Plugin

Memoria cross-sessione per DeepSeek Harness tramite il dominio di storage ufficiale: le memorie persistono tramite ctx.storage (tabella storageDomain) e sono iniettate nel system prompt tramite una sezione registrata (memory:recall), con strumenti memory_save / memory_forget così l'agente legge e scrive la propria memoria (maxMemories configurabile).

Pannello di gestione dell'attenzione ai token per DeepSeek Harness: monitoraggio di utilizzo e costo dei token per attività/giorno/settimana/mese (hit/miss dell'input, output, ragionamento), prezzi DeepSeek di punta/fuori punta, riconoscimento del tipo di attività e consigli su quando cambiare sessione, scrivere un passaggio di consegne o comprimere il contesto.

Gestore del tier di sforzo di ragionamento per modelli API personalizzati più memoria delle preferenze cross-session: toggle inline low/medium/high/max dentro Impostazioni → Modelli, con scritture atomiche delle impostazioni.

Forma in bundle statico del gate di sicurezza per l'installazione dei plugin DSH: esamina cordis_define/cordis_run con una policy fail-safe, oltre a strumenti di revisione/audit e un popup di approvazione del browser (agree / agree+whitelist / reject; agree+whitelist scrive la famiglia di plugin in tru).

Cursore di sforzo di ragionamento in pixel art per DSH Web con trascinamento continuo da 0 a 100, scritture limitate a 16 ms, conferme con aggancio al livello e un fuoco di braci WebGL che si accende mentre il cursore si muove.

Registra la skill remove-pdf-background-gray per DSH: sbianca gli sfondi grigi/bianco sporco delle scansioni nei PDF basati su immagini, preservando la risoluzione, la geometria della pagina e i bordi del testo con antialiasing (riscrittura Flate senza perdita), tramite un singolo script Python (pypdf + Pillow + numpy).

Pacchetto di competenze dell'agente per note virali Xiaohongshu/RED: ricerca di note di tendenza, generazione/riscrittura di note, verifica, analisi degli account autorizzati, accesso tramite QR e pubblicazione controllata.

Esamina il codice locale e GitHub/npm prima dello sviluppo per trovare implementazioni riutilizzabili, valuta riuso contro riscrittura e verifica il coupling dell’architettura.

Memoria nativa per workspace sulle cuciture stesse del harness: fatti e un profilo sempre attivo ma limitato nell’unità JSON del dominio di storage, scritture con approvazione e citazioni `(sessionId, seq)`, richiamo deterministico e FTS session-query sulle sessioni passate — senza server esterno, senza SQLite personalizzato.

Rivede ogni file scritto dall'agente in una sessione direttamente dall'intestazione della sessione, con hunk per file e scritture rifiutate contate a parte dalle modifiche.

Blocco di scrittura Markdown con ambito di sessione ancorato accanto alla conversazione, con modalità modifica/anteprima, riscritture IA basate sulla selezione, revisione delle differenze, annulla e recupero bozze.

Kit operativo basato sulle prove: sei strumenti in sola lettura (catalogo delle capacità, piani di workflow a stadi, lettore di skill impacchettate, ricerca limitata nella memoria locale, audit delle release del repository, checklist di release) e cinque skill impacchettate — pianifica e verifica, senza mai scrivere da remoto.

Claude Code's auto memory in DeepSeek Harness: the index in every request, and tools to write and edit it

Second-model gate on the assistant turn, installed in two parts: copy engine/ into ~/.dsh/plugins/ and mount it by absolute path in the profile patch (the bundle itself only installs the settings panel), then switch off the default dry-run mode that only logs verdicts. Once active, a separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. The web panel edits criteria and thresholds, and every verdict is appended to an audit log.

