Plugins

Balance and live session usage for the DSH web UI: header balance button (left of the Session log), dropdown with account balance, real-time token breakdown (cache miss/hit, cache write, output), cache hit rate, and official-rate cost estimates with peak/off-peak auto-switch.

A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.

会话级自动上下文压缩插件：回合中每步前 + 回合结束检测上下文用量，超过会话阈值自动 compact，摘要注入上下文后自然继续（DeepSeek Harness / DSH）

DeepSeek Harness plugin: Nocturne Memory client — automated long-term memory (boot/read/search/create/update) backed by your own Nocturne MCP server.

Turn-scoped “Allow for this task” approvals: automatically allow matching `danger-full-access` escalations only for the current task, then expire.

DeepSeek Harness 插件：闲置会话自动归档、回到会话自动取消归档，带设置卡片与归档历史。

Hy-Memory 2.0 as a native DeepSeek Harness memory component: three-tier memory (personal / project / session), three scenes (chat / working / coding), automatic recall and capture with tool traces, a Settings > Memory panel, and MemHub interoperability.

Reusable report automation skill with target-template and AI-generated standard-report flows

Phone access to the DSH web UI: LAN pairing plus remote access through your own tunnel command (e.g. cloudflared) or a fixed public URL, with automatic LAN-to-tunnel failover and dshlanpair:// deep links; the phone client is the bundled Android app (APK, Android 8+, sideloaded).

Optional external HTTP API for DSH Desktop, off by default, bound to localhost unless widened, and authenticated with a Bearer token.

WeCom smart bot over the official long connection (Bot ID + Secret, no public callback): persona, sender identity tags, three-layer memory with a forgetting curve, reminders, opt-in proactive chat, owner-only work mode guarded by tools.guard, auto-steer, image input and a wecomSoulBot host service; group chats answer when @-mentioned.

A five-stage engineering loop for agent-built projects — spec, build, verify, ship, learn — with one artifact and one gate per phase, so an agent always knows the single next action. Role policy, project templates and deployment sit behind explicit ports: swap the implementation without rewriting the loop. Its scaffold generator lays out the internal layers of a project — `init --layout {none,webapp,service,plugin} --stack {python,node,none}` — from nine layers sampled out of three unrelated production projects: entry docs, an OpenSpec plan face, a spec truth layer (INDEX, one file per domain, TESTING, CONSTITUTION), a wiki split into knowledge / progress / runbook, the six `.agents/` slots, server+web, scripts/deploy/config, tests+e2e and a gitignored out/. Non-none layouts also gate the directory contract and compile every source root. Ships a Python CLI (init/next/check/ship/new) plus a local command adapter and an SSH/systemd adapter with release directories, an atomic current/previous switch, a deploy lock, a commit-versioned JSON probe and automatic rollback on a failed probe; bootstrap and teardown provision and remove the unit and the reverse-proxy block idempotently and refuse to delete a root they did not create. Includes a runnable example workspace and a skill that keeps the agent on one phase at a time. Requires Python 3.10+ and PyYAML; remote deploys need SSH access, rsync, systemd and Caddy on the target.

Scheduled prompts that open a fresh conversation for every run, with cron, one-time and manual triggers, a per-task working directory, and run history kept out of the sidebar.

Manages game automation scripts from dsh on Windows. Installs and updates scripts such as MAA, runs them in scheduled pipelines, watches their logs and hands failures and stalls to an agent, and tracks game events.

Registers bundled full-stack, frontend-design and browser-automation skill documents as four read-only tools; a focus argument selects which reference file is returned alongside the skill body.

Provider-agnostic text-to-speech for DeepSeek Harness: synthesize speech to local audio files, manage preset, cloned and designed voices, configure providers in a bilingual settings card, and read assistant replies aloud with optional auto-read.

Dual-brain Chrome automation: registers the browserpaw skill and browserpaw_session tool to connect with the local BrowserPaw host (127.0.0.1:12306 via bridge-token), driving Chrome without losing logins.

Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.

Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.

Restarts the DSH desktop host on macOS when a change needs it, then hands the conversation back to the same session with a note the model writes about why it restarted and what comes next.

Usage panel for the provider account behind the current model: quota windows, credit balance and token usage, following the model automatically. It renders as a full page, plus a sidebar entry and a per-session usage chip in the conversation header.

Files the settings entries your installed plugins add below the ones dsh ships, behind a divider with a live count, and keeps up automatically as plugins come and go.

Derived DeepSeek Harness Auto review plugin that attaches the reviewed Agent's session identity to every reviewer request, fixing OpenCode's MissingSessionID rejection.