Plugins

Shell-style prompt history in the DSH composer: ↑ in an empty composer recalls the previous prompt and keeps walking back, ↓ walks forward to the empty draft; history is kept per workspace, persisted across restarts and records only human input, while typing or editing a draft returns ↑/↓ to normal caret movement. Adds a Settings page to export, import and clear the history.

Chat turn accordion: every interaction folds into one row with a time pill and question summary, only the newest turn stays open, and switching sessions or starting a new turn resets the open state; the execution process opens only on its own click.

Layered long-term memory for DeepSeek Harness: each turn injects a persona frame plus a relevance-ranked memory index while full transcripts stay on disk and are expanded on demand, so the vault never floods the context window. Facts are slot-keyed, so a changed mind retires the old value instead of recalling two contradictory answers. The persona frame is derived from memory by the model itself, behind three anti-pollution gates (rejecting development chatter, blocking echoes of its own injection, and merging restatements by shared content words). Periodic consolidation merges near-duplicates, rolls long topics into digests, and archives low-value old entries by tagging only — raw text is never deleted. The append-only store is compacted in place (measured 4.7 MB to 355 KB). Zero third-party dependencies, no build step. Note: per-turn injection inevitably lowers prompt-cache hit rates, so this plugin is not recommended for work scenarios.

Control plane for the harness's own Agent Teams: members are ordinary independent sessions created through the same seam the GUI uses, each with its own model, so they open and continue like any other conversation while a sidecar roster and task board coordinate them. Task entries carry a definition of done, a member's completion is submitted and waits for the Lead's review, and availability tells idle apart from awaiting-review or a failed last turn. With delegationEngine=auto it uses independent sessions, continuable subagents, or the kernel roster depending on what the composition provides.

Homepage-style chat background skin for DeepSeek Harness, ported line by line from deepseek.com/harness: WebGL fluid background (5-colour noise field, flow-field brush, light, bloom, vignette, grain), white 90px dot-line grid with mouse perturbation and spring return, and a digital point-cloud whale that assembles from particles, breathes, swims, is pushed radially by the cursor and brightened by a light beam. Dark theme only; disabled automatically under reduced-motion.

Turns a user goal into a plugin plan using community catalogs and author documentation, then continues through installation and task execution in one workbench with saved history and feedback.

Use DSH from a phone browser. Turn on phone access from the phone button in the session header (or the plugin card) and scan the QR code; the phone opens the official DSH web UI served by the desktop process, with the same sessions updating live, so you can follow a running task, reply and approve away from the computer. A gateway inside DSH (port 18765) proxies the web UI and handles the desktop login itself. One QR code works on Wi-Fi and on mobile data: turning access on also starts a free Cloudflare quick tunnel (cloudflared is downloaded from Cloudflare's GitHub releases if missing), and its address survives DSH restarts, so phones do not need to rescan. Pairing codes are one-time and expire in 10 minutes, each phone gets its own revocable credential, the header button shows when a phone is connected, and idle connections get keepalive pings. Optional push notifications go to Bark, ntfy, ServerChan, Feishu / WeCom / DingTalk group bots, Telegram or any webhook when a task finishes (after 30 seconds or more), stops with an error, or waits for an approval or an answer; they carry only the session title and status, and approval still happens in DSH. On a phone the web UI's side panels slide over the page, and it can be added to the home screen with its own icon.

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 desktop notifications for DSH that speak the turn result by default: Windows TTS needs no download, and 13 VOICEVOX voice packs can be installed from the settings page. A completed alert waits until running subagents and background jobs finish; approval, question and error alerts fire immediately. Voice packs are downloaded from GitHub after a terms confirmation.

Turns course files (PPTX, PDF, DOCX, Markdown) into an outline, per-chapter key points with quoted evidence, Bilibili video picks, syllabus coverage, and Anki/JSON exports.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.6.1 supports DSH 0.2.2-rc.1, improves CLI discovery and includes optional Retry. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox. Derived from kyle123740/dsh-zcode-cli-proxy (AGPL-3.0); it registers the same `zcode-cli` provider id, so it cannot be installed alongside the original.

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.

Desktop notification and sound when a turn completes, the agent asks a question, or an approval is requested, each independently toggleable, plus an activity ball that lists live sessions and jumps back to one.

Lighten the load on your agent: one-click toggles for skills and MCP, so the context holds only what this turn actually needs. Skills and MCP servers you switch off are no longer injected into the model context — cleaner, and lighter on tokens.

GitHub project search and analysis: describe your idea in one sentence and the agent searches GitHub for related projects, ranks them by relevance weighted with stars, and returns a structured card — last updated, relevance, stars, weighted score, language and a one-line description for each project. Pick a few repositories and it reads their README, dependency manifest, directory tree and key files to lay out their architecture — so you stand on the shoulders of giants before you start building.

Cross-session memory kept as a short Markdown living document that is rewritten in full at the end of every turn, written to by model tools, the page, and automatic rewriting alike.

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.

Model picker dialog with routing groups: a model that keeps failing hands the turn to the next usable model in its group, and the dialog also carries a metrics dashboard and a free-channel tab. That tab installs six channel plugins — Our Free Model (the only one that needs no login or API key), CodeArts, WorkBuddy, Trae, Qoder and Providers Hub — whose providers cover 23 platforms: Huawei Cloud CodeArts, Tencent CodeBuddy, WorkBuddy, Youdao LobsterAI, Qoder, TRAE, Cline, iFlytek Loomy, SenseTime Raccoon, MiniMax, Zhipu ZCode, Gemini Code Assist, Alibaba Accio, iFlytek AStudio, OpenCode, OfficeAce, AutoClaw, ModelScope, Qiniu, Codely, MonkeyCode, Baizhi Cloud and MagiCrew.

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.

Composer prompt enhancement for DeepSeek Harness: a button beside the model selector rewrites the draft through one auxiliary LLM call and writes the result back in place, with composer undo left intact; a /prompt-enhance slash command returns the rewritten prompt as a command result line without touching the draft; the enhancement call can be pinned to its own fast provider and model in the profile patch; the rewrite policy is faithful - original intent, language and information are kept, code, commands and paths are preserved verbatim, and nothing is invented or padded with placeholder text.

Turn any DSH selection into a reviewable quote — chat, file preview, terminal and diff; code quotes carry path#line. A sent quote keeps a source highlight and ordinal and jumps back, then joins a searchable review list with status, tags, multi-select insert, and Markdown/JSON export. Quotes collect above the composer as a 引用 ×N bar with per-chip edit and remove; side threads can bring their conclusion back to the main draft; a sent quote can be revised, with the old capsule marked superseded; replies can answer each quote by number.

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.