Plugins

DeepSeek Harness (dsh) plugin: live NVIDIA GPU monitor in the web rightbar. NVML-first on Linux (nvidia-smi fallback). NVIDIA only! Not AMD/Intel/macOS. Multi-GPU util/VRAM/power/temp, processes, sparklines. Installable dsh.bundle.

Live btop-style CPU/memory/temperature/GPU monitor tab for the DeepSeek Harness web GUI.

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.

Turns a dsh session into a redacted idea and delivers it end-to-end encrypted to friends on DeepHub; received ideas land as new sessions.

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

Auto-archives sessions idle beyond a configurable threshold, with safety guards (never touches live or running sessions), plus a full archived-session management UI: list, unarchive, safe delete and content preview.

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.

Live Android device pane next to your DSH conversation: scrcpy H.264 streaming, agent taps verified by screenshots and a UI tree, and screenshots / recordings / debug evidence saved into one host directory. Debug sessions keep segmented video, full logcat and per-action frames. Emulators and USB phones, human+agent co-operation, loopback-only.

Agent billing and usage observability for dsh web: session-log direct-scan recording (zstd, per-event timestamps, watermark + lastSeq double dedup), multi-account rate profiles per provider and model, per-window live badge reading the window session id via React fiber, full glassmorphism dashboard with 14-day sparkline, budget alerts, relay-station balance queries and a 332-model official price library.

Live change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.

Delete sessions from the DSH Web sidebar: adds a Delete action to the session row menu with a risk-consent dialog, then removes the session log, workspace accounting and live session state.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

DeepSeek Harness peak-hour message queue: defer selected sends and deliver them to the original conversation off-peak. / DSH 高峰消息暂存与低谷自动投递。

Live speech-to-text dictation into the dsh web composer via OpenRouter STT

Built-in browser control for dsh (DeepSeek Harness): lets the AI agent open pages, read content, click, type, scroll and take screenshots in a real local browser (Edge/Chrome via the Chrome DevTools Protocol). Includes a docked live browser pane (CDP scre

Agent-first task kanban for DeepSeek Harness web GUI, modeled on codeg-plus's 任务看板: four codeg-plus columns (todo / inProgress / attention / done), human-only acceptance, workspace-bound claims, comments and a live SSE board view. 参考 codeg-plus 任务看板语义的 ds

Typst live preview as a native right-Sidebar tab: clicking a .typ file opens a tab whose toolbar switches between the tinymist-rendered page and the highlighted source, with the preview page and its WebSocket served through the app's own origin.

File-defined subagent roles for DeepSeek Harness: roles live in project and global .dsh/roles files, a delegating agent sees one catalog line per role, and each role's tool policy decides which tools its child can see.

Composer readouts for the DeepSeek Harness: CJK-weighted draft token count, session spend at official peak/idle rates, context occupancy, and what the same usage would have cost on the costliest other model; client-only, with no host half and no credential access.

Live token cost for every chat in the DSH Web UI: the chat, its subagents and the whole session tree, priced from a bundled models.dev snapshot of seven providers and 139 priced models, with cache read and write rates wherever the provider publishes them and DeepSeek from its own peak and off-peak table. Every finished answer carries its own price in the transcript, and a chat that is not currently open is priced from the log instead of disappearing. Spend is costed per interval from an append-only JSONL ledger in the project folder, so logged work keeps the tariff it was billed at. On top of it: budget-aware work plans packed against a money limit, routing scenarios that show which models are worth connecting, a generated plan document in English, Chinese or Russian, and a warning when spend belongs to no plan unit.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Immersive read-only reading panel for DSH — the model delivers pre-formatted Markdown to a native right-sidebar tab via `reading_pad_send`, with three low-blue-light themes and 30em measure typography; also browse manuscript chapters read-only.

Windows boot autostart and one-click restart for the DSH service, from inside DSH: a resident supervisor that outlives the host, so a failed restart cannot leave DSH down; DSH spawned attached to a hidden console the supervisor owns, so no console window appears; plus a restart button, the current tokenised access URL and an optional post-start hook.

Settings section that reports token usage: totals for input, output, cache read, cache write, reasoning and call count, with breakdowns by model, day, month and project plus a per-day trend chart for the last 30 days; history is rebuilt once on a worker thread and then kept current from live session events.