Plugins

A composer switch between running always and running only in off-peak hours, set per session: a task is judged by the session that owns it, so changing one session no longer changes the others, and a session without its own choice follows a default. In off-peak mode every task, including one already running, is held at its next agent step or tool dispatch when a Beijing peak window starts (Monday to Friday 09:00-12:00 and 14:00-18:00, statutory holidays excluded), and one timer releases it at the boundary; weekends and holidays are idle all day. The holiday calendar lists every statutory day off in 2025 and 2026 from the State Council notices, and a year with no data is reported as unknown rather than assumed to be a workday.

Read-only clinic for DSH session logs: 22 named diagnostics (token waste, retry and failure loops, context bloat, cross-session amnesia, idle MCP servers and skills), each reported with a replayable evidence locator such as session.v4.jsonl.zstd#L101-L110, and each finding turned into an executable prescription — a profile-patch YAML snippet or a command with current to suggested values, risk, verification and source — plus a feedback command that retires a prescription you reject, after which the report states it was removed by your feedback. Zero dependencies, default zero egress, session files are never written.

Replaces the session topbar title with a workspace and session breadcrumb, switching workspaces, sessions and subagents from topbar dropdowns; adding a workspace opens a dialog shaped like the native one, which can hand off to the system folder picker.

Annotates every subagent with the model route it actually ran on: a badge line in each parent-catalog row and a readout in a child session's own header.

Quote text selected in a DSH Web conversation, then either attach it to the current composer or dispatch it to a subagent session: the quote sits on a bar above the composer, or opens that subagent in a new pane on the right. When the target has no subagent yet, the quote is held and the composer is seeded with a spawn request, then picked up automatically once the new session appears. Client-only.

Conversation navigation with full-history turns, collapsible process steps, final-result and structured question-and-answer keys, and pointer-following piano interaction.

JavaScript orchestration over DeepSeek Harness tools using Node.js VM or QuickJS WebAssembly backends.

Subagent model control: a Jev classifier labels each turn, and the subagent request itself is rewritten to the provider, model and reasoning effort that the label maps to, at the agent/request hook; a per-session inherit/auto/manual selector, one prompt per role injected ahead of the task, and offline replay of past verdicts.

JEV agent preset bundle with prompt-guided task routing, cross-verification and quantitative checklists.

Blocks AI coding agents from editing files without evidence and from running unapproved high-risk commands, and tells quoted dangerous strings apart from commands actually being executed.

Restarts the DSH desktop app on Windows and wakes the sessions listed for it afterwards. The agent-facing restart tool is off by default and refuses while the host is busy.

Bridge DeepSeek Harness agent sessions into Feishu (Lark) chats over the official SDK long connection, with a streaming reply card, many bots per instance, and mention-gated group replies.

Sends a macOS Notification Center alert when a session finishes or the agent is blocked on an answer, an approval, or an error. The banner carries the last reply and plays your system alert sound, and clicking it returns you to the DSH page.

Round-table meetings for DeepSeek Harness 0.2.0-rc.2 on Windows desktop, reusing existing Agent sessions with discussion, editable task cards, sequential and parallel steps, shared meeting files, and secretary minutes.

Alpha Agent Teams plugin for DSH 0.2.0-rc.2 and newer that lets same-session user Steer end the Lead’s current wait_agent call while teammates continue, with native message delivery and Node PTC continuation.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

Skill browser and switchboard for the DSH web GUI: a sidebar entry lists skills from configurable source directories as cards, clicking a card opens the full SKILL.md, and the per-card switch writes disable-model-invocation and registers or removes that skill in the agent skill catalog, so the model can load exactly the skills that are switched on. It also recognises WorkBuddy expert-team folders and shows avatar, tags, quick prompts and members, registering its lead prompt as a skill when switched on. Source directories are editable in the panel.

Cross-session memory as plain Markdown per workspace: weighted injection, bi-temporal invalidation, TTL review with stale markers, credential redaction, error and session retrospectives, SOP skills, and approval-gated self-improvement proposals.

Optional JEV decision mode with deterministic project reads, bounded semantic selection, native authorization checks and desktop credential settings.

Renders agent-authored HTML/CSS/JS inside the conversation as sandboxed iframes, with POST and SSE back to the model and reusable templates.

Deterministic goal-completion gate for DSH: a contract-first AC grammar with named failable check commands, a gate that re-runs every check itself (zero model trust), verdicts bound to a tree digest so file changes void passing verdicts, and a hard deny on false completion at update_goal via tools/pre-execute with a false-complete counter that blocks after two catches; scope-aware task-level claim handling (strict or goal-only) keeps multi-task Agent Teams loops from deadlocking.

DSH Room — Web and Desktop plugin for encrypted multi-agent collaboration

Host-layer Windows toast notifications for DeepSeek Harness: agent turn done, error or interruption, subagent done, and background job done, plus alerts when the model asks you a question or a tool approval is pending. The notification logic runs in the DSH host process, so toasts still arrive with the tab or the browser closed; a Win32 foreground probe suppresses them while you are looking at DSH. Windows only.

Bundles the official Scrapling agent skill into a DeepSeek Harness profile: anti-bot bypass, stealth browsing, the spiders framework, adaptive parsing and JavaScript rendering, discovered through the host skill catalog.