Plugins

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Six engineering skills for Claude Code and DSH: research, architecture scouting, implementation orchestration, three-axis diff review, complexity audit and mutation testing. Skills delegate through the host’s generic subagent tools when available.

Adaptive model routing: per-request complexity classification with automatic provider routing.

Forensic analysis of past model-routing decisions. Replays each session, classifies every turn's task complexity from its request shape (deterministic, no LLM), and reports two kinds of waste: an expensive model on cheap work (the difference is measurable), and a cheap model on expensive work that failed on its own merits — where every retry re-sends the whole context, so the downgrade cost more than the upgrade. Distinguishes provider-capacity retries (RATE_LIMIT/TIMEOUT/TRANSPORT) from model failures so it does not cry wolf. Derives routing rules from the evidence, priced against a built-in per-million table.

English-only fork of dsh-model-router. Routes each agent step across a configurable model pool and adjusts reasoning effort based on task complexity, tool failures, and cost.

Shows per-turn changes in cyclomatic complexity, cognitive complexity, and maximum nesting depth for TypeScript, Python, and Go in the Web UI, with expandable file and function summaries for code review.

ArcVista 观界 —— DSH 内的架构观测台：本地项目、Git 克隆或批量 Git 导入，架构图、安全守护、知识图谱、复杂度与快照对比

An Auto toggle next to the model selector that schedules reasoning_effort per request: complexity is scored by a MiniMax/OpenAI-compatible model with a zero-dependency heuristic fallback (fallbacks not cached), effort ladders adapt to each model real effort list (low/high/max, low/high/highx/max/ultra, ...), heavy tool calls upgrade the tier within the same session, the lit button and reply badges show the effort actually used, and every decision plus observed token usage lands in a JSONL ledger. A standalone-button fork of imkingjh999/dsh-adaptive-effort; do not install it and the original in the same profile.

Reasoning-mode routing plugin for V4 Flash on headless: w7 persona anchoring, first-turn tool anchoring and complexity-dispatched guidance.