플러그인

DSH의 무손실 세션 로그를 기반으로 한 출처 표기 메모리: 정제된 사실마다 `(sessionId, eventRange)` 인용이 붙어 원본 로그 발췌로 바로 펼쳐볼 수 있음

Web UI의 턴별 USD 비용 배지: 헤더에 세션 총액, 각 메시지 하단에 턴별 비용 표시, 호버 시 상세 내역 제공

DSH会话悬浮窗：实时显示运行中会话的当前工作与批准提示（WinUI 3，可拖动缩放、置顶、跟随系统主题）注：主要部分均为ai编写

A session recap plugin for DeepSeek Harness with /recap, automatic idle summaries, and configurable models.

Per-session LLM cost meter for the DeepSeek Harness Web UI: folds provider usage into uncached input / cache read / cache write / output per model and prices it against DeepSeek and Xiaomi MiMo pay-as-you-go rates (DeepSeek peak-idle tiering included).

Per-turn and per-session API cost estimation for DeepSeek Harness conversations.

DeepSeek Harness plugin: watch every session from another tab — a status ring on the original fish favicon, a tab-title prefix, and a synthesized chime

Session-aware mesh relay for DSH agents: an Ed25519-signed receive route and delivery policy, plus outbound sending, a peer directory and a mesh-peer-registry client.

DeepSeek Harness plugin: web browsing tools (markdown / screenshot / pdf / crawl) powered by Cloudflare Browser Run — real headless Chrome with JS rendering, login sessions and WebMCP support.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

ZCode CLI app-server relay for DeepSeek Harness, with GLM streaming, image input and session reuse using an existing Start Plan login; requires the ZCode client.

A browser that lives inside the DSH host: every session gets its own tab, the AI drives it with lazily published browser_embedded_* tools, and a human watches or takes over that same tab in an on-demand right-Sidebar tab — no GUI, no external browser, log

Cross-session long-term memory: captures durable facts from each turn, auto-associates them by shared entity and tag, and recalls with BM25 plus spreading activation over the link graph.

Project-isolated long-term memory for DeepSeek Harness that keeps one bank per project and adds a cross-project view; it can also seed a project's memory from its git history without opening a session there.

飞书会话监听并投递到指定工作区的会话中

DeepSeek Harness agent tool (session_search) for full-text search across historical sessions backed by core SQLite FTS5 engine without memory overhead.

Verified restart for DeepSeek Harness: restart without privileges, check that the harness really came back, report the verdict to the session that asked, and hand back what was left to do.

dsh plugin: unattended approval gate — subagent/scheduled/cron approval requests get a bounded answer window, then settle with a fail-closed default instead of hanging forever (per origin or per session)

Third-party DeepSeek Harness plugin: per-workspace custom prompt configured from a slash command and injected into the model context at session start.

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

Git worktree isolation for DeepSeek Harness: create a worktree, register it as its own project, and start the session inside it

MCP server management for DeepSeek Harness: author composition rows, choose when an allowed server loads, and filter which of its tools a session may call

Connects the Xiaozhi voice assistant to DSH Web over MCP: DSH is the tool provider, weaving 35 DSH Web endpoints into 16 voice-friendly tools for workspaces, sessions, chat, models, settings and files — outbound WebSocket to the Xiaozhi MCP access point by default (no public IP or port forwarding needed), several devices bound at once, plus a DSH settings page with live status.

Read-only side branch in the right sidebar: quote text to ask follow-ups without polluting the model context of the main session; every follow-up rebuilds the branch from the latest settled turns of the main session, and writes are refused at the tool-execution layer so the prompt prefix stays cacheable.