Plugins

Gives the agent a mouth through the ai-ball floating orb: speak text that the orb types out character by character, set its mood colour, show or hide its monologue panel, read back what you typed into it, and check or start it. The orb is a separate Python 3.10+ overlay you install yourself, and the plugin only writes the files it watches.

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.

Merge requests, review threads and pipeline job logs for GitLab over its REST API with a personal access token, in a side panel, with comment, reply, resolve and approve actions that wait for confirmation. Reads need the read_api scope, writes need api.

Windows-only. Trust a newly added workspace folder once, then grants the NTFS rights the workspace-write sandbox needs and pushes the grant plus the Low integrity label through folders that already exist; repairs show live progress.

Audits Chinese copy for AI-sounding phrasing: a 0-100 score over six dimensions, sentence-level flags with rewrite hints, and per-genre weights adjustable in conversation.

Windows only. Bilibili video summarizer: downloads the audio track, transcribes it locally with faster-whisper (Python + faster-whisper, about 725 MB of models on first run), then writes the analysis markdown and renders a one-page infographic PNG.

DSH plugin: a settings panel to list, add, rewrite and toggle @deepseek-ai/dsh-mcp-client MCP rows — no more hand-writing them into cordis.patch.yml. Zero build, zero runtime dependencies.

Drives Cadence Virtuoso from the host: VM lifecycle, SKILL execution through the bridge, window capture, Calibre DRC parsing and a write-confirmation gate, in 12 host-only tools.

Local 3D studio orchestration: detects Blender, COLMAP and ComfyUI on every run and picks the route they support, and also ships a Three.js fallback that generates models from primitive specs, edits or scales GLB files, writes an offline viewer page and renders multi-view PNGs without Blender.

Connects the Drafta notes app to DeepSeek Harness over MCP, so the agent can search, read and write notes in your local Drafta library.

Per-turn checkpoints of the whole workspace: every turn ends with a snapshot, the files it changed are listed under that turn in the chat, and any turn can be restored — files, the conversation, or both. Capture is a whole-tree scan rather than a hook on write/edit tools, so edits made by shell commands, external editors or git leave a record too. Restoring the conversation forks it from that turn instead of cutting the original, and a restore can itself be undone. History sits in a shadow git repository under DSH_HOME and never touches your project .git. Requires Git >= 2.20 and Node.js >= 20.

Token usage dashboard for the whole harness: billed tokens from every session are rolled up per session and turn (uncached input, cache read, cache write and output) with a peak/off-peak CNY cost estimate, and a "Token 用量" entry above Settings in the sidebar opens the dashboard at /token-stats, in a new tab on the web and in an in-app popup on the Desktop. The page recollects and repaints every 60 seconds while the tab is visible. Usage is read from the same session event stream dsh-token-meter consumes, accepting 0.1.x assistant/chunk and 0.2.x assistant/message and assistant/attempt, and counting an attempt repeated after an llm retry as its own billed call; cold history is seeded once from a persisted rollup file and afterwards only logs whose mtime or size changed are re-parsed. Host half and client half ship in the one package.

Local-only, read-only DSH token dashboard: provider-reported usage across all backends, all-time totals, a 365-day heatmap, input+output and cache read/write details, turn/step counts, average tok/s, and durable history after sessions are archived.

A one-line caption above the composer that tells you what the AI is doing right now: the step number, the action (e.g. running npm test), and whether it is still going, done, or failed with a short plain-language reason. Inferred locally from tool calls and the thinking text; no model calls, no network requests, no writes to DSH data.

Adds an ✦ button to the DSH composer that rewrites the current draft into a clearer, more specific prompt in the same language, with one click to restore the original, plus an enhance_prompt tool the agent can call; the rewrite replaces the draft and is never sent automatically.

Four-tier prompt enhancer for the composer — a button and a global shortcut rewrite the draft as a light tidy-up, a single paragraph, a five-section brief, or an eight-section system prompt, with a before/after panel, fill-back and undo. Never changes intent, never invents requirements.

A plain-notebook calendar in the DSH sidebar: a 70-day, Monday-first grid whose cells print that day's note; one note per day is stored in a .xlsx you choose, in the DesktopCal two-column layout (Excel date serial plus free text, newest date first). Clicking a day opens the editor for it, and import/export move that same format in and out, with a preview step and a conflict policy (keep, overwrite, concat or skip).

A continue button in the composer tool row, immediately left of the send key: one click writes an interruption-aware prompt into the draft and submits it, so an interrupted task resumes without retyping the context. The prompt names the interruption and appends the current task plus the tail of the last reply; Alt-click or right-click sends a bare 继续, and a non-empty draft is appended to rather than overwritten.

Composer prompt refinement for DSH: rewrites a rough draft into a structured, unambiguous prompt with one-click undo, reference-chip protection, three model sources (composer / account / any OpenAI-compatible endpoint) and disconnect-aware cancellation.

Adds a button to the composer that rewrites the current draft into a clearer, more specific prompt through a one-shot LLM call, with one-click revert and cancel.

Scans MCP configs from the tools it knows (28 built-in sources plus custom ones), syncs diffs into DSH, and lets you import, write back, or edit MCP servers from the DSH sidebar.

Declarative interactive cards for DSH: the model writes a spec, the Host compiles it into a JSON program, and the client renders forms, tables, charts and lists with local state and explicit submit.

A conversation-style layer that rephrases trade-off warnings: when a shortcut is cheap but has a catch, the reply may say the fast road is the rival shop and the slow one keeps its rules. Ships a rewrite engine that turns any text into a fixed-format dialogue with five independent knobs (act count, catchphrase density, ending turn, seed, preset), a slider for four on/off intensity levels, and a /bushaoxin command that reports a joke "heartburn index" from the session tool-call log. Every rewrite ends with a real technical conclusion that cannot be disabled. Zero dependencies, no build step, engine is pure functions.

Conflict diagnosis and repair for DeepSeek Harness plugins. Builds a capability graph of the running Loader profile and of the on-disk cordis.patch.yml layers, comparing imports, peer ranges and config against the host that is ACTUALLY running rather than the profile's possibly-stale copies, and reports the conflicts that fail silently: a fiber stuck PENDING on a service no plugin provides, a browser half injecting a client module nothing provides, a tool id two plugins both register, duplicate Loader entry ids, a row disabled by one layer and re-inserted by another, an import of a host subpath the running host does not export, and a cycle among inject declarations. Every finding carries its evidence, a confidence grade for who owns a name, and a repair with a risk grade — verify it with a dry-run difference table, or take the individual .patch.yml files that --fix-out writes (never auto-loaded, so picking wrong breaks nothing).