Plugins

The official billion-context plugin: a context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).

Persistent multi-model squads configured in Settings and selected in the Composer, with per-member model and tool policies. By default the lead Agent completes simple work itself and delegates only when the saved squad is needed; delegated work runs as a bounded DAG with optional review and repair. Run Center tracks retries and per-member tokens from official Harness usage events.

Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.

Installs with 25 engineering and productivity skills bundled (mattpocock/skills v1.2.3), no manual skill installation needed. Built with 30 billion tokens. This plugin delivers 10x development efficiency on top of the original skills. GitHub issues are the main supported backend; Markdown is a preview; GitLab is not supported yet.

DeepSeek Harness control center for official balance monitoring, per-session costs and tokens, third-party token totals, completion alerts, official recharge, flexible layouts, and agent-assisted session controls.

Sidebar billing dashboard: real usage aggregated from session logs (per-model and per-day calls/tokens/cache), cost estimated in CNY from a current multi-provider pricing catalog, subscription-plan (coding/token/agent) routes exempt, and per-provider health dots.

Coding-subscription OAuth for SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code and Claude Code, plus an opt-in loopback OpenAI/Anthropic gateway: local login without pasting tokens, AUTH refresh-and-retry, grok-4.6 xhigh, and API-key route coexistence.

Git-style dot timeline on the right edge of the DSH web UI: one dot per user message, hover for content and metadata (time, turn, duration, TTFT, tokens), click to jump. Also adds a full-session message list, in-session and cross-session search, bookmarks with #msg= deep links, and keyboard navigation.

Mobile remote control for the dsh web GUI: scan-to-pair QR entry with one-time pairing tokens.

Design-aesthetics skill pack (10 styles: dark SaaS, minimal white, neumorphism, brutalism, glassmorphism, Japanese minimal, bento grid, cyberpunk, vaporwave, art deco) with runnable landing-page demos: tokens, component rules, forbidden lists, and acceptance checklists per style.

Token-cost pipeline for DeepSeek Harness: pressure-aware layered compaction (lossless projection below 40% context pressure, LLM summarization above), per-agent tool allowlisting, long-text-to-image with vision summarization, and a /token-status command tracking pressure, tiers, and saved tokens.

Zero-residence context engine: large tool payloads are evicted out of the live context into a queryable store and only deterministic pointers are left behind, so per-turn prompt tokens stop growing with the transcript. Any masked content is reconstructed verbatim from the session log on demand, by tool-call id or session seq.

Route eligible shell commands through rtk to compress tool output and save tokens.

Plugin coordination layer: plugins declare their capabilities, commands route to the owning plugin without a model call, tool schemas load on demand to cut prompt tokens, run history consolidates into long-term memory while idle, and failures are classified before any retry.

Per-call cache billing inside the context-meter popover: current step, round and session totals with hit/miss/output tokens and amounts, automatic Beijing working-hour peak/off-peak pricing, per-model rates, and third-party relays billed too.

UI harmonizer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens — with live-customizable chat width, markdown font size, workspace scale, UI font stack and a rounded center-column card from Settings → General; client-only dsh bundle, zero model cost, no host side, removable without residue.

Web UI polish layer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens; live-customizable chat width, markdown font size, workspace scale and UI font stack.

css-in-js styling kit (styled / Token / Styling) for the forked conversation UI: consumes the official --dsw-* design tokens, so no CSS Modules precompile step is needed.

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.

Deterministic context compression for dsh — zero LLM calls, rule-based pruning that preserves paths, commands, error traces, and open todos verbatim. Compresses ~80k tokens to a few hundred.

Burned DSH tokens become incense; spend one stick to raise or lower today's case. The case updates daily, Liangwei decides today's Liangzi, and the result is archived at day end.

Header quota badge plus a usage-monitoring tab: live balance/quota remaining and reset countdown per provider, with requests, tokens (input/output/cache-read/cache-write), cache hit rate, estimated cost and average latency tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

Settings card for the DSH LLM auto-retry engine: tune retry count, backoff and jitter live from Settings -> General, with configurable retryableCodes chips - defaults add INVALID_REQUEST so OpenAI-style HTTP 400 reasoning_text errors in thinking mode get retried automatically.

OAuth 2.1 MCP client for Streamable HTTP servers: add a connection in Settings, sign in through the browser (PKCE with dynamic client registration), and have its tools registered in DSH, with tokens kept in the credential service and the connection written to the profile.