Plugins

Pins the model's reasoning language to a tier picked in Settings - General - Thinking language (Simplified Chinese, or a default tier that only constrains replies and leaves reasoning to the model), by injecting a system-prompt section at order -1000000 and re-hoisting it to first place at the end of the assemble waterfall, plus an optional per-turn copy placed ahead of each user message for models that follow static sections weakly.

Component checklist for the shared Semi Design package used by tnnevol DSH plugins, opened from a `Semi UI` button in a conversation header: 35 components plus a multi-account case page, organised into seven sidebar groups from inputs, forms, selectors and trees to tables, cards, overlays and feedback, each rendered live with a one-line description and a page outline, with light, dark and follow-system preview. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-semi-ui-showcase`.

Adds /btw for one-off, context-aware side questions without tool execution, with independent answer bubbles that can be copied, collapsed, or closed without adding answers to the main conversation.

Tencent CodeBuddy model provider for DeepSeek Harness that signs in with browser OAuth instead of an API key, lists the CodeBuddy model catalog with the context, output, tool-calling, reasoning and image capabilities of each model, keeps multiple accounts with automatic failover to the next usable one, shows remaining quota in the composer with a token and credit usage panel, and completes automatable CodeBuddy growth tasks per account with an execution log. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.

Read, create and edit Figma designs through natural language in DSH, including batch layer edits, components, variables, screenshots and asset exports. Local mode does not use the official Figma MCP call quota.

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.

A Blue Glass ocean-fantasy skin for DeepSeek Harness Web: crisp ocean backdrop, glass bubbles, an ocean sidebar with a gold-gradient HARNESS wordmark and a bottom cartoon character, a whale settings button, and gradient model text.

Bloom Morandi theme: ten variants (mist, cinnabar, petal, ripple, sage, stone, lapis, amber, aurora, lavender) built on OKLCH so light and dark stay perceptually even, switchable from the top bar, with all 20 foreground/background pairs measured at WCAG AA or better.

High-reliability Feishu/Lark bridge for DeepSeek Harness: QR one-click auth, card-based commands and intent-confirmation cards, at-least-once zero-loss outbox, media in/out, /doctor session-log ZIP, and a reusable DSH Web GUI that lands sessions in the right workspace.

Startup animation and chat wallpaper plugin for DeepSeek Harness: a two-act boot animation with custom animation import and three configurable transitions (first-act entry, act join, second-act exit), plus static-image and muted loop-video chat backgrounds (Wallpaper Engine project folders, custom video directories, random rotation, per-video delete).

Visually configure an agent's prompt, tools, visible skills, subagents and fallback models, and assemble several of them into a team. It never writes or edits any host preset file.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Installs four multi-agent math-research presets for DSH: v2 (probability-driven pipeline with multi-verifier debate), v3 (paper-style Markdown knowledge base with a planner agent and a reusable method library), v4 (persistent self-organizing residents that message and meet), and v5 (a research institute with an academician who decomposes and assigns work, voting researchers, temp workers, group chat and a compare-and-set task board); all four support checkpoint resume, human intervention, and an optional Lean formal-verification switch (off/encourage/require) whose passing proof turns the vote into a fidelity check of the Lean statements.

WorkBuddy-style skill picker: a button beside the composer opens a searchable list of installed skills; picking one inserts the official /skill-name gesture, so the skill loads with your message.

Use a native browser sidebar or @ to reference logged-in Chrome/Edge tabs, authorized local HTML and running Windows apps. Read compact snapshots, batch actions, capture screenshots and use available WebMCP tools; supports user-authorized file uploads, same-frame element drag/file drop and opt-in network metadata capture. Page/app context appears as expandable chips; dockable element annotations and selected local diagnostic logs append to chat drafts without sending. App control prefers a matching installed MCP or approved installation, then falls back to Cua Driver with text, hotkeys and paged controls; desktop reads present the window once per connection or when recovery is needed, and failed actions retain evidence and stop without automatic replay. Background input depends on the app. Requires Chromium-based Chrome or Edge 125+ with the companion MV3 extension loaded unpacked and paired once; installing the plugin does not install the extension.

Floating panel for the DSH web UI managing MCP servers and skills: per-server deferred tool loading (ToolSearch, off by default) keeps a server's tools out of every turn's context — the prompt lists tool names only, and a tool's full schema enters the list once the model finds it with the built-in tool_search, so a turn stops paying for schemas it never calls. MCP servers live in a global scope or a project's own .dsh/mcp.json, with per-server enable/disable, a 47-service market and import from ten other clients; skills are auto-discovered across their real scopes with shadowing, and model auto-invocation versus manual-only is a switch per skill.

Brings active DSH sessions into a 3D 'Overcooked' kitchen: AI agents work, whale-girls wander the kitchen, and you watch from the side; status bubbles show who's cooking, waiting, or done with one-click navigation — originally built to check progress, now you just can't stop watching the whales.

Configurable deterministic session titles for DeepSeek Harness from semantic prompt fields and templates.

Daily game automation on Windows for Genshin Impact, Honkai Impact 3, Honkai: Star Rail and Zenless Zone Zero: a scheduled task per game drives BetterGI, the game-daily skill family, March7thAssistant or ZenlessZoneZero-OneDragon, with per-game switches, a foreground guard, in-run supervision that only steps in on trouble, and one report session per game that later results are appended to. Requires the DSH desktop app and the matching external engine installed.

Drive OriginLab Origin scientific plotting from AI chat via MCP: 62 tools. Modal-dialog watchdog, LabTalk safety gate, release/reconnect, fit with initial/fixed/weighted params, fine-grained plot and sheet edits, matrix tools, FigureSpec declarative YAML (diff-able and replayable), MCP Resources read-only snapshot, matplotlib-figure bridge, PowerPoint assembly with panel labels, Graph Gallery template search, EPS export, file-access whitelist, visual regression baseline, and editable OPJU delivery with deterministic readback verification.

Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.

Multi-agent workflow for math-modeling contests: the "UltraMath" preset runs a problem from reading through framework, derivation, coding, verification, paper and review, plus 4 single-stage role presets (mathematician, engineer, writer, reviewer) and 33 model-library skill docs.

Local-only project memory with zero bundled runtime dependencies or external services: JSON as the source of truth plus generated PROJECT_MEMORY.md, token-bounded session-frozen Hot Memory for prompt-prefix cache stability, cached cross-project BM25 recall, trusted session/turn provenance, explainable pre-write duplicate/conflict governance, editable importance/pin/tags/supersede/archive lifecycle, configurable top-level turn-end distillation, and a bilingual Web GUI for search, inspection, diagnostics, and live settings.

Tencent CodeBuddy model provider for DeepSeek Harness that signs in with browser OAuth instead of an API key, lists the CodeBuddy model catalog with the context, output, tool-calling, reasoning and image capabilities of each model, keeps multiple accounts with automatic failover to the next usable one, shows remaining quota in the composer with a token and credit usage panel, and completes automatable CodeBuddy growth tasks per account with an execution log. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.