Plugins

Listen to Xiaoyuzhou (小宇宙) podcasts in the DSH web UI: paste a share link to play anonymously (host proxies the audio with Range/seek), or log in via QR code to sync subscriptions, keyword-search shows/episodes, page full episode lists, and unlock purchased paywalled episodes; a `podcast_play` tool lets the agent play by link, podcast pid, or episode eid.

Word auto-completion in the Web composer: prefix-matched suggestions sorted by closeness, arrow-key selection and Enter to confirm.

DSH 思维导图模式插件：课件(PPT/PDF/Word)+电子书 → 打印级复习思维导图 HTML（A3 横向、每主干一页、大括号式横向、宋体、右栏笔记区、封面总览 + 交互式测试题）

Common Word Box (常用词盒子) — DeepSeek Harness web client plugin: a persistent slide-up word/phrase panel next to the composer input, with global/current-project buckets and one-click insert. Works in every workspace.

Vector + graph memory backend: observe/remember/search/recall tools against a local memoria server, fusing HNSW semantic recall, FTS5 keyword search, and knowledge-graph signals via RRF ranking, with automatic turn-end persistence and per-agent namespace isolation.

Law paper writing corpus for DeepSeek Harness: 850 bibliographic records from four CLSCI journals (2024-2026) with title, authors, abstract, keywords and outline, supporting BM25 search, framework cards, journal profiling, submission self-check and export.

SSH terminal, SFTP file manager and port forwarding (-L/-R/-D) in the DSH right sidebar, with jump-host chains and remembered passwords kept in the operating system credential store.

Normalizes every generated .docx to one Chinese official-document layout: XiaoBiaoSong title, FangSong body at a fixed 29pt leading with zero paragraph spacing, character-unit 2-character first-line indent, fully centered table cells with repeating header rows, and a centered footer page number. Long attachment entries are split into real paragraphs at the wrap point measured by Word, producing a 2 / 6 / 5 / 6 character indent ladder. It applies the layout only when the request mentions 公文 (official document) and writes no signature block unless asked.

Xander Amazon seller-operations toolkit for DeepSeek Harness: 33 native xander_* tools and 7 skills for competitor research, keywords, listings, ads, replenishment and profit, with exact proposals, explicit approval and read-back verification for Amazon changes.

Adds a browserless deepseek-web provider that drives chat.deepseek.com, with an account pool (rotation, cooldown, auto-failover), in-panel login (browser, or email + password with MFA) and token usage stats.

Search stored DSH conversation text across all or selected workspaces and sessions, with exact, regular-expression, typo-tolerant or word-internal subsequence matching.

Turns every file artifact the agent names in chat into a clickable entry — and refuses to paint one that does not resolve. Hover resolves asynchronously, and only a file that really exists becomes a hand pointer with a dashed blue outline (30 s TTL cache, so repeated hovers cost nothing); confirmed non-artifacts stay plain text and the right-click falls through to the host menu untouched. Left click reveals the file in Explorer already selected (Shell.Application Explore plus SelectItem with SVSI_ENSUREVISIBLE, so the pane scrolls to it; explorer.exe /select is deliberately not used because it silently drops the selection when an instance is already running). Right click offers seven actions: preview in DSH's built-in sidebar, open with the default app, reveal in Explorer, save as, copy the file itself to the clipboard, copy the absolute path, or insert the path into the composer. Ctrl or Shift with left click opens with the default app, Alt with left click copies the path. Names resolve through the absolute path, the session workspace and every profile workspace, then a cached basename index built with a depth budget, shrinking from the left when a mention swallows leading words. The host half also keeps six system-prompt rules resident, so absolute paths stay in tool arguments while the body shows only file names, and every route is loopback-only.

