Plugins

Review agent file changes as a dsh-better-sidebar sidebar tab or chat turn-tail row — line-level diffs and undo.

Mobile UI shell for the DSH Web GUI: turns the desktop three-column layout into a touch-friendly phone layout (overlay drawers, draggable FAB, full-screen dialogs, infinite-scroll history) under a 1024px viewport, with zero desktop impact. - Complete mobile PWA for DSH, built on dsh-mobile-gate: secure remote-access gateway plus install-to-homescreen (manifest + service worker), offline capability, touch gestures (pull-to-refresh, edge-swipe back, pinch-zoom font), agent-done push notifications, and touch-first layout — desktop unaffected.

Restart recovery for DeepSeek Harness web: after a crash or restart, an interrupted agent turn continues automatically (host-side agent/created listener, no browser timing races).

Clickable file paths in DSH replies: Codex-style inline open, reveal in file manager, and a mentioned-files chip list at the turn tail.

Adds /review, /review-status, and /review-cancel to spawn an independent native subagent that inspects a chosen Git scope (base branch, uncommitted changes, a commit, or custom instructions) and returns a findings report in the current conversation, with English or Chinese output from the host locale.

Turns the DeepSeek Harness agent into any character: a global cosplay switch, SillyTavern v2 role cards with JSON import/export, a neutral/role thinking-style toggle, and natural-language card authoring via a built-in skill.

Host-level proactive wake-ups for DeepSeek Harness: the model schedules its own alarms (once, recurring interval, or cron, with optional random jitter), cold sessions are woken on time by session resume, model-initiated follow-ups are gated by quiet hours and a daily delivery budget, silent wake turns end with proactive_reclaim and fold out of model context as tombstones, declared schedule files glob-sync JSON schedules into host alarms idempotently, min_idle_seconds defers wakes until the destination session quiets down, and a web panel (settings section plus per-session tab, SSE live refresh) manages alarms and wake history — the heartbeat engine for AI companions and roleplay characters with their own daily routines and world evolution.

AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.

Low-cost video understanding tool: a video_understand tool turns a Bilibili link / BV / local video into an AVIS info layer (ASR + scene structure + object tracks + YOLO labels) and returns summary + Q&A. Question-driven dynamic routing across layers (L0 ASR / L1 object tracks / L2 key-frame VLM), semantic-layer reuse for repeat questions, per-question budget cap. Python engine: core layer needs faster-whisper / opencv / yt-dlp (~200-300MB); the optional semantic layer adds ~2GB of torch / transformers / ultralytics. A bundled doctor --fix sets up the venv and installs both.

Codex-style turn folding for the DSH Web UI: keeps final answers visible, groups consecutive reasoning and tool activity, and shows configurable live duration, tool-call, and token metrics with multilingual summaries.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Replaces the stat-bar output speed with two figures, for example 207(122) tok/s: outside the parentheses the decoding speed after the first token, inside it the speed over the whole request including first-token latency. Clicking it opens a breakdown of turns, steps, TTFT and per-phase timings. It replaces the native session-stats item; needs DSH 0.2.1-rc.5 or newer.

A GPT/ChatGPT-persona desktop pet pinned to the bottom-right corner of the DSH web GUI — shows balance, today's usage, peak/off-peak pricing and per-turn cost, with editable bubbles (text, balance, usage, pricing, images, random lines and weighted choices), per-line styles and fonts, a floating quick editor, sound effects, custom character art/animation/audio, and snapping/flipping. 54 GPT-flavored lines across five groups. Its routes, bundle id and data files are namespaced so it can run alongside the whale and Xiaoke widgets. A derivative of MeteorNOX/DeepSeek-Balance-Whale-Widget (MIT).

Connects Huawei Cloud CodeArts to DeepSeek Harness with built-in OAuth2 sign-in (PKCE + DPoP) or a pasted token, after which CodeArts models are available in the DSH conversation window. Reads per-account credit balance, expiring credits and daily check-in from the CodeArts credit API, counts requests and tokens locally, and shows a per-account credits popover under the chat input box; the credits line and the upstream queue hint can each be turned off in settings.

Turns a one-line DSH draft into a complete task brief (role / goal / constraints / output format). The engine is a byte-verified port of linshenkx/prompt-optimizer (three modes, 10 templates identical to upstream); history is consent-gated with version chains and structural comparison; every run reports its token usage. Nothing is written back or sent without a click.

Project documents and long-term memory as plain Markdown in a dedicated Obsidian vault: six mem_* tools (search, read, write, log, brief, admin), one budgeted recall injection at the first step of a session, and automatic distillation of completed turns. Obsidian does not need to be running, and the vault stays readable with the plugin uninstalled.

Per-event sound notifications: turn completion, approval, question, plan-review, goal-blocked, and task-failure each get their own sound and volume, configurable in the Web UI (built-in synth, mute, or local audio file).

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

DeepSeek Harness's own fast mode: the same model on the same reasoning effort, fewer output tokens, all prompt-side. Only the output-discipline switch is on by default (late mode, active from step 4); every other switch is off and can be enabled on its own; turn on the tool-output trim switch when tool output is long. Measured on one machine, not a leaderboard: 30 task pairs with long output at the trim switch 0.756x wall clock and 21% fewer output tokens; 24 pairs on 6 real pallets/click PRs 0.805x and 23% fewer. On official SWE-bench Lite instance definitions with a self-built harness it does not show a gain (8 instances, three independent runs pooled to 72 pairs: 0.933x wall, 0.903x tokens, wall still crosses 1; single runs of the same configuration differ by 30%), and stacking switches on top of the trim switch is worse than the trim switch alone. Numbers and repro in the repo.

Adds supplemental request retries, turn auto-continue and a no-response watchdog on top of built-in dsh retries, with a live countdown banner, toast notifications and a usage dashboard.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Writing tools that remove AI-sounding patterns and match your personal voice. 8 deterministic tools scan text, build a style fingerprint from your samples, and return rewrite briefs.

Runs isolated install-and-smoke test drives for DSH plugins in throwaway profiles, returning structured pass/fail records and batch matrices without touching your real profile.

A floating desktop pet for the DeepSeek Harness Web UI: idle breathing, occasional direction turns, random actions, and screen wandering.