Plugins

Restart recovery for DeepSeek Harness web: after a crash or restart, an interrupted agent turn continues automatically (host-side agent/created listener, no browser timing races).

DeepSeek Harness Web plugin that renders streamed assistant Markdown with markstream-react.

Persistent AI memory backed by a local Obsidian/Codex vault: five obsidian_memory_* read/write/search tools plus a sidebar vault browser.

Third-party adapter that registers the upstream REA (Reverse Engineer Anything) MCP server into DeepSeek Harness as mcp__rea__* tools. 2.x provisions its own runtime (Node, the REA CLI, a JDK, Ghidra) under <DSH_HOME>/plugins/rea-bundle and launches REA through a shim, so a machine with nothing pre-installed works after one setup run; 1.x (branch v1, npm 1.0.6) is configuration-only and expects REA and Ghidra to be installed already. Analysis is upstream's: native binaries (Hopper/Ghidra/IDA), JavaScript/Electron apps, .NET assemblies, websites, Android APKs and adb devices, firmware, and process captures.

A UX enhancement pack for the DSH web chat: one plugin that collects small interface conveniences, each with its own switch under Settings → UX Plus applied immediately — chat-area font size and reading width under Settings → General → Chat area, a session-row menu that copies the session ID or inherits the conversation into a new session on a chosen model, workspace and session rows ordered by recent activity with 24-hour idle auto-collapse and age labels, and settled ask_user_question cards left expanded. The switch list is generated from its own feature registry, so the pack grows as conveniences are added instead of being fixed at a count.

Multi-CLI worker sidebar for DeepSeek Harness 0.2.0-rc.2 on macOS and Windows, with task dispatch, live conversation views, stop and follow-up controls, and custom role presets.

Free conversational ChatGPT Web (GPT 5.6 Luna) model provider for DeepSeek Harness with streaming Markdown.

Multi-user login gateway for the DSH web UI: the first visit creates the admin account, admins add and manage users in the GUI settings panel, ordinary users see only their own conversations, and unauthenticated visitors are redirected to /login.

DeepSeek Harness universal preset enhancement plugin: an editable preset editor (system/user/assistant entries + camouflage model output prepopulation)

A polished floating whale desktop pet for the DeepSeek Harness Web UI with 95 categorized transparent animations, state-aware event reactions, customizable actions and triggers, click interactions, dragging and screen wandering.

Barrage-meme skill distilled from 22,771 real messages in the 6657 live room: wanjiqi-style banter, CS and DOTA cross-memes, player roasting and casting commentary.

Settings page for per-model capabilities: reasoning-effort levels with their wire spellings, input modalities, and token capacities, written as declarations or sparse catalog overrides.

Evaluation harness for DSH plugins: YAML cases drive real headless agent runs, assert on tool calls, args, results and token usage, with a baseline gate for CI regression.

Local security audit: config, plugin origins, sessions, network exposure — read-only redacted risk report.

Computer use through an external USB HID device: name a target in plain language, a vision model locates it in a cropped window screenshot, and a Raspberry Pi Pico 2 moves the real mouse and types on the real keyboard. 7 tools. Windows has window listing, per-window cropping and automatic window raising; macOS needs pyobjc and has neither; Linux is unsupported.

Render Mermaid code fences as SVG diagrams with streaming support, diagram/code switching, fullscreen zoom and pan, SVG export, and a bundled same-origin runtime.

Host-resident cron engine with a web jobs board and a timer_agent tool: fires real agent sessions on schedule, continuing a pinned session for context or starting fresh ones in a chosen project workspace.

Generate complete AI songs and BGM from prompts or lyrics, with reference-audio creation and song extension.

LLM-assisted auto approval with countdown fallback for the Auto permission preset: static rules, risk tiers, breaker and file audit.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Fine grained per tool permission rules for DSH at the tools/pre-execute gate, deny and ask lists in Claude Code rule syntax (`Bash(rm -rf:*), Read(_secrets_), mcp__server__tool`), works standalone without migrating.

Exports the session event stream to OpenTelemetry OTLP and Langfuse as sanitized, buffered traces and metrics, off by default.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.