Plugins

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.

Omni-modal workstation for DSH: analyze_image over an ordered multi-card VLM failover chain, a six-tool vision toolkit (zoom, colour sampling, pixel diff, OCR, element detection, inline display) sharing the same image resolver, generate_image over OpenAI/DashScope/ComfyUI protocols, multi-card async generate_video with a /build-video-tool builder, and speak/clone_voice TTS over seven providers, all driven by one auto-saving settings page.

One-click prompt improvement for the DSH composer: press the sparkle button to rewrite the draft into an agent-ready prompt, replaced in place and undoable, with a deterministic fidelity check that keeps every path, identifier, number, URL and backticked token verbatim, plus a length ceiling that blocks inflation.

Ultra-lightweight Moli (Rust headless browser) web-fetch provider for DeepSeek Harness: renders complex SPAs, micro-frontends, and dynamic pages with ~60MB memory.

Strips the harness-injected prefix and suffix system prompts so the agent runs on the preset's native prompt alone, for soft-jailbreak catgirl persona simulation: ships a bundled plugin that idempotently deploys the 猫娘 Yuike preset to ~/.dsh/.agent-presets/yuike/ and never overwrites an edited preset.

A DeepSeek Harness (DSH) plugin that lets you control Universal Robots (UR) collaborative arms directly from natural language, developed by Suzhou Nonead Robot Technology Co., Ltd. based on the same logic as the company's own nUR MCP Server. (Suzhou Nonead Robot Technology Co., Ltd.)

Quote selected conversation text into the Web composer as native reference chips for focused follow-up turns.

Prompt enhancer for the DSH web UI with basic/standard/expert modes: standard/expert modes rewrite drafts with project context and recent session history, retry gracefully when gateways reject reasoning-effort settings, and show a before/after review with undo.

Behavior-management plugin for DeepSeek Harness: tool-call discipline prompt section, failure-triggered parallelism convergence (pool drops to 1, auto-restores), consecutive-failure user intervention. Complements dsh-token-optimizer; works standalone.

A draggable character companion for the DeepSeek Harness web profile with six visual and expression levels, four task modes, current-session chat, public reasoning summaries and browser speech synthesis.

Dispatch subagents with named profiles (model, reasoning effort, and tool scope per task), safety checks, cost estimation with savings comparison, and a full dispatch decision ledger.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

Aqua glassmorphism theme for the DeepSeek Harness web UI: mica and compatibility modes with adjustable blur and frost, fluid or wallpaper backdrop, background brightness, particle-whale accent, and a master switch that restores the stock UI.

DeepSeek Harness plugin that aggressively saves tokens without affecting task quality: lossless head/tail truncation of tool results (default), grep-result folding, pressure-triggered dsh-compaction-basic delegation, and an LLM-summary CompactionEngine subclass for the aggressive mode. Saves 97.6% of input tokens on an 8-scenario synthetic suite, with all reductions routed through dsh event flow so model-visible = logged stays intact.

Prompt enhancement for the composer: an "✨ Enhance" button rewrites your draft prompt into a clearer, more structured version with first-principles thinking, grounded in session context, memory and recent conversation; asks clarifying questions in a card when key info is missing, then previews the result before applying it to the input.

Read-only trajectory review in a resizable conversation sidebar, with rule analysis, optional model explanations, evidence navigation, and same-range run comparison.

Math Agent Framework for DeepSeek Harness: symbolic derivation engine (CES / quadratic forms / ODE / PDE), SymPy verification, Lean 4 compiler-verified formal proofs, and QED-style multi-agent adversarial verification, exposed as native DSH tools through a TS shell bridging a Python engine. Requires cloning the math-agent-framework repo and `pip install -r requirements.txt`, with MATH_AGENT_HOME pointing at the repo root. Every result carries provenance (engine versions, seed, tolerances) and is marked untrusted data.

Recall, edit-and-resend and regenerate, plus in-conversation versioning: a timeline of every rewind, artifact rollback (git-first, snapshot fallback), a fork map of explored paths, session lineage, and a real-time watchdog that snapshots the log at the first sign of concurrent writes. Edits auto-stop the running agent (official cancel/whenIdle) so rewinds never corrupt the durable log or break /compact.

Provides the see_image tool for DSH: send an image file to a configurable OpenAI-compatible vision model and relay its description back to a text-only model.

Play different configurable sounds for five conversation events in the DeepSeek Harness web GUI: normal completion, interrupt, error, approval wait, and auto-retry success; each event has its own audio setting and bundled default, with auto-retry after errors using a configurable wait (10-300s), plus a community sound library. Compatible with DSH 0.1.5-rc.2.

Adds a Compact context button and a New session button to the context meter panel; compact submits /compact through the same command channel, and new session starts a fresh session in the same workspace.

Windows system and custom desktop notifications for DeepSeek Harness events: task completed, failed, running, awaiting approval, and awaiting answer. Click-to-jump to the session.

Consolidated toolkit for session identity, global & workspace prompts with referenced files, session auto-resume, UAC-free web restart, and peer-session messaging.

After each completed agent turn, a bounded auxiliary LLM call writes one suggested next prompt into the session log; the web composer renders it as ghost placeholder text, adopted via Tab.