Plugins

Local knowledge base for DSH: one Markdown file per note, with tags, hierarchical folders, full-text search, attachment opening via the system default app, zero-dependency Office text extraction, and citation into the conversation. Built for host DSH 0.2.0-rc.2; on Windows the default root is E:/dsh-kb.

Local-first knowledge base for DeepSeek Harness: imports Word/PPT/Excel/PDF (text or scanned), EPUB and MOBI/AZW3, builds Markdown parts with page anchors, OCR quality/confidence and column-aware PDF reading order; adds an LLM-maintained wiki layer (schema.md rules, auto index.md, append-only log.md, typed notes with sources and backlinks), adds source-trust labels (high/medium/low) with trust-aware ranking and low-trust warnings, and supports ranked search, cross-KB query, precise reading/editing, and md/jsonl/zip export. MOBI/AZW3 need Calibre; legacy .doc/.ppt need Word/PowerPoint (Windows) or LibreOffice (Linux); scanned-PDF OCR downloads models on first use.

Add one session-header button to copy the session deep link, the full conversation as Markdown, only the messages you tick (QQ/WeChat-style multi-select), or the working directory.

Colour engine for the chat UI: ships the Mariana palette as the default preset, exposes 18 colour slots and 9 Markdown prose roles, lets you save up to 12 presets, and colours LaTeX blocks by running Sublime's own LaTeX syntax.

Inkstone is a monochrome theme inspired by Obsidian Minimal E-ink, with inverted sidebar interactions, colored Markdown headings and locally installed LXGW WenKai font fallbacks; it preserves native font and appearance preferences and targets DSH 0.2.1-rc.2.

In-chat image viewer for the web UI: takes over content image clicks (Markdown images, message attachments rendered as blob: URLs, and read_image results) and opens a dialog with pointer-centered wheel zoom and an editable percentage, drag pan, 90° rotation, download with progress, copy as PNG, open with the default app, and ←/→ gallery browsing across the conversation.

Converts Office and PDF files in the DSH workspace to Markdown locally — no network, no API quota — before the model reads them. Writes each .md next to its source so only a file path enters the context, and returns byte size, line count, token estimate and a heading outline, for a single file or a whole directory.

Bridge to the local doc2md (markdown_monitor) CLI — one doc2md tool with convert, read, scan and status actions over docx, doc, xls, xlsx, pdf and image files.

Distills daily AI conversations (Doubao, ChatGPT, DeepSeek, Kimi) into structured Markdown notes in your Obsidian vault.

In-place Markdown editing for the right-sidebar document preview: a file keeps the shipped renderer's look, clicking a paragraph, heading, list, fence, or table cell puts the caret exactly where you clicked, and only the edited range is written back through ctx.fs.writeText, optionally guarded by the version it read.

Markdown input for the composer that keeps the typed Markdown as the sent text while drawing bullets and checkboxes, styling bold, italic, inline code, strikethrough, headings, quotes and fenced code blocks, continuing lists on Shift+Enter, and wrapping selections with Cmd/Ctrl+B, I and E.

Cross-session memory as plain Markdown per workspace: weighted injection, bi-temporal invalidation, TTL review with stale markers, credential redaction, error and session retrospectives, SOP skills, and approval-gated self-improvement proposals.

Turns file and directory paths in DSH chat into clickable buttons: click one to preview the file in the right sidebar, or open it with the system default application.

A novel-writing workspace: one folder per book, YAML/Markdown sections, an auto-wired relationship graph, consistency checks, four LLM tasks and four export formats.

Happy Reader（阅读增强）：隐藏输入框 / 上边栏、全屏切换、字号 10–40px、行距/字距微调、面板可拖动可拉高、复制为 Markdown（公式→LaTeX）、内容宽度扩展、中英文分别选正文字体 + 代码字体（仅列本机已装）—— 与官方设置协同，不冲突

Type Markdown, see it rendered live — Open-WebUI-style composer for the DeepSeek Harness (DSH) web, with syntax-highlighted code blocks, task lists, format toolbars and smart paste.

Three-window workbench for dsh web: chat, construct, and a read-only review window side by side for each workspace, per-window hooks, and an anonymous multi-model review that asks before it runs, groups findings by issue, and reports in Markdown.

Document intake for agents: doc_route sniffs a file's real format by magic bytes and measures a PDF's text layer and page column layout before any conversion, and pdf_markdown converts PDFs to Markdown in column reading order with PyMuPDF. The PDF path needs a Python 3 interpreter with PyMuPDF.

Adds a human-editable notes workspace with folders, full-text search, rich text, checklists, resizable tables, attachments, exports, and opt-in agent collaboration.

Google-AI-Studio-style turn controls for DeepSeek Harness, in one install: edit a prompt and re-run it, re-run a reply in place, delete a turn from the model context, and render sent prompts as Markdown. Self-contained: the plugin list shows this one row;

One private Feishu group per DSH workspace with real-time two-way message synchronization.

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

Long-term memory and self-evolving skills for the DeepSeek Harness · DeepSeek Harness 的长期记忆与自我演进能力 —— Plain Markdown on disk, no vector store