Plugins

Voice conversation mode for the DSH Web GUI: tap the mic to start a full-screen call, talk hands-free, and hear each reply read aloud as it streams. Bilingual (Chinese/English) UI, light and dark themes, adjustable speech rate, and switchable voices.

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.

Knowledge base with a corrective acquisition loop for DeepSeek Harness: when the agent keeps hitting the same failure, a background worker fetches the web under a rate limit, distills the result into a staging area, and only a two-stage commit makes it recallable — pages without sources are refused.

Generates a standard motor-repair procedure from the diagnosis and motor rating, with labour time, staffing and a quality-check point for each step.

Combines historical supplier quotes and service rates into onsite-repair, factory-overhaul, green-remanufacture and replacement options for a motor, then recommends one by total cost of ownership.

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

Peak/off-peak billing cost dial for the DSH Web GUI: session token usage billed at the official DeepSeek peak and off-peak rates, a rate dial with a model-colored needle and switch countdown, a balance ring with a low-balance alarm, drag-to-resize, and a minimized status-lamp mode.

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

Share the DSH workspace over the local network: phones, tablets and other computers browse, download and upload files via browser with no DSH login. Token gate, path boundary, read-only mode and rate limit. Zero-dependency (node:http).

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

A-share market dashboard for DeepSeek Harness: realtime market indices, stock screener with 13 technical signals and multi-strategy intersection, 7×24 multi-source news aggregation, watchlist with group management, market sentiment thermometer (limit-up ladder, breadth), K-line charts with MA/EXPMA/BOLL overlays, and sector/limit-up/longhu rankings.

Persistent memory for DeepSeek Harness with curated facts, automatic turn retention, and graph- and vector-ranked recall.

Cross-app project memory for DeepSeek Harness with role-separated writeback, a visual knowledge workspace, confirmed corrections, session controls, local Writer and organizer settings, and an account-free Windows local installation preview.

Browse the skill library from a floating-ball panel: you choose the skill root yourself through a native directory chooser (defaults to ~/.dsh/skills, no path is shipped with the plugin), skills are grouped into first and second level categories, descriptions are read from each SKILL.md frontmatter, search filters by skill name, description or original text, and a card opens the full SKILL.md. Skills can be switched on and off per card, per category or for the whole library — the toggle rewrites disable-model-invocation in that SKILL.md and keeps a .bak-toggle backup, and disabled cards grey out until restored. A failure ledger separates automatic from manual entries and records skill successes and failures by listening to tools/result events, reusing an existing ledger file if one is found in the library and otherwise creating one under skill-master/references. The DSH settings page gains a floating-ball section that shows or hides the three balls and offers one-click restore of a ball dragged off-screen.

Composer code-quote collapse for the DSH Web UI: pasting a `path:line` header followed by code folds the input into one compact inline quote chip, and at send time the `agent/pre-step` hook injects the full pasted snapshot to the model as a separate context message. 0.5.x also folds sidebar file-selections that insert only a `path:lines` line (large selections), fetching the code from disk by session cwd, and preempts Ctrl+V paste interception.

Adds a /dshpp slash command that reports session and token usage, cache-hit rate, and estimated cost from harness session logs; the repo also ships a CLI and local web console for lifecycle, provider, session, and plugin-security management.

A tiny behavioral mood ring for AI coding agents — folds session behavior (consecutive failures, repeated calls, activity) into a four-state Mood (GOOD / CONFUSED / FRUSTRATED / OVERWHELMED) shown as a low-friction session-header status light.

Provider/model-aware adaptive pacing and visible rate-limit retries for DeepSeek Harness free models.

DeepSeek Harness plugin: GitHub repository/issue search, repo and issue details, and file reading tools (github_search / github_get). Anonymous by default; an optional read-only fine-grained token unlocks code search and raises the rate limit.

Playbook de publication pour agents IA. CLI installable via npm + plugin DSH + bundle de skills. Couvre npm, les remotes GitHub+Gitee, le marketplace DSH, cargo crates.io, PyPI, l’exécutable PyInstaller, les binaires uniques Go et Rust, ainsi que les applications Electron/Tauri. Bilingue EN/ZH.

Skill de communication adaptée au profil : construit à partir de la conversation un portrait utilisateur évolutif (niveau, lacunes par domaine, état actuel) et ajuste la profondeur, la densité du jargon et le détail des étapes. Détecte le fait de feindre l’incompréhension d’après le comportement, pas les affirmations ; export transparent d’un snapshot de profil. MIT.

Découverte des skills du projet : énumère les entrées .dsh/skills contenant SKILL.md (liste en lecture seule).

Surcouche de paramètres par profil pour DeepSeek Harness : global settings.yaml reste la base, chaque profil remplaçant tout espace de noms via son profiles/<name>/settings.patch.yml — les sections d'objet fusionnent récursivement, les scalaires et tableaux remplacent en bloc, et !unset masque une valeur héritée. La surcouche est transparente aux plugins existants (ils lisent toujours ctx.settings inchangé), les écritures vont dans la seule surcouche du profil, et la validation officielle du schéma, la sémantique de révision, les conflits expectedRevision, les observateurs et événements sont intacts. Fournit une famille de commandes settings (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) et une section Profile Settings dans le panneau Settings web via un canal RPC loopback.