Plugins

Lazy-loading router for MCP servers: auto-discovers compatible MCPs and keeps only a shared router in the tool catalog, revealing a server's schemas when a turn needs them and hiding them again at turn end, so many installed MCPs stop costing context on every request. Falls open to normal visibility on any uncertainty, and the original MCP keeps ownership of execution, permissions and process lifecycle. Also supports explicit lazy connections with warm reuse, bounded reconnection, stdio and Streamable HTTP.

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.

Auto-injects user-chosen skills into DSH sessions, either every prompt or once at session start, with a settings page and a composer indicator.

SSH terminal panel and AI connection manager for DeepSeek Harness: model-driven SSH connections (connect/exec/list/status/disconnect), auto-saved connection records, keep-alive + auto-reconnect, execution mutex, credential-safe auth, and an XShell-style m

Full local-first issue board embedded in the DSH web GUI: Kanban / list / Gantt / workflow / dashboard views, AI chat per task, attachments and labels, auto-claim of todo tasks driven by dsh-routines — data lives in local SQLite (dsh plugin add @ttmouse/dsh-taskboard).

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Floating card showing your real position P&L (今日盈亏), Shanghai Composite Index, and intraday chart, auto-synced from the Tonghuashun investment-ledger — no manual watchlist setup.

LLM auto-approval for sandbox escalation requests, with presets and a fail-closed fallback.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

WeChat automation for DSH: push task progress to WeChat, listen for messages with keyword auto-reply, and a WeChat ↔ DSH two-way bridge controllable from the settings page, built on wxauto4.

Folio (兰亭) @nyantused/folio-dsh-tools: 15 schema-validated tools (memory + quality gates) plus an L0 guard of the consulting document-generation engine; pair with @nyantused/folio-dsh-events for the full session protocol.

Folio (兰亭) @nyantused/folio-dsh-events: session-protocol events — auto session-start reminder + auto-save on session close; pair with @nyantused/folio-dsh-tools.

Voice input for the Web UI: a mic button that drives local VocoType offline speech recognition and auto-inserts recognized text into the composer (auto-deploy, dedupe, continuous dictation).

Combine text, vision, and image-generation APIs into one Mix model with automatic routing: text-only requests go to the chat model, user images and agent screenshots go to the vision model, follow-ups keep using the same session image, and agents can generate or edit images with session-scoped call history.

Search-first capability workflow for DSH agents (v1.0.0): reuse local tools or review exact-source plugins before installation, adapt or create capabilities in managed source work, and use receipts that distinguish installed, loaded, activated, and verified states; version tools cover rollback, adoption, and upstream updates.

Enhanced auto-compaction defaults for DeepSeek Harness agent presets: apply tuned threshold/retention budgets and per-model policies with one command, idempotent with backups and rollback.

Human-readable Markdown memory for DeepSeek Harness: user-level (~/.deepseek-harness/MEMORY.md) + workspace-level memory injected every turn, auto daily-log writing with distillation, bridges existing WorkBuddy/CodeBuddy memory dirs, memory_note / memory_note_user / memory_read tools with built-in dedup, and a bilingual settings page. Plain-text storage, no database.

Auto-repairs the messages array after a tool-dispatch crash (orphaned tool_calls / tool messages), preventing 400 INVALID_REQUEST session lock-ups.

Weak-network adaptor: transparent long-backoff model-stream retries (10-min cap), local response replay cache, heartbeat auto-reconnect, and degraded-mode token economy, with a bilingual (zh/en) settings page.

A settings-panel skin manager that auto-discovers installed Web UI skins, switches between them in one click, and maintains the profile patch automatically.

Persistent local token-usage accounting for DSH Web with automatic history discovery and compact provider/model details.

Auto-saves large pasted text as an attachment file in the DeepSeek Harness web input box; with dsh-better-sidebar installed, the paste pill opens the file in the sidebar editor and saves it back.

Zero-touch runtime telemetry for DSH: every session auto-writes task, model tier, tools, failures, duration, status into a human-readable journal with a stats section (pure observer — no tools, no LLM calls, no injection).

模型回合结束后用 LLM 生成 3 条批判性跟进建议，点击即发送 | After a model turn, an LLM generates 3 critical follow-up suggestions shown as click-to-send chips