Plugins

Rewrites the Chinese copy of a market-installed plugin into English using a model already configured in the harness — automatically when the plugin is installed, then live-reloaded. Each file is translated in one whole-file pass, validated by a real parser where one exists (node --check for JavaScript, JSON and YAML parsers otherwise) and handed back to the model with the error for up to three repair attempts; files above 48 KB, or that never parse, fall back to a line-range pass that checks every returned line against the original for structure. Trigger phrases and locale tables can optionally be preserved rather than translated, and the untouched original is kept beside the file as a .zh.bak.

Claim-verification skill that checks design documents and plans against codebase facts, escalating behavioral claims to executable logic-primitive verification for state machines and data models, with before/after regression, domain constraints, and concurrency risk mining.

A guarded local fetch provider for the ctx.web seam — the backend dsh does not ship for its own web_fetch tool. Every redirect hop is re-resolved and checked against the non-routable ranges, with a streamed size cap and a content-type allowlist.

Adds selectable animated skins to the "Deep diving..." status row, with configurable size and optional status-text replacement.

Network optimization for the DSH web UI: reduces transfer size with caching and compression to greatly speed up page loading, plus a connection-drop indicator and automatic reconnection. Ideal for users pursuing peak performance or using unstable networks.

Global proxy for DeepSeek Harness: route agent tools, model requests and web fetches through the Windows system proxy or a custom address with one persistent toggle, an editable settings card, and agent-visible proxy status.

Cost dashboard for DeepSeek Harness: aggregates model input/output/cache tokens across all local sessions, prices them with a builtin table (including DeepSeek peak/off-peak), and shows daily trends plus per-model and per-session tables.

A super-simplified LLM-wiki memory plugin: one index document (auto-loaded) + one markdown file per topic (read only when needed) — no dumping everything into the context and burning tokens. Simple and lightweight, painless to install/uninstall, and freely editable however you like.

Draggable 3D liquid-glass floating card for the DSH web GUI: DeepSeek API balance, cumulative spend/token stats (today/yesterday/7d/30d/all), adjustable glass/3D/color controls, and one-click top-up.

Multi-window wall for the DSH Web UI: run and monitor N conversations side-by-side in one screen, with auto-discovery, per-window controls, and an authenticated LAN gateway for phone/tablet access.

One stylesheet that retypesets the DSH conversation to measured Codex metrics: 14/22 px body, tighter headings, lists and blocks, a rounded quote bar, and Tidy Tables with a themed header, row/column rules, full-width short tables and contained scrolling for wide tables; no settings or DOM rewriting, with real before/after captures.

Lazy MCP gateway for DeepSeek Harness: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

Learns what you leave unsaid in your prompts from messy turns and your own corrections, and injects the learned directives into the system prompt of every new conversation; the directives are editable in Settings and a composer button rewrites the current draft with them.

A content-aware PDF reading plugin for vision models: profiles each page for figures (vector and raster), tables, formula risk and double-column layout, then applies content-aware hybrid extraction, rendering figure/table/formula pages as high-DPI region crops. Provides a low-resolution preview to understand the page layout, and renders a specified region at high resolution. Packaged as multiple tools for agents.

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.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

DeepSeek account balance and current-session spend estimate in a top-bar chip and settings card, with pause-aware auto-refresh, an editable official price table, a `deepseek_balance` model tool, and a bilingual UI.

DeepSeek Harness 的「便携酒馆」插件：RPG 式 SillyTavern V2/V3 角色卡生成器 + 酒馆角色扮演聊天。支持世界书、角色卡 JSON/PNG 导入导出、面板主题与本地音乐。独立插件，仅依赖官方 @deepseek-ai SDK。

A corner HUD for DeepSeek Harness that shows your session's token pressure, per-model cost, and daily/monthly usage at a glance, with an editable budget and balance that tracks spending for you. 右下角常驻的 Token 仪表盘：实时看会话压力、按模型估算花费。预算和余额点一下就能改，每天每月用了多少都有记录。

Route each task to one model and its review to a different one, with qualification evidence, failover and a durable journal.

Spec-Driven Development pipeline for Odoo: 15 tools take a request from an immutable spec through architecture to module code or live configuration, then require a persisted verdict backed by evidence from a real Odoo instance, with fail-closed gates, human-approved batches in a declared environment, Odoo's own CSV/Excel importer, and a journal that reverses the data written through the plugin.

Knowledge-base plugin: build auditable KB packages (references + SQL).

Create, manage, and share portable DeepSeek Harness skins.