Plugins

Tableau de focus pour les agents DeepSeek Harness : des notes durables tenues par le modèle dans le workspace de session, qui fixent l'objectif, les contraintes et les décisions à travers la compaction et les sessions, avec injection automatique dans le contexte, archivage à l'effacement et panneau web optionnel.

Endurance-coaching skill bundle that defaults to Intervals.icu for training data (activities, intervals, streams, training load, HRV, resting heart rate, sleep in-bed hours, eFTP) and uses COROS only for training-plan read/write and for fields Intervals.icu lacks (sleep score, recovery score), with iGPSPORT as a fallback for ride details. It turns that data into readiness gating, VDOT pace and heart-rate zones, periodized weekly plans, session reviews, race-day pacing and fueling, and weather-adjusted workouts. The bundle registers the endurance-coach skill in the profile, ships deterministic helper scripts, reads an athlete profile created by its init script, and requires the agent to state when data is unavailable instead of inventing it. Data comes through separately installed MCP servers — the Intervals.icu MCP server for training data, the dsh-coros plugin for training-plan read/write and sleep/recovery scores, an iGPSPORT MCP server only as a ride-detail fallback — and its bundled scripts need Python 3.10+; with none of them it works only from numbers you type in.

Bridges the official COROS MCP server into DeepSeek Harness with a self-contained local stdio-to-HTTP bridge and on-device OAuth login, exposing 34 COROS tools on the current endpoint for sleep, HRV, resting heart rate, recovery, training load, activities and FIT files, plus workout and training-plan CRUD and scheduling.

Five-layer persona (L1–L5), event memory with FTS5 plus Dice retrieval, cognitive filter, skill cards with auto-frozen asset packs, millisecond reflex rules, three-tier safety degradation, a read-only brain star map, and an optional VPet-Simulator MOD bridge.

Nine single-ink print palettes — sage linen, kraft paper, lead type, cyanotype, risograph, CRT tube, phosphor screen, punch card, floppy disk. Each palette carries its own paper grain, type pairing, corner shape, section rule and a whale mark redrawn in its ink, plus a letterpress pass (paper tooth, sheet mottle, ink bite) that can be switched off. Every palette ships separate light and dark tokens.

JetBrains IDE bridge for DeepSeek Harness on Windows: installs as a DSH bundle, publishes the authenticated DSH URL, registers the open IDE project, relays the IDE MCP server, and serves a compact tool-window panel with streaming, approvals, Plan/Act, steer sending, session switching and archived-session filtering. The matching IDEA plugin is attached to the same release; your DSH agent can install it.

Autonomous product-polish loop skill: every round opens a fresh brainstorm from 3 forced perspectives, picks one small angle capped at ≤3 files and ≈100 lines, implements it, verifies with the repo's own tests, build or lint, and commits it as a single round commit; the round is logged to a per-project ledger, and ideas too big for one round go to an icebox. A red check ships nothing — the round commit is reverted immediately so the failed diff stays in history. Non-git targets are rejected before any work starts. Pure skill bundle: no MCP server, no runtime dependencies. Requires DSH 0.2.1-rc.2 or newer, below 0.3.0.

Zhinao (second brain) for DeepSeek Harness: Markdown-authoritative layered memory (L1 long-term model gated by user confirmation / L2 knowledge with mandatory sources / L3 recent status under daily quotas), a local recall ledger explaining every injection, lifecycle engine with weekly review and a Web panel. First-run wizard initializes a blank brain, adopts an existing Zhinao directory read-only, or fills in only missing skeleton files; existing files are never touched.

One click beside the composer turns a half-formed draft into a structured prompt the AI can act on: goal, constraints, output format and acceptance criteria filled in, placeholders only where a real decision is missing. Rewritten in place and never sent — undo with one click or Ctrl+Z. Four editable presets (general / code / writing / translation), optional conversation context to resolve references, and a model that either follows the session or is pinned to a chosen provider and reasoning effort. Requests survive session switches and typing while a rewrite is in flight; a result that no longer matches the draft is kept for retry instead of overwriting it. Pure JS, no build, no bundled dependencies.

