Plugins

Multi-model orchestrator: the main brain decomposes complex tasks and dispatches subtasks to GLM / Kimi / Qwen sub-agents by each model's strengths, with per-model token usage.

Fills missing context window, max tokens, thinking levels, and image input on custom DSH models from models.dev, and lists unmatched models for manual edits.

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.

Edge breathing border showing DeepSeek peak/valley hours, with flowing light and scheduled push reminders.

A Mimi desktop companion for DSH that follows work-session states with animated reactions and bubbles, provides a separate chat mode, and bundles Windows Computer Use for observing and controlling desktop windows.

Blocks edit/write writes that contain characters matching configurable regex rules, executed before the tool runs, with configurable messages and same-turn pwsh propagation; default rule matches full-width parentheses.

Git view for DeepSeek Harness: status, commit graph, branches and tags in one picker, diff, staging/commit, push/pull and blame.

Runs one-time and RFC 5545 recurring Agent tasks in fresh DSH sessions, with visual schedule editing and session-linked history.

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.

Governed long-term memory for DeepSeek Harness: append-only evidence ledger with write guards, 7-tier authority claims, supersede chains, and budgeted pre-step injection with per-domain quotas.

Token-efficient persona runtime for DeepSeek Harness with local catgirl rendering and progressive tool-schema disclosure.

Lightweight Markdown conversation theme plugin — enhances native color scheme with 4 built-in themes (light/dark dual), user-defined CSS themes, system-aware auto-switching, in-browser theme editor, designed to enhance reading speed and clarity.

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.

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

Tokenrhythm (基元律动) finance dashboard for DeepSeek Harness: account balance & expiring credits, category-filtered model price cards (with discounted prices), service status and platform key management; login via platform account or session cookie — credentials stay on the local host.

Personalization for the agent: a Web UI panel (about-you, reply style & tone, traits for headings/lists and emoji, output language, custom instructions) and `/soul` commands, with nickname/occupation/bio/style/traits/language compiled into a system prompt and re-injected into active sessions. Exposes `soulConfig` for other plugins and a `set_persona` tool the agent can call.

Phone access to DSH over a self-hosted relay (WSS via your own TLS-terminating proxy): bundle plugin with bridge supervisor and QR login, a native Android app, and server-side device revocation.

OpenCode Go subscription chat for DSH with per-model Completions, Responses, or Anthropic protocol selection, model discovery, context, vision and thinking metadata, effort defaults, and usage meters.

Three-pane workspace layout with file-tree browsing, file editing, a non-linear conversation mindmap view, and mobile mode support.

Switch the language of the agent's thinking/reasoning process (chain-of-thought): 简体中文, English, Русский, Français, Deutsch, Español, 日本語, 한국어 and more, or auto-follow the system locale. Adds a Settings → General row, a system-prompt instruction (per-prompt assembly, applies to new sessions), and the /thinking-language command.

Academic literature search and citation tools for DeepSeek Harness: paper search via Crossref and OpenAlex with no API key, related-works discovery, and citation formatting in GB/T 7714, APA and BibTeX.

A low-interruption Big Fat Fish companion plugin for the DeepSeek Harness web workspace

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

Research-debt guard for DeepSeek Harness: nudges coding agents to search docs, GitHub and the web before repeated local trial-and-error.