Plugins

Manage Claude Code, Codex and Grok CLIs inside dsh and dispatch tasks to them as headless subagents, with dsh models, skills and tools bridged into each task, resumable CLI subsessions, and a hierarchical task board in the right sidebar (the board tab requires the separate DSH-better-sidebar plugin; without it the tab is not registered).

Architecture map workbench: register local repos, let a restricted agent (run as a hidden subagent session) read the code with the archify skill, keep branch-level structure and domain diagrams with concepts, temporary/permanent custom diagrams, read-only Q&A, and pick the analysis model from the models DSH already has configured.

Plays a completion chime — the same sound as OpenAI Codex — on turn end or when the agent needs you (approval, question, plan review). Subagent turns are skipped; mute and volume are adjustable.

Show workflow stages and subagents on a timeline, configure model and concurrency for each stage, and reopen subagent conversations from the panel. Run names and stage settings persist under ~/.dsh.

Agent lineage tree panel for DeepSeek Harness: renders the Lead-to-member-to-grandchild agent hierarchy as a live org-chart tree, with team focus, real-time status dots, and a model routing center (hot-reload default model config and actual per-session routes). The model routing center needs the optional dsh-plugin-subagent-director plugin; the rest of the panel works without it.

Batch-manage DSH sessions: sidebar multi-select, a dashboard tree of main sessions and subagents with token/cache/context stats, bulk archive and cascade delete, and recall of ungrouped sessions into re-added workspaces.

Session operations for DeepSeek Harness: really delete persisted sessions (ungrouped, temp, archive and subagent filters; guards on running, live and workspace sessions) and move sessions between workspaces (log relocation, header.cwd rewrite, workspace registry follow). Ships the shared session-store library.

Routes subagent delegations once at spawn time by keyword rules over the delegation label and prompt: the first matching rule sets the child's provider/model/reasoningEffort, explicit caller routes are kept unless a rule opts in, and unmatched delegations pass through unchanged.

Delegates mechanical text work (translate, summarize, extract, classify, rewrite) to an Ollama-native or OpenAI-compatible endpoint by file path, so the source text never enters the main model's context. Registers local_transform, local_batch and local_health; per-workspace local-AI levels (none/light/default/high/max) add a local_worker subagent and a plan-only mode; an opt-in SlaveAgentTeams switch discovers mounted model routes, runs parallel child agents with node-level failover, and registers the endpoint chain as llm-pi-ai routes. Configured from the Web GUI; requires a reachable endpoint.

通用单人开发流程框架：文件状态机 + Gate 必停 + 角色分离。自带 9 个角色 subagent、流程骨架文档、门禁脚本与 process_init / process_uninstall 工具。

Counts the assistant rounds that call tools without writing anything to the user, then inserts a short progress reminder as a visible user message at the next model-request boundary, so a long silent tool loop reports what it has done before continuing. A Settings page adjusts the silence threshold (default 10), the reminder wording, the language (en / zh-CN / zh-TW), whether the reminder repeats every further threshold of silent rounds, whether subagent sessions are counted, and whether Agent Teams nudges the lead only or every member.

Adds an /if slash command to DSH: the first line is a condition and the remaining lines are an instruction. A fork subagent that inherits the session tools, system prompt and message history judges the condition and answers YES or NO, and only on YES is the instruction sent to the main agent as an ordinary user message, while a NO sends nothing. The condition, judge prompt and verdict never enter the main transcript. While the agent is busy the command queues with ordinary messages, editable, removable and steerable from the queue panel, and a setting switches to the 0.2.x background mode. The judge runs read-only, and falls back to a one-shot model call over a plain transcript when the host has no context-inheriting fork provider. Supports DSH 0.2.1-rc.5 and later (verified on 0.2.1-rc.5 and 0.2.2-rc.1) and Node.js 20.3 or later.

Route table assigning provider, model, and reasoning effort to subagents by workspace directory prefix; supports global default policy and in-composer session popover.

Adds two enhancements to DSH ask_user_question choice cards: right-clicking an option expands a per-option note that is merged into the submitted custom answer, and a footer field asks a side question answered by a fork subagent from the session context, read-only, with no write-back. Keeps left-click, skip, paging and the countdown working as before, and only claims generic choice cards, not plan review or approval cards. Supports DSH 0.2.x from 0.2.0-rc.1 (verified on 0.2.2-rc.1) and Node.js 20+. Derived from buaaflyaway/dsh-question-note (MIT) and inspired by MichengAI/dsh-btw (Apache-2.0); do not install it together with dsh-question-note — both take over the same ask_user_question card.

Policy-layer guard that checks tool calls before they run: a read whitelist, a sensitive-path deny list (credentials, browser profiles, chat history, other users' home directories), dangerous-command blocking, subagent isolation, and a static scan that quarantines executables. Every denial is appended to an audit log. It is a text-and-path filter, not a sandbox or antivirus: dynamically built paths, encoded payloads and packed binaries can get past it, and it does not replace the OS antivirus.

Adds a confirmed Delete session action to the sidebar menu of archived Sessions; the Host permanently removes their local JSONL logs (including hidden subagent descendants), workspace accounting and archive/pin entries, then refreshes open Web clients.

Deep-sea tidal-blue theme for the DeepSeek Harness Web client with a single accent color and matte (non-glass) surfaces in light and dark modes. Same-token UI additions: a single-line dock HUD reading real session projections (context usage vs. window, TPS, cache-hit rate, elapsed time), per-turn subagent delegation cards showing token usage and an optional cost estimate from OpenRouter public prices, sidebar pagination with pinned sections and type-to-filter, and model / reasoning-effort / permission controls under the composer. Each addition can be toggled in the plugin settings.

DSH Pixel Team：DeepSeek Harness 的像素洞府多智能体团队协作与交付流水线（AgentTeams 衍生，MIT）。

官方 subagent 的默认策略包：装上一次配好「什么时候自己干、什么时候派出去、派给谁」。

Delegate subtasks to Herdr-managed coding agents from DeepSeek Harness: pick the model, keep the pane, harvest the exact result, review in DSH.

Hogwarts-loop as a DeepSeek Harness plugin: per-role subagent dispatch on configurable models, with a client settings page.

Restart the Harness itself and come back: a dedicated restart_dsh tool hands the session over to the next process, which resumes it, replays the pending instruction and wakes the subagents again.

Declarative provider/model fallback chains for the model picker: an ordered root chain plus named pools, failure-code triggered switching, per-model cooldowns, time-slot presets, and subagent role routing. A fork of omdsh-dev/dsh-llm-fallbacks 0.6.5; do not install it alongside that plugin (both use the "llm-fallbacks" profile row id).

Adds a management page for the official DeepSeek Harness ACP subagent provider, with one-click presets, a read-only connectivity check, live switches for all three entry points, and online preset updates.