Local LoRA and QLoRA fine-tuning in a panel: import JSONL, see a VRAM estimate before training starts, evaluate, and export an adapter. One-click Python venv setup, but you must supply your own Python 3.10+ and an NVIDIA GPU (6 GB or more). Verified end to end on Windows 11 with an RTX 3060 6 GB; the installer refuses non-Windows hosts, so Linux, macOS and other GPUs are unsupported for now.

Global cyber-terminal theme: a click-through full-screen Matrix code-rain overlay, phosphor-green UI styling, a sidebar one-click toggle, and adjustable speed, density, opacity and glow with three palettes.

ADHD-friendly focus soundscape docked under the DSH composer: five procedurally synthesised noise colours (white, pink, brown, rain, fan), a live-waveform orb, a 15-90 minute fade-out timer and a liquid-glass popover. No audio assets and no network requests.

内置 zk 的 DSH 知识库 / 日记插件：装好即用 —— 自动装 zk、建笔记本，给 agent 一组 zk_* 工具（搜索、读写、日记、双链），设置页里管路径、索引与自检。

Matrix-style binary (0/1) digital rain for the Harness interface: columns spawn only while a task is running, fall off screen when it stops, and leave a blank canvas; frosted-glass token layer with adjustable digit and panel opacity.

COROS Sport panel for DeepSeek Harness: sign in to COROS inside the panel, read the account, bound devices, recovery, fitness, recent workouts, daily health and the training schedule in one dashboard, and get a plan from the model with /coros-plan. The plan page writes a fixed four-week, 16-session plan to the account only after a two-step confirmation.

Injecteur de démarrage Lingshu : exécute brain.py startup à chaque nouvelle session d’agent et injecte automatiquement persona, mémoire et tâches. Requiert Python 3 et la compétence Lingshu dans ~/.dsh/skills/lingshu ; si l’un manque, aucune action ni message. Le dépôt principal fournit aussi un point d’entrée SKILL.md intégré au bundle.

Casque de sécurité pour le code IA : niveaux d’écriture L0 lecture seule / L1 workspace seul / L2 complet, avec confinement des modifications privilégiées. Sous le niveau requis, refuse l’écriture et renvoie un bloc prêt à coller. Chaque chemin subit un contrôle raw-string de traversal et realpath, détectant aussi les échappements par junction.

Distille les conversations quotidiennes en une fiche de personnage actualisable et un module émotionnel intersessions qui entraîne la persona.

Trois skins rétrofuturistes pour DSH Web GUI : train au crépuscule, pluie néon et côte au coucher du soleil, avec sélecteur intégré et choix conservé localement.

Crée des sauvegardes froides hors ligne d'un profil DSH Windows et de données Home sélectionnées ; inspecte les ZIP séparément et restaure-les avec un assistant WPF autonome vers une nouvelle cible disposant d'un runtime compatible vérifié.

Ajoute stickers et réactions emoji au chat Web/Desktop DeepSeek Harness : sélecteur dans le compositeur, stickers agent rendus en images tandis que la transcription conserve l’étiquette du pack, réactions sous la bulle utilisateur et effet pluie d’emojis.

Thème rétro de phosphore CRT : écrans Matrix vert sur noir pur, ambre-vert 40K ou ambre TFEL, texte gras lumineux, animation de démarrage en pluie de code et panneau de contrôle façon BIOS.

Dix arrière-plans animés plein écran pour le panneau de conversation DSH — ciel étoilé, pluie de code, circuits, combat à l’épée, chat, fille, avion de chasse, course, neige, bulles — ; un thème aléatoire par tour et un voile sur la colonne de texte pour préserver la lisibilité.

Audite ce que la compaction du contexte a réellement perdu. Lit le journal brut des événements et vérifie la survie des contraintes permanentes de l’utilisateur (ne pas faire, faire, uniquement dans tel cadre), les chemins/versions/ports/identifiants inventés, les « voir ci-dessus » pointant vers du texte supprimé, la taille du résumé par rapport aux tokens libérés et les coupes non comptabilisées. Selon arXiv 2608.11242, une mesure relève ~17 % de survie des contraintes selon les compacteurs. Quatre outils agent, dont un balayage intersessions classant les conversations selon le préjudice. Déterministe, sans LLM : toute erreur relève d’une règle identifiable.