Plugins

Monitor workspace sessions, subagents, todo progress and token usage in a floating panel.

Lazy Menu for DSH — hide the duplicate DeepSeek account / official API entries in the model picker, in Settings → Models and in the subagent model list, plus sidebar and account-menu items (14 toggles); auto-fill reasoning levels (low / medium / high / max), context window and image input for new models; on DSH Desktop, add Reload / Restart to the application menu with a one-click patch to the app shell main.js (backup and one-click restore included; needs an app restart, and a DSH update reverts the patch).

Grades free physical and commit memory and refuses heavy tools (shell, workflow, subagent) before the machine thrashes. A reserve you set on the panel is held back from heavy tools so light calls still have room. Also shows in the composer how much of the machine dsh itself is using, including whole-machine CPU.

Sends one system notification when a DSH turn ends: per-outcome switches for completed, error and interrupted, a minimum-duration threshold, silent subagents and unfocused-window-only delivery. Works on Windows, macOS and Linux, delivered through a connected page or a native fallback (PowerShell toast, osascript, notify-send; the Linux native fallback needs libnotify). Clicking the notification brings DSH back to the front on the page/Electron channel; PowerShell and notify-send notifications are not clickable.

Sends Windows system notifications when DSH session turns end, with session titles, elapsed time when observed, optional foreground suppression and subagent filtering. Click a notification to focus the DSH window. DSH must remain running to deliver notifications.

Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Liveness is observable, not guessed: status returns a relay block (elapsed and lease budget, receipt presence, heartbeat and activity age, a suggested action); abandoning a plausibly-still-working attempt is refused with the judgment data unless --force; a late sealed receipt is revived by adopt after full re-verification instead of rebuilding the ticket; dispatched subagents refresh a progress heartbeat outside the worktree. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.

Adds an ARIS agent preset that loads the 84 ARIS research-workflow skills and runs their reviewer as an in-harness subagent from a different model family than the session model. Other presets are unchanged. A fork of wanshuiyin/Auto-claude-code-research-in-sleep's dsh-aris branch: install it instead of the upstream dsh-aris plugin, not alongside it - both register the mcp__codex__codex reviewer tools and the same ARIS skills.

Rolling-window batch scheduler for DeepSeek Harness subagents: one subagent_batch call carries a queue of independent subtasks plus a user-owned concurrency window, a settled child's slot is refilled immediately, and the call returns every child's final answer, stop reason and child id as one acceptance report. async mode keeps the pool running in the background for subagent_batch_status, and the window comes from config, DSH_SUBAGENT_BATCH_CONCURRENCY or a hardware recommendation.

Windows DSH session manager: recoverable recycle bin, subagent-tree cleanup, workspace file discovery and Explorer highlighting, plus categorized file-path export.

Replaces the built-in compaction provider: at a configurable fraction of the context threshold (85% by default) a detached task summarizes everything up to the previous turn, and the next step boundary commits that held summary as a checkpoint with zero model calls, so the swap itself takes milliseconds. /bcompact \[message] starts the same generation on demand and then sends the message. A settings page sets the trigger ratio, the summarization model, and how many consecutive failures stop background generation until a half-open probe gets through. Subagent sessions, a changed prefix or an expired summary fall back to the built-in synchronous path.

Named model routes for subagent delegations, configured from a settings page: each alias binds a subagent provider, model and optional reasoning effort, token cap, agent preset, tags, plus a "when to use" line the model reads to pick it, so a delegation names only the alias. Adds five tools (delegate, list routes, edit config, wait, release), shows the route a child actually ran on in its session header, lets each UI element be switched off, and keeps all configuration in one local JSON file instead of YAML.

Fills in a cheaper sibling route for subagent calls that name no provider, model or effort (for example Opus to Sonnet 5.5 at medium, Qwen max to Qwen flash); explicit choices and subagent_fork are left alone. Requires the subagent-model-selection policy to be enabled with the target route in its allowedModels - without it the plugin does nothing.

Pre-implementation design review gate: an Elephant agent drafts the design, zero-context Goldfish subagents attack it from fixed reviewer roles, and you approve before implementation.

Sets a per-root-session inference limit of 1–10; at 1, queues native subagent dispatches and runs child branches serially while the parent waits.

Run your DSH agents like a company: departments, order dispatch, attempt credentials, an audit ledger and cost accounting on top of ctx.agents/subagents — plus a work board, an org chart and DAG task planning, no native team layer required.

在 DSH 右侧栏查看外部子代理任务（Claude Code / Codex / ACP）收到的委派提示词、运行上下文与返回结果。Inspect the delegation context and returned outcome of external subagent tasks in the DSH Web right sidebar.

Role-based model manager for DeepSeek Harness: assign models to planning, execution, vision and main roles, route subagent work by role, escalate sessions that invoke a planning skill (grilling / grill-me) to the planning role, report which model every su

DeepSeek Harness 插件：对话区左侧可收起的子 Agent 面板，只整合当前会话的 subagent 谱系（根会话/自己/子 agent）。

Standalone DSH plugin: Codex/Claude continuable CLI subagents, wait_subagent, child exit guard and model tiers. Pure ESM, no build step.

Two DSH delegation presets — a fixed 8-seat crew, or up to 3 day-rate temps by convention — with call-time guards that refuse the other shape's delegation tools. The 8-seat preset additionally needs @deepseek-ai/dsh-experimental-agent-team-profile in the profile's dsh.profile.bundles; without it that preset has no team tools and degrades to solo work.

Cursor-style mode switching for the dsh web UI: plan mode with a delegation gate, multitask mode with a tool-call quota, and the create_plan / request_more_edits / list_running_agent tools. Adds a plan card with Build buttons and compacts the subagent dropdown to running rows.

Windows-only: per-session auto-shutdown switch in the session header — once every armed session has no turn, job or subagent still running (by default every other live session must be idle too), a two-minute countdown starts and the machine powers off; clicking the countdown cancels it, and sessions without the switch never start one.

Manage subagents and Agent Teams teammates in DeepSeek Harness: stop running instances, then really remove them by retiring their catalog and roster records with seq-preserving log tombstones and moving their session directories to a recoverable trash; model tools, a conversation-header panel and an offline CLI.

Per-session switches for which tools a DSH conversation may call, plus a guest mode that keeps file tools inside the workspace and turns off shell and subagents.