Plugins

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).

DSH book-to-skill plugin: a 5-stage long task (fetch → parse → understand → generate → install) with 3 human gates, host tools for the agent and a browser timeline panel

DingTalk group-robot notifications (notify/text/health; webhook + HMAC signing, zero runtime dependencies).

Host-level proactive wake-ups for DeepSeek Harness: let the model schedule its own alarms (once / interval / cron with random jitter), wake cold sessions on time, gate model-initiated follow-ups with quiet hours and a daily budget, and reclaim silent wake

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

Windows minimal agent preset for DeepSeek Harness: fixed one-line persona, three tools, no runtime context.

A faster, more efficient, and more accurate coding Agent preset. On 100 hard SWE-bench Pro tasks selected using multidimensional difficulty criteria, average elapsed time decreased by 36%, average input tokens per task decreased by 17%, and accuracy increased by 5 percentage points.

Business knowledge-network context for DeepSeek Harness: bind a session to an OpenBKN knowledge network, query its objects and metrics through managed MCP tools, and open trace-backed provenance (execution facts and a business graph) for each answer. Ships with the OpenBKN Runtime; the provenance views need an OpenBKN enterprise license.

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.

Registers six spec-driven + test-driven workflow skills for DeepSeek Harness: OpenSpec spec authoring fused with Superpowers TDD discipline into a Phase 0-4 pipeline with review gates. Zero runtime dependencies.

SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks, with 13 model tools and a bilingual zh/en UI.

Local model plugin for DeepSeek Harness: manage GGUF models in settings, auto-launch llama.cpp on first message, and auto-unload after 5 minutes of idle time to free VRAM.

Compresses DSH time-context from ~280 chars to 46 chars by injecting a compact date line into the runtime-context snapshot; zero runtime dependencies.

Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.

Per-project runtime environments for DeepSeek Harness: auto-adopt or create a project-local Python venv (.venv_local/python) and wire in the toolchains and env vars for the runtimes each project uses (python venv / node / go) — python & pip always resolve to the project, never silently to system Python.

Automatically retrieves time-of-use pricing data (with Beijing Time) and notifies users during peak periods to reduce costs.

Self-evolving project-level Agent for DeepSeek Harness: 16 SDD workflow skills (clarification, PRD, issue, coding, locating, acceptance, review) plus project memory and knowledge that compound over time.

Whale girl desktop pet for DeepSeek Harness: browser floating mascot plus Windows desktop pet sharing one data backend, with real-time balance board, task notices, head-pat interaction, 19 pre-synthesized voiced lines with per-line emotion, and presence-aware idle speech.

Financial quantitative workbench and stock ticker: floating ball and drawer panel, real-time A/HK/US/global market quotes, multi-period K-lines and 5-day intraday charts, depth order book, capital flow, sector heat map, and AI investment research.

Per-model capability profiling for DSH: turns local session history into per-model dashboards of session counts, tool usage, error rates, and top error signatures, with time-range filters and multi-model comparison.

Browser-first, LAN-only access to the current DeepSeek Harness Web UI with one-time QR pairing, revocable devices, event-driven diagnostics, and a slot-preserving mobile layout; no companion app, cloud relay, or remote tunnel.

Real-time hot topics panel for the DSH web GUI: AI news and engineering news, each item with a distilled summary and the source link, shown from a sidebar entry with three views, keyword/source filters, read-state marking and hotkeys.

ChatGPT-style question nav rail with up/down arrow buttons — per-question tick marks on the chat edge, hover-triggered drawer listing every user question with real-time search filter, one-click smooth-scroll jump, and active-question highlight synced to scroll position.

Conversation timeline dock bar for DeepSeek Harness: a turn-level timeline above the composer with user-prompt hover tooltips and click-to-jump back to the exact chat position.