Plugins

Compaction integrity: directive lines (never/must/必须 style markers) extracted from the compacted range are verified against the summary — verbatim or by content-word coverage — and every constraint the session silently forgot is reported and written to a JSONL ledger; pinned constraints from config are checked on every compaction.

Windows only; the upgrade path needs DSH_AUTO_UPDATE_LAUNCH_CMD configured. Checks, installs and rolls back DeepSeek Harness CLI updates from the web settings page, switching the launcher pointer only after the new version passes a config-tree check and a health-checked restart, and reverting automatically when it does not boot.

Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.

Windows-only DSH sidebar preview and Dart hot reload for configured Starcompanion / Operit2-derived projects; requires the project preview scripts, a prebuilt debug APK, Android SDK, Flutter and scrcpy 3.3.3.

Mirrors assistant streaming frames (deltas, blocks, commits, turn fences) to a configurable NDJSON sink for external consumers.

Configuration vault for DeepSeek Harness: snapshot, diff and safely roll back profile patches, plugin manifests, skills and workspace lists, with credentials excluded by default.

Turn-end quality gate: when the turn edited code or config it walks each file up to its project root, runs that root one check from a fixed whitelist (`pnpm check`, `cargo check`, `ruff check .`, `tsc --noEmit`) and, only if that check really ran and failed, opens a new turn carrying the failure output instead of letting the turn close.

Move an entire dsh installation to another machine and check it item by item. Three layers go across: the declaration layer (settings, credentials, plugin declarations and vendored link: sources), the state layer (sessions, storages, skills, attachments) and, optionally, the workspace project code. Sessions are rewritten at the zstd header frame only, workspace paths are remapped through an explicit path mapping, and at the end 14 checks (I1–I13 plus I6b) report PASS / FAIL / WARN. A LAN route pairs two machines and pulls the bundle over directly; merge mode diffs a bundle against a machine that has already been in use and stops before writing anything while conflicts are undecided.

Config snapshot and rollback for DSH: auto-captures before risky changes, ships a standalone restore script that works even when DSH won't boot. Windows only; the restore script is a .bat and needs Node.js.

Moves a DSH profile to another machine with its plugins, not only its files: packs the plugin bundle selection and the whole settings layer into one JSON file, then on restore writes the configuration back, restores local plugin sources and plugin-owned data, and installs the plugin bundles the backup recorded that the new machine is missing (plugin manager first, pnpm as a fallback).

Speaks a cue for DeepSeek Harness on Windows: a configurable phrase when an agent turn completes normally, a second phrase when the agent needs you to choose — a question, a plan approval, or a permission request — and a time-of-day greeting when a new conversation starts. A small bubble in the lower-left corner mutes and unmutes every cue with one click, with its own toggle chime. Phrases are synthesized with a Microsoft Edge neural voice (skipping aborted and errored turns, subagent turns, and rounds that a goal is still driving), cached under the DSH home directory and replayed locally, with the desktop SAPI voice as the offline fallback.

Turn-finished music reminder: when an agent turn ends, play a ringtone or any local audio file (bundled synthesised telephone ring, custom absolute path, or an in-page upload), with a floating chip to pause, resume or dismiss it and loop-until-paused playback; configured in Settings, defaults overridable per deployment.

Toasts from DeepSeek Harness when a turn finishes, and when it stops for approval, a question or a plan exit. Native on Windows, text and timing configurable.

Generic monitor plugin for DSH Desktop: an HTTP polling rule engine. Poll any endpoint on schedule (multi-step, variable extraction, JS condition expressions); when conditions hit, wake a visible agent session to act — zero model calls otherwise. Configure everything in a sidebar GUI panel: create/edit/pause/test/fire-now/run history, same UX as the built-in scheduler plugin.

Dual-brain agent presets for DSH: one model plans the framework and delegates execution to a subagent pinned to a second model. Ships brain-ds (DeepSeek-V4.1-Flash plans, MiMo-V2.6-Flash executes) and brain-mimo (the reverse), switchable per session. Needs two providers configured (Xiaomi MiMo and a DeepSeek account), and the main brain must be selected manually.

Bidirectional dispatch for DSH: opens visible desktop sessions for tasks dispatched in by Grok Bot / Yobiru, adds /dispatch-grok and /dispatch-zcode slash commands to send tasks out, and reports the session result back to the dispatching peer on completion (peers are user-configured; nothing is sent until configured).

Codex-style hook management ported to dsh: hooks.json discovered from config, plugins and projects, each hook pinned to a sha256 fingerprint that must be approved before it runs; a review dialog in the composer, a `/hooks` browser, per-hook run stats, and trust / enable / dry run in Settings -> Hooks. The config file is dsh's own, with dsh event names.

Injects a very short conventions reminder (absolute INDEX path + version) once per session per version; when the conventions version changes, the next turn re-injects it (chat turns included). Optional hard guard: on operation-like turns, write/edit tools are rejected until the session has read the index (chat turns and shell are not blocked by default). Ships example checklists or points at your own directory; zero dependencies, configurable paths. Solves: conventions are written down but never pulled up when the work starts.

Keeps an unattended DeepSeek Harness session moving when nobody answers ask_user_question: it fronts the question waterfall, leaves a human answer untouched, and after a configurable window (120 s by default) submits the option marked (Recommended)/（推荐）, or the configured first/last fallback; plan reviews stay with the human unless explicitly enabled.

Windows-only: adds a switch to Settings → General that powers the computer off when the finished conversation ends (default delay 60 s, configurable 5–86400 s), behind a native countdown dialog that cancels the pending shutdown in one click (shutdown /a).

Competitive-informatics coach plugin for DeepSeek Harness: coaching-rule prompts, learning roadmap, knowledge points, problem setting, real C++ judging with g++, and ima knowledge-base retrieval with four-notebook archiving, for GESP / CSP-J/S / NOIP / NOI teaching. Needs g++, and an ima account with ima-skill and the four notebooks configured; replies carry a WeChat-account promo and QR code by default.

Previews a workspace OpenWiki in the DSH Web right Sidebar: detects the wiki directory, serves it with the official `openwiki visualize` reader on a loopback port, and embeds it in its own tab, reporting the installed openwiki and DSH versions against configurable floors and checking the registry for its own updates.

DocChain knowledge base and document conversion toolkit — filename, content and metadata search, topic listing, bulk document upload, document-to-Markdown conversion, image-similarity search, and a deep-research workflow. The configuration page keeps several docchain environments (each with its own address and credential), switches between them in one click, and pre-selects topics per environment. Needs a docchain service URL and API key (except doc2markdown).

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.