Composer-side prompt library: a button next to the input opens a picker with group chips and word-split AND search over saved snippets, inserting one into the draft or appending it, filling {{variables}} before insertion, with 13 built-in templates. Snippets live in one local JSON file behind a rev lock, a per-save backup, and whole-library JSON import/export; a settings page handles editing, grouping, pinning and a 6-second delete undo.

Local, transparent writing-style analysis for DeepSeek Harness: vocabulary, repeated words and sentences, and cliche evidence.

VSCode-style remote development for DSH: SSH host manager (key/password), helper deploy pipeline with version check, remote file explorer + editor + terminal in dsh-better-sidebar.

Database access for DeepSeek Harness through the DBHub MCP server: configure MySQL, MariaDB, PostgreSQL, SQLite and SQL Server connections per workspace and environment, then let the agent configure, list, query and search SQLite objects through four fixed tools. Passwords and full connection strings are entered in the settings UI and never accepted as tool arguments, so the model only sees metadata such as mysql://host:3306/db; each environment can be read-only (the model may enable it but not clear it) or reached through a manual SSH tunnel. Every call runs its own short-lived dbhub process and dbhub installs itself when missing.

Adds one system-prompt section that keeps private words out of formal deliverables and, every few of them, leaves a short note at the end.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.

A memory subsystem for DeepSeek Harness: full ontological memory (event/fact/rule three-ontology) plus a goal system (goal.js) — belief values written via Bridge trigger words, goal activation scored at read time (0.25 domain + 0.35 bridge + 0.40 sim) to recover goal/value long-range associations, journal ledger, episodic archive, low-confidence decay, memory_append/read/consolidate plus linghun_goal_update/get/state closed loop. Independent of the original dsh-linghun line. 16/16 on LoCoMo-Plus.

Runs the standalone opencode2api backend (jasonxu114514/opencode2api, Windows x64/ARM64, no Docker or OpenCode CLI) with DSH and on exit stops only the process it launched; its settings card installs, updates or rolls back the backend from checksum-verified GitHub releases, copies the initial admin password and syncs /v1/models into an opencode2api provider with context, vision and reasoning efforts, re-syncing every 10 minutes.

Run one deterministic skill-routing pass on every user instruction, so the skill catalog is consulted before the model answers instead of after it remembers. On the host it scores the live catalog from the instruction's keywords and the catalog metadata, with no LLM or embedding call, and appends a single producer-tagged message to the step: a ranked shortlist by default, the winning SKILL.md body once the score clears a threshold, or an instruction to call a named router skill exactly once. Unrelated instructions stay silent.

Project-level memory built around a ledger whose structure the AI designs per project; the plugin only handles detection, injection, write-back, archiving and git. Memories are split by meaning: the active ledger holds current state, the turn journal is append-only, and decisions, the goal tree and lessons are one-card-per-file (with a multi-dimension index over the card folders); the fundamental principles file can be changed only by the user. There is a single compaction mode: before compacting, the AI sorts the work into three buckets - what must stay in context and is re-injected verbatim, what is written to the project's _stash/ for later lookup, and what is dropped. When a conversation is opened in a container workspace holding several projects, it can be locked to one sub-project (the lock lives in the plugin's own home and survives restarts; it leaves no marker in your project). Also an activity log with five levels, where L4 stores the user's own words verbatim (never injected, queryable on demand). Before each compaction a verbatim capsule (user quotes, raw errors, changed files) is written to disk, and both the capsule and its source material survive a restart; a handoff document lets a new conversation resume the previous one. 21 tools, 12 subcommands, 39 settings (one of them switches whether the settings panel or each project's manifest wins). Runs locally, no runtime dependencies.

Reads and writes a self-hosted Bitwarden/Vaultwarden vault from any session: eleven bitwarden_* tools, real-time WebSocket sync with a polling fallback, a settings panel with readonly, ask and auto write modes, and optional local masking — with masking on, passwords surface as stable placeholders unless revealed one field at a time, and on-disk session logs are swept for bitwarden secrets. Masking and log sweeping are separate switches.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.