Plugins

Thinking in Chinese: injects a system prompt so thoughts and replies stay in Chinese, expands the reasoning block by default with interactive collapse, and localizes UI labels (npm: `dsh-think-zh-expand`).

Per-model reasoning effort (off/minimal/low/medium/high/xhigh) for GPT, Codex, Gemini and OpenAI-compatible models. Installs a helper, not a runtime adapter: run enable-capabilities.ps1 once per profile (Windows) and restart — it declares the levels in ~/.dsh/settings.yaml, with a disable script and a backup to revert.

Hello Kitty-styled task-completion and question alerts for DSH Web, bundled with an optional light/dark pink Skin Center v2 theme and local install scripts.

An Obsidian-style knowledge base: ingest sources, let the LLM build and maintain an interlinked wiki, and ask questions grounded in it.

Fold completed turns into their final conclusions, split thinking from prose with a divider, and jump between turns from a rail dockable left or right with line or dot marks, an optional ring and hover summaries; it can hide the host right-edge TurnNavigator, load earlier history, and open a pre-filled diagnostics issue.

Transactional uninstall engine: every destructive action runs validate/preview/execute/undo with Saga rollback, WAL crash recovery, hash-chain audit, hardlink dedup, and a Bayesian oracle that predicts success probability before you commit.

Link straight to one DeepSeek Harness session: the GUI opens on it instead of wherever it was left.

Markdown viewer for the dock workbench: GFM rendering with DOMPurify sanitization, document outline and relative-path image/link resolution, with one-click switch to editing.

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

Aemeath theme for the dsh web GUI — sakura pink × icy cyan × pearl white × deep navy, dual light/dark, animated pulsing composer border, and wallpaper backdrops

Local tool-call failsafe for DSH: blocks a fixed list of high-risk shell patterns and credential-file reads before execution, with a per-session hash-linked JSONL audit log, and an optional external Gateway for centralized policy.

DSH Tool Router — deterministically shrink model-visible tool schemas per step with a safe fallback

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.

Project memory for dsh with native task-system integration: session todos and file reads auto-condense into cross-session task records (task↔file links), so workflows are switchable and resumable without re-contextualizing. Read-time memory (no upfront scan): extracts code symbols, summarizes docs, and cross-links docs↔symbols; optional TS semantic enhancement (auto on when TS installed). Experience notes auto-dedup. Every recall includes a traceable citation. Pure JS, single dep, works out of the box, silent operation, zero overhead.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

A balance and cost widget for the DSH web GUI: a sidebar footer card shows the account balance, a remaining-ratio bar and today costs; clicking opens a four-tier cost breakdown (last prompt / this session / today-this-project / today-all) with term explanations and a one-click top-up link. Zero external dependencies, works on Node 24.

China A-share stock research: ticker search, announcements over any date range, financial report cards, valuation profiles and signal-factor explanations (~5,000 stocks since 2011, public read-only data service), plus a link-out tool to an external trading-sandbox product.

Adds COS storage browsing and transfers, workspace artifact uploads, temporary links, and conversation attachments that retain local copies with cloud object identity, plus Agent tools for Tencent Cloud COS, CI, and MetaInsight.

Cross-session recall for dsh web: '@' mentions and a composer picker link previous sessions as reference chips; the host snapshots them in as recall context right before the question, recorded read-only in a session-header chain badge

Floating phone-pairing QR button for the DSH WebUI. One click opens the dsh-remote-link pairing QR (image + 6-digit code + TTL) in an in-app overlay — works in both browser and DSH Desktop (same-origin img, no iframe).

Easy-fold plugin for the dsh Web GUI: sticky Think fold row and fold scroll compensation for long expanded content

Copy selections from assistant messages as Markdown, preserving links, LaTeX sources, and code-fence language info.

A whip for DeepSeek V4 Pro: it watches the reasoning fingerprint of every thinking block and pulls the model back when it slips from focused "We will / I will" mode into scattered "let me" mode.