Plugins

Archive, restore, permanently delete, and move DeepSeek Harness sessions across workspaces from one unified settings panel.

Task-event notification center: 6 event kinds (ask / approval / completion / subagent completion / error / turn end), dual channels (browser Notification + host system toast) plus Bark/Webhook push channels (ntfy, Gotify, self-hosted gateways); quiet hours with urgent exceptions, approval-timeout re-reminders, completion-storm aggregation, and notification text redaction.

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.

DeepSeek Harness plugin: 15 obra/superpowers engineering skills, bilingual descriptions, per-skill toggles.

Live subagent run monitor for the Web UI: a sidebar footer trigger plus a fixed top-right card panel showing each subagent of the current session in real time (running/elapsed, terminal outcomes, tree indent), with one-click jump into the child conversation and a return button, refresh-surviving and mobile-hidden by default.

Automatic conversation distillation: background subagent reflection + skill create/update.

Terminal-native TUI frontend for DeepSeek Harness that presents sessions, models, plugins, jobs, subagents, todos, and provider configuration through Harness capabilities while preserving real terminal scrollback.

Role-based LLM retry & fallback strategies.

Live flowgraph visualization for DeepSeek Harness sessions, including tool calls, parallel groups, subagent branches, and drill-down details.

Provides a better model experience, including but not limited to: filling model parameters in multiple ways, improving model compatibility, remembering reasoning efforts, subagents following the parent's model and reasoning effort in real time, and AI self-adjusting reasoning effort.

Per-subagent LLM provider/model selection with role templates.

Continual self-evolution: versioned, auditable, rollback-safe harness state (prompts, memory, skills, subagent specs) refined from session trajectories, with review gates and hot-reloaded skills.

Ports the pstack agent workflow system to dsh: 58 pstack skills, 23 playbooks, four native tools and five agent presets, with skill routing, role-based model configuration and role-routed subagents.

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

Role-based LLM retry & fallback strategies.

Role-based LLM retry/fallback strategy.

Role-based multi-agent team for DeepSeek Harness — your digital workforce. One goal assembles a team of product, architect, frontend, backend, reviewer and QA roles that deliver through a nine-phase gated pipeline, plus a persistent team you can keep directing across sessions. Zero runtime dependencies, no build step.

Multi-platform API balance and usage dashboard for the DSH web GUI: balances for DeepSeek, Zhipu GLM, Kimi, StepFun, SiliconFlow, MiniMax, OpenRouter, Novita and xAI under the composer, estimated per-session and per-subagent cost with DeepSeek peak/off-peak pricing, automatic discovery of relays configured in DSH settings, and an optional draggable whale widget.

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.

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.

Shows the current session's equivalent cost in the stats bar below the input, priced from a bundled table of published token prices. Uncached input, cache reads and writes, and output including reasoning are priced separately; model changes add up as separate per-currency segments; subagent costs are included. Clicking the cost opens a per-session and per-subagent breakdown.

Adds /review, /review-status, and /review-cancel to spawn an independent native subagent that inspects a chosen Git scope (base branch, uncommitted changes, a commit, or custom instructions) and returns a findings report in the current conversation, with English or Chinese output from the host locale.

Full-featured TUI for DeepSeek Harness: streaming conversation, powerline status bar, real-time think/tool/todo panels, subagent dual-view, theme hot-switch — all as pure cordis plugins with zero upstream patches.