Plugins

Private loopback DSH Web gateway for Tailscale Serve, Cloudflare Access, and Headscale TCP Serve, with exact principal allowlists and guided fail-closed setup.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

SSH remote workspace — run bash, file tools, glob and grep on a remote machine over plain sshd (exec + SFTP), zero remote install, purely additive.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill. Its settings section now carries its own navigation mark (a brain half wired to a node cluster, since the shell offers no icon slot to plugins) and a feedback entry that opens this repository. Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): injected messages declare the producer-owned source kind plugin:memory.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Deterministic context compression for dsh — zero LLM calls, rule-based pruning that preserves paths, commands, error traces, and open todos verbatim. Compresses ~80k tokens to a few hundred.

Desktop pet drawn from the official whale outline, for both the desktop app and the web UI: SVG animations and facial expressions follow agent state (thinking, working, done, error, waiting for confirmation), and it can follow other running sessions with a count badge; poke it, drag it, shake it dizzy, squash it against a screen edge, or rub the cursor over its head for a headpat; 7 palettes, 4 sizes, synthesized sounds, light/dark theme sync, and a playable web preview.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Replay sessions on a playable timeline with per-step token usage, audit sensitive operations, estimate cost, view fork lineage, compare sessions, and export standalone HTML replays.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

DSH（DeepSeek Harness）插件：把 ego-lite 浏览器（给 AI Agent 用的 Chromium）接入 HARNESS——13 个结构化 ego_* 工具（文本语义快照、语义定位点击、表单填充、截图、CDP 控制、任务空间隔离），内置 ego 运行时，Linux + Chrome 开箱即用，无需克隆官方仓库或手动构建。

LAN access for the Web GUI: 0.0.0.0 bind plus a crypto.randomUUID polyfill for non-secure (LAN HTTP) contexts.

Skill pool manager in the Settings sidebar: enable/disable, folder batch import with rename-conflict prompts, state-driven one-click DSH-spec check & auto-fix, system/project scope labels.

Connect multiple Overleaf projects to DSH through OverleafMCP for browsing, analysis, and Git-based file updates.

Select part of a conversation and ask about it in a right-side side chat; bring AI replies back to the main chat directly or as a summary.

Connects DSH to a local anet node through a stdio MCP client, with three skills and 14 tools to discover agents on the AgentNetwork, send, track and answer end-to-end encrypted A2A tasks, pay or decline priced skills within the operator's limits, read the local evidence chain and report the node state. Linux/macOS only; requires an anet 0.3.0+ node running locally.

Aggregated multi-upstream web search for DeepSeek Harness: replaces native web_search with model-native grounding and agent search APIs, source attribution, and rich citation cards.

用中文对话操控 WPS 表格 / 文字 / 演示的 DeepSeek Harness 插件（仅 Windows x64 / COM）。自带 MCP server、常驻 COM 宿主与技能文档，免装 WPS 加载项、免配环境变量。

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

Local literature knowledge-base RAG for DSH: hybrid BM25 + vector retrieval, cross-encoder reranking, cited answers with section- and page-level provenance, metadata-only refresh and background ingest with progress polling, over a SQLite index.

Automatic session retrospective: after a conversation wraps up, distills useful experience into reusable skills stored in the skill library for the model to call, with signal-accelerated triggers, manual runs, an approval mode, and skill-library governance (archive/restore, never deletes directly).