The cyber-elixir of youth for the desktop client: fixes the `desktop welcome: Web authentication failed` (HTTP 431) launch failure — an Electron random-port launch lets `dsh-auth-*` login cookies pile up per port (70+ of them, ~229 B each), the startup request headers blow past Node's default 16 KB cap, and the client can no longer launch. Two fixes in one: a scriptable cleaner that removes leftover login cookies from the cookie database (Chromium SQLite) — explicit, offline, keeps a `.bak` copy, `--expired-only` narrows the scope — and a `patch` feature on the settings panel that fixes the launch port through the profile `cordis.patch.yml`, so the client always starts from a single port and cookies stop accumulating across different ones (rewrite `port` as a `!!js` expression to keep the `--port` flag in charge; a per-profile snapshot makes one click revert it). Read the README for usage. Interface, CLI output and market metadata in 9 languages. The purge runs from the bundled CLI (`dsh-cookie-cleaner --clean`) only while the client is fully closed; the in-app half is read-only. npm: `dsh-cookie-cleaner`.

A consent-gated personal profile store: people are indexed by name, entries by person and key, and no profile record is read before the current session is authorised. Sensitive entries come back masked unless the user authorises that tier separately; credential-like values are refused at write time. Ages and next birthdays are computed at read time, so asOf restores the answer for a past date, and facts that rot (height, weight, address) carry freshness warnings. Five profile_* tools plus a settings page to browse, edit, delete and revoke grants.

A memory plugin that forgets on purpose: short-term memories expire after 48h, long-term ones are rescheduled by Ebbinghaus/SM-2 curves and rarely-used ones fall asleep instead of bloating your context. Long-term writes stop in an approval center, so the agent cannot rewrite your persona on its own.

Prompt booster for the composer. Left-click the composer button and the draft is lightly polished and replaced in place (undoable, no popup). Right-click opens a menu with 8 built-in modes plus your own, where each mode's template can be edited or new modes added (saved on the host), and the model used for the rewrite is picked from the live dsh model list. Other modes show a before/after preview. Based on rongxingda/dsh-prompt-enhance (Apache-2.0); do not install both — both add a composer button and share Ctrl+Alt+E, so disable one of them if the upstream is present.

Adds two enhancements to DSH ask_user_question choice cards: right-clicking an option expands a per-option note that is merged into the submitted custom answer, and a footer field asks a side question answered by a fork subagent from the session context, read-only, with no write-back. Keeps left-click, skip, paging and the countdown working as before, and only claims generic choice cards, not plan review or approval cards. Supports DSH 0.2.x from 0.2.0-rc.1 (verified on 0.2.2-rc.1) and Node.js 20+. Derived from buaaflyaway/dsh-question-note (MIT) and inspired by MichengAI/dsh-btw (Apache-2.0); do not install it together with dsh-question-note — both take over the same ask_user_question card.

Optimize prompts in the DeepSeek Harness composer: identify missing requirements, insert a sentence from 90 method cards, or compare and edit a full rewrite before you send.

A sticky-note wall in the DSH sidebar: nine paper colors, categories, search, archive, to-do checklists with stable item ids, and agent read/write tools.

Brings the rtk token-saving setup from Claude Code to DeepSeek Harness: commands rtk can rewrite are rewritten, and builds, tests and logs it cannot reach are compressed; git, cargo, npm and pytest are covered. Compressed output tells the model what was elided and how to recover it; when the sandbox cannot reach the rtk store the original is saved and its path given. Savings show without a command: a pill below the composer, with `/rtk stats` for detail. When a rewrite is unreliable the original command runs as usual: if rtk cannot run, or the returned command would drop arguments, nothing breaks. The rtk binary ships with the package, so mainstream platforms need no separate rtk install, unlike most other rtk plugins.

Qoder-style workspace mode and branch chips on the session row; picking a branch arms it, and the first message creates a dedicated git worktree and moves the session into it. Windows only: the write grant runs PowerShell Set-Acl; elsewhere Worktree mode reports an error and stays in the main checkout.

Multi-round deep research in the DSH sidebar: each round fans sub-questions out to parallel sub-agents, then continues from where the last round stopped and writes a cited report.