Plugins

Palette universelle en verre translucide dense pour DeepSeek Harness Web : regroupe Commands, Models, Sessions et Conversation Hits avec classement déterministe et interopérabilité vérifiée des contrats publics.

Change en un clic de moteur de recherche près du sélecteur de modèles DeepSeek Harness ; modifie le fournisseur `dsh-free-search` et convient aux réseaux universitaires à l’étranger qui bloquent le point de terminaison de recherche DeepSeek Official.

Recherche hors ligne et déterministe dans un catalogue d’API publiques pour DeepSeek Harness, avec requêtes en chinois/anglais et filtres exacts par authentification, HTTPS, CORS, statut, niveau de source et catégorie.

Adds a reasoning-effort rail above the DSH composer: drag or use the keyboard to preview and submit the levels the current model exposes (Off through Max), while a procedurally rendered micro-universe contracts and collapses into a black hole as effort rises. Levels go through the DSH model-selection interface, so the rail shows the level DSH confirms, and the plugin writes only to $DSH_HOME/stellar-effort/.

Typing companion with five characters and composer following. This entry installs the universal page package (page mode only); the optional Rust desktop mode for macOS and Windows ships in the platform-specific release packages (darwin-arm64, darwin-x64, win32-x64).

Daily check-in for Nanjing Forestry University's ACM AI Hub plus seat booking for its library — both site addresses are hardcoded — with a settings page and a progress badge; built for DeepSeek Harness Mobile (DSHM) on Android.

Measures one university department's research output: matches author affiliation strings against a college's known name variants (detecting same-named departments at other universities), backfills papers that only name the university by faculty author IDs, classifies each paper by journal tier (CAS partition with Top flag, JCR quartile, CCF, Chinese core via a CNKI export merger), splits staff from student first authors, and writes a workbook with a dashboard sheet, a filterable paper list, a teacher-by-direction matrix and per-teacher statistics. Student authorship is inferred from affiliation and staff lists, not verified against enrolment records. Requires Python 3.9+ with pandas and openpyxl (pip install -r requirements.txt); papers come from the OpenAlex API, whose free per-IP quota is limited, and Chinese-journal coverage needs a manual CNKI export.

Manages the lifecycle of the local UM GenAI proxy (127.0.0.1:8788) that DSH's um-genai provider talks to: wakes it on demand for llm/stream calls, stops it after an idle period, and reports health plus a read-only status endpoint. Also ships a DSH settings page for port, always-on mode, idle minutes, interpreter and paths, plus the UM account and proxy API key, and a button that writes the providers.um-genai entry into the profile patch and fills in its model list, since a fresh profile has no provider and the model picker would otherwise stay empty. A renewal watchdog logs in to the campus gateway on a hidden Windows desktop when the upstream token expires. The proxy itself is um_opencode_setup.py, a single-file tool distributed by the University of Macau; a copy is vendored in vendor/ so a fresh install works out of the box, while a copy in ~/.um-opencode/ takes precedence when present. The plugin still does not produce tokens: those come from logging in to the campus gateway. Requires Windows (process discovery and idle shutdown use netstat/taskkill; renewal uses PowerShell and a hidden desktop), Python 3.10+ and a University of Macau account.

Ajoute un curseur d'effort de raisonnement au menu des modèles de DeepSeek Harness, y compris pour les fournisseurs et modèles sans métadonnées d'effort. Basé sur Microqian2th/dsh-codex-effort-slider ; désinstallez ce plugin amont avant d'installer celui-ci.

Étalonnage vidéo local avec LUT DJI Log adaptées à la caméra, hautes lumières et ombres indépendantes, commandes facultatives peau/couleurs sélectives, aperçu des images et export HEVC 10 bits. Le tarball universel indiqué ne fournit aucun runtime : au premier lancement, « configure environment » télécharge par HTTPS un runtime épinglé (Python 3.12 + FFmpeg 9, ~100 Mo) ou permet d’indiquer son Python 3.10+ et FFmpeg/ffprobe 8+. Les releases suffixés par plateforme incluent ce runtime.

Plugin hôte pour le compagnon de barre de menus macOS : état en direct des sessions DeepSeek Harness, Approve/Deny pour les approbations d’outils, arrêt du tour courant et ouverture de la session exacte. L’application native est une build universelle gratuite sur GitHub Releases.

Hôte universel MCP Apps et plugin d’interface pour DeepSeek Harness (DSH).

Passerelle de vision universelle IntelligentEyes pour agents DeepSeek Harness.