Plugins

A long conversation that renders many LaTeX formulas at once can become laggy, because the browser keeps styling, laying out and painting content that is off screen. This plugin applies content-visibility: auto to the off-screen message bodies, so that work is skipped and the lag is reduced.

Personal WeChat and WeCom (企业微信) bridge: QR pairing, one DSH conversation per chat, two-way text/image/video/document/archive transfer, chat commands (/help, /status, /new, /stop, /friends) answered by the bridge itself without spending a model turn, a switch that restricts the bot to 1:1 chats (group messages are dropped silently and counted), remote approval by replying 1 or 2 in the chat, and a two-way WeCom intelligent robot over its long connection (no public URL needed) that also receives and sends images, files and videos.

Windows toast notifications for approval requests, questions, completed or failed runs, and sign-in prompts; clicking a notification reopens the conversation that raised it, and toasts are attributed to the DeepSeek Harness app identity.

Runs persistent bash and Linux-path file and search tools inside the current WSL distribution. A new conversation that selects WSL mode asks which of that distribution's folders to use as the workspace, and nothing is installed inside the distribution.

A searchable, workspace-grouped multi-select panel over DSH conversations for batch delete, archive and pin, with Shift-range and Ctrl-add selection.

Session favorites: bookmark any conversation into a browser-style favorites panel — one-click star from session rows, folders for organization, notes, custom display names, resume session, fork into a new session, basic session stats, plus a fork-relationship graph showing how conversations derive from one another.

Generative UI: the model calls render_ui with a React snippet and the answer renders as an interactive card in the conversation. The snippet runs in a sandboxed iframe with an opaque origin, so it cannot read the host page, its storage or its cookies, and the frame CSP blocks the network; a message from a card is only sent after the user confirms it, and a failing card shows its error with the source behind a toggle.

Desktop only. DeepSeek web chat, temporary side conversations, the API platform and conversation migration in DSH.

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Diagnoses third-party LLM API endpoints from the sidebar: a four-layer check (DNS/TCP/TLS, key and model, a real streaming conversation, then timed repeat runs) reporting time-to-first-token, output speed and success rate, with every failure attributed to the step it stalled at and the byte count that actually left the machine. 37 provider presets, no model names hardcoded.

Pulls GitHub repo content into DSH conversations at start and writes extracted long-term memory back with SHA-locked multi-file commits at conversation end; per-file read/write permissions, native settings page, turn indicators and global change notices.

Preview conversation context and selectively keep, summarize, or omit exchange groups before applying persistent compaction through Harness session services.

Per-turn session cost chip in the composer stats row: each turn's spend with the model it used, the conversation total split into cache-hit and cache-miss (CNY), priced from an official price table that refreshes on demand.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

Select a term in a DeepSeek Harness conversation and press the Search button beside it to read the explanation in place: basic meaning, purpose and usage, with the token cost of that answer. The call is auxiliary — it writes nothing to the session log.

Adds Delete conversation and Batch delete to the sidebar session menu; a deleted conversation and its subagent sessions are moved to the Windows recycle bin, from where they can be restored.

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.

Four adjustable terse levels plus independent switches for reasoning effort, web search and subagents, on the conversation header and in the Settings page. No output ceiling.

Stops DeepSeek Harness from compacting (summarizing) your conversation far too early. Without it, compaction fires around half-full on smaller context windows; with it, compaction waits until the window is as full as you want (80% by default), settable per provider/model. It only changes when compaction happens — what a summary keeps is still DSH’s decision.

Select text in the DSH Web GUI and ask about it in place (floating button, or the Alt+Q shortcut): an independent subagent that inherits no parent context answers, streaming into a side card hosted by the native right sidebar, dsh-better-sidebar, or a built-in overlay — and the question can be routed to the main conversation instead.

Edit any user turn in DeepSeek Harness and re-run it: an inline editor on the message row rolls the conversation back to just before that turn through the official surface-replace contract, then re-prompts the agent with the revised text. The append-only

On-demand skill tools for DeepSeek Harness: registers skill_search / skill_load / skill_ref so the model searches a staged skill library first and loads a skill body only when it needs it, keeping the library out of the resident session catalog and out of every turn's context; adds a Skills tab to the conversation view ring that reads back the whole session and lists which skills were actually loaded, and in which turn. Zero dependencies, and the records render client-side only, never entering the model's context.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Feishu/Lark gateway for DeepSeek Harness with topic-persistent conversations, live execution cards, image and file inputs, in-chat approvals and questions, source allowlists, and durable one-time or recurring agent tasks created in natural language.