Plugins

独立本地记忆插件：JSONL 记忆条目、每轮 runtime-context 注入、local_memory_search/local_memory_remember 工具、设置面板管理页。不依赖 Mnemon。

IDE-style Git panel in the DSH Web GUI: a resident tab with a three-column overview (branch/tag list, searchable commit-history graph, commit detail with changed-file tree and message) and a changes page (stats bar, uncommitted list with per-file stage/unstage/discard, commit box with amend); side-by-side diffs carry lazy highlight.js syntax highlighting, on-demand between-hunk context expansion and word-level intra-line emphasis, with image files shown as before/after panes; plus a zsh-style branch marker in the input bar. Every git command runs as an argv array through the host subprocess service, cwd locked to the repo root.

A port of the T3 Code model picker into the composer: a provider rail, search results grouped under provider headings, favorites kept in the browser, unavailable-provider badges, and Cmd/Ctrl+1..9 jump shortcuts for the first nine rows of the visible list.

On-demand skill tools for DeepSeek Harness: registers skill_search / skill_load / skill_ref so the model searches a staged skill library first and loads a skill body only when it needs it, keeping the library out of the resident session catalog and out of every turn's context; adds a Skills tab to the conversation view ring that reads back the whole session and lists which skills were actually loaded, and in which turn. Zero dependencies, and the records render client-side only, never entering the model's context.

Sandboxed ripgrep / fd / ast-grep under allowRoots (defaults include ~/.dsh/im-workspace).

Mail list/search via himalaya / notmuch (no send).

DeepSeek Harness plugin: DejaVu memory client — automated long-term memory (boot/read/search/create/update/delete) backed by your own DejaVu MCP server.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Bridges a WSL dsh agent to a Windows Obsidian vault on NTFS: status/list/search/read/write/append, wikilink resolve, write/append require confirm=true, plus obsidian:// open. Keep the vault under /mnt/<drive>/; Linux-disk vaults via \\wsl$ are unreliable.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

OAuth2-capable IMAP email reader for accounts where password authentication is disabled. Microsoft disabled Basic Auth for personal Outlook IMAP in 2024, so this plugin authenticates via refresh-token OAuth2 (XOAUTH2) with automatic token refresh, plus app-password login for Gmail through an optional local HTTP/SOCKS proxy. Registers list/read/search as ol_email_* so it can coexist with the market dsh-email plugin without tool-name clashes.

Compresses older DSH context into a structured handoff, retains recent messages, and keeps session history searchable.

Self-contained personal portfolio and investment-research workspace for DSH with local registration, asset import and allocation views, market and news tracking, a research library, and optional user-configured AI briefs; ships a Windows runtime and stores data locally.

Local SQLite long-term memory with CJK-aware search, BM25 and character n-gram cosine reranking, deduplication, and lifecycle management.

Searches wallhaven.cc from a settings page and sets any wallpaper as the DSH web GUI background, with opacity, blur and scrim controls, a sidebar shuffle button and one-click original download; all fetching runs in the host process, so the browser never needs to reach wallhaven.

Skill that fact-checks a claim against the open web rather than model memory: it splits the claim into independently checkable fact points, routes each point to the primary-source ladder for its domain (policy, academic, medical, financial, disaster and accidents, food safety, science, education, sports, entertainment, judicial, and more), searches domestic and international ecosystems in parallel, fetches primary pages, grades sources by type, re-searches with debunking keywords, and reports conclusion-first with a full URL and citation position behind every statement, keeping unverified and undecidable points separate from confirmed ones. Three factual judgements can be routed to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not; a model verdict can only lower a confidence tier.

Blocks an agent from reading, searching, writing, or editing chosen files and directories, keeping their contents out of the conversation — including sensitive-word files whose text can make later provider requests fail with a 400. Rules are picked from a file/directory browser on the plugin page.

Compaction fallback for compaction-basic: when its LLM summary throws, comes back empty or cannot fit the window, the span is compiled deterministically with a seq pointer on every line (vendored dsh-compaction-instant compiler). Adds recall and search tools, /recall and /context commands, an idle trigger at 45% of the window and an on-disk span archive. The engine mounts as one row in the agent preset (docs/dsh-integration.md).

Discord-like communities in DSH with channels, roles and permissions, message search, and sharing or cloning of DSH sessions.

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

Takes over the built-in web_search and web_fetch providers with Tavily, each behind its own toggle: a key pool with balance-aware scheduling that reads real credit balances from /usage, failover with hard exclusion of cooling or exhausted keys, and call history with a 14-day credit chart.

SearXNG search and Scrapling multi-tier fetch provider bundle for DeepSeek Harness ctx.web with SSRF protection and markdown conversion.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.