optional file badges, styles chat file paths, and offers optional folded-row tinting and thinking-text ink, with a settings page for six presets, colours and fonts.

蛋白质结构预测与设计插件：序列设计（ProteinMPNN/SolubleMPNN/LigandMPNN）、结构预测（ESMFold）、复合物界面筛选、序列理化打分与多样性聚类——零手动自举（本地 CPU/GPU 自适应），供 dsh-bio-genie 消费 | Protein structure prediction & design toolkit for dsh (sequence design, folding, interface screening)

Wraps the external `ocr` (open-code-review) CLI in five model tools — one-shot review, whole-tree scan, deterministic scope/rule scaffolding and session lookup — and reports what OCR found separately from whether the run actually covered the selected files.

Ports the obra/superpowers methodology as 14 native DSH skills — brainstorming, writing-plans, executing-plans, subagent-driven development, test-driven development, systematic debugging, parallel agent dispatch, git worktrees, code review, verification before completion and skill authoring — served through the DSH skills registry with their scripts, references and cross-links intact (frontmatter folded into a manifest, prefixes realigned to DSH skill names). Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): the /superpowers slash command declares the producer-owned source kind plugin:dsh-plugin-superpowers.

Local-folder knowledge base for DSH: builds a SQLite FTS5 index over Office, text, PDF and scanned files, ships five tools (kb_search / kb_read / kb_list / kb_status / kb_session) plus a Web panel, and retrieves or syncs only when the user explicitly asks.

Token usage panel in DeepSeek Harness Settings: folds session logs into day, week and month totals per model or per provider, persisted in the plugin storage domain and served over a same-origin /token-usage-rpc route; SVG line chart with crosshair hover, ranking with share and optional cost, cache hit-rate and cache read/write cards, a user-supplied price table priced per million tokens, daily and monthly budget alerts, CSV or JSON export of the current range, auto-refresh while visible, preset and custom start/end date ranges, and a rebuild that asks for confirmation before dropping history whose session logs no longer exist.

Folds each 4-50 KB paste in the DSH composer into its own chip (expand or delete it individually), and turns a paste of 50 KB or more into a real file attachment. Declares DSH >=0.1.7-rc.2 <0.3.0-0, so it stays visible on the 0.2 release line.

Chain-of-thought panel for the DSH Web right sidebar: folds the live reasoning stream of each session into turn → step groups carrying the reasoning text and the tool calls made in that step. Only the newest turn is expanded by default and earlier turns collapse to one line; steps are grouped into activity phases by a local rule, the step waiting on a tool is marked, tool failures show their reason, full reasoning text is fetched per step on demand, an all-turn directory searches turn titles, user text and turn numbers locally, and a whole turn can be summarised into a Chinese title with one model call.

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

One @ for files, folders, skills, past chats, plugins and git — with line ranges, paths outside the workspace, typo tolerance, and token cost before you send.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Role-based subagent delegation for DeepSeek Harness: one delegate tool over a folder of role files, with a roster that ships and stays overridable

Fixes the Windows workspace-open action. The shipped opener runs `explorer.exe "<file:// URI>"`, which on some hosts reports success without raising a window — the exit-code verdict cannot tell an opened window from nothing happening. This routes that one action to `explorer.exe /e,<dir>`, which raises a window reliably, and leaves every other application in the menu on the shipped path.

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Replaces the chat input model picker with a provider-grouped, collapsible list: groups models by provider, folds vision-bridge mirror providers back into their upstream, and carries the reasoning-effort options each model declares in settings. Tested on DSH Desktop only; the DSH web build is untested.

Keeps the question you are currently on pinned above the composer, with a dropdown of every earlier question that scrolls the conversation back to that turn; questions folded into process groups are expanded first, and Escape, scrolling or clicking outside collapses the panel.

Scaffold DSH local bundles in the dph format from any workspace and keep a pitfall experience library to steer later development.

Manages CSS and JS snippets for the DSH web GUI, injecting enabled CSS as style elements and running enabled JS in the page, with a sidebar-footer quick toggle, its own page in the Settings navigation, and optional folder or Gist sync.

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.

DSH (DeepSeek Harness) Web GUI plugin: global model token usage stats as a dedicated "Token 用量" page in Settings — incremental session-file scanning with a persistent fold cache, date-range picker with presets, model/provider filters, per-day and per-mode