Plugins

Deep-sea tidal-blue theme for the DeepSeek Harness Web client with a single accent color and matte (non-glass) surfaces in light and dark modes. Same-token UI additions: a single-line dock HUD reading real session projections (context usage vs. window, TPS, cache-hit rate, elapsed time), per-turn subagent delegation cards showing token usage and an optional cost estimate from OpenRouter public prices, sidebar pagination with pinned sections and type-to-filter, and model / reasoning-effort / permission controls under the composer. Each addition can be toggled in the plugin settings.

macOS 14.2+ only: the macOS counterpart to Lingwuxin/dsh-audio-rail — the DSH conversation rail pulses with whatever the Mac is playing, a real 12-band spectrum that only changes bar length, leaving the host state colours and lengths untouched. Requires the Audio Recording permission on first run. Do not install it alongside dsh-audio-rail: both drive the same rail and register the same /audio-rail/events and /audio-rail/status routes.

Phone-portrait layout shell for the DSH Web UI: the sidebar becomes an off-canvas drawer opened by swiping from the left, a persistent 56px action bar sits under the composer, and the settings panel plus the model and permission pickers are reflowed for touch. Ships native, merged and floating layout presets, all scoped to html\[data-dshm-mode="mobile"], so desktop, tablet and landscape keep the stock layout.

Session replay view for DSH conversations: replays a session turn by turn at reading pace for prompts and answers while reasoning and tool output stream past, and every prompt is followed by a one-second pause. It can also re-run the original prompts in a new session, and record the replay — screen recording the conversation itself — to a WebM video through a 1280x720 canvas, with no OS screen-recording permission.

Let a pet whale girl browse Bilibili on her own: she picks videos, reads subtitles, posts comments and moments once you allow it, and writes daily digests with optional local video production. Maintained fork of c1overzz/dsh-bili-scroll (MIT) with per-action permissions, memories, stickers and local video production added; it registers the same bili_* tool names as the upstream, so the two cannot be installed together. Video production needs Python 3.11-3.13 (or uv); the media dependencies are installed on first use.

Refuses agent-generated SQL that reads tables or columns outside a configured blacklist or whitelist, returning a structured permission reason instead of rewriting the query.

Per-workspace session defaults for DeepSeek Harness: save the Agent preset, permission preset, model, reasoning effort, Chat work-details level and collapse timing per workspace; new or reused blank sessions in that workspace start from them.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. First-run defaults (persistent inbound dedupe, configurable outbound-hook budget, optional default permission preset, extension seeding) are written only where nothing was configured and never overwrite user changes. Interview and quiz practice run inside chat with local scoring and configurable transcript retention. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

Permission guard for DSH: four scopes with read/write/execute bits in the native permission menu, plus an optional Jev semantic classifier for bash commands.

Composer UI for DeepSeek Harness that does two things. The reasoning-effort row in the model menu becomes a continuous slider drawn on the row itself, with the rungs read live from the model adapter so any ladder length works; each rung paints its own ember plume into a canvas behind the knob. Separately, the permission trigger renders in the theme error colour whenever full access is the active preset, including its row in the permission menu.

Feishu IM bridge for dsh: create a dedicated Feishu bot by scanning a QR code, get one Card JSON 2.0 notice per finished turn, answer tool approvals and structured questions from the chat, and drive a session from it — listing and switching the bound session with /sessions and /resume, steering a running turn, and choosing per-chat permission modes (read-only, workspace, Auto Review, full). Long output paginates instead of being cut. Owner binding: the QR scan binds the scanner; with manually entered credentials the first sender claims ownership and everyone else is refused.

AFK controls for ask_user_question: profile-wide or per-session settings, configurable automatic replies or blocking new calls, and session-log question history with read tracking; does not approve permissions or plans. Supports DSH 0.2.1-rc.2 and 0.2.1-rc.3 only.

Restores the permission preset a session was last set to when that session is reopened; a session opened for the first time is left untouched. Load it after dsh-experimental-auto-review to restore the auto preset.

Native Deepwork roles, routing, profiles, and permission controls for DeepSeek Harness.

An independent permission gate above the built-in sandbox. It blocks writes outside the workspace and to protected paths even under danger-full-access, refuses whole-file overwrites without a complete fresh read, and keeps ZIP restore points plus Recycle Bin copies before destructive actions.

A global permission watchdog: a hard budget on auto-approved permission requests. At most 10 per rolling 60 seconds, at least 3 seconds apart; anything past either limit is deferred to the human answerer and waits. It never refuses and never changes what is asked -- it only decides who answers and how fast. Installs disabled; enable it with the plugin manager toggle.

macOS 13+. Plays a macOS system sound when DeepSeek Harness needs a tool approval, an agent question, a macOS permission prompt, or an administrator password sheet, then repeats on a 0/25/20/15/10/5 second cadence until the request is resolved. Ships as a bundle with a switch and a config form in the Plugins page.

Graph-based code context, impact analysis, review workflows, interactive graphs, and permission-controlled refactoring for DSH using the code-review-graph engine.

SSH workspaces for Linux/macOS with SSH config import, remote folder selection, and file tools, Bash and persistent remote terminals following native DSH session permissions.

Search the documents and pictures in your Quberi knowledge base, browse its spaces and documents, save notes to it, and upload files into it with your approval for each one, from DeepSeek Harness over OAuth.

Three-tier deny/ask/auto gate for the computer-use (cua-driver) tool family: each tool category gets one segmented control in Settings, and an allow list or deny list overrides the tiers per tool name.

Permission-wall-immune file search for DeepSeek Harness (DSH): the find_file agent tool skips unreadable directories, reports them with errno, and never lets a failed walk pose as an empty result.

Makes a connection between two DSH sessions a first-class object: drag from the composer anchor or a session row to open one, set a permission in each direction, and mount cards on it. Each end gets five host tools for messaging at a chosen urgency, reading the peer work state, and sharing a convention box; awareness is pull-based, so an idle connection costs no context.

Drive a DSH instance from another device: a host plugin opens a token-authenticated TCP port that a single-file Python CLI drives - listing and creating sessions, sending prompts with images, streaming replies, and switching models, permissions and workspaces.