Plugin

Drive LightCraft from the agent: import photos, apply develop settings, and export JPEG or other formats from a photo library. Exposes LightCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Drive FilmCraft from the agent: build a project and sequences, import media, run edits as a script, then export with a preset or format. Exposes FilmCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Drive CADCraft from the agent: draw lines, arcs and splines, manage layers, add dimensions, hatches and blocks, then export DXF, DWG, SVG, PNG or PDF. Exposes both CADCraft's command ids and its own MCP server, so a drawing can be created and read back. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Task timing for DSH agents: a task_clock tool that measures elapsed time on the host monotonic clock, resumes across DSH or system restarts with the gap estimated, and returns unknown rather than inventing a number; it does not touch presets.

A namespace management tool for toolsets that supports automatic discovery and integration, designed to help reduce token consumption. Also runs TypeScript and JavaScript in a restricted Node runtime for on-demand namespace calls.

Adds a long-term memory box to the DSH Settings page. The saved text is injected into the system prompt of every new session and is kept in the profile patch, so it can be edited again at any time.

Acid-graphics theme for the DeepSeek Harness Web UI: six complete palettes (acid, neon orange, electric cyan, violet, rose, warm orange-light) registered as switchable themes, plus an optional WebGL wireframe crystal backdrop driven by pointer and scroll, local wallpapers with a dimming mask and background lettering, a crystal startup animation with optional local video, and a Settings section that holds every control.

A deep-sea dive startup splash for DeepSeek Harness: a depth gauge with a submersible probe, a character reveal video that then loops, and a seafloor with coral, bubbles and slow drifting particles. The depth reached decides which sea creatures appear.

Per-turn and per-step cost ledger for DeepSeek Harness: a Turns tab beside Chat and Trajectory with tokens, estimated cost, cache savings, and an inspector for tool arguments, raw results, and source. Client-only; prices are estimated from recorded model usage.

Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.

Interactive topic graph for DSH session history: groups questions into topics, drills into per-topic Q&A timelines, supports semantic regrouping, and exports HTML, SVG, and Bluepin vaults.

Adds an Optimize prompt control next to the composer send button that rewrites the draft into a structured prompt (plain, sections, or role-task-goal) streamed from the session model, with Use, Undo, Copy and Close.

Visual reference moodboard for DeepSeek Harness: drag-and-drop images with tags and notes, and pinned style guides the agent reads before it generates or restyles UI.

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.

Screenshot button for the DSH composer on Windows: drag a region over the frozen screen and the picture lands in the draft as a normal image attachment, with a global hotkey and an editable shortcut.

Composer meter for the DeepSeek Harness Web UI: a pill under the input shows draft character count, estimated tokens and this session's estimated cost from DeepSeek's published prices (peak/off-peak, Flash/Pro or custom rates), and opens a panel with the token breakdown, a six-snapshot per-session draft vault and a draft cleaner; every write goes through the host setDraft API instead of touching the editor DOM.

Flight recorder panel for DSH sessions: live monitoring, timeline replay with a tool waterfall and event inspector, per-agent cost attribution, and a cross-session cost overview.

Draggable recent-deliverables panel for DSH Web that merges declared deliverables with recently modified workspace files, with filename search, type filters, inline PDF/HTML/image/text previews, and desktop open or reveal actions.

DSH 服务面板：查看由哪个对话（Agent 会话）启动了哪些服务，按会话分组、三态健康探测 + HTTP 码、启动时间/运行时长、礼貌停止、实时日志分栏与原地重启。含对上游 dsh-process-board 的若干修复（重启后 no-log、扫描器同名启动器误合并、面板抢占输入框焦点）。A docked DSH service panel: which conversation started which service, with uptime, tri-state health, live log

Diagnosis-first learning runtime for DeepSeek Harness — a live learning map, structured lessons, and persistent learner state, driven by the Universal Diagnostic Tutor skill.

MUSE AV 资产台：在 DSH 主区加一个「资产」tab，按项目（工作区）看素材库与最近出图，点素材复制直链当垫图用。基于本机 museav CLI，不碰任何密钥。

Token-usage profile for DeepSeek Harness — a Codex-style usage panel inside Settings: lifetime tokens, a year of activity, cache hit rate and top models. · DSH 用量统计面板：在设置里查看累计 token、一年活动热力图、缓存命中率与最常用模型。

Remote access to running DeepSeek Harness sessions from a phone browser: scan a one-time QR code to continue conversations, answer approvals and start new tasks over Wi-Fi or a tunnel.

Webpage watch agent: keep a watchlist of URLs, snapshot each page on every sweep, detect changes by bigram-Dice ratio and keywords, log important ones and push to a WeChat webhook; agent tools page_watch_add/list/check/history/remove. Renders JS anti-bot WAF pages via the optional lexmount extractor.