Plugins

A dsh-better-sidebar tab that statically parses Qoder Canvas `*.canvas.tsx` files into structured pages in the DSH right sidebar (the source is never executed: no eval, no bundler, no sandbox iframe), with a file-viewer takeover for `.tsx` and a bundled Skill for authoring the format.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Top-right status plate for six session states (complete, error, approval, question, unopenable, subagent), plus an OS notification when you are away.

Discord-like communities in DSH with channels, roles and permissions, message search, and sharing or cloning of DSH sessions.

Multi-channel notification plugin for DeepSeek Harness: dispatches in-page toasts in the foreground and PWA system notifications (Service Worker) or browser notifications in the background, with per-event toggles for task complete, approval request, question, plan review and errors, persistent notifications, and Web Audio synthesized alert sounds without audio files.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

A local-first personal state record and decision engine for dsh: keeps every input byte-for-byte with line-level provenance, argues against its own conclusions by generating defeaters first, ages each stored fact with its own TTL, and reports where a decision rests on nothing at all.

Merges other sessions' context into the current turn: evidence-weighted conflict resolution, retraction of claims whose premises were retracted, trust labelling that resists cross-session prompt injection, and budget-bounded packing. Ships a benchmark.

Shows a Chinese translation under each English thinking block in the DSH web chat, without modifying the session transcript; per-chunk caching, a configurable translation model, and a settings panel.

Plugin-author upgrade skill for DeepSeek Harness: one package carrying a corridor index, which detects the caller peer band and routes to the closed corridor card that matches it (0.1.3-alpha.1 -> 0.1.5-rc.1 as legs A+B, 0.1.5-rc.2 -> 0.1.6-alpha.2 as leg C), plus a zero-dependency seam scanner shipped as a bundle skill and an npx CLI.

Turns the MacBook keyboard Caps Lock light into an agent status light: on while the agent works, flashing when it waits for your approval or answer, off when idle.

Distills session work into background observations and reflections to preserve context across compaction.

Live progress bar under the composer with a percentage and an estimated time left for the current DeepSeek Harness turn; the estimate re-anchors as the turn runs and never reads 100% until the turn ends, and the bar turns red when the turn fails or is interrupted.

Forwards an unattended DeepSeek Harness run's tool-call approvals and ask_user_question prompts to Feishu cards on your phone. The desktop GUI answers first — a card is only sent after `delaySeconds` (120 by default) with no answer there — and a phone approval grants `allowed-once`, so no authority accumulates on the phone. One outbound WebSocket long connection to Feishu: no public IP, domain, tunnel or relay.

Mind-map project planning with blocking drift protection: plans, modules and tasks as a dependency DAG with topological execution order, an agent position marker, a human approval gate on every board edit, git cross-checks, and evidence-gated task completion.

Runs a thesis-antithesis-seal debate whose verdict is computed from real command exit codes and case counts, never from agent prose.

Plays a voice line or a sound when a turn finishes and a failure cue when a tool call or a turn errors — user aborts stay silent by default and subagent sessions are skipped, both configurable. Three alert modes: voice, effects, or off. Effects is the default and ships 20 built-in sounds (10 alert chimes + 10 nature), each assignable to the done, fail or approval event with per-row preview, so it needs no API key and no audio files; the voice route uses Volcengine TTS with cloned or preset voices, batch-imported voice IDs and fingerprint reuse that skips re-synthesis when text, voice and parameters are unchanged. A third approval slot exists but has no automatic trigger — it only plays when called manually. Playback goes through winmm/waveOut as-is, never changing the system volume or mute state, and the player is spawned detached so session teardown cannot silence it. Windows only.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

SQLite memory entries, a calendar with due-time reminders, and cron-scheduled agent tasks, with 13 model tools and a bilingual zh/en UI.

On-demand memory for DeepSeek Harness: session logs are distilled into layered markdown (a summary, an index and per-topic files), and a mem_query tool returns only the matched entries rather than the whole index. Nothing is injected per turn, there are no dependencies, and every entry keeps a source pointer back to the conversation it came from.

Wishing House theme skin with warm amber glow, live moon phases, meteors, typing sparks, procedural chime audio, and daily fortune slips.

Windows system-drive (C:) cleanup for DSH: rule-based scan, five-tier safety grading, a staging area with a rollback ledger, UAC elevation, and migration to another drive — a model tool plus a Web GUI panel.

蒸馏主管（distillation-director）：把一本书蒸馏成可执行 Agent 技能的判态制元技能（V4.6：V4.3–V4.5 防坑体系与判官工作流之上，增 §21 **强制门禁**——gate_start 开工自证闸（手册哈希＋条款逐字抄录＋执行单＋机器层＋官方模板）／gate_stage 阶段依赖链（前阶段未过不得进入）／preflight 自动纳入活跃蒸馏任务）

DSH RedTeam 模式：一句话拉起红队作战智能体（资产测绘 / 攻击链 / 得分目标 / 报告 / POC 知识库），含四个角色、13 个原生技能与常驻右侧控制台