Plugins

MarkPilot — an IDE-style Markdown × AI workspace inside DSH. Files, editor and chat sit side by side with draggable panes; send a selection's Markdown source and its file path into the chat with one click or Ctrl/Cmd+Shift+Enter, or reference the open note with @mp. Resume the last note per project, start a blank draft that saves into its own folder, and keep your place as conversations change. Typora-style live rendering with click-to-source formulas, cell-level tables, offline Mermaid and KaTeX, ten themes and transparency; a 150k-character document is parsed in a worker so typing stays smooth. Saves are version-guarded and atomic — conflicts raise a banner instead of overwriting; external disk edits are adopted within 1–2 s, drafts are recoverable, and file:// links or absolute .md path chips open in the workspace. 2.0 adds durable document state, missing/renamed/read-only lifecycle banners, a recovery center and Save As. Fully offline assets, MIT, 544 automated tests.

Trellis-style workflow for DeepSeek Harness: per-turn phase breadcrumbs via agent/pre-step, bundled skill provider, and DSH-native task/phase state with git-cleanliness guardrails.

Private Tailscale access for DeepSeek Harness Web that allowlists users from the trusted Tailscale-User-Login header that Serve injects, with a loopback-only gateway and guarded Serve setup.

Typora-style Markdown editor for the DSH right sidebar: live math and Mermaid rendering, click right of an image to keep writing on the next line, Ctrl/Cmd+S with version-guarded saves that also work outside the session workspace, and selections inserted into chat with their absolute file path.

DeepSeek Harness adapter for Koma Miko Agent Specs.

Three-tier now/next/later input planning dock for the DeepSeek Harness web GUI: a red/yellow/green priority strip replaces the busy-Enter queue, plain Enter queues to later, with in-place multi-line editing, drag reorder, and session-isolated freeze/resume; the freeze button bridges a separate plugin, [dsh-session-guard](https://github.com/drscrewdriver/dsh-session-guard) (installable from dsh-market), via stopNextTurn/resume RPC + composer lock for a real per-session lock, pairing with its global peak-hour auto-pause to stop sessions during DeepSeek's high-cost windows and resume off-peak.

Rewrites the blocked at-sign and four channel fingerprints in system messages at the fetch layer, so WorkBuddy's China gateway stops answering DSH requests with HTTP 400 code 11128; dry-run mode only observes and never modifies the request.

Per-conversation persona / master prompt plugin: create, edit, switch and delete persona templates from the composer toolbar, with highest-priority system-prompt injection, fixed interaction guardrails, subagent inheritance, new-conversation default, and local JSON persistence.

Union IM bridge for DSH — an independent implementation uniting the capability sets of community peer plugins (xmanrui/dsh-im, MichengAI/dsh-im-connect). Drive your agent session from 15 channel adapters across 12 platforms (including email; WeCom/DingTalk/QQ each contribute two: bot + self-built app or notify tier) — WeChat (official iLink QR bind), Feishu/Lark (long-connection + streaming cards; the voice tier requires system ffmpeg), Telegram, Discord, WeCom intelligent bot & self-built app (signed callback), DingTalk (stream + AI Card and custom-robot notify), QQ official bot (plus notify tier), Slack (Socket Mode), WhatsApp (Baileys QR pairing; the dependency ships as an optionalDependency of the plugin package), Matrix, iMessage (macOS only), Email (IMAP/SMTP thread routing). The cross-version narrow waist auto-adapts settings gen1/gen2/gen3 across hosts 0.1.2-rc.1→0.2.1-rc.2 (12-tag enum; rc.2 verified by a real desktop-profile install with double read-back) using capability probing only, never version branches. In chat: a 25-command panel, tool-approval and question loops answered in the originating chat (deny-by-default, initiator-only, 5-min expiry), image/file input gated on host model metadata, deliverable file return, a delivery log with bounded retry (uncertain is never re-sent), proactive delivery and fragment composition. It also splits the native sidebar into self-owned Tasks / Channels tabs (standing down entirely when another plugin already owns the slot), registers an `im-concise` agent preset plus reply sanitisation that keeps GenUI fences and raw HTML out of text-only chats, renders `svg` fences to PNG images, guards model choice with an allowlist, and mirrors each turn's final answer to notify channels via `/relay` (addressed by account ID or alias, never guessed on ambiguity). Secrets are one-way into the vault and never echoed back. npm: `dsh-im-union`.

