Plugins

DSH session workflows for packaging verifiable capsules, evaluating reusable Skills, and comparing controlled session trajectories.

Context compaction / headroom for DeepSeek Harness — compress the live context so the prompt stays small without losing the state that matters (layer 3).

dsh port of the shared handoff kit: handoff and task-id-bootstrap skills plus host-side automation — baseline state injection, per-turn snapshots with an Auto Log trail, task=<id> routing, continuation re-injection, a compaction guard with clear-required alerts, and read-only subagent handling — all writing the same .agents/state/ as the Codex, Claude, and pi editions for one-repo multi-agent handoff.

Serves the obra/superpowers skill catalog to the harness and injects its using-superpowers bootstrap as a persistent, compaction-safe system-prompt section.

Tree-shaped Markdown knowledge base for DSH agents: kb_list/kb_read/kb_write tools, tree/node HTTP routes, and a browser panel companion.

Voice control for the DSH web composer: push-to-talk speech-to-text into the input box (with optional auto-send), spoken playback of assistant replies via the Web Speech API, right-click settings popover, and a global Ctrl+M hotkey.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Switchable web-search provider for DSH: native DeepSeek web search or an OpenAI-compatible custom backend. Installation automatically routes DSH web searches to the plugin; only provider, API key and model are required. Published on npm as @lp181818/web-search-advanced@0.1.3.

Algorithm learning toolkit syncing Codeforces and AtCoder submissions, profiling weaknesses, generating AI training plans, and tracking spaced-repetition reviews across a 114-lesson algorithm curriculum.

From chat to canvas to artwork — drive ComfyUI as a visual workflow IDE inside DSH. Embed ComfyUI (local or cloud) as a split-screen canvas in DeepSeek Harness Web: the agent sparks ideas, writes prompts and scripts right in the chat, applies them live to the canvas in front of you, and produces images, music, video, and 3D. From idea to finished output without ever leaving the conversation or switching front-ends: Canvas ops — compose and arrange pipelines, read/write workflows, edit nodes, wire links, run, tune parameters, and debug errors, all live and WYSIWYG on the exact canvas you are looking at; Production tasks — batch parameter sweeps (batch_run) and automatic output-image retrieval back into the chat (get_outputs), powering multi-modal creative and batch generation across images, music, video, and 3D; Environment upkeep — one-click launch of ComfyUI and one-click upgrade of the core plus every custom node (upgrade), keeping the stack healthy without interruption. This package is the DSH-side plugin, and it ships the ComfyUI-side bridge node too.

Realtime Avatar (realtimeavatar.ai) for agents: the developer API key held by the harness credentials store, the public docs as five on-demand skills, rta_* tools over the public REST API (balance, avatars, clips, sessions, usage) with approval-gated credit spending, and a /rta command that walks a developer from no key to a live avatar call.

Drag-and-drop enhancer for the composer: drop .md/.txt/.markdown to inline small files into the draft or save large ones to .dsh-drop with @-references (Shift forces inline), and drop SKILL.md packages to validate frontmatter and install them to project/user skill roots with one click - effective immediately via the skill watcher.

Single-file persistent companion memory: interests, preferences, tasks, and past works summarized into the system prompt, with read/update tools.

Session-memory autopilot: watches DSH sessions and extracts OKF entries in-process through the harness LLM (ctx.llm, deepseek-official by default) at idle, commit, compaction and end checkpoints, storing them via the vault MCP server.

Project-level Local Context Engine for DeepSeek Harness: retrieval/compression/prioritization over history, code, files, user preferences and agent trajectories, producing a dynamic context window for any LLM.

A /remember command that writes facts into the AGENTS.md instruction hierarchy dsh already loads, plus a Memory tab showing which instructions the loader kept within its byte budget.

Temporary workspace for DSH web — one click creates a throwaway workspace whose conversations are deleted at the next restart (immediately or after a delay, optionally behind a confirm dialog). Pin a temp workspace to keep it: its files move into the folder you pick, its title becomes that folder's name, its conversations migrate, and a real host-level restart re-indexes them.

Daily rotating anime companion persona: deterministic date pick from JSON character cards, roster/reroll tools, and a voice-map route.

Sakura theme, companion notifications (approval/job/answer), message read-aloud, and voice settings for the DSH web GUI.

Real-time token estimates for the DSH conversation composer, combining the current context baseline with the draft and showing exact or heuristic counts.

Shows MiniMax Token Plan usage beside the DSH Web UI model selector with compact 5h/7d bars, click-to-refresh, automatic idle and heartbeat refreshes, and endpoint fallback. Reuses subscription keys configured under Settings → Model and appears only for MiniMax Token Plan providers.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Composer button that opens a panel listing every skill available to the current session with Chinese titles, purposes and usage examples, and lets you catalogue newly installed skills in one click (saved locally).