Plugins

Établi complet en barre latérale avec rendu et édition de fichiers, terminal, Git et sous-agents ; les plugins tiers peuvent enregistrer de nouveaux onglets.

Plugin d'agent de workflow pour l'ingénierie de harness/boucle, piloté par skills.

Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness — continuable children, durable session recovery, per-role product permissions, and delegation with a permission ceiling.

Stratégies de nouvelle tentative et de repli LLM basées sur les rôles.

Migrate and import a whole Claude Code or Codex setup into DSH. Skills, slash commands, MCP servers, hooks, subagents and permission rules, with a dry-run moving estimate, a migration diff report and a post-move doctor; installs as a plugin exposing a movein_from_claude_code tool so the agent can do the move for you.

Installs a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.

Expert-mode agent preset for DeepSeek Harness (v0.3.0, bilingual EN/ZH): a chief coordinator plus 11 domain-expert subagents with automatic task delegation. Features: Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), expert persistence, cross-expert communication protocol, cross review, and experience pool. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance.

Affiche les sous-agents d'une session et les exécutions de workflow durables sous forme de DAG en direct, avec statut, navigation et historique résistant aux redémarrages.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

Load Claude Code assets into DSH at runtime — skills, slash commands, rules, permission rules (deny/ask/allow), subagents and hooks from .claude/ plus Claude Code plugins (plugin.json / marketplace / skills / agents / MCP), via a memory-IR parse layer that keeps .claude as the source of truth with no writes back. Six installable packages: loader, skills, permissions, agents, hooks, mcp.

Chaînes de repli automatiques entre fournisseurs/modèles pour les agents DeepSeek Harness lorsque les requêtes LLM échouent de façon répétée (nouvelles tentatives épuisées, authentification, quota, limite de débit)

Étend dsh-subagent-tools avec un cwd par appel pour les sous-agents, livré avec les deux correctifs de fournisseur in-process qu'il nécessite.

File d'attente de tâches inter-sessions avec notes de passation : les sessions et sous-agents publient, réclament, terminent et annulent des tâches sur une file partagée sauvegardée sur fichier, et laissent un résumé de passation pour la personne suivante.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

Exposes bounded Prometheus metrics for DSH sessions, agents, LLM calls, tools, approvals, subagents, and jobs, with a Grafana dashboard and a loopback-only endpoint by default.

Minimal prompt x full PTC tools: one-line persona, Code Mode SDK, subagents, workflows, web search, and Windows Git Bash.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

Engineering workflow agent preset for dsh: five gated phases (requirements clarification, plan approval, TDD, parallel subagents, verified finishing) with six workflow skills adapted from obra/superpowers.

Sub-agent matrix swarm that routes heterogeneous tasks to the most suitable model from an OpenRouter-like gateway plus cfgpu.com/llm/square, dispatches each via in-process subagents or direct LLM calls, and tracks per-model token consumption with a feedback-driven ranking.

Office workspace & session dashboard: a floating 6-column sprite panel visualizing workspaces, sessions, token usage and subagents.

DeepSeek Harness bundle: oh-my-opencode-slim style Orchestrator agent preset with model-pinned specialist subagents (explorer/oracle/librarian/designer/fixer/council).

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.