Plugins

Ranks workspaces holding a session that wants attention to the top of the sidebar session list - waiting on you first, then running, then finished-but-unopened, then just read - and draws those rows with a state bar, tinted surface and coloured title, plus a one-shot settle pulse when a run stops. Every colour is taken from the active theme's own tokens, and the three windows that decide how long a finished session stays promoted are settings.

Resumes turns interrupted by a DSH host restart: hooks agent activation (once a session is live), reads the crash-repair turn/end, and sends a continuation that requires verifying real-world state first rather than assuming a side effect succeeded or failed. Permanent failures (AUTH, QUOTA, context overflow) are skipped, with a cross-restart budget, adaptive backoff and a minimal-context payload.

Let `dsh web` be reachable from other machines on the LAN / a virtual LAN (SD-WAN, Tailscale, ZeroTier) with no extra command line: ships a profile patch layer that binds all interfaces, widens the /api Host trust fence, and extends the browser-session co

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

A Genshin Impact Hu Tao (Wangsheng Funeral Parlor) skin for the dsh web GUI - a 14-token ink-black, crimson and amber palette, falling plum petals and spirit butterflies, a plum-blossom brand mark, and a floating petal toggle that tracks the sidebar.

Conversation outline panel for the DSH web surface: user questions as root nodes (index, time, tool count and text volume per turn) with the Markdown headings of assistant replies hanging beneath them, plus level slider, search scope, bookmarks, copy and export as Markdown, section jump, keyboard navigation, a right-edge density rail and per-session reading-position memory. Read-only UI: it never touches prompts, tool results or provider traffic, and writes nothing outside its own localStorage keys.

English word bank for one or more children, built for DSH 0.2 and newer (0.2.0-rc.1 and 0.2.0-rc.2 verified, including the desktop shell; 0.1.7 through 0.2.x all work). 1.10 added pronunciation: in the memory cards and in the online quiz every word and every example sentence has a speaker button that reads it aloud with the built-in Windows voice - offline, with no network call and no model call - and the whole batch of audio is pre-rendered in the background whenever cards or an exam are generated, so a click starts instantly. 1.11 adds: pick words in bulk straight from the library (10 at a time, top-down, up to 50 selected, with a live counter); turn the words a child got wrong in a quiz into a one-click review set - an online card page that speaks plus a printable PDF; and every card example sentence now carries its Chinese translation underneath. Words marked on textbook or workbook photos (highlighter, red pen) are found by their marks, then translated and stored in a local SQLite bank with an occurrence count; the clipboard picker, the photo route and dictation all land in the same bank. High-frequency words surface by count, three correct answers in a row flag a word as learned, and any selection prints as a memory card set (a word split into chunks, real IPA per chunk, a grade-7 example sentence, a mnemonic hook, an A4 sheet of eight) in HTML, PDF or Word, with a print-and-answer exam page whose four options are set against each other for meaning. On 0.1.5 the settings panel does not appear - install dsh-word-vault@1.0.2 instead.

Customize the interface font, size, weight, color and layout from the settings page, Word-style and WYSIWYG, auto-saved. Ships two bundled open-source fonts (STIX2Text, Latin Modern Mono Light) plus an author-recommended typography, and stores settings under ~/.dsh.

dsh plugin: switch named model profiles (default model, think level, per-subagent models) interactively via the host ask-user flow — one implementation for the TUI and web surfaces, a clean fast-fail on headless

Kaze Tachinu (The Wind Rises) skin for the DSH Web GUI: a full-screen film wallpaper behind glassmorphism surfaces, sky-blue interaction tokens, redrawn vector logos for the sidebar and home hero, a restyled composer card with themed placeholder text, and a bottom fade on the message list.

Keeps an unfinished task list visible across turns. DSH clears the todos projection at the start of every turn and expects the model to rewrite the whole list, so when a turn is interrupted the plan is durably in the session log but permanently gone from the UI — and todo_write is write-only, so neither the user nor the model can read it back. This plugin registers one ordinary session/event listener, remembers the last list per session, and when a turn/start arrives whose remembered list still has unfinished work, re-appends that list so the projection stops reporting an empty plan. No fork of tool-todo and no waterfall: a plugin cannot replace the projection (the registry throws on a stateVersion mismatch), so appending the event the fold reacts to is the reachable seam. Deliberately narrow — only unfinished lists, at most one event per turn start, fails open. Verified by a controlled A/B on real sessions: identical runs differing only in whether the plugin was installed, folded through the real projection definition. Zero dependencies.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

WeChat login watchdog for DSH: surfaces dsh-wechat session loss as a Web UI banner instead of silently dropping queued messages. AI-generated, educational use only.

Agent-native API client for DeepSeek Harness: Postman-like debugging UI (request tree with context menus and full keyboard navigation, resizable sidebar, layered auto-generated header preview with per-item suppression and constant secret masking), six api_client_* agent tools sharing the same request core, redaction and audit chain with the human UI, Postman Collection v2.1 import with a migration report, environment variables with SecretRef indirection, and a fail-closed SSRF network policy.

A plugin for dsh: quantify every dsh Agent interaction as a visualized performance metric and automatically sync it to WakaTime, using data to showcase your productivity with Agent.

A focused end-user QA surface backed by native DeepSeek Harness sessions

What's up - a zero-maintenance status board for your sessions. Scans every conversation on the host, extracts a goal + one-line status per session (multi-provider LLM, fingerprint-cached), surfaces half-done, unanswered and recent work in a sidebar panel, and jumps you back into any session with one click.

Standalone mobile surface for dsh: scan-to-pair device trust, realtime SSE sync, three-channel completion notifications (in-app / Web Push / Server酱·Bark·Telegram), offline outbox, approval & question panels, per-provider usage meters, PWA; a native narrow-screen phone UI.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Chrome DevTools Protocol Plugin for DeepSeek Harness. Use chrome-remote-interface to connect to and control Chrome via CDP. The connection includes a graphical interface.

Per-provider concurrency gate on the llm/stream waterfall: holds surplus model requests in a FIFO queue inside DSH so main agent, subagents and compaction take turns on a single-slot local server (llama.cpp --parallel 1) instead of timing out; maxConcurrent / maxQueued / queueTimeoutMs.

Fast `@` file/session reference caching for the DSH Web GUI: preloaded indexes, browser-local keystroke filtering and native mention serialization.

Localizes the DeepSeek Harness interface — tool call cards, plugin list, command menu and permission selector display Chinese text while keeping the English originals.

Single-password authentication gate for the dsh web surface: configurable session validity, Ctrl+Shift+L lock, CLI password management, brute-force lockout, in-UI password controls.