Plugins

Requires DSH 0.1.5-rc.1. Mobile UI fixes for the dsh web profile: narrow-screen drawer and settings tabs, a full-width model menu, a stuck-request network chip, and a narrow-header collector that folds the lineage, subagent and background-job chips into one tappable sheet.

Voice call assistant for the DSH desktop app and the Web GUI (the same plugin, only the profile name differs): a draggable floating call ball, browser-side VAD that sends each utterance after a pause, speech recognition through the local SenseVoice model already downloaded by the official voice-input plugin (no second model), FunASR HTTP or streaming, or a cloud-compatible API, MiniMax / MiMo-V2.5-TTS (director mode and voice clone) / OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate sessions with progress, stop, and spoken completion reports.

Xianxia desktop pets linked to live agent sessions: MC pixel-style companions appear when subagents spawn (up to 3 on screen), with storage-bag collection, a right-click artifact menu, a pet gallery picker, and export to the Codex desktop-pet format.

An RTS-style orchestration dashboard where commands replace chats: a resident commander agent decomposes each order into task briefs with acceptance criteria, typed subagent troops (recon/engineer/medic/scribe) execute them across isolated workspaces, and every session is indexed by the order that started it.

Competition math (IMO/Putnam/USAMO/AIME) solved with a pure-reasoning pass, an adversarial verifier in a fresh subagent context, and calibrated confidence output (high / medium / honest "no confident solution"); optional LaTeX-to-PDF rendering.

Explicit model routing for Main, Subagents, web_search, and image generation, plus a catalog-driven Composer and Plan Review picker with Model, Effort, Context, Fast, and Thinking variants.

Adds subagent_route and subagent_fork_route delegation tools where the model itself picks the provider/model route for each child; the deployment only sets the spawn/fork backend, background policy and allowedProviders allowlist, while continuable children and background jobs reuse the official send_message / job_output tools.

Hand a DSH web session to the locally installed Claude Code CLI: a per-session engine selector (DSH | Claude Code), Claude models and reasoning effort in the model seat, Claude permission modes in place of the access-mode selector, and permission requests, AskUserQuestion and ExitPlanMode routed to the native DSH approval, question and plan-review cards. The stream is written as native DSH session events, so the built-in transcript, tool cards and nested subagents render it; Claude slash commands merge into the command palette; the CLI is held by a detached broker, so plugin updates and DSH restarts do not interrupt a running turn.

Codex-style /btw command: answer side questions in a conversation-seeded subagent (fork provider), rendered in the UI without entering the main session history.

Bot Mode for DeepSeek Harness: a roster of named bots with avatars, personas and per-bot chats, each backed by one durable continuable subagent session that keeps memory across turns.

Autonomic heartbeat for each root agent: silent pulses diff the session's todos, Agent Team board and goal against what the last pulse saw, and speak only on a signal — L1 report, L2 ask (ask_user_question), L4 escalate — never starting work. Each message carries a why-now line, an optional one-line physiology signature (time since your last message and how many times it has reached out today) and a compact task snapshot (800-char cap); a dedupe window, quiet hours, a daily budget, refractory/restart cooldowns and persisted vitals keep it quiet, while busy-safe followup injection never stacks. It shares one advisory speech floor with dsh-plugin-memory (~/.dsh/proactive-cooldown.json, 180 s) so the two never talk over each other, stays silent while a child subagent or teammate is still working, and surfaces a "subagents working · N" pill in the conversation header (polling pauses while the tab is hidden). v0.8 adds a diagnostics panel that explains recent quiet pulses and names the current speech-floor holder, plus panel controls for the arbitration window, presence suppression and the physiology line; its settings section carries a stroked heart mark (16×16, stroke 1.3, same spec as dsh-plugin-memory). v0.8.1 makes the plugin compatible with DSH 0.2.2-rc.2: the agent registry is read with agents.roots() when available and falls back to agents.list() on rc.2, and every agent/created listener is exception-guarded — on rc.2 an unguarded throw there rejects agent registration and no session can be created, so rc.2 users must upgrade to 0.8.1 or newer.

Durable Git worktree isolation and delivery for DeepSeek Harness subagents

Interactive canvas for visualizing Agent, Subagent, Workflow, Phase, and tool relationships in DSH Web.

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.

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.

让 DeepSeek Harness 的第三方 API 支持低、中、高等推理强度，并可为每次子 Agent 调用选择模型｜Add Low, Medium, High, and other reasoning levels to third-party APIs, with model selection for each subagent call

A slim tool strip beside the conversation: one-line notes into a sticky note, a follow-up or a reminder (the sticky-note and follow-up modes need the dsh-sticky-wall and dsh-followup plugins installed); selected text quoted, saved or handed to the model; saved prompts into the composer in one click; a recap of this thread or the previous one; a read-only panel for context use, tokens, subagents and open follow-ups; plus custom entries that open a path or run a command.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

Follow list above the sidebar conversation list: a status dot per conversation (unread, waiting for you, running, failed), newest reply first, running ones last, and a follow toggle beside the model selector. Marking a row unread lifts it to the top, opening one expands and scrolls to its row in the Workspace list below, a finished turn always counts as unread until the conversation is opened, and a conversation whose delegated subagents are still working keeps counting as running until the last child reports back.

Two-stage session deletion for DSH on Windows: move a conversation to the recycle bin and restore it to its original sidebar slot; deletion confirmed in two steps to prevent deleting files by mistake, clearing the whole subagent tree, sidebar ledger, projection cache, log lines and exclusive attachments along the way. It also scans the files a conversation actually wrote, adds a file query that pastes the path information into the conversation so an agent can judge which files are safe to delete, highlights them in Explorer, and copies the paths grouped by type. Both this and iamwuzhanglin/dsh-session-recycler install under the package name dsh-session-recycler, so install only one of them.

Registers a read-only tool that lets a parent agent read what each subagent is actually doing, not just whether it is running: the progress notes the child wrote itself, oldest first, paged backwards by seq, plus how many steps passed since the last look, and a quiet count when five or more steps go by with no new note.

Picks each subagent model from the local catalog by task category, unless the caller already named one. Free and quota tiers are ranked together by per-model capability tags; a pricier model is used only when no cheap model is tagged as good at that kind of work. Only providers whose remaining balance is readable, or that are account-backed, enter the candidate pool; the rest stay listed but are not routed. A panel adds per-model manual priority above the automatic order plus allow/revoke controls.

Layered system-prompt profiles — global, per-workspace and per-session entries injected in order — where individual builtin sections and runtime contexts can be disabled or overridden, with a line-level diff of what an override changed; each entry carries a subagent scope that targets the main agent only, subagents only, or both; assembly snapshots record what each turn actually received, subagents included. Managed from a Web panel and a `prompt_manager` tool.

Registers a wrapper provider that gives delegated subagents their own LLM route — one-off spawns through provider.start, Agent Teams members through a hook on startActivation — while the main agent keeps its model. Ships a Settings section for picking that route, a per-expert override file, a capability flag reporting which seams the hook caught, and a readiness record written at mount.