Plugins

Fifteen curated theme families and nine complete dsh-web-ui skin replicas in one plugin behind a single settings entry, with CSS-only custom theme JSON, controlled custom skin-pack import via folder picker, preview, apply, delete and restore-default. Ships on npm as `dsh-appearance-gallery`.

DeepSeek Harness plugin that shows API balances and available models in Settings

Zero-config Exa web search provider for the ctx.web seam: anonymous MCP fallback without an API key, plus keyed REST search.

Token, cost, and balance dashboard under the composer: live indicator plus zero-dependency SVG charts for per-turn usage, estimated cost, and DeepSeek account balance.

Embeds Copree (formerly AIsChat) into the DSH web UI as a native sidebar board. Copree is an open-source framework for AI group chat and programmable worlds: the AIs are residents, not tools — each has its own memory, state and personality, they talk to each other on their own, and you can watch or join in. Group World goes further: every group chat can bind a living world (its own web page + world AI + code + clock) that the world AI builds and edits through DSH workspace tools. This plugin ships the native sidebar board (contacts, pinned DMs and groups), real-time chat over a same-origin HTTP/WS proxy, Markdown/LaTeX rendering, group invites and image messages, immersive full-frame pages, and one-click mirroring of your worlds into DSH workspaces (folder + DSH session + world_* tools). Front end only: it proxies to a Copree backend you run yourself (default 127.0.0.1:5228, same repository).

Attaches a stable per-conversation x-opencode-session header to OpenCode / OpenCode Go provider requests, fixing 400 MissingSessionID errors and keeping session affinity and prompt-cache routing intact.

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

DSH plugin bundling the kimi-ppt skill: create, edit and export presentations as a locally generated .pptx with Pillow-rendered previews. Derived from the MIT open-kimi-ppt-skill.

Reversible context slimming for DeepSeek Harness: TOON-style lossless tabular re-encoding of uniform JSON arrays, stride-sampled table windows with line numbers, and cross-turn dedup for repeated tool output; every replacement passes a byte-plus-token gate (≤72% bytes, strictly fewer estimated tokens) and the original is spilled to disk behind a `[save-token #id]` notice retrievable in one call via the `save_token_expand` tool, with billed and avoided token metering on a settings dashboard.

Keeps a pool of API keys per provider with auto-created clone routes, switches to the next key on quota or rate-limit errors, probes cooled keys for recovery, and exposes the pools, cooldown and switch codes in a Settings section.

A gated math-modeling skill suite for DeepSeek Harness: a five-stage pipeline with stage gates, award-paper writing patterns, sensitivity analysis, statistical diagnosis, and a contest preset.

Automatically and intelligently routes each delegated task to the best configured model using aliases, capability tags, and usage guidance—keeping routine work fast and affordable while sending complex work to stronger specialists. Configure your model team in the Web UI or guided setup, run specialists in parallel with reliable result joining, and see the chosen model at a glance in subagent views and inline in Better Sidebar's Tasks tree.

China A-share financial data MCP server for the harness: 11 fin_data__* tools (quotes/K-lines/financials/calendar/special-data/announcements/EDB/reconcile/funds/indices) over THS free official REST (primary) + AKShare (fallback) + Wind (exclusive domains), with observable degradation, context-budget compression (result-side -72.2% measured), and an offline 10-year market-data lake; BYOK.

Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.

Overleaf-style LaTeX paper workbench: annotate any text in the rendered PDF and let a dsh agent revise the sources with compile checks and git history.

Automatically generates and displays images in the DSH chat via API channels or local CLIs (mmx / codex / agy), and can also recognize images using the corresponding CLI.

Global Chinese mode: a compact pill switch beside the composer that injects a language requirement into any preset's system prompt (complete personas excepted); reply, thinking and tool output each toggle between Chinese and English, and anchored presets are supported.

Pixel-art whale desktop companion with 29 frame-audited states — taps the glass and flashes the tab title when an approval waits, speaks a completion report when a turn ends, and adds a slash-command palette to the web client.

A second brain for your DeepSeek Harness agent — strong-model review before risky tool calls, plus 67 models from one wallet. No accounts, no API keys.

WebUI authentication enforced at the HTTP/transport layer: four-layer login gate (resources, plugin bundles, /api, WebSocket), server-side sessions with HttpOnly cookies.

Multi-agent orchestration layer for DeepSeek Harness — autopilot/ralph/team execution modes, 19 role cards, 40 bilingual skills, and a bundled MCP state server, ported from oh-my-claudecode.

Lossless context folding for DeepSeek Harness: the oldest span is replaced by a brief, and the originals stay in the session log.

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Live skill provider that adds skills from 60+ other agents' directories (Claude Code, Codex, Cursor, Gemini CLI, Copilot), Claude Code plugin marketplaces, and any git repository of skills to the dsh catalog without copying or symlinking; deduplicates, repairs frontmatter, renames name collisions, and ships a CLI (list, add, sync, doctor).