Plugins

Applique les prompts personnels et les modifications du system prompt globalement ou à une session unique, afin que chaque session ait sa propre configuration sans toucher aux autres.

Contrôle de l’ordinateur sous Windows pour DeepSeek Harness, avec captures d’écran, UI Automation, 18 outils de bureau, activation par Agent, transfert à l’intervention humaine, demandes d’approbation et workers natifs précompilés.

Prompt library stored in the plugin config, with a Settings page and a composer picker: the ticked prompts are injected into every model step of that session, and a subagent inherits the selection of its nearest ancestor session.

Ajoute aux questions à choix multiples DSH une carte TypeSafe Jev de second avis destinée à l'utilisateur : recommandations, distributions de probabilité, confiance, JSON brut et adoption en un clic.

Gérez les skills et les commandes DSH depuis les Réglages : lister, activer/désactiver, modifier, supprimer et ajouter des skills aux échelles globale et projet, et enregistrer des prompts réutilisables comme commandes slash.

Supprime les prompts en file d'attente qu'un enfant de fork DSH hérite de son parent, afin que le premier tour d'une nouvelle branche exécute le prompt saisi à cet endroit plutôt que le suivant du parent.

Panneau d'aide GitHub MCP : affiche des prompts d'exemple copiables dans Réglages → Plugins → GitHub MCP (4 aléatoires parmi 30), visualise les stars/fork/langage des dépôts d'un utilisateur public et ajoute les outils de modèle gh_repo_stats et gh_current_user.

Utilisez votre téléphone comme télécommande périphérique DSH : envoyez des messages (saisis ou dictés avec le clavier du téléphone), répondez aux invites oui/non et de choix, parcourez les messages et changez de session sur un écran de style Game Boy, appairé via QR LAN ou un tunnel Cloudflare intégré.

Configurations d'exécution de style IDE pour DSH : enregistrez des prompts LLM et des commandes shell comme run configs réutilisables (globales ou par workspace), exécutez-les depuis l'en-tête de session ou la page de nouvelle session, et gérez-les via l'outil task_run_config avec des écritures soumises à approbation.

Analyse les images de conversation via des invites spécifiques au mode (caption, UI, document, grounding, topologie, etc.) et injecte des preuves structurées avec des primitives de coordonnées (boîtes, points, références) sous forme de texte, avec mise en cache au niveau de la session pour réutilisation lors du replay et de la compaction.

Refine prompts with guided questions and editable previews using Harness AI or native Codex across Web, desktop and TUI, applying drafts only after user confirmation.

A project-scoped memory plugin for DSH. Knowledge authoring and the plugin's own prompts are open to editing, so users can redesign the library structure and how the model is driven without changing a line of code. By default the library is built on one core idea: a project document you design yourself (a handoff by default) is the project entity; the plugin detects which project a session belongs to, binds captured knowledge to that project, and promotes what generalizes into theme and global layers. The most natural logic there is does the pre-filtering of knowledge, with controllable compression and archiving of context.

Drive a DSH instance from another device: a host plugin opens a token-authenticated TCP port that a single-file Python CLI drives - listing and creating sessions, sending prompts with images, streaming replies, and switching models, permissions and workspaces.

Google-AI-Studio-style turn controls for DeepSeek Harness, in one install: edit a prompt and re-run it, re-run a reply in place, delete a turn from the model context, and render sent prompts as Markdown. Self-contained: the plugin list shows this one row;

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Maintains stable emoji session titles in DeepSeek Harness after user prompts without adding naming messages.

Forwards an unattended DeepSeek Harness run's tool-call approvals and ask_user_question prompts to Feishu cards on your phone. The desktop GUI answers first — a card is only sent after `delaySeconds` (120 by default) with no answer there — and a phone approval grants `allowed-once`, so no authority accumulates on the phone. One outbound WebSocket long connection to Feishu: no public IP, domain, tunnel or relay.

Drive a local DeepSeek Harness agent from QQ and other IM channels through AstrBot: send tasks with /dsh, continue by quoting or @-mentioning the bot, answer approvals and ask_user_question prompts from chat (in parallel with the DSH web UI), and get results, inline images and file cards back. Ships session / workspace / model / permission commands, /compact and /last recovery, three progress-display modes, and group-shared or per-user session scoping.

Arrow-key input history for DSH 0.1.2-alpha.1: press ↑ in an empty composer to recall this session's prompts, ↓ to go forward, Esc to restore the draft.

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.

Matches prompts to installed skills for automatic activation, applies skill-declared lifecycle hooks and tool policies, and manages GitHub-hosted skills from Settings or the skill_manager tool.

Délégation planificateur/exécuteur avec rôles nommés : un planificateur fort pilote, des sous-agents exécuteurs jetables (routes et invites par rôle) implémentent. Rôle par défaut plus remplacement par délégation, un réglage global d’effort de raisonnement dans la puce du composeur, et une page de paramètres pour la gestion des rôles.

Ajoute un rail de navigation de messages façon Codex pour retrouver rapidement les prompts antérieurs dans les longues conversations de l'interface Web DeepSeek Harness.

Amélioration de la zone de saisie Web : rappelle les invites envoyées entre les sessions avec Flèche haut/Flèche bas, les recherche avec Ctrl+R, restaure les brouillons riches, et ouvre une conversation ancrée /btw ou /side.