Plugins

Auto-compaction that writes a handoff note first: as a session approaches a token threshold it asks the model to save a project checkpoint into the workspace, then optionally starts a fresh session seeded with a continue instruction and parks the old one. The note must be written within the current compaction cycle and its conclusions section must actually change, so a stale or merely touched file cannot slip through.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Lets one session read, write and run bash across several folders, not just the primary root — additional roots are registered from a sidebar Folders panel or the /workspace-folders command (inherit/read-only/read-write) and share the primary root's file-fence + OS-sandbox authorization; adds no new tools.

Memory in global and per-project scopes: memories are injected into the system prompt at session start, a settings panel edits them with confirmation on write, and the agent gets a read-only memory_query tool (npm: `dsh-my-memory`).

Directed fuzzing driven by an LLM agent: from a target repository and a bug (CVE description, patch, crash trace, or file:line), it runs a PLAN, IMPLEMENT, EXECUTE, REFLECT loop in which the model writes Python input generators, until an input triggers the campaign's stderr-pattern oracle or the campaign stops.

File encoding guard: byte-exact read/write/edit for GBK, Big5, Shift-JIS, EUC-KR, Windows-125x, UTF-16 and UTF-32 files, so editing a legacy file leaves it in its original encoding instead of silently rewriting it as UTF-8; UTF-8 BOM preserved exactly as it was, line endings (CRLF/LF/CR) kept, characters the encoding cannot represent refused rather than written as "?", and non-UTF-8 files listed with candidate encodings so the model can re-read them explicitly.

Bridge Claude Code's .claude/ directories into DSH with zero migration: project and user-level skills, commands, rules (one system-reminder envelope), agent files, hooks (PreToolUse/PostToolUse/UserPromptSubmit/ SessionStart/SessionEnd) and .mcp.json servers, plus Claude Code plugin marketplaces. Ships /cc-plugin for full plugin/marketplace management (claude CLI first, self-implemented fallback), /cc-resume to list and import Claude Code sessions into DSH as native event-sourced logs, and /cc-export to write DSH skills back as Claude Code skills. Two-way Claude Code <-> DSH bridge, versioned and released as dsh-claude-compat.

Tieba (Baidu forum) reader and companion for DSH: reads threads, writes daily digests, signs in, and builds a per-forum style library from high-liked replies. Optional replies to threads or to sub-replies under your own comments are off by default and limited per round and per day. Also ships a read-only MCP stdio server that MCP-capable clients can launch; not tested against specific clients.

Knowledge base as a canvas in the right sidebar: notes are nodes, and nine tools let the model read, write, link and remove them. A node can carry pictures and documents, and reading one returns their text — Office files extracted in place — while pictures can be handed over as images.

DSH input assistant for next-message prediction, draft autocomplete (text completion), and prompt polishing/rewrite. Session-local suggestions; Tab accepts into the draft without sending. Requires a configured model; calls may incur charges. Source-available; modifications require prior written permission.

Cross-session persona and diary for DeepSeek Harness: a local gate decides whether a turn is worth remembering, then one extra model call turns it into a first-person diary entry plus an impression of the user, where every impression carries the specific moment that produced it. Later conversations inject about 2000 tokens of that as a self-memory block in three registers: a persona core, a section for judgements the model wrote itself, and the diary. There is a tool for the model to record a judgement in its own words, and a plain markdown hand-note file the human can write into which the plugin only ever reads. A sidebar panel lets you read, forget or export the archive, and forgetting demotes an entry rather than deleting it, so an old one still surfaces on a strong topical match. Local-only, secrets are stripped before anything is sent, and the archive is a plain folder you can read, edit or carry to another account. Zero runtime dependencies, no build step.

Mobile-first Web UI quality-of-life pack for the DeepSeek Harness: a Chrome-style active-session tab bar, full-screen sidebar swipe open/close, overlay sidebar, collapsed-sidebar recents, keyboard-suppressing session switching, viewport/IME keyboard adaptation, touch feedback, code/table inner scrolling, hidden permission dropdown, a full-screen settings rewrite with tab memory, and a compositor-driven status pulse, no-touch-drag long-press protection — 14 features, each independently toggleable from the Settings QoL section with instant effect, persisted per browser in localStorage; pure client-side CSS/JS, mobile rules locked to viewports of 768px and below so desktop stays untouched.

Noname (Sanguosha-like game) extension workshop. AI writes skill and card extensions behind confirmation gates, static validation and block-based safe writes.

小说写作助手插件（v4.1.1）：句式/情感/意象分析、伏笔设定管理、本地语义检索、氛围光谱、风格画像报告、文笔六维基线带、原创模式与创作资料、写作哨兵（衔接/OOC/大纲）；附 stdio MCP 服务器（Claude Desktop / Cursor 可用）。

Pending-change review for DeepSeek Harness: every `edit`, `write` and `str_replace_editor` change is collected automatically into the file list, where a single change block, the blocks within a selection, or the whole file can be kept or reverted, and undo/redo is supported. It imports the workspace's version-control changes, shows the diff in a single-column or side-by-side view, and provides a Markdown preview in which changes can also be kept or reverted, in-file search, block jumping and copyable line references; the diff data is stored persistently, so the review continues after a restart.

Multi-machine sync: keeps multiple dsh replicas consistent through one private GitCode repository — skills, sessions, settings and plugin manifests each with an independent switch; changes go through branch, PR and merge, remote-only additions are pulled back before every push so nothing is deleted, and an AI smart-align step semantically merges files both sides changed (plus one-click conflict resolution); private repos enforced, pull never overwrites local edits.

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.

Persistent AI memory backed by a local Obsidian/Codex vault: five obsidian_memory_* read/write/search tools plus a sidebar vault browser.

Manage DSH sessions the way Windows Explorer manages files: move, delete, search, archive, favorite and flag sessions as to-dos, and organize them with tags, notes and folders across workspaces. An AI pass can summarize a session and write its notes and tags in one go.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Union workspaces: merge multiple directories into one session, manage unions from a settings panel, and read/write member files via uw_read/uw_write/uw_edit/uw_delete/uw_move tools.

Session change-review plugin for DeepSeek Harness: tracks write/edit tool calls per session and renders line-level diffs with customizable colors, with session isolation, subagent aggregation, and SSE live updates.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Secondary working directories for a DSH project: the agent keeps the primary workspace as cwd and gains equal read/write/exec permissions on configured secondary directories, configurable from the session header and the new-session page.