Plugins

21 outils de gouvernance du cycle de vie en lecture seule dans un plugin DSH autonome : classement des tâches ; validation de l’état, du plan et des preuves ; précontrôle et agrégation des gates ; audits de publication et d’installation ; analyse du contexte et de l’avancement ; chemin critique ; rapprochement à la reprise ; aperçu des mutations qui refuse toujours l’exécution. Installation npm : @240xu/dsh-tech-lead.

v0.8.6 corrige le crash au démarrage : runtime Host peer optionnel, pas une dépendance installée. TypeSafe Jev/System One fournit 7 outils : `jev_decision` (1–25 verdicts typés parallèles, sans prose), `jev_choose` (classe 2–10 options), `jev_batch` (1–20 textes, 1–5 jugements, un appel réel/texte à concurrence bornée ; erreurs brutes, sans supposition), `jev_usage`, `jev_overview`, `jev_guard_status`, `jev_verify` (26/27 au benchmark fixe de 27 questions, concurrence 6). Ledger persistant par défaut : `$DSH_HOME/jev-usage.json`. Remaining=`quota.declaredBalanceUsd` moins dépenses locales depuis `quota.balanceSince` ; aucun endpoint de solde, rien d’inventé. API key absente : erreur explicite ; échecs isolés par surface. Client après refresh ; serveur après redémarrage Host.

Génère une nomenclature (BOM) de pièces de rechange pour réparer le moteur à partir de la panne et de sa puissance nominale, avec stock, délai et alternatives nationales ou importées.

Remplace les icônes en tête des cartes d’outil par des emoji tout en conservant les cartes d’origine.

Plugin DSH autonome regroupant 21 outils de gouvernance du cycle de vie en lecture seule : classification des tâches ; validation de l’état, du plan et des preuves ; précontrôle et agrégation des portes ; audits de mise en production et d’installation ; analyse du contexte et de l’avancement ; chemin critique ; rapprochement à la reprise ; aperçu des modifications qui refuse toujours l’exécution. S’installe depuis npm sous `@240xu/dsh-tech-lead`.

Token usage analytics for DeepSeek Harness: scans the host's own session logs and reports consumption by provider and model, cache hit rates, daily trends and a capability leaderboard for every model you can currently call.

To-do list panel for DeepSeek Harness: large task cards in collapsible sections, hour-precision due times, per-task reminder lead times, and DingTalk notifications through a group robot webhook or an enterprise-app work notice. Each task can bind to a workspace session and jump to it on click.

Normalizes every generated .docx to one Chinese official-document layout: XiaoBiaoSong title, FangSong body at a fixed 29pt leading with zero paragraph spacing, character-unit 2-character first-line indent, fully centered table cells with repeating header rows, and a centered footer page number. Long attachment entries are split into real paragraphs at the wrap point measured by Word, producing a 2 / 6 / 5 / 6 character indent ladder. The plugin disables itself when the request mentions a lab report, and writes no signature block unless asked.

Adds a Community Bench tab that reads the public task-conditioned registry and shows the same score everyone sees; it does not compute a local score.

Project Development Mode preset plus an in-chat development board for DeepSeek Harness: the lead conversation clarifies requirements and delegates to an Agent Team, and the floating board tracks each user change request through dispatch, execution, testing and acceptance with 7 board tools.

AI research toolkit for DSH: a model release radar, a per-model benchmark and community report from 13 structured leaderboards plus Chinese and English community discussion, and an AI news radar over 46 feeds and 22 official X accounts; registers four tools and three skills and renders every report to Markdown with a generated table of contents.

Five production-grade DSH tools bundled into one plugin (8 tool slots total): git regression finder (find introducer, recent changes, bisect, blame age), stack-trace decoder with local code context, YAML/ENV/properties config validator with typo suggestions, cross-platform shell escape (POSIX/PowerShell/cmd), and MyBatis Plus SQL static auditor (N+1, missing @Transactional, LIKE leading %, SELECT *, missing WHERE). Zero npm dependencies, all offline; concurrency-safe except the bisect tool (dsh-when-broke). Each sub-plugin is also installable standalone (dsh-when-broke, dsh-stackdecoder, dsh-config-guard, dsh-cmd-shield, dsh-mp-auditor).

Adds per-member model and reasoning-effort routing to DeepSeek Desktop Agent Teams, plus leader-initiated release of a teammate subagent run instance.

Renders an Agent Teams swimlane canvas above the composer: lead centred with members below, tasks laid out in lanes by longest dependency path, and four SVG connector families drawn as dashed paths (task dependency as a cubic bezier from the upstream card edge to the downstream card edge, lead bus, peer bus, member-to-task tether). Cards are absolutely positioned DOM, connectors are one SVG layer sharing the same geometry constants. Layout constants and path algorithms are ported from cc-haha. Reads the live per-session agentTeam projection (roster, shared tasks, dependency edges, running state) and falls back to the session todo list when the session has no team; team messages are not part of the projection yet, so the communication panel shows an empty state. Body colours come from host theme tokens; the eight member identity colours are the deliberate exception — fixed hues mixed with the theme accent via color-mix, declared as CSS variables because the same values feed an SVG stroke attribute that rejects colour functions. Ships zh/en dictionaries with identical keys.

A price-aware task runner for DeepSeek: during an off-peak pricing window a batch of prompts goes straight to deepseek-flash; near peak it queues the batch behind a self-held timer and runs it at the start of the next off-peak window. Exposes `peak_run`, `peak_schedule` and `peak_cancel`, with configurable peak windows and a lead time.

起诉状要素齐备性核对（按诉请、事实、证据、法条四要素核对文书齐备，仅提示差异，不作出定性结论）

Alpha Agent Teams plugin for DSH 0.2.0-rc.2 and newer that lets same-session user Steer end the Lead’s current wait_agent call while teammates continue, with native message delivery and Node PTC continuation.

Skill browser and switchboard for the DSH web GUI: a sidebar entry lists skills from configurable source directories as cards, clicking a card opens the full SKILL.md, and the per-card switch writes disable-model-invocation and registers or removes that skill in the agent skill catalog, so the model can load exactly the skills that are switched on. It also recognises WorkBuddy expert-team folders and shows avatar, tags, quick prompts and members, registering its lead prompt as a skill when switched on. Source directories are editable in the panel.

22 light-only palettes (Pantone / Chinese traditional / Morandi) and 14 composable surface effects for DeepSeek Harness, with twelve-shichen clock rotation, manual picks that lead until the next boundary, workspace binding, per-session colour marks and a nickname/avatar row whose editor lives in the settings page.

LiveBench leaderboard for DSH — discovers the release the official site currently publishes, then reads its CSV and category JSON, and renders model rankings in an isolated same-origin iframe opened from a button beside the composer. Search, organization / open-weight / reasoning filters, per-category sorting, task-level detail, up to four models side by side, CSV export; refreshes every 60 s by default (configurable 30–3600) and caches only to the plugin's own .cache/rankings.json.

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Fiche de score qualité pour les plugins DeepSeek Harness : note de 0 à 100 avec mention, 6 composantes, suggestions de correction par déduction, classement par lots — CLI plus un outil quality_score appelable par l'agent.