Plugins

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

Puts sessions into the built-in Auto review permission preset: new sessions at creation, existing root sessions when they are restored.

Local-only telemetry service for DSH plugins: records operation trails and error events into a storage-domain KV table, applies a configurable redaction rule set before the write and again when the analysis reads back a record stored before a rule existed, and groups one plugin's failures by feature-code anchor, reporting the window it read, the route each group ran on, and the attempts recorded after its last failure in write order.

GitHub issue service for DSH: turns a telemetry failure analysis into a uniform issue report, builds a pre-filled new-issue URL that is shortened when it would exceed a configured length budget, rewrites a plain description into a structured issue with the deployment's model, and closes the intake loop by listing the open issues that carry a claim label and handing each one to a fresh session, skipping issues an earlier pass already dispatched and repeating the pass on the first start of each local day when autopilot is enabled.

Records every session as one readable Markdown timeline inside the session workspace - the full request sent to the model (system prompt and plugin injections included), user input, replies, reasoning, tool calls and results, file reads and writes, web searches, skill loads, command runs and token usage - with a review page, a per-session tab and configurable capture scope.

Adds a Restart dsh button above Settings that restarts dsh in place: through systemd when dsh runs as a systemd unit, otherwise via process.execve with the same PID (a thin wrapper parent on Windows or Node < 22.15), so whatever started dsh needs no supervisor config (verified on Linux; Docker, macOS and Windows not yet run for real); the page reloads once the new boot id answers.

DSH Cordis computer-use provider for the ZTE Nde desktop. npm install auto-fetches the musl binary built by computer-use-linux-zte-nde (v0.7.7-nde.3) into the package's own bin/ via postinstall; resolveCommand() resolves the cordis command path against import.meta.url so the mount works regardless of dsh web's cwd. Reserves the shared computer-use slot via ctx.computerUse.register and exposes MCP tools under mcp__computer-use-linux-nde-mcp__* (screenshot, list_windows, click, type_text, doctor, etc.). Two notable Nde fixes upstream of this provider: KWin caption+coords fallback for window targeting, and SnapshotCache that keeps AT-SPI single-wake per (app, pid) so Chrome is not repeatedly disturbed.

Installs a self-evolving development-constraints rule library, exposes it to the agent through a constraints tool and a once-per-session reminder, and audits AI token cost and context usage.

Emails you when a long turn finishes or errors, when a goal completes or blocks, and when an approval or a question has waited past a timeout; each new notification deletes the previous one from the inbox over IMAP, so the inbox holds at most one.

System notifications, a tab-title dot and a PWA taskbar badge when a reply finishes in the background or a session waits for your approval, plan review or answer, all cleared when you return to the window.

Send local files to WeChat from any DSH session by reusing an installed IM plugin, plus cron-scheduled tasks that run in fresh sessions, a workspace activity glow, a header activity indicator, a completion chime, a macOS sidebar vibrancy toggle and a one-click host restart.

Persistent WeChat bridge for DSH: one WeChat user maps to one persistent agent session via the official iLink channel, with context and the user-to-session registry surviving restarts. There is no sender allowlist — anyone who can message the paired WeChat account can start a conversation with a session that has tool access, and the working directory defaults to the home directory; use a dedicated account and set WECHAT_PERSISTENT_CWD.

Git tab in the DeepSeek Harness conversation view: reviews every repository in the session working directory and commits each on its own, with change groups, whole-file / changes-only / side-by-side diffs, in-panel editing, and a push button that lists every commit it would publish.

Sidebar Git panel for the DSH web GUI: Local Changes and All Commits views, branch, tag and stash management with fetch, pull and push dialogs, merge with conflict handling, and a zsh-style branch marker in the input bar.

Zagent — unified three-role self-improvement loop with three operators. Data-RSI (daily cross-sectional cleaning: winsorize → cross-sectional standardization → median fill, plus experience extraction), Harness-RSI (evolves system prompt / memory / skills), and Model-RSI (evolves alpha training recipes via framework-native walk-forward with 2-day gap and multi-seed). Offline one-command run, GPU auto-detect. Ships one skill.

A resident assistant for DeepSeek Harness that is deliberately not another chat box: one floating window plus one standing conversation, both independent of every other session. The heartbeat is held back by four gates — an authority grant, a daily turn budget, quiet hours and a pacing cooldown — and it keeps working across restarts through a lease it has to hold. Each wake is decided by a model that must answer SKIP or a short message, so silence is a decision rather than a failure. The window shows the standing conversation's real message flow, read from the host session store, or from the on-disk session log when the host does not publish that session, and it can send into that conversation directly. den carries the same reach as the person it stands in for, with one limit: read-only. It may read every session, this machine and work channels such as GitHub, but it does not write, send or publish, it never asks anyone for permission, and it never gates another session's tool calls. `npm run digest:github` turns GitHub notifications and your own open pull requests into three Chinese sections — waiting on you, waiting on your review, and yours — with reply drafts that are explicitly marked as unsent.

Daily brief for DeepSeek Harness. Every day at a fixed hour it ranks the plugin market by real install counts and stars, cross-checks it against your own agent memory and working conventions, and proposes two kinds of item: concrete deltas on the plugins people actually use (original does A, the proposal does B) and directions nobody has built yet. The popularity numbers come from the catalog the market itself publishes and are quoted into the prompt rather than guessed; an entry the market has not measured is shown as unmeasured, never as zero. Approving an item opens a new session named after it and hands that session a fixed delivery contract — implement independently, never fork, test green before publishing. Rejected sources are remembered so they stop coming back.

Answers a hard question with a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled dependency-free `am` CLI builds the layout, CSS and diagram coordinates. Vendors the upstream answer-me-with-html skill verbatim as a skill-only DSH bundle with no Host code.

Provides 15 Superpowers skills for DeepSeek Harness, covering test-driven development, debugging, planning, and code review.

Live skill provider that reads every Xiaomi MiMo (MiMo Desktop / MiMoCode) skill into the DSH session catalog: the engine-bundled skills under engine-config (unpacked from app.asar when that directory is absent), the MiMoCode global and project roots, extension-contributed skill directories declared in extensions.json, and the brand compatibility roots MiMo's own skillPathCompat setting enables.

A mandatory 7-step plan on every request, each step with a binary acceptance criterion, executed through worker subagents and validated by independent memoryless verifier subagents that report PASS or FAIL with evidence.

Write and read Markdown notes: switch between reading, editing and side-by-side preview, with an outline, three preview themes, math and Mermaid, nested folders, and autosave to local .md files.

Overlay reader for agent output files: Markdown rendering, in-panel PDF, DOCX/XLSX/PPTX text preview and reply-end file chips, with search, outline and position memory.