Plugins

Contrôles de restauration pour le dernier message de conversation terminé

Transforme le dernier tour de session DSH terminé en vidéo récapitulative verticale partageable : storyboard modifiable en cinq scènes, masquage de confidentialité côté hôte, amélioration IA et narration TTS facultatives, export MP4/WebM avec couverture PNG.

Enregistre la compétence Inspiration Deck Workshop pour DSH : jeux de présentation HTML statiques locaux (6 modèles de jeux, plus de 25 mises en page, 23 thèmes et vitrine d'animations) avec un CLI de validation et d'export PNG/PDF et des tests fumigatoires, sans dépendances d'exécution.

Plugin de domaine de développement Rust pour DeepSeek Harness (dsh) : pyramide de vérification fmt→clippy→build+test→miri+audit(+semver) en tant qu'outils exposés au modèle + gouvernance au niveau du graphe (8 règles anti-Goodhart, dont densité de #[allow] / tests supprimés, blind-spot via Cargo.toml et pub

Plugin de succès et de gamification : débloque des badges pour les tours, appels d'outils, sessions, séries quotidiennes et comportement de codage (modifications/lectures/tests), avec mur de badges, toasts de déblocage et SDK ctx.achievements.

Badge dans l'en-tête de conversation affichant la version de DeepSeek Harness, vérifiant la dernière version sur npm et proposant des mises à niveau.

Tests d’acceptation indépendants dans un navigateur pour les livrables d’agent : une spec JSON en entrée, un verdict basé sur un vrai Chromium en sortie.

Scanner d’initialisation de dépôt en lecture seule (outil repo_setup_scan) : détecte stack/tests/docs/git/db et recommande des plugins, des serveurs MCP et des fichiers d’hygiène.

Génération automatisée de tests unitaires : une commande /testgen et un outil generate_tests qui échafaudent, exécutent et corrigent les tests jusqu'à ce qu'ils passent (générateurs LLM + modèles hors ligne ; vitest/jest/mocha/node:test).

On-screen test-progress HUD for DSH — a click-through panel drawn over the app under test, showing each step's expectation vs actual and whether the waiting human may take back the mouse and keyboard. Ships a universal prebuilt binary (arm64 + x86_64), so no Xcode Command Line Tools are needed; the panel itself requires macOS 14+.

Five tools that build, test and run the Inimerse engine, and drive its Verse layers over the server's line protocol. Needs a local Inimerse checkout built with CMake; point the bundle's repoRoot at it (the shipped default is the author's path).

Asset governance console for self-hosted AI infrastructure. Registers MCP servers, skills, agents and AI apps in one ledger with a lifecycle state machine, per-tool RBAC permission points, department x agent x skill cost attribution, dependency topology and an append-only audit trail. Ships 27 plugin packages, 354 REST routes and 83 MCP tools; selftest runs 1486 end-to-end assertions. Not a hosted service, no cloud contract.

Learning Mode toggle in the input toolbar: injects a teaching prompt into the current session so the assistant introduces a topic, teaches it, tests it, and corrects mistakes, rendering graded quizzes through GenUI. Requires the GenUI plugin (@changfenhuang/dsh-genui); without it the teaching text still works but quizzes, sliders and charts degrade to plain text.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

An easter-egg brake-pedal self-test. A draggable pill in the DSH web UI runs six full-force braking stomps; the bracket snaps at a pseudo-random stomp between the second and the sixth, or the run passes entirely, and then a fictional notice appears. The pedal force is derived and labelled as such, while the session figures it derives from are read from the real session log. It never intercepts, delays or takes over the real stop action.

Network explorer for kids: my identity, DNS lookup, a traceroute trip, speed test and who is home on the LAN.

Enforces a check-fix-recheck loop when a task is wrapping up: it auto-runs your tests/lint/audit, blocks any round that still has unfixed problems, and only calls the task done after three consecutive clean full checks, then notifies the user.

Backs up DeepSeek Harness sessions, plugin config and workspace memory to Nutstore (Jianguoyun) over WebDAV, with incremental upload, connection test and one-click restore on a new machine.

Tracks this turn cost under the input box, today tokens and spend in the sidebar with peak and idle pricing, and pins the latest question to the top of the conversation.

AI-agent-driven automated testing platform for DeepSeek Harness (dsh): Markdown case library, bug reports, per-project serial queue, development board and built-in load testing.

Read-only work report rebuilt from local session logs: tools used and how often, commands run, files read and written, whether tests passed, failures and their causes, token usage, and whether the task finished.

Browser automation for DSH: the agent fills in forms, scrapes lists and works across tabs in real pages, using the logins you already have. It drives its own visible window on your desktop — minimise it and it keeps working without stealing focus — and a sign-in, CAPTCHA or native dialog stops the run and hands the page back to you: it never confirms on your behalf. Login state persists (own profile plus session-cookie re-injection). 23 Playwright tools (20 always on, 3 gated and off by default), with a URL allowlist, dialog suspension and a CDP method allowlist that are mechanism-level and pinned by tests.

Zero-token DuckDuckGo search provider for the DeepSeek Harness (DSH) web seam — local headless browser, no API key, no model billing