Message-level rollback, single-message deletion, and replay-based restore for DSH sessions; operations are append-only surface replacements, with confirmation prompts and a running-session guard. Requires Node.js 23.5+.

Git worktree panel for DSH Web: replaces the workspace sidebar with project → main/linked worktree → session groups, creates and removes worktrees, switches the main branch, and migrates configurable project-local or global storage with dirty-tree and active-session safeguards.

Workflow and automation (`workflow`): task dispatch, optional Agent Teams, and tiered verification; usage and billing (`usage`): session token tracking and automatic context folding (no bill calculation); sessions and messages (`session`): persistent fold state, protected recent messages, and watermark-triggered handoff; models and account access (`model`): six dispatch pools and optional intent-based routing (no account integration); skills (`skill`): read-only MySQL/Redis checks, commit-message generation, and requirements/design docs; development and runtime (`dev`): Host/Client settings UI and tool-call safeguards. Together, these features are designed to balance output quality with token efficiency and model-use costs.

AX-first macOS computer use for DeepSeek Harness: accessibility snapshots with stable refs, background input, Unicode typing, menus and apps, set-of-mark screenshots, on-device OCR and verified actions — 11 tools bridged to the macos-cu CLI.

Sanitizes leaked DeepSeek DSML closing tags from model text streams.

Hardening guard for mcp__omni__parse in DeepSeek Harness: a tools/pre-execute listener that denies private/reserved host URLs (SSRF), enforces an allow-list or ask (consent), and is fail-closed when allowedRoots is empty.

Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.

Runtime requirement drift guard that keeps long-running DSH agents aligned with the user's approved goal, constraints, and decisions.

Resident Rust sidecar for Windows that folds shell-heavy tool calls into one warm worker: 11 tools (10 rust_* tools plus a native_help entry point; 5 resident, 6 activated on demand) for command execution, sha256-guarded file reads and writes, code indexing and search, session-log projection and resource sampling, served by a lane pool with soft RSS and CPU limits over 8 HTTP routes.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

Keeps one reasoning-only turn from making an entire session unusable. When a turn produces no visible text and no tool call, the assistant message is persisted empty, the gateway then rejects every later request in that session with 'content or tool_calls must be set', and the session is dead with no way back through chat. This plugin registers a single llm/stream waterfall listener and, only when the turn carried nothing visible, injects a small text block immediately before the terminal finish, so the persisted message is never empty. Ships the fixture DSH's own mock cannot express (a strictly reasoning-only SSE server, since llm-mock-server forbids an empty successText and always appends text after reasoning), plus an end-to-end reproduction that replays a real persisted session through DSH's own serializeMessages. Preventive, not a repair. Zero dependencies, one file, no process or filesystem access.

Per-step model router: named presets with ordered image/keyword-group rules route each agent step across every mounted provider and model, adding collaboration flows for image transcription, an image guard, a multi-plan quota panel, and per-step decision observability.

Agent-driven kanban board: one board per workspace, per-task agent sessions, and a guarded human/agent workflow (Backlog → To Do → In Progress → Review → Done).

A guarded local fetch provider for the ctx.web seam — the backend dsh does not ship for its own web_fetch tool. Every redirect hop is re-resolved and checked against the non-routable ranges, with a streamed size cap and a content-type allowlist.

Multi-device DSH network: sidebar topology, peer health, delegation, file transfer and node management over TLS, LAN and public tunnels. DSH spawns its mesh server (127.0.0.1:8124) detached at startup and restarts it if it exits, and the server always answers LAN discovery on UDP 0.0.0.0:8129. Once a peer is paired, the default ACL lets it read, search and write files under ~/Code, read session history and logs, and delegate tasks to your DSH sessions; shell_run, channel messages, remote desktop and repair stay off until you allow them. If SakuraFrp is installed it reads that launcher's account token (or SAKURA_TOKEN) to query api.natfrp.com tunnels. Its /api/dsh-mesh routes are guarded only by a loopback peer-address check.