DeepSeek Harness プラグイン — 55 ページ

One card under Settings → Plugins for the community session importer (dsh-chat-import): what happens to a source transcript's system prompt on import — dropped by default, at most a context message inside the imported session when the importer's switch is on, never dsh's own system prompt or a plugin's section. The importer's own settings page belongs to that plugin (single-owner locale namespace, no slot inside it), so the sentence lives here.

Repo-root manifest for dsh-kb-rag. The installable plugin bundle is published from npm-package/ as dsh-kb-rag; this file exists so the repository itself declares a dsh.bundle (registry tooling reads <repo>/HEAD/package.json) and points at that bundle. Not published: version is intentionally 0.0.0, the real version lives only in npm-package/package.json.

Deny unpaired LAN devices the bare /api when the DeepSeek Harness web server binds all interfaces: removes the auto-derived LAN IP authorities from the connection trust list in place, without any core change, so pairing-fronted remote access is safe by default and a core upgrade never reopens the hole.

Per-model context window, max output and thinking levels for every DeepSeek Harness route (DeepSeek official, OpenRouter, local LM Studio / Ollama …); probes local backends and auto-teaches their levels. Managed from the DSH Launcher "Model parameters" page; OpenRouter :online web-search variants on the Model parameters page.

DSH manuscript GUI: generic workspace tree, prose editor, ghost completion

PII masking middleware for DeepSeek Harness: regex-detect and replace phones, emails, ID cards, bank cards, keys, and (opt-in) IPs with placeholders before they reach the model, keep the restore table host-side (memory plus a controlled storage domain, never the session log) with the /mask restore command and the exported RestoreStore seam, and expose /mask status and the mask_test tool. Name and address recognition needs an external NER recognizer, which this pure-host form does not bundle: mode "regex+ner" and the person/address entities fail loudly at load. The phone and ID-card detectors match mainland-China formats only.

Extra media APIs for DeepSeek Harness: image generation, video generation, text-to-speech and transcription behind one settings panel, with adapters for OpenAI-compatible endpoints, Google Gemini/Veo, Replicate, fal, ElevenLabs, Fish Audio, MiniMax and any custom HTTP endpoint.

Lightweight memory for DeepSeek Harness: stores compaction summaries and extracted facts, recalls them lexically (BM25, CJK-aware) or with local embeddings, injects relevant items as a separate context message, offers memory_recall / memory_note tools, and lets the user view and edit every session's active compaction summary.

Render Mermaid code blocks in DeepSeek Harness with a diagram/code toggle.

Private, zero-trust gateway for DeepSeek Harness Web: loopback-only proxy, exact principal allowlists, and provider-agnostic onboarding

OOMOL Connector integration for DeepSeek Harness: connect apps and call Actions through progressive MCP discovery.

Reach the DeepSeek Harness on your dev machine from your phone — across networks, through no server at all (iroh P2P)

Portable Tavern for the DeepSeek Harness web GUI: an RPG-style SillyTavern V2/V3 character-card generator plus tavern roleplay chat, with world-book generation and JSON/PNG import-export.

Hover price hints on the dsh model picker: shows input/output USD per 1M tokens (from the cost-meter price table) as a native tooltip on every model entry.

Standalone deterministic Chinese text proofreading for DSH

Keeps an OpenRouter route's model list in DeepSeek Harness current: pulls the public catalog on a schedule (and on demand), adds new models, refreshes names / context windows / output limits, and declares the reasoning-effort levels for every model that supports them — so the reasoning picker works instead of answering 'unsupported'.

Create a dsh workspace by absolute path over HTTP, so the DSH Launcher can add one without the native folder dialog (works around the ungrouped '+' being inert for the no-workspace group).

Deny destructive shell commands (rm -rf /, git push --force, raw-device writes, drive formats) at the dsh tools/pre-execute gate before they run; extra deny / ask-first regexes hot-load from ~/.dsh/safe-guard.json.

Load a user frontend skin ($DSH_HOME/frontend-skin.css) into the dsh Web UI as a token-override style tag. Managed by DSH Launcher.

Skin Studio for DeepSeek Harness: a model-facing skin_studio tool that lets the agent design and one-click install launcher or frontend skins on user request — with a guided flow (ask requirements first; request an image from the user when the model cannot generate one, or call an image-generation tool when it can), local image inlining as data URIs, and instant apply through the DSH Launcher API.

DSH Web GUI right sidebar: VS Code-style file explorer plus source control (git status, stage/unstage/discard, commit, diff, commit graph, sync fetch/pull/push, branch/remote management, git init, multi-repo switch, color-coded file status, file-type icons, image preview) with an editable full-file diff view (hunk stage/revert), a syntax-highlighted editor (15 languages), file operations (new/move/copy/delete), a collapsible icon rail, a multi-tab bottom terminal (ConPTY), AI-generated commit messages from a host-configured model, and save.

Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)

DeepSeek Harness 内置可视化插件市场 — 浏览、搜索、一键安装、热切换与全生命周期管理

Live Agent Teams task, communication, subagent, and Workflow topology for DeepSeek Harness