Plugins

A calmer reading view for DeepSeek Harness: native process details, live reasoning, and clean final answers. Fork adds answer message bubbles with a settings switch.

DeepSeek Harness plugin: bounded-file memory for local agents. ME.md + project MEMORY.md vault, cache-stable inject, plain-line inbox, Memory rightbar. No embeddings, no LLM calls.

The child-scoped report tool for continuable in-process subagents on DeepSeek Harness: installs `report` plus its usage guidance into every continuable child scope, so findings reach the parent before the child finishes.

Summarizes the current DeepSeek Harness session with /recap or after inactivity, with configurable models, Chinese and English output, and expandable summaries in the conversation.

2005-era instant-messenger skin for the DeepSeek Harness client: right-angle 1px window chrome, a blue-gradient title bar, SimSun for the Chinese UI, a buddy-group sidebar with an avatar card and editable signature, per-message name/time headers, and three switchable intensities. All artwork is original SVG; the reskinned toolbar also carries a cross-session notepad, a running-session panel, and an 8-ball game, minesweeper, a token garden and heads-up poker that a built-in focus mode silences.

Control how the DeepSeek Harness Web GUI is reachable: local only, Tailscale, all local networks, or off.

Tavily-backed search provider for the DeepSeek Harness web seam (ctx.web): keyless-first credentials, a cooldown after the keyless tier refuses, and a user-visible notice when it falls back to the key.

Kite-flying engine: while the agent codes, an animated kite drifts and sways in the wind on screen, tethered to the bottom edge of the window — the busier the agent, the denser the events and the higher it flies; ships a Weifang-style framework card deck (sand-swallow, goldfish, butterfly, bagua, dragon-head and more, hard-wing / soft-wing / flat / dimensional frames), with shape x pattern x colors all swappable data configs, and supports pasting user images onto the kite face with real-time affine transforms as the kite banks.

A grouped, searchable replacement for the DSH composer model selector.

中瑞世联工作台 / CRWU audit workbench for DeepSeek Harness: pick a pending audit report, dispatch one AI audit subagent, watch and stop/restart it, auto-upload deliverables to Aliyun OSS.

Enhances the native right-sidebar Files tab rather than replacing it: each row gets an @ reference button that inserts the canonical path mention into the composer, plus a size column, a sortable modification-time column, and a status dot for untracked, unstaged and staged files. Below the tree a git bar shows the branch with ahead/behind counts and expands upward into the 20 most recent commits, with a repository selector when a workspace has independent repositories in subdirectories. A header search box walks the workspace recursively and can open a result or expand the tree at it, preview tabs offer reveal-in-tree and one-click @, the tree is keyboard navigable with ARIA tree semantics, and a right-click entry on the Files tab switches back to the native tree at runtime.

Model usage panel for DeepSeek Harness: automatic per-call accounting from session logs with real timestamps, full history and live increments, showing tokens, cost, requests, trend and model composition with per-model, per-project and per-session views and editable tiered pricing.

Configurable Git commit and pull request prompt instructions for DeepSeek Harness

Model relay station for DeepSeek Harness (模型中转站): serve any registered DSH LLM provider (e.g. @tnnevol/dsh-codebuddy) over an OpenAI-compatible /v1 API, so other projects can call those models with a standard OpenAI client.

MCP server manager for DeepSeek Harness: add, edit, enable and test stdio / Streamable HTTP MCP servers from the Web settings page and from agent tools, connected and disconnected at runtime without restarting DSH

Claude-compatible memory for DeepSeek Harness: a user-chosen memory directory with MEMORY.md index and topic files, the memory tool, and a settings page

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

Federated plugin registry aggregator for DeepSeek Harness — combine npm, GitHub, and JSON catalogs into one searchable index.

Gives DSH the full 33-tool browser surface (ctx.browser seam -> a self-hosted headless Chromium over CDP: one 127.0.0.1 daemon with Bearer-token auth, request-path whitelist and WebSocket rewriting, no root/GUI/Electron needed), plus a web panel — a real page you can click, scroll and type in, operation/console/network logs with one-click cleanup, a customizable window (border color, transparency, glass, fit-to-picture with no black bars, top-inset and self-centering) and an adjustable page size (1920x1080 by default) — plus a collapsed pill that can be dragged to any spot on the screen (free position), a live view that auto-resumes when you switch back to the web tab, and a 1920px default max edge for the live frame — and two bundled skills (browser, browser-runtime) served through the plugin built-in skill provider, so the skill centre lists them as system-level by default without writing into $DSH_HOME/skills.

A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.

Theme studio for the DeepSeek Harness web GUI: eight switchable preset styles, accent and panel-translucency fine-tuning, host-side wallpapers painted on the first frame, and a one-click fix when the wallpaper-engine glass tint greys out light styles.

A newspaper-style front page for a session you left running, as a Conversation View tab beside Chat and Trajectory: a per-turn timeline (duration, steps, tools, tokens, outcome), file churn counted per file, where the wall clock went and how much of it was the model rather than tools, which single turn ate the spend, failures nobody retried quoted with their failing command, and a context-pressure gauge measured against the routed model's own declared capacity. The briefing is folded from the durable session log and never generated by a model, so it costs no tokens, cannot hallucinate, and is byte-identical for the same log and clock; it appends nothing to the session and reaches no model, and it reports a pending approval without ever answering it. Pages are offered only when they have content, and the tab refreshes itself on turn settle and on a two-speed poll backed by a metadata-only tail probe.

Matrix digital rain: drapes the chat window in the classic green character rain — cascading columns with incandescent white heads and green tails, streaming the tokens the agent is generating into the rain in real time; opacity, speed, density, font size and colors are all adjustable, and rain intensity follows agent activity.

DeepSeek Harness (dsh) plugin: live local LLM endpoint health in the web rightbar. llama.cpp slots (busy/TTFT/wedged, /metrics) + Ollama MODELS (loaded vs empty). Engine fingerprinted by response shape. Installable dsh.bundle.