Plugin

Chat wallpaper for the DSH desktop UI: paint one image from a local folder across the app, tune the left sidebar, main window and right sidebar scrims separately, rotate through a group with fade effects, and add a bar under the composer, a task progress bar and an all-session token total.

Beads issue-graph panel in the left sidebar of the Web GUI: filter ready, in-progress, open, and all beads, read a bead's description, notes, dependencies, and comments, and create, claim, or close beads through the bd CLI. Requires the bd CLI on PATH and a workspace with a Beads database.

Monitor workspace sessions, subagents, todo progress and token usage in a floating panel.

A kanban board in the dsh sidebar. Every project gets its own section with four fixed columns (todo, in progress, feedback, done); add, rename, recolor, reorder and delete projects and tasks, advance a task with one click, reorder by drag and drop or with the card menu, undo a deletion, and collapse a project. Colors, radii and shadows come from the dsh theme, so it follows light and dark, and the layout reflows from four columns to two to one.

DailyBoard — a daily work task board for the DSH Web GUI with a one-month calendar of colored timeline bars and day tasks, a daily checklist, a seven-day week view with completion checkboxes and drag-to-reschedule, a draggable 24-hour day timeline, ordered per-day subtasks, weekly and every-N-days recurring tasks with per-occurrence result records, a long-term progress view opened from the calendar header, per-day completion for long-term tasks, tasks that can be marked “For others” by choosing one of the added recipients (shown as note + email), a collapsible daily email reminder that can be pushed to WeChat and can remind other people such as partners or relatives (each extra recipient has an email, a note and its own send time), and AI extraction of tasks from natural language.

Game market and runtime for DSH. While the agent runs a long task, a game fills the main workspace and a small whale in the corner shows the agent state (working, waiting for you, done, error); progress is saved and continues next time. Ships five built-in games, a game SDK and CLI, and a community catalog installable from the market.

Adds an UpdateNotify tool and a live progress panel docked above the composer in the DSH Web UI, so the model can narrate what it just did, found, or is waiting on while a turn runs.

Runs local Codex CLI tasks from DSH on Windows with background execution, progress queries, follow-up instructions, completed chat records, and optional supervision; requires Node 22.23.4+, DSH >=0.2.1-rc.3 <0.3.0, and an installed, authenticated Codex CLI.

Skill shell that installs, runs and troubleshoots React-Monitor-Agent, a human-agent operation board built on review replay and checkpoints: the agent writes its work as a structured replay timeline of screen-recording, screenshot, diff and text nodes, and the human decides at plan, progress, risk and delivery checkpoints, with verdicts branching the timeline and rejected branches kept greyed-out for audit. The skill guides cloning the source repo and starting a zero-dependency Node event service on 127.0.0.1:8790 plus a React board on localhost:5173 that ships an offline FIXTURE demo mode. The bundle embeds the skill only; product source stays in the repo.

Session cost meter forked from dsh-cost-meter, retargeted at OpenCode Go: per-session and per-day cost, a 90+ model price catalog with automatic matching, OpenCode Go subscription usage as rolling 5-hour / weekly / monthly percentages with progress bars, Coding Plan quotas, provider balances, peak/off-peak pricing notices, bilingual UI. It provides service:cost-meter like Han-1413141/dsh-cost-meter and the other dsh-subscribe-meter variants, so install only one cost meter: it replaces dsh-cost-meter rather than running alongside it.

OpenCode Go subscription usage beside the composer: the rolling 5-hour, weekly and monthly windows each as a small ring with the used percentage (amber at 70%, red at 90%). Clicking the meter opens a detail card with per-window progress bars, reset countdowns and a refresh button, and when it is not clicked nothing floats over the conversation. The API key stays in the Host process and never reaches the browser.

Live step pill in the DSH session header: folds the durable session event stream into the agent's current action (tool name plus its argument summary), the step index inside the running turn, the elapsed turn time and the todo progress, polls it every 1.2 seconds, and renders blue pulse while working, green for a finished turn and red for a failed tool call; hides itself 9 seconds after a turn ends. On Windows it also opens an always-on-top desktop HUD (set DSH_AGENT_STATUS_HUD=0 to disable).

Reads a few lines of a txt or epub novel inside the sidebar bottom panel, styled to pass for scratch notes; pages with Ctrl+Alt+J/K and keeps progress locally. Requires dsh-better-sidebar 0.26+ - the reader exists only as a tab in its bottom panel.

