Plugins

Requires DSH 0.1.6-alpha.2. Annotate completed assistant replies, submit multiple drafts with official composer text and attachments as one Session message, navigate linked model replies, and use Settings to hide selected reasoning or tool details without changing stored events.

Long-term cross-session markdown memory with an LLM-Wiki structure and a SOUL.md persona, injected at session start (by default only after the first user message and only in the active session), plus remember/recall/consolidate/forget workflows, an embedded memory skill, pack/unpack migration tooling, and an idle-time first-person recall nudge that surfaces real memories in a companion voice. Also gives the store observability and upkeep it lacked: a per-file boot-block budget that keeps the index routing table from being truncated, automatic last_access stamping so salience decay actually works, a read-only memory health dashboard (size, freshness, lint-parity checks), a declarative index compiler (pages declare summary:, one command re-lines the index), an interactive memory graph (page links plus shared tags, draggable, wheel zoom), structured queries (tag/type/salience/hot/stale filters), cross-link suggestions for pages that have no relationship yet, and a `checkup` report that ends in a prioritised action list. The boot payload was also cut by ~23% by moving operational detail into the on-demand skill.

A balance and cost widget for the DSH web GUI: a sidebar footer card shows the account balance, a remaining-ratio bar and today costs; clicking opens a four-tier cost breakdown (last prompt / this session / today-this-project / today-all) with term explanations and a one-click top-up link. Zero external dependencies, works on Node 24.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Multi-channel IM bridge for DeepSeek Harness: route WeChat (ClawBot/iLink), QQ, and Feishu (Lark) chat messages to a DSH agent and relay its replies back, with per-channel sessions and reply dedup.

Cross-session archive: overview workbench, folded timeline, subagent lineage, full-text search, rule+LLM summaries, ZIP export, live tracking. Native session-page embeds: turn rail, docked right panel (live mode, pinned to original session on switch), rename (official-synced), conclusion digest, health monitoring + persistent header chip (idle / active / tool-wait / stalled). dsh v0.1.2+: fuses with the official TurnNavigatorRail — vector-icon info chips (duration, tool calls, errors, thinking) plus lazy tool distribution inside the official preview card, right-click opens the workbench; the classic piano-key strip is on by default and delegates unloaded-turn jumps to the official auto-load engine; the official rail can be hidden entirely. Settings dialog section with 10 tunable behavior params.

A desktop pet plugin for DeepSeek Harness (DSH): import Codex-style sprite-sheet pets and render them in the DSH Web GUI as a floating shell.overlay, with a pet library, interactions, and Agent-state linkage. / DSH 桌面宠物插件：导入精灵图序列帧宠物并在 Web GUI 悬浮渲染。

Side web-preview panel: local static hosting, Markdown/code/image preview, one-click run of non-static projects (Cargo/npm/Go/Python) with live logs, drag files into the chat (saved to the workspace), element mark & annotate, workspace file search on 404, and link-click takeover into the side panel.

Circuit breaker for idle agent turns: watches agent/assistant-stream and cancels a turn that produces only reasoning — no text and no tool call — after 45s, after 80000 reasoning characters, or on a degenerate repetition pattern (exact repeat unit, sentence-template repeat, sparse repeat, or 6-gram density). On trip it injects a continue instruction that requires the next action to be a tool call, and ships 11 regression cases plus per-gate tuning.

Persona engine for DeepSeek Harness: one config.json drives the AI's self-name (per model, per tier), how it addresses you, relationship stance, character text, per-item work contracts with individual toggles, thinking-chain language, appearance and reply tone (both opt-in and per-model overridable), and long-term memory gated by human confirmation - the AI can only append proposed candidates, a human confirm line flips them into effect, and the log is physically append-only and replayable. Confirmed entries are injected as a quoted data-not-instructions block; entries tagged with a kind can instead be routed to arbitrary files on confirmation and never reach the prompt. Three prompt sections re-evaluate from disk on every assembly, so edits apply on the next step with no restart. Persona presets are shareable JSON snapshots (imports and exports SillyTavern character cards, v2/v3 read, v2 written) and deliberately never carry memory. Zero runtime dependencies, no network, no shell; any error degrades to an empty section rather than a broken session. Ships blank - installing changes nothing until you write something.

Model switching and reasoning-effort control for DeepSeek Harness: set_model and list_models agent tools let the agent autonomously change its provider, model or thinking depth (reasoning effort) mid-task with a mandatory reason, a provider whitelist and a context-window token-pressure guard, the active model is injected into the runtime context, and Plan Mode auto-transition switches to a configured planning model on entering plan mode and restores the previous execution model on exit.

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Reasoning-wait thinking indicator for the DeepSeek Harness web composer

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes you can open in Obsidian; query your history, browse recent reads, or search your own Obsidian vault and link related notes to a reading record. Nine tools, a /codevault command, and a code-reading skill.

Xianxia desktop pets linked to live agent sessions: MC pixel-style companions appear when subagents spawn (up to 3 on screen), with storage-bag collection, a right-click artifact menu, a pet gallery picker, and export to the Codex desktop-pet format.

Registers the MathWorks MATLAB/Simulink MCP server into a dsh profile, so agent sessions get mcp__matlab__* tools for running MATLAB code and reading, editing and testing Simulink models.

Folds Think and tool-call rows into a floating summary pill with red failure counts, for a cleaner writer-friendly chat view.

Compaction fix for NInfer-hosted qwen3.8-27b gateways: disables thinking on dsh context-compaction and session-title calls so xhigh reasoning stops burning the whole output budget; the same idea applies to other launch methods, this package targets NInfer only.

Local long-term schedule panel: top-bar "日程" text button, today/week/history month-calendar views with stats, completion checkmarks with per-day history, schedule↔conversation links with click-to-jump, recurring tasks (daily/weekly), optional auto carry-over for unfinished one-time tasks, and dailytask_* agent tools.

Markdown viewer for the dock workbench: GFM rendering with DOMPurify sanitization, document outline and relative-path image/link resolution, with one-click switch to editing.

Smooth comet-mode animated caret for the DSH Web composer: a glowing comet trail replaces the native blinking caret and glides across the input as you type, with configurable accent color, thickness, and trail, IME-aware for CJK input.

Task-scoped Workspace to Task to Session control center for DSH Web, with Session boards, archived conversation viewing, and bounded long-term memory shared across linked Sessions.

Adds COS storage browsing and transfers, workspace artifact uploads, temporary links, and conversation attachments that retain local copies with cloud object identity, plus Agent tools for Tencent Cloud COS, CI, and MetaInsight.