Mascotte desktop trasparente e sempre in primo piano: conversa tramite il modello host, riproduce animazioni al clic, sussurra a intervalli, racconta i progressi delle attività e mostra il saldo account. Funziona in DSH Desktop con il runtime Electron incluso (~/.dsh/electron); senza quel runtime la mascotte non appare. Solo Windows.

Installa, aggiorna e rimuove plugin DSH da una scheda nella pagina Plugins. L'installazione chiama il servizio pluginManager in-process del profilo, per aggiungere plugin mentre l'app desktop è in esecuzione senza passare solo dal CLI. Gli aggiornamenti usano la update API v1 pubblica di dsh-market (necessaria per la sezione) e mostrano fase, percentuale e byte scaricati in una barra; rollback solo quando il market segnala un restorepoint. Se la rimozione di un bundle in uso viene rifiutata, lo disattiva, lo elimina dal manifest del profilo e mette in coda i file residui per la pulizia al successivo avvio.

Cockpit di sviluppo a ciclo chiuso integrato in DeepSeek Harness: da un pannello l'agente compila, flasha, verifica tramite debug e monitora schede STM32; l'utente segue ogni passaggio dal vivo, con fasi di avanzamento, log in streaming, uso RAM/FLASH e forme d'onda seriali decodificate. Richiede Python 3.10+ dell'host nel PATH (il plugin non può installarlo). La toolchain ARM si scarica automaticamente al primo uso (~400 MB, solo Windows x64); serve una scheda STM32 con debug probe.

Barra di stato per la barra laterale DSH. Durante una sessione, la riga diventa una scheda verde con avanzamento basato sulla durata stimata del turno (traccia tratteggiata in movimento) e percentuale live sul bordo anteriore. Superata la stima, mostra il tempo trascorso mm:ss. Al termine diventa arancione e resta accesa finché non apri la conversazione. Solo client, senza servizi aggiuntivi, usa poche chiavi localStorage.

Compagno animato nella notch di macOS che mostra in tempo reale i progressi dell’agente DSH.

Sistema di registrazione dei progetti per DeepSeek Harness: bacheca di avanzamento a nodi, ledger decisionale e UI nella barra laterale destra.

Aggiunge a DSH Web GUI caricamenti a blocchi con avanzamento e ripresa, e download nativi dei file workspace e dello ZIP del log sessione, anche per sessioni raggiunte tramite collegamento remoto associato.

Pannello di avanzamento che analizza progetti locali in una radice configurabile, deduce l’attività da anchor e prove Git ed esporta un report HTML scuro autonomo.

Rifiuta le attese in primo piano degli agenti DSH: comandi di attesa (sleep, wait, tail -f, watch, ping senza -c, cicli infiniti), strumenti bloccanti (wait_agent, job_output con wait: true), ripetizione dello stesso comando di controllo entro una finestra e comandi che richiedono input/conferma umana (sudo senza -n, ssh senza BatchMode, login, editor interattivi, docker -it). Suggerisce un’alternativa concreta: eseguire in background o terminare il turno. Budget e finestra di polling configurabili; lingua secondo system (zh/en). Nessuna dipendenza runtime.

Trasforma le sessioni archiviate in memoria durevole, non in file inutilizzati. Distilla ogni archivio in skills riutilizzabili e fact ledger con decisioni ADD/UPDATE/NOOP, `validUntil` e `supersededBy`, ritirando i fatti obsoleti. Raggruppa gli argomenti con similarità single-linkage. Elabora anche sessioni in corso con seq watermark in sola lettura, lasciando il session log identico byte per byte. L’autoverifica misura fusione dei fatti duplicati, ritiro degli obsoleti e consolidamento delle skills; agisce solo con opt-in e non cancella mai definitivamente, usa solo supersede.

Aggiunge al selettore i modelli del proprio Space Hugging Face con GPU, avvia lo Space all’invio di un messaggio, mostra l’avanzamento e lo mette in pausa se inattivo o al limite di tempo. Richiede un account Hugging Face, uno Space GPU con API compatibile con OpenAI, un token salvato nel vault DSH come HF_TOKEN e un piano a pagamento per l’hardware GPU. Hugging Face addebita il tempo GPU.